WO2023167074A1 - 制御支援装置および制御支援方法 - Google Patents
制御支援装置および制御支援方法 Download PDFInfo
- Publication number
- WO2023167074A1 WO2023167074A1 PCT/JP2023/006489 JP2023006489W WO2023167074A1 WO 2023167074 A1 WO2023167074 A1 WO 2023167074A1 JP 2023006489 W JP2023006489 W JP 2023006489W WO 2023167074 A1 WO2023167074 A1 WO 2023167074A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- substrate processing
- processing apparatus
- correspondence
- component
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
- H01L21/67005—Apparatus not specifically provided for elsewhere
- H01L21/67242—Apparatus for monitoring, sorting or marking
- H01L21/67253—Process monitoring, e.g. flow or thickness monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
- H01L21/67005—Apparatus not specifically provided for elsewhere
- H01L21/67011—Apparatus for manufacture or treatment
- H01L21/67017—Apparatus for fluid treatment
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/41—Servomotor, servo controller till figures
- G05B2219/41108—Controlled parameter such as gas mass flow rate
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/45—Nc applications
- G05B2219/45031—Manufacturing semiconductor wafers
Definitions
- the present invention relates to a control support device and a control support method.
- a substrate processing apparatus that processes substrates such as semiconductor substrates (semiconductor wafers) includes an air supply/exhaust system to keep the atmosphere in the chamber where the substrates are processed clean.
- Patent Document 1 describes a configuration for supplying clean air into a chamber and a configuration for discharging air from the chamber. Generally, the inside of the chamber of the substrate processing apparatus is kept at a constant pressure in order to prevent scattering of particles.
- Patent Document 2 describes an exhaust duct including an exhaust valve and an FFU (fan filter unit) provided at the air outlet of the chamber. In the substrate processing apparatus, the pressure in the chamber is kept constant by controlling the components (parts or equipment) of the air supply and exhaust system.
- control parameter values for each component is made by engineers.
- the engineer in order to determine the value of the control parameter, the engineer must repeatedly fine-tune the value of the control parameter for each component and each processing recipe (processing procedure) by teaching the substrate processing apparatus. A lot of time is spent on these tasks.
- An object of the present invention is to provide a control support device and a control support method that can reduce labor for determining control parameter values of components of an air supply and exhaust system of a substrate processing apparatus.
- a control support device is a control support device that determines parameter values, which are control parameter values for controlling components in an air supply/exhaust system of a substrate processing apparatus, wherein the substrate processing Correspondence between a plurality of model identification information for respectively identifying a plurality of judgment models for respectively judging the normality of the operation of the component from the processing information indicating the operation or state related to the substrate processing of the apparatus, and the plurality of parameter values.
- a correspondence acquisition unit that acquires a relationship; and an information acquisition that acquires model identification information corresponding to a judgment model capable of obtaining an appropriate judgment result from processing information during operation of the component among the plurality of judgment models.
- a determination unit that determines the parameter value for controlling the component based on the correspondence acquired by the correspondence acquisition unit and the model identification information acquired by the information acquisition unit.
- the constituent elements of the air supply and exhaust system of the substrate processing apparatus are controlled based on the parameter values.
- the normality of the component is determined by a plurality of determination models from the processing information of the substrate processing apparatus.
- a plurality of model identification information and a plurality of parameter values are associated in advance.
- Correspondence relationships between the plurality of model identification information and the plurality of parameter values are acquired by the correspondence acquisition unit.
- model identification information corresponding to a judgment model capable of obtaining an appropriate judgment result among a plurality of judgment models is acquired from the processing information during operation of the component. In this case, it is possible to determine a judgment model that can obtain an appropriate judgment result based on the model identification information.
- parameter values are determined based on the obtained correspondence and the obtained model identification information. Therefore, the parameter values for controlling the components in the air supply/exhaust system of the substrate processing apparatus are automatically determined as appropriate parameter values. As a result, it is possible to reduce labor for determining appropriate values of the control parameters of the components in the air supply and exhaust system of the substrate processing apparatus.
- the information acquisition unit may acquire model identification information of a judgment model corresponding to a judgment result indicating the highest degree of normality among the plurality of judgment results of the plurality of judgment models.
- the degree of normality is determined by a plurality of determination models from the processing information during operation of the equipment in the air supply and exhaust system, and the model identification information corresponding to the determination model corresponding to the determination result indicating the highest degree of normality is acquired.
- the model identification information corresponding to the determination model corresponding to the determination result indicating the highest degree of normality is acquired.
- the substrate processing apparatus includes a plurality of constituent elements of the same type as the constituent elements, the plurality of parameter values are values for controlling the plurality of constituent elements, respectively, and the determination unit includes: The parameter values for controlling each component may be determined based on the correspondence obtained by the correspondence obtaining unit and the model identification information obtained by the information obtaining unit.
- the parameter value corresponding to the other device when determining the parameter value corresponding to each device, the parameter value corresponding to the other device can be determined as the parameter value corresponding to the one device. Therefore, it is possible to easily determine parameter values for a plurality of devices.
- the control support apparatus may further include a transmission section that transmits the parameter value determined by the determination section to the substrate processing apparatus.
- the parameter values to be used for controlling the equipment in the air supply/exhaust system of the substrate processing apparatus are transmitted to the substrate processing apparatus. Thereby, it becomes possible to automatically set the parameter values for controlling the equipment in the air supply/exhaust system of the substrate processing apparatus in the substrate processing apparatus.
- the determination unit determines whether the The parameter values used to control the component may be determined.
- the parameter values used in the apparatus after installation or replacement can be automatically determined to appropriate values in a short period of time.
- the correspondence obtaining unit acquires model identification information corresponding to the determination model capable of obtaining the appropriate determination result, and the determination unit acquires the correspondence relationship acquired by the correspondence acquisition unit.
- the parameter value to be newly used for controlling the component may be determined based on the correspondence relationship and the model identification information acquired by the information acquisition unit.
- the judgment result of the judgment model corresponding to the parameter value will be abnormal. May indicate status.
- new parameter values to be used for controlling the equipment can be determined automatically and in a short time. As a result, it is possible to continue using the device.
- Each of the plurality of judgment models is an invariant relationship between the plurality of processing information indicating operations or states related to substrate processing of the substrate processing apparatus and actually collected from the substrate processing apparatus.
