WO2024209589A1 - Estimation device, estimation method, and compressor production method - Google Patents

Abstract

An estimation device (10) comprises: a data acquisition unit (111) that acquires first component data, which relates to at least one first component used in a first step of assembly of a compressor (6), and characteristic data, which relates to a characteristic of the compressor (6); and an estimation unit (113) that uses a trained model (20), which is for estimating second component data relating to at least one second component on the basis of the first component data and the characteristic data, to estimate second component data relating to at least one second component which is assembled to at least one first component in a second step after the first step, on the basis of the first component data and the characteristic data acquired by the data acquisition unit (111).

Description

Inference device, inference method, and method for manufacturing compressor

The present disclosure relates to an inference device, an inference method, and a method for manufacturing a compressor that infer data regarding at least one part used in assembling a compressor.

　Conventionally, as disclosed in JP 2016-149905 A (Patent Document 1), electric motors that supply power to connected mechanical parts are known.

JP 2016-149905 A

An electric motor such as that disclosed in JP 2016-149905 A (Patent Document 1) can be used in a compressor. In general, a compressor is composed of an electric motor and a compression mechanism that compresses a refrigerant using the power supplied from the electric motor. The electric motor and the compression mechanism are each assembled by combining multiple parts, but since each part has individual variations, the characteristics of a compressor made up of multiple parts may vary from compressor to compressor. Furthermore, even if the dimensions of each part before assembly are within the allowable range, when multiple parts are combined, the multiple parts may affect each other, resulting in gaps outside the allowable range, which may affect the deterioration of the compressor's characteristics. Furthermore, the characteristics of the compressor may vary depending on the manufacturing equipment used to manufacture the compressor or the environment of the manufacturing site.

　To check the characteristics of a compressor, it is sufficient to actually inspect the compressor characteristics, but each time the characteristics of the compressor are inspected, the pressure conditions in the inspection device must be stabilized, and inspecting the characteristics of every compressor in the manufacturing process takes a lot of time. For this reason, compressor characteristic inspections are usually performed by sampling inspection. However, as mentioned above, the characteristics of compressors vary from compressor to compressor due to various factors such as individual variations in each part, so it is difficult to guarantee that the characteristics of all manufactured compressors are within the tolerance range using sampling inspection. If the characteristics of the compressor are not within the tolerance range, the assembled compressor must be corrected by manual rework or the assembled compressor must be discarded, resulting in a waste of the time required to assemble the compressor and the parts used to assemble the compressor.

This disclosure has been made to solve the above problems, and aims to provide technology that can eliminate waste in the assembly of compressors.

The inference device according to the present disclosure is an inference device that infers data related to at least one part used in assembling a compressor. The inference device includes a data acquisition unit that acquires first part data related to at least one first part used in a first step in assembling the compressor and characteristic data related to the characteristics of the compressor, and an inference unit that infers second part data related to at least one second part that is assembled to the at least one first part in a second step that is subsequent to the first step, based on the first part data and characteristic data acquired by the data acquisition unit, using a trained model for inferring second part data related to at least one second part based on the first part data and characteristic data.

The inference method according to the present disclosure is an inference method in which data relating to at least one part used in assembling a compressor is inferred by a computer. The inference method includes, as processing executed by the computer, a step of acquiring first part data relating to at least one first part used in a first step in assembling the compressor and characteristic data relating to the characteristics of the compressor, and a step of inferring second part data relating to at least one second part that is assembled to the at least one first part in a second step that is subsequent to the first step, based on the first part data and characteristic data acquired by the acquiring step, using a trained model for inferring second part data relating to at least one second part based on the first part data and characteristic data.

The manufacturing method according to the present disclosure is a method for manufacturing a compressor by a computer. The manufacturing method includes, as processing executed by a computer, a step of assembling at least one first part in a first process, a step of acquiring first part data related to the at least one first part used in the first process and characteristic data related to the characteristics of the compressor, a step of inferring second part data related to at least one second part to be assembled to the at least one first part in a second process subsequent to the first process, based on the first part data and characteristic data acquired in the acquiring step, using a trained model for inferring second part data related to at least one second part based on the first part data and characteristic data, and a step of assembling at least one second part selected or processed based on the second part data into at least one first part in the second process.

According to the present disclosure, when assembling at least one second part in a second process subsequent to the first process with at least one first part used in a first process, it is possible to infer second part data for at least one second part based on first part data for the at least one first part and characteristic data relating to compressor characteristics using a trained model. This makes it possible to obtain at least one optimal second part to be assembled with at least one first part, thereby eliminating waste associated with assembling the compressor.

1 is a diagram showing a configuration of a compressor according to a first embodiment; FIG. FIG. 2 is a cross-sectional view of a compression mechanism portion. FIG. 4 is a diagram showing an example of an assembly of a compression mechanism portion. FIG. 1 is a diagram illustrating a configuration of an inference device according to a first embodiment. FIG. 1 is a diagram for explaining an overview of supervised learning. 3 is a diagram for explaining input and output of supervised learning in the inference device according to the first embodiment. FIG. FIG. 2 is a diagram illustrating a configuration of a learning device in a learning phase. FIG. 1 is a diagram illustrating a configuration of a neural network. 11 is a flowchart showing a process executed by a learning device (control unit) in a learning phase. FIG. 13 is a diagram showing the configuration of an inference device in the utilization phase. 13 is a flowchart showing the processing executed by the inference device (control unit) in the utilization phase. 3 is a diagram for explaining an example of input and output of supervised learning in the inference device according to embodiment 1. FIG. 4 is a flowchart relating to a method of manufacturing a compressor in the inference device according to the first embodiment. 13 is a flowchart relating to a method of manufacturing a compressor in the inference device according to the second embodiment.

Below, the embodiments of the present disclosure will be described in detail with reference to the drawings. Several embodiments will be described below, but it is planned from the beginning of the application that the configurations described in each embodiment will be appropriately combined. Note that the same or equivalent parts in the drawings will be given the same reference numerals and their description will not be repeated.

Embodiment 1.
[Compressor configuration]
A compressor 6 according to a first embodiment will be described with reference to Figures 1 to 4. The compressor 6 can be used in an air conditioner that cools or heats an object to be air-conditioned, such as a room, by circulating a refrigerant through a refrigerant circuit. The compressor 6 may also be used in a refrigeration device that cools an object to be cooled, such as a showcase or a unit cooler, by circulating a refrigerant.

FIG. 1 is a diagram showing the configuration of a compressor 6 according to the first embodiment. In FIG. 1, when the compressor 6 is correctly installed, the horizontal direction of the compressor 6 is defined as the X-axis direction, the vertical direction of the compressor 6 is defined as the Y-axis direction, and the direction perpendicular to the X-axis and Y-axis is defined as the Z-axis direction. In FIG. 1, a longitudinal cross section of the compressor 6 taken along the X-Y plane is shown.

The compressor 6 is a rotary compressor and includes a shell (housing) 60, a compression mechanism 62 for compressing a refrigerant (e.g., a refrigerant gas), an electric motor 61 for supplying power to the compression mechanism 62 for compressing the refrigerant, a shaft 613, a glass terminal 67 for supplying power to the electric motor 61, an accumulator 63 for drawing the refrigerant into the shell 60, and a discharge pipe 66 for discharging the refrigerant compressed by the compression mechanism 62 from inside the shell 60.

The shell 60 houses the electric motor 61, the compression mechanism 62, and the shaft 613. The electric motor 61 is fixed in the shell 60 by press fitting or shrink fitting. The electric motor 61 may have a stator 611 (described later) directly attached to the shell 60 by welding. Inside the shell 60, the compression mechanism 62 is disposed below the electric motor 61. Refrigeration oil is stored at the bottom of the shell 60 to lubricate sliding parts such as the rolling piston 622 (described later). The compression mechanism 62 is connected to the electric motor 61 via the shaft 613.

The accumulator 63 has a suction pipe 64 through which the refrigerant is drawn into the accumulator 63, and a supply pipe 65 that supplies the refrigerant to the compression mechanism 62.

The compressor 6 described above is assembled by joining multiple parts by welding using wax or the like. For example, the shell 60 is constructed by welding shell part 60A arranged on the upper surface of the compressor 6 to shell part 60C arranged on the side of the compressor 6 at welding part W1, and by welding shell part 60B arranged on the lower surface of the compressor 6 to shell part 60C at welding part W2. The shell 60 and the accumulator 63 are welded at welding part W3. The shell 60 and the supply pipe 65 are welded at welding part W4. The shell 60 and the discharge pipe 66 are welded at welding part W5.

FIG. 2 is a diagram showing a cross section of the electric motor 61. FIG. 2 shows a cross section of the electric motor 61 when the electric motor 61 is cut along the X-Z plane at the line A-A' shown in FIG. 1. As shown in FIG. 2, the electric motor 61 comprises a stator 611, a winding 615 wound around the stator 611, and a rotor 612 arranged inside the stator 611. The electric motor 61 is, for example, a PM (Permanent Magnet) motor in which a permanent magnet is provided in the rotor 612.

The stator 611 is formed of an iron core or coil, and includes a stator core 610 with a circular or nearly circular cross section. A central hole 619 with a circular cross section is formed in the center of the stator core 610 for positioning the rotor 612. The rotor 612 can rotate in a direction along the X-Z plane in the central hole 619 formed in the stator core 610.

Furthermore, the stator core 610 has a plurality of slots 614 formed in the circumferential direction. A winding 615 is attached to each of the plurality of slots 614. Power is supplied to the winding 615 via glass terminals 67. Note that the winding 615 may be attached to the stator core 610 using any known winding method, such as a distributed winding method or a concentrated winding method, and there are no particular limitations on the method of attaching the winding 615.

The rotor 612 has a circular or nearly circular cross section. The outer diameter of the rotor 612 is smaller than the inner diameter of the stator 611. As a result, the rotor 612 is disposed inside the stator 611 so as to fit into the central hole 619 of the stator core 610 without contacting the stator 611. A shaft hole 616 having a circular cross section for passing the shaft 613 along the Y-axis direction is formed in the center of the rotor 612. In addition, a plurality of air hole portions 617 are formed in the rotor 612 so as to surround the shaft hole portion 616. A plurality of permanent magnets 618 are provided outside the plurality of air hole portions 617. Note that the electric motor 61 is not limited to an IPM (Interior Permanent Magnet) motor in which the permanent magnet 618 is embedded inside the rotor 612, but may be an SPM (Surface Permanent Magnet) motor in which the permanent magnet 618 is attached to the outer circumferential surface of the rotor 612.

FIG. 3 is a diagram showing a cross section of the compression mechanism 62. FIG. 3 shows a cross section of the compression mechanism 62 when the compression mechanism 62 is cut along the X-Z plane at line B-B' shown in FIG. 1. As shown in FIG. 3, the compression mechanism 62 includes a cylinder 621 and a rolling piston 622 arranged inside the cylinder 621.

Cylinder 621 has a circular or nearly circular cross section. A compression chamber 630 having a circular cross section for compressing the refrigerant is formed in the center of cylinder 621 and in which rolling piston 622 is disposed. Rolling piston 622 can rotate in a direction along the X-Z plane in compression chamber 630 formed in cylinder 621.

Furthermore, a back pressure chamber 628 and a vane groove 624 are formed in the cylinder 621. The vane groove 624 connects the compression chamber 630 and the back pressure chamber 628. A long vane 625 is provided in the vane groove 624. In the example of FIG. 3, the vane 625 can slide in the Z-axis direction along the vane groove 624.