- the degree of normality of the component may be determined based on a plurality of pieces of processing information.
- the normality of the operation of the equipment is appropriately determined based on the invariant relationship between the processing information of the substrate processing apparatus.
- the acquired model identification information indicates a judgment model that can obtain a more appropriate judgment result. Therefore, it is possible to determine more appropriate parameter values used for device control.
- the control support device further includes a storage unit that stores the correspondence relationship, the correspondence acquisition unit acquires the correspondence stored by the storage unit, and the determination unit acquires the correspondence relationship.
- the parameter values for controlling the components may be determined using the correspondences stored in the unit.
- the substrate processing apparatus includes a chamber in which substrate processing is performed, and the constituent elements include an air supply unit for supplying and exhausting air in the chamber and an exhaust unit for exhausting air in the chamber. and wherein the parameter value may be a value associated with operation of at least one of the air supply section and the exhaust section.
- the control parameters include a first parameter corresponding to the air supply section and a second parameter corresponding to the exhaust section, and the parameter value of the first parameter is the value of the air supply section.
- An operation-related value, wherein the parameter value of the second parameter may be an operation-related value of the exhaust.
- At least one of the parameter values of the first and second parameters related to air supply and exhaust in the chamber of the substrate processing apparatus can be determined to an appropriate value in a short time. As a result, it is possible to accurately control the air supply and exhaust in the chamber.
- a control support method is a control support method for determining a parameter value, which is a value of a control parameter for controlling components in an air supply/exhaust system of a substrate processing apparatus, wherein the substrate a plurality of model identification information for respectively identifying a plurality of judgment models for respectively judging the normality of the operation of the component from the processing information indicating the operation or state related to substrate processing of the processing apparatus; and a plurality of parameter values.
- control support method it is possible to determine a judgment model capable of obtaining an appropriate judgment result based on the model identification information. Also, based on the correspondence relationship, it is possible to discriminate the parameter values corresponding to the discriminated judgment model. Accordingly, parameter values are determined based on the obtained correspondence and the obtained model identification information. Therefore, the parameter values for controlling the equipment in the air supply/exhaust system of the substrate processing apparatus are automatically determined to be appropriate parameter values. As a result, it is possible to reduce labor for determining appropriate values of the control parameters of the components in the air supply and exhaust system of the substrate processing apparatus.
- FIG. 1 is a diagram for explaining the configuration of a substrate processing system including a control support device according to one embodiment.
- FIG. 2 is a diagram for explaining a specific calculation example of the degree of divergence.
- FIG. 3 is a diagram for explaining a specific calculation example of an abnormality score.
- FIG. 4 is a conceptual diagram for explaining operations of the substrate processing apparatus 1, the information analysis apparatus, and the control support apparatus in the learning operation and proper parameter value updating operation.
- FIG. 5 is a conceptual diagram for explaining a plurality of judgment models.
- FIG. 6 is a conceptual diagram for explaining the correspondence between judgment model numbers and parameter values.
- FIG. 7 is a block diagram for explaining the functional configuration of the information analysis device and control support device of FIG. FIG.
- FIG. 8 is a flow chart showing an example of the operation of the control device of the substrate processing apparatus during the learning operation.
- FIG. 9 is a flow chart showing an example of the operation of the information analysis apparatus during learning operation.
- FIG. 10 is a flow chart showing an example of the operation of the control support device during the learning operation.
- FIG. 11 is a flow chart showing an example of the operation of the substrate processing apparatus in the proper parameter value update operation.
- FIG. 12 is a flow chart showing an example of the operation of the information analysis device in the proper parameter value updating operation.
- FIG. 13 is a flow chart showing an example of the operation of the control support device in the proper parameter value update operation.
- FIG. 14 is a schematic diagram for explaining a substrate processing system including a substrate processing apparatus according to a reference embodiment.
- the substrate means a semiconductor substrate (semiconductor wafer), a substrate for FPD (Flat Panel Display) such as a liquid crystal display device or an organic EL (Electro Luminescence) display device, an optical disk substrate, a magnetic disk substrate, a magneto-optical Disc substrates, photomask substrates, ceramic substrates, solar cell substrates, etc.
- FPD Fluorescence Deposition
- OLED Electro Luminescence
- FIG. 1 is a diagram for explaining the configuration of a substrate processing system including a control support device according to one embodiment.
- a substrate processing system 100 of FIG. 1 includes a substrate processing apparatus 1 , an information analysis apparatus 3 and a control support apparatus 4 .
- the control support device 4 is connected to the substrate processing device 1 and the information analysis device 3 .
- the control support device 4 is connected to each of the substrate processing device 1 and the information analysis device 3 via a wired or wireless communication path or network.
- the control support device 4 is connected to each of the substrate processing device 1 and the information analysis device 3 via a communication network such as the Internet.
- the control support device 4 is connected to the substrate processing device 1 and the information analysis device 3 via a wired or wireless LAN (Local Area Network).
- a wired or wireless LAN Local Area Network
- the substrate processing apparatus 1 includes a control device 40 and a plurality of substrate processing units WU.
- Each substrate processing unit WU has a spin chuck SC and a chamber CH for holding and rotating the substrate W.
- the chamber CH has an opening through which the substrate W can pass, and has a shutter (not shown) for opening and closing the opening.
- the substrate processing unit WU includes, for example, a substrate cleaning unit, a photosensitive film forming unit, an edge exposing unit, a developing unit, and the like.
- the substrate processing apparatus 1 includes various components (devices, parts, etc.) that constitute the substrate processing apparatus 1 .
- the substrate processing apparatus 1 includes an air supply/exhaust system AES for keeping the atmosphere inside the chamber CH of each substrate processing unit WU clean.
- various processes are performed on the substrate W held by the spin chuck SC.
- the substrate W is cleaned by supplying the cleaning liquid to the substrate W.
- the air supply/exhaust system AES includes, as components, an air supply unit FFU, an exhaust unit ED, and pressure gauges PG1 and PG2.
- the control device 40 includes a first controller 40a for controlling the plurality of air supply units FFU and a second controller 40b for controlling the plurality of exhaust units ED.
- the substrate processing apparatus 1 is provided with a display device, an audio output device, and an operation unit (not shown).
- the substrate processing apparatus 1 is operated according to a predetermined processing procedure (processing recipe) of the substrate processing apparatus 1 .
- the air supply unit FFU is provided at the air supply port of the chamber CH to supply clean gas (for example, air or inert gas) into the chamber CH.
- the air supply unit FFU is, for example, a fan filter unit including a fan motor. The rotation speed of the fan motor is adjusted in the air supply unit FFU. Thereby, the flow rate of the gas supplied into the chamber CH is adjusted.
- the exhaust part ED is provided at the exhaust port of the chamber CH to exhaust the gas inside the chamber CH.
- the exhaust part ED includes an exhaust damper including, for example, a damper motor. In the exhaust section ED, the opening of the exhaust damper is adjusted by the damper motor. Thereby, the flow rate of the gas discharged from the chamber CH is adjusted.
- the pressure gauge PG1 measures the pressure of the gas supplied to the chamber CH (hereinafter referred to as first control pressure).
- the pressure gauge PG2 measures the pressure of the gas discharged from the chamber CH (hereinafter referred to as second control pressure).
- the first control unit 40a of the control device 40 sets the value of the first control pressure to a predetermined pressure value (hereinafter referred to as a first target pressure value). to control.
- the second control unit 40b of the control device 40 operates the exhaust unit ED to set the value of the second control pressure to a predetermined pressure value (hereinafter referred to as a second target pressure value). Control.
- the first control unit 40a in order to keep the pressure of the gas supplied into the chamber CH constant, the first control unit 40a, based on the difference between the first control pressure and the first target pressure value, The electric power supplied to the fan motor of the air supply unit FFU is controlled by PID (proportional-integral-derivative). Thereby, the pressure of the gas supplied into the chamber CH is kept constant.
- the second control unit 40b controls the pressure of the exhaust unit ED based on the difference between the second control pressure and the second target pressure value. Power supplied to the damper motor is PID-controlled. Thereby, the pressure of the gas discharged from the chamber CH is kept constant.
- the pressure in the chamber CH is kept constant by the control of the first controller 40a and the second controller 40b.
- the substrate processing apparatus 1 of FIG. 1 is provided with a plurality of air supply units FFU of the same type and a plurality of exhaust units ED of the same type corresponding to the plurality of substrate processing units WU.
- the controller 40 controls the components of the substrate processing apparatus 1
- the components are controlled with various control parameter values.
- the control device 40 controls the operation of each component according to control parameters determined for each type of component. In this case, even components of the same type have different characteristics due to individual differences. Therefore, appropriate control parameter values are set for a plurality of components of the same type.
- the values of the control parameters are hereinafter referred to as parameter values.
- the control parameters used to control the air supply unit FFU and the exhaust unit ED are the P gain, I gain, D gain, control period, dead band area, and the like.
- Processing Information In the substrate processing apparatus 1, a plurality of processes indicating operations or states related to processing of substrates W in the substrate processing apparatus 1 are stored as information for managing abnormalities in constituent elements of the substrate processing apparatus 1. Information is defined.
- the processing information is transmitted from the control device 40 of the substrate processing apparatus 1 to the information analysis device 3 via the control support device 4 at predetermined intervals, as indicated by the thick solid arrow in FIG. be done.
- the processing information transmitted from the substrate processing apparatus 1 to the information analysis apparatus 3 via the control support apparatus 4 includes "a. FFU fan rotation speed” and “b. FFU internal pressure value”, “c. current position of exhaust damper”, “d. chamber exhaust pressure value” and “e. shutter open/close timing”.
- processing information relating to the component air supply unit FFU and exhaust unit ED is shown.
- Fan rotation speed of FFU indicates the rotation speed of the fan of the air supply unit FFU.
- Internal pressure value of FFU is the value of the pressure in the air supply unit FFU.
- Exhaust damper current position is a value indicating the opening degree of the damper of the exhaust section ED.
- Chamber exhaust pressure value is the value of the pressure of the gas exhausted from the exhaust part ED.
- Shutter open/close timing is a value indicating the open/close timing of the shutter provided in the chamber CH.
- the information analysis device 3 is, for example, a server, and includes a CPU (Central Processing Unit) and memory.
- the information analysis device 3 collects a plurality of pieces of processing information transmitted from the substrate processing device 1 .
- a plurality of combinations of two pieces of processing information that are different from each other are predetermined for a plurality of pieces of processing information transmitted from the substrate processing device 1 to the information analysis device 3 .
- an invariant relationship (hereinafter referred to as an invariant relationship) is maintained between the two pieces of processing information that make up each combination.
- the invariant relationship is set for each predetermined processing procedure (processing recipe) of the substrate processing apparatus 1 .
- the information analysis device 3 calculates the degree of divergence between a plurality of combinations of actually collected processing information and a plurality of invariant relations predetermined for the plurality of processing information. Calculate as degrees. Further, the information analysis device 3 calculates the degree of abnormality of the component as an abnormality score based on the plurality of degrees of divergence that have been calculated.
- the anomaly score represents the normality of the operation of the component. That is, when the anomaly score is low, the normality of the behavior of the component is high, and when the anomaly score is high, the normality of the behavior of the component is low. A specific example of the method of calculating the anomaly score will be described later.
- anomaly score changes depending on the parameter values set for each component. If the parameter values set for each component are appropriate, the normality of the operation of that component will be high and the abnormality score will be low. Conversely, if the parameter values set for each component are not appropriate, the normality of the operation of that component will be low and the abnormality score will be high. As described below, in the present embodiment, anomaly scores can be used to determine appropriate parameter values.
- FIG. 2 is a diagram for explaining a specific calculation example of the degree of divergence.
- an example of calculation of the degree of divergence corresponding to the combination of "a. fan rotation speed of FFU" and “b. internal pressure value of FFU” in FIG. 1 will be described.
- the data of "a. fan rotation speed of FFU” will be referred to as "a” data
- the data of "b. internal pressure value of FFU” will be referred to as "b” data.
- ideal "a” data and "b” data are obtained, for example, based on a plurality of pieces of processing information transmitted from the substrate processing apparatus 1 when the substrate processing apparatus 1 is actually operating normally. .
- the ideal 'a' data and 'b' data may be generated by simulation or the like.