The rolling piston 622 has a circular or nearly circular cross section. The rolling piston 622 is attached to the outer periphery of an eccentric shaft portion 626 that has a circular or nearly circular cross section. A shaft hole portion 627 having a circular cross section for passing the shaft 613 along the Y-axis direction is formed in the eccentric shaft portion 626 at a position offset from the center of the rolling piston 622 and the eccentric shaft portion 626. In other words, the shaft 613 is inserted into the rolling piston 622 and the eccentric shaft portion 626 along the Y-axis direction.

The tip of the vane 625 is ideally in contact with a portion of the outer circumferential surface of the rolling piston 622, dividing the compression chamber 630 formed by the inner circumferential surface of the cylinder 621 and the outer circumferential surface of the rolling piston 622 into an intake side and a compression side.

The rolling piston 622 rotates in a direction along the XZ plane in accordance with the rotation of the shaft 613. However, because the shaft 613 is inserted at a position that is off-center of the rolling piston 622, the rolling piston 622 rotates eccentrically along the inner circumferential surface of the cylinder 621, with the off-center position as its axis. When the rolling piston 622 rotates eccentrically within the cylinder 621, part of the outer circumferential surface of the rolling piston 622 ideally comes into close contact with part of the inner circumferential surface of the cylinder 621.

FIG. 4 is a diagram showing an example of the assembly of the compression mechanism 62. As shown in FIG. 4, the vane 625 is attached to the vane groove 624 formed in the cylinder 621, and the rolling piston 622 is attached to the center of the hollow cylindrical cylinder 621, thereby assembling the compression mechanism 62.

As shown in FIG. 1, the compression mechanism 62 further includes an upper frame 623A, a lower frame 623B, an upper muffler 624A, and a lower muffler 624B.

The upper frame 623A and the lower frame 623B support the cylinder 621 and rolling piston 622 of the compression mechanism 62 by sandwiching them from above and below (Y-axis direction). The upper frame 623A supports the cylinder 621 and rolling piston 622 by ideally coming into close contact with the upper parts of the cylinder 621 and rolling piston 622. The lower frame 623B supports the cylinder 621 and rolling piston 622 by ideally coming into close contact with the lower parts of the cylinder 621 and rolling piston 622.

The upper frame 623A and the lower frame 623B allow the shaft 613 to be inserted along the Y-axis direction, and bearings (not shown) support the shaft 613 for rotation in a direction along the X-Z plane. An upper shaft portion 613A constituting part of the long shaft 613 is inserted into the upper frame 623A, and the shaft 613 is rotatably supported by the upper frame 623A at the upper shaft portion 613A. A lower shaft portion 613B constituting part of the long shaft 613 is inserted into the lower frame 623B, and the shaft 613 is rotatably supported by the lower frame 623B at the lower shaft portion 613B.

If the electric motor 61, compression mechanism 62, and shaft 613 are assembled in the shell 60 in the correct position, and the dimensions of each part are accurate, ideally the central axes of each part along the Y-axis direction will coincide. For example, as shown in FIG. 1, the central axis of the upper frame 623A coincides with the central axis of the lower frame 623B. The central axis of the shell 60 also coincides with the central axis of the shaft 613.

[Compressor operation]
In the compressor 6 configured as described above, when a current flows through the windings 615 of the stator 611 by the power supplied from the glass terminal 67, a rotating magnetic field is generated in the stator 611. The permanent magnets 618 act on the rotating magnetic field generated in the stator 611 so as to be attracted thereto, causing the rotor 612 to rotate. As the rotor 612 rotates, the shaft 613 inserted in the rotor 612 rotates. The rotational force of the shaft 613 is then transmitted to the rolling piston 622, causing the rolling piston 622 to rotate eccentrically along the inner circumferential surface of the cylinder 621.

The refrigerant sucked by the accumulator 63 is supplied to the compression chamber 630 of the compression mechanism 62 via the supply pipe 65. In the compression chamber 630, the rolling piston 622 rotates to compress the refrigerant. As shown in FIG. 3, the compression chamber 630 includes an intake side region where the sucked refrigerant exists, and a compression side region where the compressed refrigerant (hereinafter also referred to as "compressed refrigerant") exists. These intake side and compression side regions are created by the outer circumferential surface of the rolling piston 622 contacting the inner circumferential surface of the cylinder 621 and the tip of the vane 625, respectively. The compressed refrigerant is discharged from the compression side region and rises inside the shell 60 through the upper muffler 624A. Refrigerant oil is mixed into the compressed refrigerant.

The mixture of compressed refrigerant and refrigeration oil is separated into compressed refrigerant and refrigeration oil when passing through the air hole 617 formed in the rotor 612. This makes it possible to prevent the refrigeration oil from flowing into the discharge pipe 66. The compressed refrigerant separated from the refrigeration oil is supplied through the discharge pipe 66 to the high-pressure side of the refrigerant circuit in which the refrigerant circulates.

[Correlation between individual compressor variations and compressor characteristics]
The characteristics of the compressor 6 include the performance of the compressor 6. The performance of the compressor 6 is represented by a coefficient of performance (COP) calculated from the input power of the compressor 6 (input power supplied from the glass terminal 67) and the refrigeration capacity. The coefficient of performance (COP) indicates the refrigeration capacity per unit of power (for example, 1 kW). The characteristics of the compressor 6 also include noise data and vibration data of the compressor 6. The noise data of the compressor 6 includes the sound pressure level (for example, in decibels) of the sound (noise) generated from the compressor 6 when the compressor 6 is driven. The vibration data of the compressor 6 includes a vibration level indicating the degree to which the compressor 6 vibrates when the compressor 6 is driven.

Factors that reduce the performance of the compressor 6 include individual variations in each part of the compression mechanism 62. In particular, major factors that affect the performance of the compressor 6 in the compression mechanism 62 include the size of the gap (G1 in FIG. 1) between the rolling piston 622 and the upper frame 623A, the size of the gap (G2 in FIG. 1) between the rolling piston 622 and the lower frame 623B, the size of the gap (G3 in FIG. 3) between the outer circumferential surface of the rolling piston 622 and the inner circumferential surface of the cylinder 621, the size of the gap (G4 in FIG. 3) between the tip of the vane 625 and the outer circumferential surface of the rolling piston 622, the size of the gap (G5 in FIG. 3) between the side surface of the vane 625 in the sliding direction and the vane groove 624 of the cylinder 621, the size of the gap (not shown) between the vane 625 and the upper frame 623A, and the size of the gap (not shown) between the vane 625 and the lower frame 623B. If the gaps between the components of the compression mechanism 62 described above are large, the amount of refrigerant that leaks from the gaps increases, and the compression capacity decreases. Furthermore, if the inner diameter of the rolling piston 622 is larger than the standard, the force of the electric motor 61 is not fully transmitted to the compression mechanism 62, and the compression capacity may decrease. If the inner diameter of the rolling piston 622 is smaller than the standard, the rolling piston 622 and the shaft 613 may come into contact with each other.

If the gaps between the components of the compression mechanism 62 are large, the amount of refrigerant that leaks from the gaps increases, and the refrigeration capacity decreases. The coefficient of performance of the compressor 6 is the refrigeration capacity per unit of power, so if the refrigeration capacity decreases, the coefficient of performance decreases. In other words, if the gaps between the components are large, the performance of the compressor 6 decreases. In particular, the main factors that affect the performance of the compressor 6 include the degree of welding at the welded parts W1 and W2 of the shell 60, the welded part W3 between the shell 60 and the accumulator 63, the welded part W4 between the shell 60 and the supply pipe 65, and the welded part W5 between the shell 60 and the discharge pipe 66. If the weld strength at each weld is low, gaps will occur at the joints between multiple components, and refrigerant may leak.

The noise data and vibration data of the compressor 6 can also fluctuate due to individual variations in the components of the compression mechanism 62. In particular, the main factors that affect the noise data and vibration data of the compressor 6 in the compression mechanism 62 include the concentricity of the upper shaft portion 613A and the lower shaft portion 613B, and the size of the gap (G1 in FIG. 1) between the vane 625 and the vane groove 624.

The concentricity of the upper shaft portion 613A and the lower shaft portion 613B represents the degree of misalignment between the central axis of the upper shaft portion 613A and the central axis of the lower shaft portion 613B, and when the concentricity is 0, the central axis of the upper shaft portion 613A and the central axis of the lower shaft portion 613B completely coincide. In other words, the greater the concentricity of the upper shaft portion 613A and the lower shaft portion 613B, the greater the misalignment of the center of rotation of the shaft 613 above and below the cylinder 621, preventing the transmission of rotational energy from the electric motor 61 to the compression mechanism portion 62 and converting the rotational energy into vibration energy. Therefore, the greater the concentricity of the upper shaft portion 613A and the lower shaft portion 613B, the greater the sound pressure level of the noise of the compressor 6 and the greater the vibration level of the compressor 6, qualitatively. In this way, variations in the concentricity of the upper shaft portion 613A and the lower shaft portion 613B tend to deteriorate the noise and vibration characteristics of the compressor 6.

If the gap between the vane 625 and the vane groove 624 is too large, the vane 625 will be more likely to vibrate in the vane groove 624, and the vane 625 will collide with the vane groove 624, generating vibration energy. In other words, if the gap between the vane 625 and the vane groove 624 is too large, qualitatively the sound pressure level of the noise of the compressor 6 will increase, and the vibration level of the compressor 6 will also increase. Also, if the gap between the vane 625 and the vane groove 624 is too small, vibration energy will be generated due to the frictional force generated between the vane 625 and the vane groove 624. The rotational speed of the motor 61 will pulsate due to the frictional force generated between the vane 625 and the vane groove 624, making the compressor 6 more likely to vibrate and generate noise. In other words, if the gap between the vane 625 and the vane groove 624 is too small, qualitatively the sound pressure level of the noise of the compressor 6 increases, and the vibration level of the compressor 6 increases. In this way, variations in the gap between the vane 625 and the vane groove 624 tend to deteriorate the noise and vibration characteristics of the compressor 6.

In order to prevent the characteristics of the compressor 6 from deteriorating, it is important to ensure that the compression mechanism 62 is airtight. For this reason, each component of the compression mechanism 62 described above is precisely machined and surface treated before assembly. However, there is always individual variation in the dimensions of each component, and gaps may occur due to individual variation in each component. When the compressor 6 is manufactured, the dimensions of each of these components are inspected to see if they are within a predetermined tolerance range, and the compressor 6 is manufactured using components whose dimensions are determined to be within the tolerance range.

The compressor 6 is manufactured by combining the various parts of the compression mechanism 62, and it can be qualitatively understood that the dimensions of each part affect the performance of the compressor 6. However, even if the dimensions of each part of the compression mechanism 62 are within the allowable range, this does not necessarily mean that the dimensions of each gap in the assembled compressor 6 are within the allowable range.

For example, when a part having a dimension close to the lower limit of the tolerance range (e.g., the outer diameter of rolling piston 622) is combined with a part having a dimension close to the upper limit of the tolerance range (e.g., the inner diameter of cylinder 621), the gap between those parts becomes large and the gap dimension may exceed the tolerance range. Also, when a part having a dimension close to the upper limit of the tolerance range (e.g., the outer diameter of rolling piston 622) is combined with a part having a dimension close to the lower limit of the tolerance range (e.g., the inner diameter of cylinder 621), the gap between those parts becomes small and the gap dimension may fall below the tolerance range.

Furthermore, multiple gaps occur when the various parts of the compression mechanism 62 are combined, and these multiple gaps may affect each other. For this reason, even if it is possible to grasp the gaps between two parts to some extent, it is not possible to grasp the individual gaps after the various parts of the compression mechanism 62 are combined, and ultimately, it is difficult to confirm the performance of the compressor 6 as a whole until after the compressor 6 has been manufactured.

Another factor that reduces the characteristics of the compressor 6 is individual variation in each part of the motor 61. In particular, the main factors that affect the performance of the compressor 6 in the motor 61 include the amount of magnetic flux of the rotor 612 that links with the windings 615 and the resistance value of the windings 615. Due to the amount of magnetic flux of the rotor 612 that links with the windings 615, an induced voltage occurs based on the law of electromagnetic induction. The magnitude of the induced voltage is proportional to the amount of magnetic flux of the rotor 612 that links with the windings 615. In other words, the amount of magnetic flux of the rotor 612 that links with the windings 615 corresponds to the induced voltage. In addition, the main factors that affect the noise data and vibration data of the compressor 6 in the motor 61 include the amount of magnetic flux of the rotor 612 that links with the windings 615, the inner diameter roundness of the stator 611, and the amount of eccentricity of the rotor 612.

The amount of magnetic flux of the rotor 612 interlinked with the winding 615 varies mainly depending on the magnetic flux density of the permanent magnet 618 inserted in the rotor 612, the dimensions of the permanent magnet 618, the outer diameter of the rotor 612, and the inner diameter of the stator 611, and the variations in these factors also tend to cause the input power of the compressor 6 (input power supplied from the glass terminal 67) to vary. In general, when the amount of magnetic flux of the rotor 612 decreases, the current flowing to the winding 615 of the motor 61 also increases, causing copper loss to increase, and the driving power supplied to the motor 61 increases. This causes the input power of the motor 61 to vary. Furthermore, in order to control the motor 61, data indicating the amount of magnetic flux of the rotor 612 interlinked with the winding 615 of the stator 611 is input in advance to the control device of the motor 61. However, the amount of magnetic flux input in advance is a representative value that does not reflect the individual variations of the compressor 6. Therefore, the greater the deviation of the actual magnetic flux amount from the representative value input to the control device, the more likely the input to the compressor 6 will fluctuate, making the operation of the motor 61 unstable.

Furthermore, the input power of the compressor 6 varies due to variations in the resistance value of the windings 615. The coefficient of performance of the compressor 6 is the refrigeration capacity per unit of power, so as the input power of the compressor 6 increases, the coefficient of performance decreases. In other words, the performance of the compressor 6 varies depending on the amount of magnetic flux of the rotor 612 that links with the windings 615 and the resistance value of the windings 615.

Furthermore, the greater the variation in the amount of magnetic flux of the rotor 612 interlinked with the windings 615, the more likely the sound pressure level of the noise of the compressor 6 and the more likely the vibration level of the compressor 6 are to fluctuate qualitatively. In this way, the variation in the amount of magnetic flux of the rotor 612 interlinked with the windings 615 of the stator 611 tends to deteriorate the noise and vibration characteristics of the compressor 6.

The inner diameter roundness of the stator 611 indicates whether the circle forming the inner peripheral surface of the stator 611 having a circular cross section is close to a perfect circle, and when the inner diameter roundness is 0, the stator 611 is a perfect circle. As shown in FIG. 2, a gap is generated between the inner peripheral surface of the stator 611 and the outer peripheral surface of the rotating rotor 612, and the size of the gap between the inner peripheral surface of the stator 611 and the outer peripheral surface of the rotor 612 increases or decreases depending on the inner diameter roundness of the stator 611. If the size of this gap fluctuates, the magnetic attraction force acting between the stator 611 and the rotor 612 becomes unstable, and qualitatively, the sound pressure level of the noise of the compressor 6 increases, and the vibration level of the compressor 6 increases. In this way, the variation in the inner diameter roundness of the stator 611 tends to deteriorate the noise and vibration characteristics of the compressor 6.

The eccentricity of the rotor 612 represents the amount of deviation between the rotation axis of the rotor 612 and the ideal position when the rotation axis of the rotor 612 deviates from the ideal position, and when the eccentricity is 0, the rotation axis is located at the ideal position. As described above, the outer peripheral surface of the rolling piston 622 and the inner peripheral surface of the cylinder 621 are ideally in close contact with each other, but depending on the eccentricity of the rotor 612, a gap (G2 in FIG. 1) may be generated between the outer peripheral surface of the rolling piston 622 and the inner peripheral surface of the cylinder 621. Also, as shown in FIG. 3, the tip of the vane 625 and the outer peripheral surface of the rotating rolling piston 622 are ideally in close contact with each other, but depending on the eccentricity of the rotor 612, a gap (G3 in FIG. 3) may be generated between the tip of the vane 625 and the outer peripheral surface of the rolling piston 622. That is, depending on the amount of eccentricity of the rotor 612, the size of the gap between the inner circumferential surface of the stator 611 and the outer circumferential surface of the rotor 612, and the size of the gap between the tip of the vane 625 and the outer circumferential surface of the rolling piston 622, increase or decrease. If the size of these gaps fluctuates, the magnetic attraction force acting between the stator 611 and the rotor 612 becomes unstable, and qualitatively, the sound pressure level of the noise of the compressor 6 increases, and the vibration level of the compressor 6 increases. In this way, the variation in the amount of eccentricity of the rotor 612 tends to deteriorate the noise and vibration characteristics of the compressor 6.

Furthermore, there is an interaction between individual variations in the compression mechanism 62 and individual variations in the electric motor 61. For example, if a large amount of refrigerant leaks through the gaps in the compression mechanism 62, less refrigerant is available for compression, resulting in a smaller refrigeration capacity and a smaller compression torque, which in turn results in a smaller torque generated in the electric motor 61. If the torque of the electric motor 61 is small, this has the effect of reducing the input power to the electric motor 61, and so on. Furthermore, the effect on the electric motor 61 differs depending on the location of the gaps that occur in the compression mechanism 62.

The individual variation of the individual parts, the accuracy of the combination of the multiple parts, and the state of the welding that joins the multiple parts as described above can be affected by the dimensional accuracy of each part processed by the manufacturing device and the working environment of the worker at the manufacturing site. Therefore, the individual variation of the individual parts, the combination of the multiple parts, and the state of the welding that joins the multiple parts can vary depending on the identification information of the manufacturing device, the current generated in the manufacturing device, the voltage generated in the manufacturing device, the time required to manufacture the compressor 6, the welding temperature during the manufacturing of the compressor 6, the welding amount (for example, the amount of wax) in the welding, the temperature at the manufacturing site of the compressor 6, and the humidity at the manufacturing site. For example, the expansion rate of the parts and the work efficiency of the worker can vary depending on the temperature and humidity at the manufacturing site. In addition, when the parts are processed by the manufacturing device, a current or voltage is generated when the blade comes into contact with the parts. The state of the parts processed by the manufacturing device depends on the current or voltage generated in the manufacturing device. Furthermore, if any abnormality occurs in the manufacturing of the compressor 6, the time required to manufacture the compressor 6 may be extended. In this way, the characteristics of the compressor 6 can vary depending on the identification information of the manufacturing device, the current generated in the manufacturing device, the voltage generated in the manufacturing device, the time required to manufacture the compressor 6, the temperature (heat) of the welding during the manufacturing of the compressor 6, the amount of welding (for example, the amount of wax), the temperature at the manufacturing site of the compressor 6, and the humidity at the manufacturing site.

As such, the characteristics of the compressor are determined by the complex intertwining of the various parts in the compression mechanism 62 and the various parts in the electric motor 61, so it is difficult to accurately confirm the characteristics of the compressor 6 as a whole until the various parts in the compression mechanism 62 and the various parts in the electric motor 61 have been combined to manufacture the compressor 6.

In order to check the characteristics of the compressor 6, it is sufficient to inspect the compressor 6 after it has been manufactured; however, it is necessary to stabilize the pressure conditions in the inspection device each time the compressor 6 is inspected, and it would take a great deal of time to inspect the performance of all the compressors 6 during the manufacturing process. For this reason, the characteristics of the compressor 6 are usually inspected by sampling inspection. However, as described above, there are individual variations in each component of the compression mechanism 62 and the electric motor 61, and therefore the characteristics of the compressor 6 when multiple components are combined vary from compressor to compressor 6. In other words, even if the dimensions and characteristics of each component of the compression mechanism 62 and the electric motor 61 are guaranteed individually, it is not possible to grasp the synergistic effect when these are combined, and it is difficult to guarantee the characteristics of all the compressors 6 manufactured by sampling inspection.

Furthermore, when the characteristics of the compressor 6 are checked after assembling the compressor 6 by combining a plurality of parts, if the characteristics of the compressor 6 do not meet the standards, the assembled compressor 6 must be corrected by manual adjustment or the assembled compressor 6 must be discarded. For example, examples of inspection items during assembly of the compressor 6 include the gap between the stator 611 and the rotor 612 of the electric motor 61, the airtightness or welding state of the compressor 6 to confirm that no refrigerant is leaking from the compressor 6, and noise or vibration during operation of the compressor 6. If the characteristics of the compressor 6 do not meet the standards in these inspections, the compressor 6 must be corrected by manual adjustment or the compressor 6 must be discarded. In this case, the time required to assemble the compressor 6 and the parts used in assembling the compressor 6 are wasted. If, during the assembly of the compressor 6, it were possible to select or process parts to be used in the assembly of the compressor 6 in a later process, taking into account the individual variations of individual parts and the effects of combining multiple parts, the worker would be able to avoid waste, such as reworking or discarding the assembled compressor 6. For example, when assembling at least one second part in a second process subsequent to the first process for at least one first part used in the first process of assembling the compressor 6, if it were possible to obtain in advance at least one optimal second part to be assembled with at least one first part, taking into account the individual variations or the effects of the combination of at least one first part, the compressor 6 having characteristics that meet a predetermined standard could be manufactured without waste.

The present disclosure provides a technology that utilizes AI (Artificial Intelligence) to obtain in advance data regarding at least one optimal second part to be assembled in a subsequent second process for at least one first part used in a first process.

[Inference device]
Fig. 5 is a diagram showing the configuration of inference device 10 according to embodiment 1. As shown in Fig. 5, inference device 10 includes, as main functional components, a control unit 11, a storage unit 12, and an input unit 13.

The control unit 11 is a computing entity that executes various processes by executing various programs, and an example of such a computing entity is a computer such as a processor. The processor is, for example, composed of a microcontroller, a CPU (central processing unit), or an MPU (micro-processing unit). The processor has the function of executing various processes by executing programs, but some or all of these functions may be implemented using dedicated hardware circuits such as an ASIC (Application Specific Integrated Circuit), a GPU (Graphics Processing Unit), or an FPGA (Field-Programmable Gate Array). The term "processor" is not limited to a processor in the narrow sense that executes processes using a stored program method such as a CPU or an MPU, but may also include hardwired circuits such as an ASIC, a GPU, or an FPGA. For this reason, the processor may also be interpreted as a processing circuit in which processing is defined in advance by computer-readable code and/or hardwired circuits. The processor may be composed of one chip or multiple chips. Furthermore, the processor and associated processing circuitry may be configured as multiple computers interconnected by wire or wirelessly, such as via a local area network or wireless network. The processor and associated processing circuitry may be configured as a cloud computer that performs remote calculations based on input data and outputs the results of the calculations to other devices in remote locations.