- FIG. 2 An example of the temporal change of ideal "a" data and "b" data is shown by a graph.
- the horizontal axis represents time and the vertical axis represents the rotational speed value of the fan of the air supply unit FFU.
- the horizontal axis represents time
- the vertical axis represents the internal pressure value of the air supply unit FFU.
- the horizontal axis (time axis) is common between the "a" data graph and the "b" data graph.
- an invariant relationship is created for each combination of a plurality of pieces of processing information (the "a” to "e” data described above).
- an invariant relationship is created for each component of the exhaust system of the substrate processing apparatus 1 (FIG. 1).
- the substrate W is processed in the substrate processing apparatus 1, and the actual "a" data and "b” data are collected by the information analysis device 3.
- the information analysis device 3 In the central part of FIG. 2, an example of the temporal change of actually collected "a” data and "b” data is shown by a graph.
- the "b” data is predicted based on pre-stored invariant relations. Also, once the actual 'b' data is collected, the 'a' data is predicted based on pre-stored invariant relationships.
- FIG. 2 an example of the temporal change of the "a” data and the "b" data predicted based on the invariant relationship is shown graphically. In the lower graph of FIG. 2, the predicted “a” data and “b” data are indicated by solid lines, and the actually collected "a” data and "b” data are indicated by dotted lines.
- the difference value between data that is actually collected processing information and data that is predicted processing information is calculated as the degree of divergence.
- the information analysis device 3 calculates the difference value between the actual "a” data and the predicted "a” data as the deviation when calculating the deviation at a certain time.
- the information analysis device 3 also calculates the difference value between the actual "b" data and the predicted "b” data as the degree of divergence.
- FIG. 3 is a diagram for explaining a specific calculation example of an anomaly score.
- the information analysis device 3 calculates the degree of divergence for all combinations of multiple pieces of processing information.
- a plurality of values arranged in the row on the right side of each of the processing information “a” to “e” in the left vertical column of FIG. 3 were predicted from each of the processing information “a” to “e” in the upper horizontal column. It represents the degree of divergence between processing information and actually acquired processing information.
- the value “35” in the column at the intersection of the right row of the processing information "a” in the left vertical column and the lower column of the processing information "b” in the upper horizontal column is the processing information "b ” and the actually acquired processing information “a”.
- the value "21” in the column at the intersection of the right row of the processing information "b” in the left vertical column and the lower column of the processing information "a” in the upper horizontal column is the processing information "a , and the actually acquired processing information “b”.
- FIG. 3 shows a plurality of divergence degrees calculated for all combinations of a plurality of pieces of processing information related to one component.
- the information analysis device 3 calculates the sum of the calculated plurality of degrees of deviation as the abnormality score corresponding to the component.
- the anomaly score is 161.
- a decision model that determines the normality of operation of the component is generated and updated by machine learning.
- a plurality of determination models are generated and updated corresponding to a plurality of components of the same type (for example, a plurality of air supply units FFU) of the substrate processing apparatus 1.
- FIG. in the present embodiment the determination result of the degree of normality of the operation of the component corresponding to each determination model is calculated as the abnormality score.
- parameter values to be set for one or more components are determined based on anomaly scores calculated by a plurality of judgment models.
- An operation of generating a plurality of decision models by machine learning is hereinafter referred to as a learning operation.
- the operation of updating (finely adjusting) the parameter values set for each component is called proper parameter value updating operation.
- FIG. 4 is a conceptual diagram for explaining operations of the substrate processing apparatus 1, the information analysis apparatus 3, and the control support apparatus 4 in the learning operation and the proper parameter value updating operation.
- FIG. 5 is a conceptual diagram for explaining a plurality of judgment models.
- FIG. 6 is a conceptual diagram for explaining the correspondence between judgment model numbers and parameter values.
- n is an integer of 2 or more.
- the controller 40 of the substrate processing apparatus 1 controls the operations of the plurality of components C1-Cn based on the parameter values PR1-PRn set in the memory ME.
- PIn respectively corresponding to the plurality of components C1 to Cn are transmitted from the substrate processing apparatus 1 to the information analysis apparatus 3.
- Each of the plurality of pieces of processing information PI1-PIn includes one or more pieces of processing information. For example, when a plurality of components C1 to Cn are a plurality of air supply units FFU, a plurality of pieces of processing information “a” to “e” corresponding to each air supply unit FFU are transmitted to the information analysis device 3. .
- the judgment model generator 32 of the information analysis device 3 generates a plurality of judgment models MD1, MD2, . Generate. For example, determination models MD1 to MDn corresponding to the plurality of air supply units FFU in FIG. 1 are generated. In the present embodiment, judgment model numbers M1 to Mn are given to the plurality of judgment models MD1 to MDn as model identification information for identifying each judgment model.
- FIG. 5 shows examples of two decision models MD1 and MD2.
- the judgment models MD1 and MD2 have different functions representing the relationship between changes in each piece of processing information and changes in other processing information.
- processing information "a” is represented by a function f1 having processing information "b” as a variable.
- processing information "b” is represented by a function g1 having the processing information "a” as a variable.
- the processing information "a” is represented by a function f2 having the processing information "b” as a variable.
- the processing information "b” is represented by a function g2 having the processing information "a” as a variable.
- a plurality of parameter values PR1 to PRn corresponding to a plurality of components C1 to Cn are transmitted from the substrate processing apparatus 1 to the control support device 4, and a plurality of judgment models MD1 of the information analysis device 3 are transmitted.
- a plurality of judgment model numbers M1 to Mn corresponding to .about.MDn are transmitted from the information analysis device 3.
- the control support device 4 stores the correspondence CR between the plurality of judgment model numbers M1 to Mn and the plurality of parameter values PR1 to PRn.
- FIG. 6 shows the corresponding relationship for one air supply unit FFU in FIG.
- the control parameters include control period, P gain, I gain, D gain, and dead zone area.
- a plurality of judgment model numbers M1 to Mn are associated with control period values, filter coefficient values, P gain values, I gain values, D gain values, and dead zone values. be done.
- a plurality of decision models MD1 to MDn corresponding to a plurality of components C1 to Cn are generated, and the correspondence relationships CR between the plurality of decision model numbers M1 to Mn and the plurality of parameter values are generated. is set.