The memory unit 12 is a memory that provides a storage area for temporarily storing program codes or work memory when the control unit 11 executes various programs. The memory unit 12 may be one or more non-transitory computer readable mediums. Examples of the memory unit 12 include volatile memories such as dynamic random access memory (DRAM) and static random access memory (SRAM), or non-volatile memories such as read only memory (ROM) and flash memory. Furthermore, the memory unit 12 may be a storage device that provides a storage area for storing various data required for the control unit 11 to execute various programs. The memory unit 12 may be one or more computer readable storage mediums. Examples of the memory unit 12 include storage devices such as solid state drives (SSDs) and hard disk drives (HDDs).

The input unit 13 is an interface into which input data is input by an operator using a keyboard or mouse (not shown). For example, the input unit 13 is an input interface for connecting a keyboard or mouse to the inference device 10. In this case, data input using the keyboard or mouse is input to the input unit 13 as input data. The input unit 13 may also be a communication interface for communicating with an external device such as a cloud server (not shown). In this case, data stored in the external device is input to the input unit 13 as input data. In the embodiment, first part data relating to at least one first part used in the first step in the assembly of the compressor 6 and characteristic data relating to the characteristics of the compressor 6 that serve as a predetermined reference are input to the input unit 13 as input data.

The control unit 11 includes a data acquisition unit 111, a model generation unit 112, an inference unit 113, a selection unit 114, a processing unit 115, and an assembly unit 116.

The data acquisition unit 111 acquires the input data input from the input unit 13. Specifically, the data acquisition unit 111 acquires the first part data and characteristic data as the input data.

The model generation unit 112 uses the learning data 30 described below, which is a set of input data (first part data, characteristic data) acquired by the data acquisition unit 111 and second part data related to at least one second part to be assembled with at least one first part, which is the correct answer data corresponding to the input data, to generate a trained model 20 described below for inferring the second part data based on the input data (first part data, characteristic data).

The inference unit 113 uses the trained model 20 to infer the second part data based on the input data (first part data, characteristic data).

The selection unit 114 performs control to select at least one optimal second part to be assembled to at least one first part used in the first process from among a plurality of second part candidates prepared in advance, based on the second part data inferred by the inference unit 113. For example, if the second part data is a parameter indicating the dimension or dimensional range of at least one optimal second part to be assembled to at least one first part used in the first process, the selection unit 114 selects at least one second part having dimensions that satisfy the dimension or dimensional range indicated by the second part data.

The processing unit 115 performs control to process at least one second part prepared in advance based on the second part data inferred by the inference unit 113 to create at least one optimal second part that can be assembled to the at least one first part used in the first process. For example, if the second part data is processing parameters (e.g., dimensions or dimensional ranges) for processing at least one optimal second part that can be assembled to the at least one first part used in the first process, the processing unit 115 processes at least one second part prepared in advance based on the processing parameters indicated by the second part data.

The assembly unit 116 performs control in the second process to assemble at least one second part selected by the selection unit 114 to at least one first part. Alternatively, the assembly unit 116 performs control in the second process to assemble at least one second part machined by the processing unit 115 to at least one first part.

[Learning Phase]
6 to 10, an application example of the inference device 10 in the learning phase will be described. As described above, the inference device 10 performs supervised learning using learning data 30 that is a set of input data (first part data, characteristic data) correlated with the second part data and the second part data that is the correct answer data corresponding to the input data. Supervised learning is a method of learning the features in the learning data 30 using a data set of factors and results (labels) and inferring the result from the input.

FIG. 6 is a diagram for explaining an overview of supervised learning. As shown in FIG. 6, in the learning phase, the inference device 10 executes a learning program 40 to generate (update) a trained model 20 based on training data 30 including an input 1 and an input 2 (correct answer).

In the utilization phase, the inference device 10 uses the trained model 20 to obtain an output based on the input 1.

FIG. 7 is a diagram for explaining the input and output of supervised learning in the inference device 10 according to the first embodiment. As shown in FIG. 7, in the inference device 10, data correlated with the second part data is used as input data for input 1. Specifically, the input data includes first part data relating to at least one first part used in the first process, and characteristic data relating to the characteristics of the compressor 6 that serve as a predetermined reference. The input data for input 1 can be obtained before assembling the compressor 6 or during the assembly of the compressor 6.

In the inference device 10, second part data relating to at least one second part that is assembled to at least one first part is used as input 2, which is the correct answer data. In addition, in the inference device 10, second part data similar to input 2 is obtained as output.

FIG. 8 is a diagram showing the configuration of the learning device 110 in the learning phase. The learning device 110 is realized by the control unit 11 of the inference device 10. The learning device 110 is capable of transferring data to and from each of the learning program storage unit 121 and the learned model storage unit 122. The learning program storage unit 121 and the learned model storage unit 122 are realized by the storage unit 12 of the inference device 10.

As shown in FIG. 8, the learning device 110 includes a data acquisition unit 111 and a model generation unit 112. The learning device 110 executes a learning program 40 stored in a learning program storage unit 121 to generate a trained model 20 based on learning data 30 including an input 1 and an input 2 (correct answer).

The data acquisition unit 111 acquires learning data 30 including input 1 and input 2 (correct answer). Specifically, the data acquisition unit 111 acquires the first part data and characteristic data as input 1. The data acquisition unit 111 acquires the second part data as input 2 (correct answer). Specific examples of the input data (first part data and characteristic data) and the second part data will be described later with reference to FIG. 13.

The model generation unit 112 uses the learning data 30 including the input 1 and the input 2 (correct answer) acquired by the data acquisition unit 111 to generate a trained model 20 that infers the second part data based on the input data. The model generation unit 112 stores the generated trained model 20 in the trained model storage unit 122.

FIG. 9 is a diagram showing the configuration of a neural network. The model generation unit 112 generates a trained model 20 by supervised learning, for example, according to a neural network model.

A neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. There may be one intermediate layer, or two or more layers.

In Figure 9, a three-layer neural network is shown. In Figure 9, a configuration with three inputs and three outputs is shown. When multiple inputs are input to the input layers X1, X2, and X3, the values multiplied by weights w11 to w16 are input to the intermediate layers Y1 and Y2, and the results are further multiplied by weights w21 to w26 to be output from the output layers Z1, Z2, and Z3. This output result changes depending on the values of the weights w11 to w16 and w21 to w26.

The neural network performs supervised learning based on learning data 30 including input 1 and input 2 (correct answer) acquired by data acquisition unit 111. In other words, the neural network learns by inputting input 1 into the input layer and adjusting the weights so that the result output from the output layer approaches input 2 (correct answer).

The model generation unit 112 generates the trained model 20 by performing supervised learning as described above.

FIG. 10 is a flowchart of the processing executed by the learning device 110 (inference device 10) in the learning phase. Note that FIG. 10 shows the processing executed by the inference device 10 corresponding to the learning device 110. Also, in FIG. 10, "S" is used as an abbreviation for "STEP."

As shown in FIG. 10, the inference device 10 acquires learning data 30 including input 1 and input 2 (correct answer) by the data acquisition unit 111 (S1). Note that the inference device 10 is not limited to acquiring input 1 and input 2 (correct answer) simultaneously, and may acquire input 1 and input 2 (correct answer) at different times.

The inference device 10 generates a trained model 20 by performing supervised learning based on the training data 30 using the model generation unit 112 (S2). The inference device 10 stores the generated trained model 20 in the trained model storage unit 122 (S3) and ends this process.

[Utilization phase]
An application example of the inference device 10 in the utilization phase will be described with reference to Fig. 11 and Fig. 12. Fig. 11 is a diagram showing the configuration of the inference device 10 in the utilization phase. The inference device 10 is capable of transferring data to and from a trained model storage unit 122.

As shown in FIG. 11, the inference device 10 includes a data acquisition unit 111 and an inference unit 113. The inference device 10 uses a trained model 20 to obtain an output based on an input 1.

The data acquisition unit 111 acquires input 1. Specifically, the data acquisition unit 111 acquires the first part data and characteristic data as input 1.

The inference unit 113 uses the trained model 20 to obtain the second part data as an output based on the input 1. Specifically, the inference unit 113 reads out the trained model 20 from the trained model storage unit 122. The inference unit 113 uses the trained model 20 to infer the second part data as an output based on the first part data and characteristic data, which are the input 1 acquired by the data acquisition unit 111.

FIG. 12 is a flowchart of the process executed by the inference device 10 (control unit 11) in the utilization phase. In FIG. 12, "S" is used as an abbreviation for "STEP."

As shown in FIG. 12, the inference device 10 acquires input 1 by the data acquisition unit 111 (S11). The inference device 10 inputs the acquired input 1 to the trained model 20 (S12). The inference device 10 uses the trained model 20 to infer second part data as output based on the first part data and characteristic data, which are input 1 (S13). This allows the inference device 10 to obtain the second part data based on the first part data and characteristic data, using the trained model 20. Thereafter, the inference device 10 ends this process.

[An example of input and output in supervised learning]
An example of input and output of supervised learning in the inference device 10 will be described with reference to Fig. 13. Fig. 13 is a diagram for explaining an example of input and output of supervised learning in the inference device 10 according to the first embodiment.

In the example of FIG. 13, the first part data used as input 1 includes at least one of data related to individual variations of individual parts, data related to the manufacture (assembly and processing) of compressor 6, and data that may arise from the combination of multiple parts.

The data relating to the individual variations of the individual components includes at least one of the dimensions of the rolling piston 622, the dimensions of the cylinder 621, the dimensions of the vane 625, the dimensions of the upper frame 623A, the dimensions of the lower frame 623B, the outer diameter of the stator 611, the inner diameter of the stator 611, the width of the stator 611, the outer diameter of the rotor 612, the inner diameter of the rotor 612, the dimensions of the shaft 613, the dimensions of the shell 60, the dimensions of the accumulator 63, the amount of magnetic flux of the rotor 612 interlinked with the winding 615, and the resistance value of the winding 615.

The dimensions of the rolling piston 622 include, for example, at least one of the dimensions (outer diameter) of the outer peripheral surface of the rolling piston 622 that contacts the inner peripheral surface of the cylinder 621 and the tip of the vane 625, and the height of the rolling piston 622 (length in the Y direction in FIG. 1). The dimensions of the cylinder 621 include, for example, at least one of the dimensions (inner diameter) of the inner peripheral surface of the cylinder 621 that contacts the outer peripheral surface of the rolling piston 622, and the thickness of the vane groove 624 of the cylinder 621 that contacts the side surface in the sliding direction of the vane 625 (length in the X direction in FIG. 3). The dimensions of the vane 625 include, for example, the dimension of the side surface in the sliding direction of the vane 625 that contacts the vane groove 624 of the cylinder 621 (length in the Z direction in FIG. 3), and the width of the vane groove 624 in the direction perpendicular to the sliding direction of the vane 625 (X direction in FIG. 3). The dimensions of the upper frame 623A include, for example, the height of the upper frame 623A (length in the Y direction in FIG. 1). The dimensions of the lower frame 623B include, for example, the height of the lower frame 623B (length in the Y direction in FIG. 1). As shown in FIG. 2, the width dimension of the stator 611 includes the dimension 610A between the outer periphery and the inner periphery of the stator 611 (stator core 610).

The data relating to the manufacture (assembly and processing) of the compressor 6 includes at least one of the following: identification information of a manufacturing device (not shown) used to manufacture the compressor 6, the current generated in the manufacturing device, the voltage generated in the manufacturing device, the noise generated in the manufacturing device, the vibration generated in the manufacturing device, the time required to manufacture the compressor 6, the welding temperature during the manufacture of the compressor 6, the amount of welding (e.g., the amount of wax), the temperature at the manufacturing site of the compressor 6, and the humidity at the manufacturing site.

The manufacture of the compressor 6 includes processing a number of parts, such as the stator 611, rotor 612, shaft 613, shell 60, and accumulator 63, and assembling these parts to form the compressor 6. The manufacturing equipment also includes, for example, equipment that uses a blade to process each of the parts, such as the stator 611, rotor 612, and shaft 613. The identification information of the manufacturing equipment includes, for example, a serial number and a management number that identify the manufacturing equipment.

Data that can be generated by combining multiple parts includes the dimension of the gap between the rolling piston 622 and the upper frame 623A (G1 in Figure 1), the dimension of the gap between the rolling piston 622 and the lower frame 623B (G2 in Figure 1), the dimension of the gap between the outer circumferential surface of the rolling piston 622 and the inner circumferential surface of the cylinder 621 (G3 in Figure 3), the dimension of the gap between the tip of the vane 625 and the outer circumferential surface of the rolling piston 622 (G4 in Figure 3), the dimension of the gap between the side of the vane 625 in the sliding direction and the vane groove 624 of the cylinder 621 (G5 in Figure 3), the dimension of the gap between the vane 625 and the upper frame 623A (not shown), the dimension of the gap between the vane 625 and the lower frame 623B (not shown), the dimension of the gap between the shaft 613 and the upper frame 623A, the dimension of the gap between the shaft 613 and the lower frame 623B, a value indicating the deviation between the central axis of the upper frame 623A and the central axis of the lower frame 623B, a value indicating the deviation between the central axis of the shell 60 and the central axis of the shaft 613, the shrink fit (tightening) between the stator 611 and the rotor 612, the dimensions of the shell 60 after welding, and at least one of the dimensions of the accumulator 63 after welding.

The above-mentioned first part data may be data of a lot to which at least one part belongs. For example, the first part data may be average data of a lot to which each part, such as rolling piston 622, cylinder 621, vane 625, upper frame 623A, lower frame 623B, stator 611, rotor 612, shaft 613, shell 60, accumulator 63, and winding 615, belongs. Specifically, the first component data may be the average dimension of the rolling piston 622 in the lot, the average dimension of the cylinder 621 in the lot, the average dimension of the vane 625 in the lot, the average dimension of the upper frame 623A in the lot, the average dimension of the lower frame 623B in the lot, the average outer diameter dimension of the stator 611 in the lot, the average inner diameter dimension of the stator 611 in the lot, the average width dimension of the stator 611 in the lot, the average outer diameter dimension of the rotor 612 in the lot, the average inner diameter dimension of the rotor 612 in the lot, the average dimension of the shaft 613 in the lot, the average dimension of the shell 60 in the lot, the average dimension of the accumulator 63 in the lot, the average amount of magnetic flux in the lot of the rotor 612 interlinked with the winding 615, or the average resistance value in the lot of the winding 615.

In the example of FIG. 13, the characteristic data used as input 1 includes at least one of the noise data of the compressor 6, the vibration data of the compressor 6, assembly data relating to the assembly state of the compressor 6, and the performance (coefficient of performance) of the compressor 6. Furthermore, the assembly data of the compressor 6 includes at least one of the dimensions of the gap (hereinafter also referred to as the "air gap") between the stator 611 and rotor 612 of the electric motor 61, the airtightness of the compressor 6, and the natural value (natural frequency, resonant frequency) of the compressor 6. These characteristic data are predetermined reference data for various characteristics of the compressor 6.

The noise data of the compressor 6 included in the characteristics data indicates the standard value (upper limit) of the noise of the compressor 6 guaranteed in the specifications. If the noise of the compressor 6 exceeds the standard value, noise will leak from the air conditioner in which the compressor 6 is installed. For this reason, an upper limit is set for the noise of the compressor 6, and this upper limit is applied to the characteristics data related to the noise of the compressor 6.

The vibration data of the compressor 6 included in the characteristics data indicates the standard value (upper limit) of the vibration of the compressor 6 guaranteed in the specifications. If the vibration of the compressor 6 exceeds the standard value, the vibration of the air conditioner in which the compressor 6 is installed will increase, which may cause an abnormality to occur. For this reason, an upper limit is set for the vibration of the compressor 6, and this upper limit is applied to the characteristics data related to the vibration of the compressor 6.

The air gap dimensions included in the characteristic data indicate the reference values (lower limit, upper limit) of the air gap dimensions guaranteed in the specifications. If the air gap dimensions are smaller than the lower limit, the performance of the compressor 6 (e.g., coefficient of performance) will decrease, and the noise or vibration of the compressor 6 will worsen. On the other hand, if the air gap dimensions are larger than the upper limit, the performance of the compressor 6 will also decrease. For this reason, at least one of a lower limit and an upper limit is set for the air gap dimensions, and at least one of such lower limit and upper limit is applied to the characteristic data related to the air gap of the compressor 6.

The airtightness of the compressor 6 included in the characteristic data indicates the standard value of the airtightness of the compressor 6 guaranteed in the specifications. The airtightness of the compressor 6 can be confirmed, for example, by detecting the amount of refrigerant or gas bubbles that appear on the liquid surface when the compressor 6 is submerged in liquid, the size of the bubbles, or the frequency with which the bubbles appear. For this reason, the value indicating the airtightness of the compressor 6 can be a value that quantifies or levels the amount of bubbles, the size of the bubbles, or the frequency with which the bubbles appear. If the airtightness of the compressor 6 does not meet the standard value, the performance of the compressor 6 will decrease. For this reason, standard values are set for the airtightness of the compressor 6, and such standard values are applied to the characteristic data relating to the airtightness of the compressor 6.

The characteristic values (natural frequency, resonant frequency) of the compressor 6 included in the characteristic data indicate the reference values of the characteristic values of the compressor 6 guaranteed in the specifications. If the characteristic values of the compressor 6 do not meet the reference values, the noise or vibration of the compressor 6 may worsen. For this reason, reference values are set for the characteristic values of the compressor 6, and such reference values are applied to the characteristic data relating to the characteristic values of the compressor 6.

The performance of the compressor 6 included in the characteristic data indicates the standard value of the performance of the compressor 6 guaranteed in the specifications. If the performance of the compressor 6 does not meet the standard value, the air conditioning capacity of the air conditioner in which the compressor 6 is installed may decrease. For this reason, standard values are set for the performance of the compressor 6, and such standard values are applied to the characteristic data related to the performance of the compressor 6.

The noise data and vibration data of the compressor 6 may vary due to individual variations in individual components. The noise data and vibration data of the compressor 6 may vary due to changes in the characteristic values caused by welding or assembly. For example, if the amount of wax used during welding (brazing) is large, the welding may be strong, and the characteristic values of the compressor 6 may change. If the temperature of the heat used during welding is high or the welding time is long, distortion may occur in the compression mechanism 62, and the noise of the compressor 6 may worsen. If the discharge current of the manufacturing device during welding is large, the welding may be strong, and the characteristic values of the compressor 6 may change. The noise data and vibration data of the compressor 6 may vary due to the accuracy of the combination of multiple parts. Data that may be generated by the combination of multiple parts includes the dimensions of the shell 60 after welding and the dimensions of the accumulator 63 after welding. If the dimensions of the shell 60 after welding or the dimensions of the accumulator 63 after welding are small, the welding may be strong, and the characteristic values of the compressor 6 may change, and the noise may worsen.

In this way, at least one of the data on individual variations of individual parts, data on the manufacture of the compressor 6, and data that may arise from the combination of multiple parts, which are included in the first part data, may affect the noise data and vibration data of the compressor 6, which are included in the characteristic data.

The dimensions of the air gap may be affected by the misalignment of the assembly centers of the stator 611 and the rotor 612, the inner diameter of the stator 611, the outer diameter of the rotor 612, the inclination of the shaft 613, and the state of fixation between the stator 611 and the rotor 612. For example, one factor that may cause the dimensions of the air gap to not meet the standard values is that the shaft 613 is inclined beyond an acceptable range from the central axis of the compressor 6. Even if the inclination of the shaft 613 is within the acceptable range, for example, if the outer diameter of the rotor 612 is larger than the standard and the inner diameter of the stator 611 is smaller than the standard, these dimensional errors may accumulate and cause the dimensions of the air gap to not meet the standard values.

Furthermore, the smaller the outer diameter of the rotor 612, the larger the air gap, and the larger the outer diameter of the rotor 612, the smaller the air gap. The smaller the inner diameter of the stator 611, the smaller the air gap, and the larger the inner diameter of the stator 611, the larger the air gap.

If the inner diameter of each of the upper frame 623A and the lower frame 623B is too small, there is a risk of damaging the shaft 613 when assembling the compressor 6, and the gap between each of the upper frame 623A and the lower frame 623B and the shaft 613 becomes small, making it impossible to form an appropriate oil film. As a result, when the compressor 6 is in operation, each of the upper frame 623A and the lower frame 623B and the shaft 613 will seize up, making it impossible for the shaft 613 to rotate. On the other hand, if the inner diameter of each of the upper frame 623A and the lower frame 623B is too small, the shaft 613 will tilt.

If the minor axis dimension of shaft 613 is short, the bearings in lower frame 623B are reduced, causing shaft 613 to tilt. If the diameter dimension of shaft 613 is large, upper frame 623A and lower frame 623B each come into contact with shaft 613. If the diameter dimension of shaft 613 is small, upper frame 623A and lower frame 623B prevent the central axis from being exposed, causing shaft 613 to tilt.

In this way, at least one of the data included in the first part data regarding individual variations of individual parts and the data that may arise from the combination of multiple parts may affect the dimensions of the air gap included in the characteristic data.

The airtightness of the compressor 6 may be affected by individual variations in individual parts, the state of welding that joins multiple parts, and the accuracy of the combination of multiple parts. The individual variations in individual parts, the state of welding that joins multiple parts, and the combination of multiple parts may vary depending on the identification information of a manufacturing device (not shown) for manufacturing the compressor 6, the current generated in the manufacturing device, the voltage generated in the manufacturing device, the time required to manufacture the compressor 6, the welding temperature during the manufacturing of the compressor 6, the amount of welding (for example, the amount of wax), the temperature (heat) at the manufacturing site of the compressor 6, and the humidity at the manufacturing site. For example, the expansion rate of the parts and the work efficiency of the worker may vary depending on the temperature and humidity at the manufacturing site. In addition, when a part is processed by the manufacturing device, a current or voltage is generated when a blade comes into contact with the part. The processing state of the part by the manufacturing device depends on the current or voltage generated in the manufacturing device. Furthermore, if any abnormality occurs in the manufacturing of the compressor 6, the time required to manufacture the compressor 6 may be extended. If the amount of wax used during welding (brazing) is small, the welding will be poor, leading to refrigerant leakage from the compressor 6. If the heat temperature during welding is low or the welding time is short, the welding will be poor, leading to refrigerant leakage from the compressor 6. If the discharge current of the manufacturing equipment during welding is small, the welding will be poor, leading to refrigerant leakage from the compressor 6.

Data that may result from the combination of multiple parts includes the dimensions of the shell 60 after welding, and the dimensions of the accumulator 63 after welding. The dimensions of the shell 60 include the width dimension of the shell 60 in its cross section (X-Z cross section). The dimensions of the accumulator 63 include the width dimension of the accumulator 63 in its cross section (X-Z cross section). If the dimensions of the shell 60 after welding or the dimensions of the accumulator 63 after welding are large, the welding will be weak, which may reduce the sealing performance of the compressor 6.