- the control device 40 controls the operations of the plurality of components C1-Cn based on the parameter values PR1-PRn set in the memory ME. As a result, a plurality of pieces of processing information PI1-PIn respectively corresponding to the plurality of components C1-Cn are transmitted from the substrate processing apparatus 1 to the information analysis apparatus 3.
- FIG. 1 a plurality of pieces of processing information PI1-PIn respectively corresponding to the plurality of components C1-Cn are transmitted from the substrate processing apparatus 1 to the information analysis apparatus 3.
- the information analysis device 3 determines the degree of normality of the components C1 to Cn corresponding to the plurality of determination models MD1, MD2, . . Abnormality scores AS1-ASn corresponding to a plurality of components C1-Cn may be sent to substrate processing apparatus 1 or control support apparatus 4. FIG. Thereby, the operator can recognize whether each component C1 to Cn of the substrate processing apparatus 1 is normal or abnormal.
- the component whose characteristics have deteriorated is replaced with a new component. Due to individual differences between the component before replacement and the component after replacement, the characteristics of the component after replacement may differ from the characteristics of the component before replacement. In this case also, it is necessary to update (finely adjust) the parameter values for the pre-replacement component to appropriate parameter values for the post-replacement component.
- the controller 40 of the substrate processing apparatus 1 controls the component C1 with the parameter value PR1 already set for the component C1. Thereby, the processing information PI1 related to the component C1 is transmitted from the substrate processing apparatus 1 to the information analysis apparatus 3.
- FIG. 1
- the processing information PI1 related to the component C1 is given to a plurality of judgment models MD1 to MDn.
- a plurality of determination models MD1 to MDn calculate abnormality scores AS1 to ASn as determination results based on the processing information PI1 by the method described with reference to FIGS. 2 and 3, respectively.
- the minimum score determination unit 35 determines the abnormality score having the minimum value among the abnormality scores AS1 to ASn calculated by the plurality of determination models MD1 to MDn, and performs determination corresponding to the determination model that has calculated the abnormality score having the minimum value.
- the model number is sent to the control support device 4 .
- the anomaly score with the lowest value indicates the highest degree of normality.
- the abnormality score ASn calculated by the judgment model MDn has the minimum value.
- the determination model number Mn corresponding to the determination model MDn is transmitted from the minimum score determination unit 35 to the control support device 4 .
- the control support device 4 determines the parameter value PRn corresponding to the judgment model number Mn acquired from the information analysis device 3 as the appropriate parameter value based on the correspondence CR acquired during learning.
- the determined appropriate parameter value PRn is transmitted from the control support device 4 to the substrate processing apparatus 1 .
- the parameter value PR1 for the component C1 is updated to the proper parameter value PRn.
- the parameter values PR2-PRn for the other components C2-Cn can be updated.
- FIG. 7 is a block diagram mainly for explaining the functional configuration of the information analysis device 3 and the control support device 4 in FIG. It is a diagram.
- the substrate processing apparatus 1 includes the control device 40 of FIG. In FIG. 7, the illustration of the plurality of components C1 to Cn and the storage unit ME in FIG. 4 is omitted.
- the information analysis device 3 of FIG. 7 includes an information reception section 31, a judgment model generation section 32, a minimum score judgment section 35, a judgment model storage calculation section 33, and a judgment model number transmission section .
- the information analysis device 3 is composed of, for example, a CPU (Central Processing Unit) and a memory.
- a plurality of functional units (31 to 35) in FIG. 7 are implemented by the CPU executing a control program stored in the memory.
- the control support device 4 is composed of, for example, a CPU (Central Processing Unit) and a memory.
- a plurality of functional units (41 to 48) in FIG. 7 are implemented by the CPU executing a control program stored in the memory. The functions and operations of the functional units (31 to 35, 41 to 48) shown in FIG. 7 will be described with reference to flowcharts shown in FIGS. 8 to 13, which will be described later.
- FIG. 8 is a flowchart showing an example of the operation of the control device 40 of the substrate processing apparatus 1 during the learning operation.
- FIG. 9 is a flow chart showing an example of the operation of the information analysis device 3 during the learning operation.
- FIG. 10 is a flow chart showing an example of the operation of the control support device 4 during the learning operation.
- step S10 the controller 40 of the substrate processing apparatus 1 determines whether or not a command to start the learning operation has been issued. If the start of the learning operation has not been commanded, the control device 40 waits until the start of the learning operation is commanded. When the start of the learning operation is instructed, a plurality of constituent elements C1 to Cn are controlled with a plurality of preset parameter values PR1 to PRn in FIG. 4 (step S11).
- control device 40 transmits a plurality of pieces of processing information PI1 to PIn obtained by the operations of the plurality of components C1 to Cn to the information analysis device 3 via the control support device 4 (step S12). Note that the control device 40 may directly transmit the obtained plurality of pieces of processing information PI1 to PIn to the information analysis device 3.
- step S13 the control device 40 determines whether or not an instruction to end the learning operation has been issued (step S13). If the end of the learning operation has not been instructed, the control device 40 returns to step S11. Thereby, the operations of steps S11 to S13 are repeated. When the end of the learning operation is commanded in step S13, the learning operation ends.
- the information receiving unit 31 of the information analysis device 3 determines whether or not the start of the learning operation has been instructed (step S20). If the start of the learning operation has not been commanded, the information receiving section 31 waits until the start of the learning operation is commanded. When the start of the learning operation is instructed, the information receiving section 31 determines whether or not the plurality of pieces of processing information PI1 to PIn transmitted in step S12 of FIG. 8 have been received (step S21). When the plurality of pieces of processing information PI1 to PIn have not been received, the information receiving section 31 waits until the plurality of pieces of processing information PI1 to PIn are received.
- the judgment model generator 32 When receiving a plurality of pieces of processing information PI1 to PIn, the judgment model generator 32 generates a plurality of judgment models MD1 to MDn corresponding to the plurality of components C1 to Cn by machine learning (step S22). At this time, the judgment model generator 32 gives judgment model numbers M1 to Mn to the plurality of judgment models MD1 to MDn as model identification information for identifying each judgment model.
- the determination model storage/calculation unit 33 stores the plurality of determination models MD1 to MDn generated by the determination model generation unit 32 (step S23).
- the determination model number transmission unit 34 transmits the determination model numbers M1 to Mn of the plurality of determination models MD1 to MDn stored in the determination model storage calculation unit 33 to the control support device 4 (step S24). After that, the information receiving section 31 determines whether or not an instruction to end the learning operation has been issued (step S25). If the end of the learning operation has not been instructed, the information receiving section 31 returns to step S21. Thereby, the operations of steps S21 to S25 are repeated.
- the judgment model storage calculation unit 33 stores a plurality of judgment models MD1 to MDn corresponding to the plurality of components C1 to Cn.
- the learning operation ends.
- the processing information acquisition unit 41 of the control support device 4 determines whether or not a command to start the learning operation has been issued (step S30). When the start of the learning operation has not been commanded, the processing information acquiring unit 41 waits until the start of the learning operation is commanded. When the start of the learning operation is instructed, the processing information acquisition unit 41 determines whether or not a plurality of pieces of processing information PI1 to PIn have been received (step S31). If the plurality of pieces of processing information PI1 to PIn have not been received, the processing information acquiring unit 41 waits until the plurality of pieces of processing information PI1 to PIn are received.
- the processing information acquiring unit 41 transmits the received pieces of processing information PI1 to PIn to the information analysis device 3 (step S32).
- the processing information acquiring section 41 does not perform steps S31 and S32.
- the parameter value acquisition unit 42 determines whether or not a plurality of parameter values PR1 to PRn set for controlling the constituent elements in the substrate processing apparatus 1 have been acquired (step S33). If the set parameter values PR1 to PRn have not been obtained, the parameter value obtaining unit 42 waits until the set parameter values PR1 to PRn are obtained.
- the determination model number acquisition unit 43 determines whether or not the multiple determination model numbers M1 to Mn transmitted by the information analysis device 3 have been acquired (step S34). If the plurality of judgment model numbers M1 to Mn have not been obtained, the judgment model number obtaining unit 43 waits until the plurality of judgment model numbers M1 to Mn are obtained.
- the correspondence generation unit 44 When the determination model number acquisition unit 43 acquires a plurality of determination model numbers M1 to Mn, the correspondence generation unit 44 generates a plurality of parameter values PR1 to PRn acquired by the parameter value acquisition unit 42 and the determination model number acquisition unit 43 A correspondence relationship CR is generated between the plurality of judgment model numbers M1 to Mn obtained by (step S35).
- the correspondence storage unit 45 stores the correspondence CR generated by the correspondence generation unit 44 (step S36).
- the processing information acquisition unit 41 determines whether or not an instruction to end the learning operation has been issued (step S37). If the end of the learning operation has not been instructed, the process returns to step S31. Thereby, the operations of steps S31 to S37 are repeated. When the end of the learning operation is instructed, the learning operation ends.
- FIG. 11 is a flow chart showing an example of the operation of the substrate processing apparatus 1 in the proper parameter value updating operation.
- FIG. 12 is a flow chart showing an example of the operation of the information analysis device 3 in the proper parameter value update operation.
- FIG. 13 is a flow chart showing an example of the operation of the control support device 4 in the proper parameter value update operation.
- PRk be the parameter value to be updated
- Ck be the component to be updated.
- k is any integer from 1 to n.
- the control device 40 of the substrate processing apparatus 1 determines whether or not a command to start the appropriate parameter value updating operation has been issued (step S40). If the start of the proper parameter value update operation has not been commanded, the control device 40 waits until the start of the proper parameter value update operation is commanded. When the start of the appropriate parameter value update operation is commanded, the control device 40 controls the component Ck with the preset parameter value Pk (step S41).
- control device 40 transmits the processing information PIk obtained by the operation of the component Ck to the information analysis device 3 via the control support device 4 (step S42). Note that the control device 40 may directly transmit the obtained processing information PIk to the information analysis device 3 . After that, the control device 40 determines whether or not the proper parameter value transmitted by the transmission unit 48 of the control support device 4 is received in step S64 described later (step S43). If the correct parameter values have not been received, the controller 40 waits until the correct parameter values are received.
- the control device 40 When receiving the proper parameter value, the control device 40 updates the parameter value Pk of the target component Ck to the proper parameter value (step S44). The control device 40 determines whether or not an instruction to end the proper parameter value update operation has been issued (step S45). If the end of the appropriate parameter value updating operation has not been instructed, the control device 40 returns to step S41. When the end of the proper parameter value update operation is commanded, the proper parameter value update operation ends.
- the information receiving unit 31 of the information analysis device 3 determines whether or not an instruction to start the appropriate parameter value updating operation has been issued (step S50). When the start of the proper parameter value update operation has not been commanded, the information receiving section 31 waits until the start of the proper parameter value update operation is commanded. When the start of the proper parameter value update operation is instructed, the information receiving unit 31 determines whether or not the processing information PIk transmitted by the control device 40 via the control support device 4 in step S42 of FIG. 42 has been received. (step S51).
- the information receiving unit 31 waits until the processing information PIk is received.
- the plurality of judgment models MD1 to MDn stored in the judgment model storage calculation unit 33 respectively calculate abnormality scores AS1 to ASn based on the received processing information PIk (step S52).
- the minimum score determination unit 35 determines the minimum abnormality score among the plurality of abnormality scores AS1 to ASn, and selects the determination model that has calculated the minimum abnormality score (step S53).
- the determination model number transmission unit 34 transmits the determination model number of the selected determination model to the control support device 4 (step S54). After that, the information receiving section 31 determines whether or not an instruction to end the proper parameter value updating operation has been issued (step S55). If the end of the appropriate parameter value update operation has not been instructed, the process returns to step S51. When the end of the proper parameter update operation is commanded, the proper parameter update operation is ended.
- the processing information acquisition unit 41 of the control support device 4 determines whether or not an instruction to start the appropriate parameter value updating operation has been issued (step S60).
- the processing information acquiring unit 41 waits until the start of the proper parameter value update operation is commanded.
- the determination model number acquisition unit 43 determines whether or not the determination model number transmitted from the determination model number transmission unit 34 of the information analysis device 3 in step S54 of FIG. (step S61). If the judgment model number has not been acquired, the judgment model number transmission unit 34 waits until the judgment model number is acquired.
- the correspondence acquisition unit 46 acquires the correspondence stored in the correspondence storage unit 45 (step S62).