In this way, at least one of the data on individual variations of individual parts, data on the manufacture of the compressor 6, and data that may arise from the combination of multiple parts, which are included in the first part data, may affect the sealing performance of the compressor 6, which is included in the characteristic data.

The characteristic value of the compressor 6 can change depending on the strength of the welding. For example, if a large amount of wax is used during welding (brazing), the welding will be strong and the characteristic value of the compressor 6 can change. Also, if the discharge current of the manufacturing equipment during welding is large, the welding will be strong and the characteristic value of the compressor 6 can change.

In this way, the data regarding the manufacture of the compressor 6 contained in the first part data can affect the characteristic values of the compressor 6 contained in the characteristic data.

Factors that cause the performance of the compressor 6 to fluctuate include individual variations in individual components. Another factor that causes the performance of the compressor 6 to fluctuate is refrigerant leakage from the compression mechanism 62. The cause of refrigerant leakage from the compression mechanism 62 is gaps between components that can occur when multiple components are combined.

In this way, at least one of the data on individual variations of individual components contained in the first component data and the data that may arise from the combination of multiple components may affect the performance (coefficient of performance) of the compressor 6, which is contained in the characteristic data.

In the example of FIG. 13, the data used as input 2 (correct answer) and output 2 includes at least one of the dimensions of the part used in the second process, the dimensional range of the part, and the processing parameters for processing the part.

Based on the first part data, the inference device 10 recognizes at least one of data on individual variations of individual parts, data on manufacturing, and data that may arise from the combination of multiple parts for at least one first part used in the first process, and performs machine learning to determine what second part should be combined with at least one first part in various states to satisfy the standard values of the characteristics of the compressor 6, such as noise, vibration, assembly state, and performance, indicated by the characteristic data. There are a wide variety of quality check items when assembling the compressor 6, and multiple parts are combined in a complex manner in the assembly of the compressor 6. For this reason, it is difficult for a human being to determine which combination of parts affects the characteristic data of the compressor 6. However, the inference device 10 can use the trained model 20 to infer second part data on a second part to be combined with the first part so as to satisfy the standard values of the characteristics of the compressor 6 indicated by the characteristic data, based on the first part data and the characteristic data.

[Flowchart for manufacturing a compressor]
The inference of the second part data in the manufacture of the compressor 6 will be described in detail with reference to Fig. 14. Fig. 14 is a flowchart relating to the manufacturing method of the compressor 6 in the inference device 10 according to the first embodiment. The flowchart shown in Fig. 14 specifies each step (manufacturing method) of an assembly process for manufacturing the compressor 6 by a computer having the functions of the inference device 10 (controller 11). In Fig. 14, "S" is used as an abbreviation for "STEP".

As shown in FIG. 14, the inference device 10 assembles at least one first part in a first step (S21). The first step may be the first assembly step in the manufacture of the compressor 6, or may be the second or subsequent assembly step in the manufacture of the compressor 6. Furthermore, the at least one first part may be a single part, or a part formed by combining multiple parts. For example, the inference device 10 combines a vane 625 with a cylinder 621 to assemble a combined part including the cylinder 621 and the vane 625 as the first part.

As shown in FIG. 13, the inference device 10 acquires first part data related to at least one first part used in the first step, and characteristic data related to the characteristics of the compressor 6 to be assembled by the assembly process of FIG. 14 (S22). Specifically, the inference device 10 acquires first part data related to the first part assembled in S21. The inference device 10 also acquires characteristic data related to the characteristics of the compressor 6 to be assembled. For example, the inference device 10 acquires, as the first part data, at least one of the dimensions of the cylinder 621 assembled in S21, the dimensions of the vane 625, and the dimensions of the gap (G5 in FIG. 3) between the side surface of the vane 625 in the sliding direction and the vane groove 624 of the cylinder 621. The inference device 10 also acquires, as characteristic data, at least one of the noise data of the compressor 6 to be assembled by the assembly process of FIG. 14, the vibration data of the compressor 6, assembly data related to the assembly state of the compressor 6, and the performance of the compressor 6.

The inference device 10 uses the trained model 20 based on the first part data and the characteristic data to infer second part data regarding at least one second part to be assembled to at least one first part in the second process (S23). For example, the inference device 10 infers, as the second part data, at least one of the dimensions and dimensional ranges of the rolling piston 622 that satisfy the characteristic data acquired in S22 for the rolling piston 622 that is combined with a combination part including a cylinder 621 and a vane 625.

The inference device 10 determines the shape or characteristics of the second part based on the inferred second part data (S24). For example, the inference device 10 determines at least one of the optimal dimensions and the optimal dimension range of the rolling piston 622 to be combined with the combination part including the cylinder 621 and the vane 625 in the second step.

The inference device 10 determines whether there is a second part that satisfies the second part data (S25). Specifically, the inference device 10 determines whether there is at least one optimal second part that satisfies the shape or characteristics of the second part determined in S24 among a plurality of second part candidates prepared in advance. For example, the inference device 10 determines whether there is an optimal rolling piston 622 that satisfies at least one of the dimensions and dimension ranges determined in S24 among a plurality of rolling piston 622 candidates prepared in advance.

If there is a second part that satisfies the second part data (YES in S25), the inference device 10 selects the second part based on the second part data (S26). Specifically, the inference device 10 selects at least one optimal second part that satisfies the shape or characteristics of the second part determined in S24 from among a plurality of second part candidates prepared in advance. For example, the inference device 10 selects an optimal rolling piston 622 that satisfies at least one of the dimensions and dimension ranges determined in S24 from a plurality of rolling piston 622 candidates prepared in advance.

In the second step, the inference device 10 assembles at least one second part to at least one first part (S27). For example, in the second step, the inference device 10 controls an assembly device (not shown) to assemble the rolling piston 622 selected in S26 to the combined part including the cylinder 621 and vane 625 assembled in the first step of S21. Thereafter, the inference device 10 ends this process.

On the other hand, if there is no second part that satisfies the second part data (NO in S25), the inference device 10 performs a process to modify the first part by rework, or a disposal process to discard the first part (S28). For example, the inference device 10 displays an image on a display (not shown) that prompts the worker to modify the combined part including the cylinder 621 and the vane 625 by rework, or moves the combined part to a disposal route. The inference device 10 then ends this process.

In this way, the inference device 10 can infer second part data for selecting a second part, taking into account the variability of the first part, by inputting into the learned model 20, together with the first part data, characteristic data relating to the characteristics of the compressor 6 that are targets to be achieved by combining the first part with the second part. The inference device 10 can determine, based on the inferred second part data, whether or not there is a second part that satisfies the inferred second part data among the second parts prepared in advance. Furthermore, if there is a second part that satisfies the inferred second part data among the second parts prepared in advance, the inference device 10 can select the second part and combine the selected second part with the first part to easily manufacture a compressor 6 that satisfies the target characteristics. This allows the inference device 10 to obtain an optimal second part to be assembled with the first part. Therefore, after the assembly of the compressor 6 is completed, the inference device 10 does not need to modify the assembled compressor 6 or discard the assembled compressor 6, and it is possible to prevent the time required to assemble the compressor 6 and the parts used in the assembly of the compressor 6 from being wasted.

Note that in FIG. 14, an example has been described in which the inference device 10 (control unit 11) executes each process, but the inference device 10 (control unit 11) may execute only the processes of S22 and S23, and the remaining processes may be executed by a functional unit other than the inference device 10 (control unit 11) included in the computer.

In addition, FIG. 14 illustrates the process of assembling one combined part (e.g., compression mechanism 62) by combining a first part (e.g., a combined part including cylinder 621 and vane 625) with a second part (e.g., rolling piston 622), but the flowchart shown in FIG. 14 may also be applied to the process of assembling two or more combined parts including other combined parts (e.g., electric motor 61).

For example, in the example of FIG. 14, a combination part including a cylinder 621 and a vane 625 is exemplified as the first part, and a rolling piston 622 is exemplified as the second part, but the inference device 10 may assemble the compressor 6 by combining a plurality of other parts. For example, the first part may be a stator 611, and the second part may be a winding 615 wound around the stator 611. In such an example, in S22, the inference device 10 acquires data related to the rotor 612, such as the outer diameter of the rotor 612, as the first part data. In addition, in S22, the inference device 10 acquires a value indicating the variation in the coefficient of performance of the compressor 6 to be assembled by the assembly process of FIG. 14 as the characteristic data. For example, the value indicating the variation is the coefficient of performance guaranteed in the specifications, and if the median is ±0%, the lower limit is −2% of the median, and the upper limit is +2% of the median. That is, the inference device 10 infers second component data (e.g., the resistance value of the winding 615) for selecting the second component, the winding 615, so that the coefficient of performance of the compressor 6 assembled by the assembly process of FIG. 14 falls within the range of the coefficient of performance guaranteed in the specifications.

For example, in S23, the inference device 10 infers +5% of a predetermined value (e.g., 10 ohms) as the resistance value of the winding 615 at which the coefficient of performance of the compressor 6 is the lower limit, infers +1% of a predetermined value (e.g., 10 ohms) as the resistance value of the winding 615 at which the coefficient of performance of the compressor 6 is the median, and infers -3% of a predetermined value (e.g., 10 ohms) as the resistance value of the winding 615 at which the coefficient of performance of the compressor 6 is the upper limit. That is, the inference device 10 infers the lower limit, median, and lower limit of the resistance value of the winding 615 as the second component data. In S26, the inference device 10 selects a winding 615 that falls within the lower limit, median, and lower limit of the resistance value of the winding 615 inferred in S23, and assembles the compressor 6 by winding the selected winding 615 around the stator 611.

In this way, the inference device 10 can infer upper and lower limit values of the resistance value for selecting the winding 615, taking into account the variation of the rotor 612, by inputting data such as the shape of the rotor 612 and characteristic data related to the characteristics of the target compressor 6 into the learned model 20. The inference device 10 can determine whether or not there is a winding 615 that satisfies the upper and lower limit values of the inferred resistance value among the multiple windings 615 prepared in advance, based on the inferred upper and lower limit values of the resistance value. Furthermore, if there is a winding 615 that satisfies the upper and lower limit values of the inferred resistance value among the multiple windings 615 prepared in advance, the inference device 10 can select the winding 615 and wind the selected winding 615 around the rotor 612 to easily manufacture a compressor 6 that satisfies the target characteristics. This allows the inference device 10 to obtain the optimal winding 615 to be assembled to the rotor 612, and can eliminate waste related to the assembly of the compressor 6.

Furthermore, the inference device 10 can rework the first part if the assembly of the compressor 6 cannot be continued. This allows the inference device 10 to reduce the effort and time required for rework compared to detecting that the characteristics of the compressor 6 do not satisfy the reference values during inspection after the assembly of the compressor 6 is completed.

Note that in FIG. 14, an example has been described in which the inference device 10 (control unit 11) executes each process, but the inference device 10 (control unit 11) may execute only the processes of S22 and S23, and the remaining processes may be executed by a functional unit other than the inference device 10 (control unit 11) included in the computer.

Embodiment 2.
An inference device 10 according to the second embodiment will be described with reference to Fig. 15. Note that, in the following, only the parts of the inference device 10 according to the second embodiment that are different from the inference device 10 according to the first embodiment will be described.