- the appropriate parameter value determination unit 47 determines the parameter value corresponding to the determination model number acquired by the determination model number acquisition unit 43 based on the correspondence CR acquired by the correspondence acquisition unit 46 as the appropriate parameter value (step S63).
- the transmission unit 48 transmits the proper parameter values determined by the proper parameter value determination unit 47 to the substrate processing apparatus 1 (step S64).
- the processing information acquisition unit 41 determines whether or not an instruction to end the proper parameter update operation has been issued (step S65). If the end of the proper parameter update operation has not been commanded, the process returns to step S61. When the end of the proper parameter update operation is commanded, the proper parameter update operation is ended.
- the parameter value CRk for controlling at least one component Ck is updated to a proper parameter value by the proper parameter update operation.
- the plurality of parameter values PR1 to PRn can be updated (finely adjusted) to appropriate parameter values by performing similar appropriate parameter value updating operations.
- the operation of the component is controlled using the updated parameter value, so that the information analysis device 3 can detect the updated parameter value A judgment model corresponding to is generated by the learning operation described above.
- the determination model storage calculation unit 33 of the information analysis device 3 stores a new determination model in addition to the determination model corresponding to the parameter value before update.
- the number of determination models for calculating anomaly scores increases during the proper parameter value update operation.
- the appropriate parameter value updating operation is repeatedly performed, thereby improving the accuracy of the appropriate parameter value.
- the judgment model number in the example of FIG. 4, the judgment model number Mn
- a determination model determination model MDn in the example of FIG. 4 capable of obtaining an appropriate determination result
- a parameter value (parameter value PRn in the example of FIG. 4) corresponding to the determined determination model (determination model MDn in the example of FIG. 4) can be determined.
- the parameter value (the parameter value PRn in the example of FIG. 4) is determined based on the obtained correspondence CR and the obtained judgment model number (the judgment model number Mn in the example of FIG. 4).
- the parameter value for controlling the component (the component C1 in the example of FIG. 4) in the substrate processing apparatus 1 is automatically determined to be an appropriate parameter value (the parameter value PRn in the example of FIG. 4).
- parameter values for controlling other components can be automatically determined to appropriate parameter values.
- the information analysis apparatus 3 based on the invariant relationship between the processing information of the substrate processing apparatus 1, the information analysis apparatus 3 appropriately determines the degree of abnormality (degree of normality) of the operations of the plurality of components. .
- the judgment model number acquired by the judgment model number acquisition unit 43 of the control support device 4 corresponds to the judgment model that can obtain a more appropriate judgment result (anomaly score with the lowest degree of anomaly). number.
- the proper parameter value determination unit 47 determines the parameter value corresponding to the judgment model number acquired by the judgment model number acquisition unit 43 among the correspondence acquired by the correspondence acquisition unit 46 as the proper parameter value. be able to. As a result, it becomes possible to determine appropriate parameter values for controlling the components of the air supply/exhaust system AES of the substrate processing apparatus 1 .
- control support device 4 includes the transmission unit 48, so that the appropriate parameter values can be transmitted to the substrate processing apparatus 1.
- transmission unit 48 so that the appropriate parameter values can be transmitted to the substrate processing apparatus 1.
- the parameter values used for the components after installation, after inspection, or after replacement are automatically adjusted to appropriate values in a short time. Time can decide.
- control support device 4 since the control support device 4 includes the correspondence storage unit 45, there is no need to provide a configuration for storing the correspondence outside the control support device 4.
- the decision model is generated based on the invariant relationship, but the present invention is not limited to this.
- the decision model may be generated by using other machine learning methods such as deep learning.
- control support device 4 includes the transmission unit 48, but the present invention is not limited to this.
- a notification unit for notifying the appropriate parameter value determined by the appropriate parameter value determination unit 47 to the control support device 4 may be provided.
- the operator can input to the substrate processing apparatus 1 the appropriate parameter values notified by the notification unit.
- control support device 4 includes the correspondence storage unit 45, but the present invention is not limited to this.
- a configuration for storing the correspondence may be provided outside the control support device 4 .
- the correspondence may be stored in a cloud or the like on the Internet. In this case, the capacity of the storage device of the control support device 4 can be reduced.
- the substrate processing apparatus 1 and the control support device 4 are provided separately, but the substrate processing apparatus 1 and the control support device 4 may be provided as a single unit. Further, although the information analysis device 3 and the control support device 4 are provided separately in the above-described embodiment, the information analysis device 3 and the control support device 4 may be provided as a single unit.
- control support device 4 is used to determine the proper parameter values of the air supply unit FFU of the air supply/exhaust system AES among various components of the substrate processing apparatus 1. It is also possible to apply the control support device 4 according to the above embodiment to determine proper parameter values for other components of the substrate processing apparatus 1 . For example, the control support device 4 according to the above-described embodiment may be used to determine appropriate parameter values for each flow control valve of the substrate processing unit WU among various components of the substrate processing apparatus 1 .
- FIG. 14 is a schematic diagram for explaining a substrate processing system 100a including a substrate processing apparatus 1a according to another embodiment.
- the substrate processing apparatus 1a includes, as components, a processing liquid flow path RP, a flow meter, and a flow meter to supply the processing liquid onto the substrate W held by the spin chuck SC in the substrate processing unit WU.
- the flowmeter FM measures the value of the flow rate of the processing liquid flowing through the processing liquid flow path RP.
- the pressure gauge PM measures the value of the pressure inside the processing liquid flow path RP.
- the discharge valve DV performs an opening/closing operation to supply the processing liquid in the processing liquid flow path RP to the substrate processing unit WU.
- the flow control valve MV is a motor needle valve.
- the flow rate control valve MV includes a motor and a needle, and the flow rate is adjusted by moving the needle within the internal flow path by the motor.
- the control device 40 controls the electric power supplied to the motor of the flow control valve MV based on the flow rate of the processing liquid flowing through the processing liquid flow path RP detected by the flow meter FM.
- the substrate processing apparatus 1a it is possible to determine an appropriate parameter value for controlling the flow control valve MV by updating the appropriate parameter value by the information analysis device 3 and the control support device 4 in the above embodiment. is.