FIG. 15 is a flowchart of a method for manufacturing a compressor 6 in the inference device 10 according to the second embodiment. The flowchart shown in FIG. 15 defines each step (manufacturing method) of an assembly process for manufacturing a compressor 6 by a computer having the functions of the inference device 10 (control unit 11). In FIG. 15, "S" is used as an abbreviation for "STEP."

As shown in FIG. 15, in a first step, the inference device 10 assembles at least one first part (S31). For example, the inference device 10 combines a cylinder 621 with a vane 625 to assemble a combined part including the cylinder 621 and the vane 625 as the first part.

As shown in FIG. 13, the inference device 10 acquires first part data related to at least one first part used in the first step, and characteristic data related to the characteristics of the compressor 6 to be assembled by the assembly process of FIG. 15 (S32). Specifically, the inference device 10 acquires first part data related to the first part assembled in S31. The inference device 10 also acquires characteristic data related to the characteristics of the compressor 6 to be assembled. For example, the inference device 10 acquires, as the first part data, at least one of the dimensions of the cylinder 621 assembled in S31, the dimensions of the vane 625, and the dimensions of the gap (G5 in FIG. 3) between the side surface of the vane 625 in the sliding direction and the vane groove 624 of the cylinder 621. The inference device 10 also acquires, as characteristic data, at least one of the noise data of the compressor 6 to be assembled by the assembly process of FIG. 15, the vibration data of the compressor 6, assembly data related to the assembly state of the compressor 6, and the performance of the compressor 6.

The inference device 10 uses the learned model 20 based on the first part data and the characteristic data to infer second part data regarding at least one second part to be assembled to at least one first part in the second process (S33). For example, the inference device 10 infers processing parameters for processing the rolling piston 622 that satisfies the characteristic data acquired in S32 for the rolling piston 622 that is combined with a combination part including a cylinder 621 and a vane 625 as the second part data. The processing parameters include, for example, at least one of the dimensions and dimension ranges of the rolling piston 622.

The inference device 10 determines the machining parameters of the second part based on the inferred second part data (S34). For example, the inference device 10 determines the optimal machining parameters (dimensions or dimension ranges) of the rolling piston 622 that is combined with the combined part including the cylinder 621 and the vane 625 in the second process.

The inference device 10 determines whether or not the second part can be machined based on the second part data (S35). Specifically, the inference device 10 determines whether or not a previously prepared, unmachined second part can be machined according to the machining parameters (dimensions or dimensional range) of the second part determined in S34. For example, the inference device 10 determines whether or not a previously prepared, unmachined rolling piston 622 can be machined according to the machining parameters (dimensions or dimensional range) of the rolling piston 622 determined in S34.

If the inference device 10 can machine the second part based on the second part data (YES in S35), it machines the second part based on the second part data (S36). Specifically, the inference device 10 machines the second part, which has been prepared beforehand and is not yet machined, according to the processing parameters (dimensions or dimensional range) of the second part determined in S34. For example, the inference device 10 controls a processing device (not shown) to process the rolling piston 622, which has been prepared beforehand and is not yet machined, according to the processing parameters (dimensions or dimensional range) of the rolling piston 622 determined in S34.

In the second step, the inference device 10 assembles at least one second part to at least one first part (S37). For example, in the second step, the inference device 10 assembles the rolling piston 622 machined in S36 to the combined part including the cylinder 621 and vane 625 assembled in the first step of S31. The inference device 10 then ends this process.

On the other hand, if the inference device 10 cannot machine the second part based on the second part data (NO in S35), it performs a process to modify the first part by hand, or a disposal process to discard the first part (S38). For example, the inference device 10 displays an image on a display (not shown) that prompts the worker to modify the combined part including the cylinder 621 and the vane 625 by hand, or moves the combined part to a disposal route. The inference device 10 then ends this process.

In this way, the inference device 10 can infer second part data for machining the second part, taking into account the variability of the first part, by inputting the characteristic data related to the characteristic of the compressor 6 that is the target to be achieved by combining the first part with the second part, together with the first part data, into the trained model 20. The inference device 10 can determine whether or not the second part before machining can be machined, based on the inferred second part data. Furthermore, if the inference device 10 can machine the second part, it can easily manufacture a compressor 6 that satisfies the target characteristics by machining the second part and combining the machined second part with the first part. This allows the inference device 10 to obtain an optimal second part that can be assembled to the first part. Therefore, the inference device 10 does not need to modify the assembled compressor 6 or discard the assembled compressor 6 after the assembly of the compressor 6 is completed, and can prevent the time required to assemble the compressor 6 and the parts used in the assembly of the compressor 6 from being wasted.

<Modification>
The data of each part related to the first part data used for the input 1 may be data obtained by a sampling inspection performed during the manufacture of the compressor 6. In this way, the more compressors 6 are manufactured and the longer the manufacturing period, the more individual data that can be used for the learning data 30 can be collected.

The inference device 10 may be a server device communicatively connected to a control device that controls the compressor 6 via a network, or may be a cloud server. The inference device 10 may acquire the first part data, the second part data, and the characteristic data collected from a plurality of compressors 6 that exist in the same area as the learning data 30, or may acquire the first part data, the second part data, and the characteristic data collected from a plurality of compressors 6 that exist in different areas as the learning data 30. In this case, by including area information in the learning data 30, machine learning can be performed taking into account the difference between areas. This area may be treated as a different area even if the individual inspection device that inspects the performance of the compressor 6 is different. After machine learning is performed on a certain compressor 6, machine learning may be performed again on another compressor 6.

The learning algorithm used by the model generation unit 112 of the inference device 10 may be deep learning, which learns to extract the features themselves, or other known methods. For example, the model generation unit 112 may perform machine learning according to genetic programming, functional logic programming, support vector machines, etc.

The inference device 10 described above uses supervised learning, but known learning methods such as unsupervised learning, semi-supervised learning, or reinforcement learning may also be used. For example, when performing unsupervised learning, the inference device 10 may use only the first part data and characteristic data of input 1 shown in FIG. 13 as learning data 30. In the learning phase, the inference device 10 learns the features or tendencies of the collected first part data and characteristic data by clustering the collected first part data and characteristic data. Then, in the utilization phase, the inference device 10 may use the trained model 20 to identify the class to which the input first part data and characteristic data belong, and output the second part data corresponding to that class as the inference result.

<Summary>
An inference device 10 according to one embodiment infers data related to at least one part used in the assembly of a compressor 6. The inference device 10 includes a data acquisition unit 111 that acquires first part data related to at least one first part used in a first step in the assembly of the compressor 6 and characteristic data related to characteristics of the compressor 6, and an inference unit 113 that infers second part data related to at least one second part to be assembled to the at least one first part in a second step subsequent to the first step, based on the first part data and the characteristic data acquired by the data acquisition unit 111, using a trained model 20 for inferring second part data related to at least one second part based on the first part data and the characteristic data.

With the above configuration, when assembling at least one second part to at least one first part used in a first process in a second process subsequent to the first process, the inference device 10 can use the trained model 20 to infer second part data for at least one second part based on first part data for at least one first part and characteristic data relating to the characteristics of the compressor 6. This makes it possible to obtain at least one optimal second part to be assembled to at least one first part, thereby eliminating waste associated with the assembly of the compressor 6.

The second part data is a parameter indicating the shape or characteristics of at least one second part that can satisfy the characteristic data by assembling it with at least one first part. The inference device 10 further includes a selection unit 114 that selects at least one second part based on the second part data inferred by the inference unit 113.

With the above configuration, the inference device 10 can select the optimal second part from the second parts prepared in advance that satisfies the characteristics of the target compressor 6.

The second part data is a parameter for machining at least one second part that can satisfy the characteristic data when assembled with the at least one first part. The system further includes a machining unit that machines the at least one second part based on the second part data inferred by the inference unit.

With the above configuration, the inference device 10 can optimally process the unmachined second part so as to satisfy the target characteristics of the compressor 6.

The inference device 10 further includes an assembly unit 116 that assembles at least one second part to at least one first part in the second step.

With the above configuration, the inference device 10 can manufacture a compressor 6 that meets the target characteristics by assembling the second part to the first part.

The first part data is data of a lot to which at least one first part belongs.
According to the above configuration, the second part data can be inferred based on the data of the lot to which the first part belongs. This eliminates the need to obtain data of each first part, making it possible to simplify the inference process and improve the speed of the inference process.

The compressor 6 includes a compression mechanism 62 for compressing the refrigerant, an electric motor 61 for supplying power to the compression mechanism 62 for compressing the refrigerant, a shaft 613 for connecting the compression mechanism 62 and the electric motor 61, a shell 60 for housing the compression mechanism 62, the electric motor 61, and the shaft 613, and an accumulator 63 for drawing the refrigerant into the shell 60. The first part data indicates individual variation of at least one of the compression mechanism 62, the electric motor 61, the shaft 613, the shell 60, and the accumulator 63.

With the above configuration, the inference device 10 can infer the second part data based on the individual variation of at least one of the compression mechanism 62, the electric motor 61, the shaft 613, the shell 60, and the accumulator 63.

The compression mechanism 62 comprises a cylinder 621, a rolling piston 622 that rotates along the inner surface of the cylinder 621 based on power from the electric motor 61, a vane 625 that divides the compression chamber 630 formed by the inner surface of the cylinder 621 and the outer surface of the rolling piston 622 into a suction side and a compression side, an upper frame 623A that supports the rolling piston 622 from above, and a lower frame 623B that supports the rolling piston 622 from below. The first part data includes at least one of the following: the dimensions of the rolling piston 622, the dimensions of the cylinder 621, the dimensions of the vane 625, the dimensions of the upper frame 623A, the dimensions of the lower frame 623B, the dimensions of the gap between the rolling piston 622 and the upper frame 623A, the dimensions of the gap between the rolling piston 622 and the lower frame 623B, the dimensions of the gap between the rolling piston 622 and the cylinder 621, the dimensions of the gap between the vane 625 and the rolling piston 622, the dimensions of the gap between the vane 625 and the cylinder 621, the dimensions of the gap between the vane 625 and the upper frame 623A, the dimensions of the gap between the vane 625 and the lower frame 623B, the dimensions of the gap between the shaft 613 and the upper frame 623A, the dimensions of the gap between the shaft 613 and the lower frame 623B, a value indicating the deviation between the central axis of the upper frame 623A and the central axis of the lower frame 623B, and a value indicating the deviation between the central axis of the shell 60 and the central axis of the shaft 613.

According to the above configuration, the inference device 10 can calculate the dimensions of the rolling piston 622, the dimensions of the cylinder 621, the dimensions of the vane 625, the dimensions of the upper frame 623A, the dimensions of the lower frame 623B, the dimensions of the gap between the rolling piston 622 and the upper frame 623A, the dimensions of the gap between the rolling piston 622 and the lower frame 623B, the dimensions of the gap between the rolling piston 622 and the cylinder 621, the dimensions of the gap between the vane 625 and the rolling piston 622, the dimensions of the gap between the vane 625 and the cylinder 621, The second part data can be inferred based on at least one of the following: the gap size between the vane 625 and the upper frame 623A, the gap size between the vane 625 and the lower frame 623B, the gap size between the shaft 613 and the upper frame 623A, the gap size between the shaft 613 and the lower frame 623B, a value indicating the deviation between the central axis of the upper frame 623A and the central axis of the lower frame 623B, and a value indicating the deviation between the central axis of the shell 60 and the central axis of the shaft 613.

The electric motor 61 includes a stator 611, a winding 615 wound around the stator 611, and a rotor 612 provided inside the stator 611. The first part data includes at least one of the following: the outer diameter of the stator 611, the inner diameter of the stator 611, the width of the stator 611, the outer diameter of the rotor 612, the inner diameter of the rotor 612, the amount of magnetic flux of the rotor 612 interlinked with the winding 615, the resistance value of the winding 615, and the shrink fit between the stator 611 and the rotor 612.

With the above configuration, the inference device 10 can infer the second part data based on at least one of the compression mechanism 62, the outer diameter of the stator 611, the inner diameter of the stator 611, the width of the stator 611, the outer diameter of the rotor 612, the inner diameter of the rotor 612, the amount of magnetic flux of the rotor 612 interlinked with the winding 615, the resistance value of the winding 615, and the shrink fit between the stator 611 and the rotor 612.

The first part data includes at least one of the following: identification information of the manufacturing equipment for manufacturing the compressor 6, the current generated in the manufacturing equipment, the voltage generated in the manufacturing equipment, the noise generated in the manufacturing equipment, the vibration generated in the manufacturing equipment, the time required to manufacture the compressor 6, the welding temperature during the manufacturing of the compressor 6, the welding amount during welding, the temperature at the manufacturing site of the compressor 6, and the humidity at the manufacturing site.

With the above configuration, the inference device 10 can infer the second part data based on at least one of the identification information of the manufacturing equipment, the current generated in the manufacturing equipment, the voltage generated in the manufacturing equipment, the noise generated in the manufacturing equipment, the vibration generated in the manufacturing equipment, the time required to manufacture the compressor 6, the welding temperature during the manufacturing of the compressor 6, the welding amount during welding, the temperature at the manufacturing site of the compressor 6, and the humidity at the manufacturing site.

The characteristic data includes at least one of performance data related to the performance of the compressor 6, noise data related to the noise of the compressor 6, vibration data related to the vibration of the compressor 6, and assembly data related to the assembly state of the compressor 6.

With the above configuration, the inference device 10 can infer second part data that satisfies at least one of the performance, noise, vibration, and assembly state of the compressor 6.

The assembly data includes at least one of the following: the size of the gap between the stator 611 and rotor 612 of the electric motor 61 of the compressor 6, a value indicating the airtightness of the compressor 6, a value indicating the welding condition of the compressor 6, and the performance of the compressor 6.

With the above configuration, the inference device 10 can infer second part data that satisfies at least one of the dimensions of the gap between the stator 611 and the rotor 612, a value indicating the airtightness of the compressor 6, a value indicating the welding condition of the compressor 6, noise data indicating the noise of the compressor 6, vibration data indicating the vibration of the compressor 6, and the performance of the compressor 6.

The trained model 20 is generated by performing machine learning using training data including the first part data and characteristic data, and the second part data, to infer the second part data based on the first part data and characteristic data.

With the above configuration, the inference device 10 can use the trained model 20 to infer the second part data based on the first part data and characteristic data.

The inference method according to one embodiment is an inference method inferring data related to at least one part used in the assembly of the compressor 6 by a computer. The inference method includes, as processing executed by the computer, steps of acquiring first part data related to at least one first part used in a first step in the assembly of the compressor 6 and characteristic data related to the characteristics of the compressor 6 (S22, S32), and steps of inferring second part data related to at least one second part to be assembled to the at least one first part in a second step subsequent to the first step, based on the first part data and characteristic data acquired in the acquiring step, using a trained model 20 for inferring second part data related to at least one second part based on the first part data and characteristic data.

With the above configuration, when assembling at least one second part to at least one first part used in a first process in a second process subsequent to the first process, the computer can use the trained model 20 to infer second part data for at least one second part based on first part data for at least one first part and characteristic data relating to the characteristics of the compressor 6. This makes it possible to obtain at least one optimal second part to be assembled to at least one first part, thereby eliminating waste associated with assembling the compressor 6.

The manufacturing method of the compressor 6 according to one embodiment includes, as processes executed by a computer, steps of assembling at least one first part in a first step (S21, S31); acquiring first part data related to the at least one first part used in the first step and characteristic data related to the characteristics of the compressor 6 (S22, S32); inferring second part data related to at least one second part to be assembled to the at least one first part in a second step subsequent to the first step based on the first part data and characteristic data acquired in the acquiring step using a trained model 20 for inferring second part data related to at least one second part based on the first part data and characteristic data (S23, S33); and assembling at least one second part selected or processed based on the second part data into at least one first part in the second step (S27, S37).

With the above configuration, in the manufacturing process of the compressor 6, the computer can use the trained model 20 to infer second part data for at least one second part based on first part data for at least one first part and characteristic data related to the characteristics of the compressor 6. This makes it possible to obtain at least one optimal second part that can be assembled to at least one first part, thereby eliminating waste associated with the assembly of the compressor 6.

The embodiments disclosed herein should be considered in all respects as illustrative and not restrictive. The scope of the present disclosure is indicated by the claims, not by the description of the embodiments above, and is intended to include all modifications within the meaning and scope of the claims.

6 Compressor, 10 Inference device, 11 Control unit, 12 Memory unit, 13 Input unit, 20 Learned model, 30 Learning data, 40 Learning program, 60 Shell, 60A, 60B, 60C Shell parts, 61 Motor, 62 Compression mechanism unit, 63 Accumulator, 64 Suction pipe, 65 Supply pipe, 66 Discharge pipe, 67 Glass terminal, 110 Learning device, 111 Data acquisition unit, 112 Model generation unit, 113 Inference unit, 114 Selection unit, 115 Processing unit, 116 Assembly unit, 121 Learning program memory unit, 122 Learned model memory unit, 201 First Trained model, 202 second trained model, 610 stator core, 611 stator, 612 rotor, 613 shaft, 613A upper shaft portion, 613B lower shaft portion, 614 slot, 615 winding, 616, 627 shaft hole portion, 617 air hole portion, 618 permanent magnet, 619 central hole portion, 621 cylinder, 622 rolling piston, 623A upper frame, 623B lower frame, 624 vane groove, 624A upper muffler, 624B lower muffler, 625 vane, 626 eccentric shaft portion, 628 back pressure chamber, 630 compression chamber.

Claims (14)

1. An inference device for inferring data relating to at least one component used in assembling a compressor, the inference device comprising:
a data acquiring unit that acquires first part data related to at least one first part used in a first step in the assembly of the compressor and characteristic data related to characteristics of the compressor;
and an inference unit that infers, based on the first part data and the characteristic data acquired by the data acquisition unit, the second part data regarding the at least one second part to be assembled to the at least one first part in a second process subsequent to the first process, using a trained model for inferring second part data regarding at least one second part based on the first part data and the characteristic data. the second part data being parameters indicative of a shape or a characteristic of the at least one second part capable of satisfying the characteristic data by being assembled into the at least one first part;
The inference device according to claim 1 , further comprising a selection unit that selects the at least one second part based on the second part data inferred by the inference unit. the second part data is a parameter for machining the at least one second part capable of satisfying the characteristic data by assembling the at least one first part;
The inference device according to claim 1 , further comprising a processing unit that processes the at least one second part based on the second part data inferred by the inference unit. The inference device according to claim 2 or 3, further comprising an assembly unit that assembles the at least one second part to the at least one first part in the second step. The inference device according to any one of claims 1 to 3, wherein the first part data is data on a lot to which the at least one first part belongs. The compressor includes a compression mechanism for compressing a refrigerant, an electric motor for supplying power to the compression mechanism for compressing the refrigerant, a shaft for connecting the compression mechanism and the electric motor, a shell for accommodating the compression mechanism, the electric motor, and the shaft, and an accumulator for drawing the refrigerant into the shell;
The inference device according to any one of claims 1 to 3, wherein the first part data indicates individual variation of at least one of the compression mechanism, the electric motor, the shaft, the shell, and the accumulator. the compression mechanism includes a cylinder, a rolling piston that rotates along an inner peripheral surface of the cylinder based on the power from the electric motor, a vane that divides a compression chamber formed by the inner peripheral surface of the cylinder and the outer peripheral surface of the rolling piston into a suction side and a compression side, an upper frame that supports the rolling piston from above, and a lower frame that supports the rolling piston from below,
7. The inference device of claim 6, wherein the first part data includes at least one of a dimension of the rolling piston, a dimension of the cylinder, a dimension of the vane, a dimension of the upper frame, a dimension of the lower frame, a dimension of a gap between the rolling piston and the upper frame, a dimension of a gap between the rolling piston and the lower frame, a dimension of a gap between the rolling piston and the cylinder, a dimension of a gap between the vane and the rolling piston, a dimension of a gap between the vane and the cylinder, a dimension of a gap between the vane and the upper frame, a dimension of a gap between the vane and the lower frame, a dimension of a gap between the shaft and the upper frame, a dimension of a gap between the shaft and the lower frame, a value indicating a deviation between a central axis of the upper frame and a central axis of the lower frame, and a value indicating a deviation between a central axis of the shell and a central axis of the shaft. The electric motor includes a stator, a winding wound around the stator, and a rotor provided inside the stator,
7. The inference device of claim 6, wherein the first part data includes at least one of an outer diameter dimension of the stator, an inner diameter dimension of the stator, a width dimension of the stator, an outer diameter dimension of the rotor, an inner diameter dimension of the rotor, an amount of magnetic flux of the rotor interlinked with the winding, a resistance value of the winding, and a shrink fit between the stator and the rotor. The inference device according to claim 6, wherein the first part data includes at least one of identification information of a manufacturing device for manufacturing the compressor, a current generated in the manufacturing device, a voltage generated in the manufacturing device, a noise generated in the manufacturing device, a vibration generated in the manufacturing device, a time required to manufacture the compressor, a welding temperature during the manufacturing of the compressor, a welding amount in the welding, a temperature at the manufacturing site of the compressor, and a humidity at the manufacturing site. The inference device according to any one of claims 1 to 3, wherein the characteristic data includes at least one of performance data related to the performance of the compressor, noise data related to the noise of the compressor, vibration data related to the vibration of the compressor, and assembly data related to the assembly state of the compressor. The inference device according to claim 10, wherein the assembly data includes at least one of the following: a dimension of a gap between a stator and a rotor of an electric motor included in the compressor, a value indicating the airtightness of the compressor, a value indicating a welding condition in the compressor, and a characteristic value of the compressor. The inference device according to any one of claims 1 to 3, wherein the trained model is generated by performing machine learning using training data including the first part data, the characteristic data, and the second part data to infer the second part data based on the first part data and the characteristic data. 1. A method for inferring by a computer data relating to at least one component used in assembling a compressor, comprising:
The process executed by the computer is
acquiring first part data relating to at least one first part used in a first step in the assembly of the compressor and characteristic data relating to characteristics of the compressor;
and inferring, based on the first part data and the characteristic data acquired in the acquiring step, second part data regarding the at least one second part to be assembled to the at least one first part in a second step subsequent to the first step, using a trained model for inferring second part data regarding at least one second part based on the first part data and the characteristic data. 1. A computer-implemented method for manufacturing a compressor, comprising:
The process executed by the computer is
Assembling at least one first part in a first process;
acquiring first part data relating to the at least one first part used in the first step and characteristic data relating to characteristics of the compressor;
inferring, based on the first part data and the characteristic data acquired by the acquiring step, second part data regarding the at least one second part to be assembled to the at least one first part in a second step subsequent to the first step, using a trained model for inferring second part data regarding at least one second part based on the first part data and the characteristic data;
and in the second step, assembling the at least one second part, selected or processed based on the second part data, to the at least one first part.

Images