- the proper parameter value update operation is performed when the substrate processing apparatus 1 is installed, when the substrate processing apparatus 1 is inspected, the parameter values for each component are updated (fine adjustment), or when any of the components of the substrate processing apparatus 1 is replaced.
- this is done for updating (fine tuning) of parameter values
- the present invention is not limited to this.
- the appropriate parameter value updating operation may be performed. In this case, the parameter value of the component in which the abnormality was detected is updated to the proper parameter value. As a result, if no abnormality is detected in the component controlled with the updated appropriate parameter values, the component can be used continuously without being replaced with a new component.
- a motor needle valve is used as the flow control valve MV of the substrate processing apparatus 1a
- an abnormality of the motor needle valve is detected due to a change in the shape of the needle due to aged deterioration of the needle.
- the control support device 4 it is possible to update the parameter value for the motor needle valve in which an abnormality has been detected to an appropriate parameter value. If the motor needle is controlled with proper parameter values and no abnormality of the motor needle is detected, the motor needle can be used continuously. As a result, it is possible to extend the remaining life of the motor needle while it is in service.
- the determination model number acquisition unit 43 is an example of an information acquisition unit
- the correspondence storage unit 45 is an example of a storage unit
- the appropriate parameter value determination unit 47 is an example of a determination unit.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Power Engineering (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Container, Conveyance, Adherence, Positioning, Of Wafer (AREA)
- Cleaning Or Drying Semiconductors (AREA)
- Feedback Control In General (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
Description
図1は、一実施の形態に係る制御支援装置を含む基板処理システムの構成を説明するための図である。図1の基板処理システム100は、基板処理装置1、情報分析装置3および制御支援装置4を含む。制御支援装置4は、基板処理装置1および情報分析装置3に接続される。制御支援装置4は、基板処理装置1および情報分析装置3の各々に対して有線または無線の通信経路または通信回線網により接続される。例えば、制御支援装置4は、基板処理装置1および情報分析装置3の各々に対してインターネット等の通信回線網を介して接続される。本実施の形態において、制御支援装置4は、基板処理装置1および情報分析装置3に対して有線または無線のLAN(Local Area Network)により接続される。
図1の例では、基板処理装置1は、制御装置40および複数の基板処理ユニットWUを備える。各基板処理ユニットWUは、基板Wを保持して回転させるスピンチャックSCおよびチャンバCHを有する。チャンバCHは、基板Wが通過可能な開口を有し、開口を開閉するシャッタ(図示せず)を有する。基板処理ユニットWUは、例えば、基板洗浄ユニット、感光性膜形成ユニット、周縁露光ユニットおよび現像ユニット等を含む。基板処理装置1には、基板処理装置1を構成する種々の構成要素(機器または部品等)が含まれる。例えば、基板処理装置1は、各基板処理ユニットWUのチャンバCH内の雰囲気を清浄に保つための給排気システムAESを含む。チャンバCH内においては、スピンチャックSCに保持された基板Wに対して種々の処理が行われる。例えば、基板Wに洗浄液が供給されることにより基板Wが洗浄される。給排気システムAESは、構成要素として、給気部FFU、排気部EDおよび圧力計PG1,PG2を含む。制御装置40は、複数の給気部FFUを制御するための第1の制御部40aおよび複数の排気部EDを制御するための第2の制御部40bを含む。なお、基板処理装置1には、上記の複数の構成要素の他に、図示しない表示装置、音声出力装置および操作部が設けられる。基板処理装置1は、基板処理装置1の予め定められた処理手順(処理レシピ)に従って運転される。
基板処理装置1には、当該基板処理装置1の構成要素の異常を管理するための情報として、基板処理装置1における基板Wの処理に関連する動作または状態を示す複数の処理情報が定められる。本実施の形態においては、これらの処理情報は、図1に太い実線の矢印で示すように、基板処理装置1の制御装置40から制御支援装置4を介して情報分析装置3に所定周期で送信される。
情報分析装置3は、例えばサーバであり、CPU(中央演算処理装置)およびメモリを含む。情報分析装置3は、基板処理装置1から送信される複数の処理情報を収集する。情報分析装置3においては、基板処理装置1から情報分析装置3に送信される複数の処理情報について、互いに異なる2つの処理情報の複数の組み合わせが予め定められている。
上記のように、情報分析装置3においては、互いに異なる2つの処理情報の複数の組み合わせが定められている。構成要素の異常スコアを算出するために、組合せごとに乖離度が算出される。図2は、乖離度の具体的な算出例を説明するための図である。ここでは、図1の「a.FFUのファン回転速度」と「b.FFUの内圧値」との組み合わせに対応する乖離度の算出例を説明する。以下の説明では、「a.FFUのファン回転速度」のデータを適宜「a」データと呼び、「b.FFUの内圧値」のデータを適宜「b」データと呼ぶ。
図4は、学習動作および適正パラメータ値更新動作における基板処理装置1、情報分析装置3および制御支援装置4の動作を説明するための概念図である。図5は、複数の判定モデルを説明するための概念図である。図6は、判定モデル番号とパラメータ値との対応関係を説明するための概念図である。
ここで、基板処理装置1の同種の構成要素C1~Cnは、個体差により異なる特性を有する。そのため、工場等における基板処理装置1の据え付け(セットアップ)時においては、構成要素C1~Cnごとにそれぞれ適切なパラメータ値を設定する必要がある。初期状態では、基板処理装置1の各構成要素C1~Cnに対して、例えば、既定のパラメータ値が設定されている。この状態で、各構成要素C1~Cnに対するパラメータ値を適切なパラメータ値(以下、適正パラメータ値と呼ぶ。)に更新(微調整)する必要がある。また、経年変化により基板処理装置1の複数の構成要素C1~Cnのいずれかの特性が劣化することがある。この場合、特性が劣化した構成要素が新たな構成要素に交換される。交換前の構成要素と交換後の構成要素との個体差により、交換後の構成要素の特性が交換前の構成要素の特性と異なる場合がある。この場合にも、交換前の構成要素に対するパラメータ値を交換後の構成要素に適切なパラメータ値に更新(微調整)する必要がある。
図7は、主として図1の情報分析装置3および制御支援装置4の機能的な構成を説明するためのブロック図である。
上記実施の形態に係る制御支援装置4によれば、適正パラメータ値更新動作により情報分析装置3から取得された判定モデル番号(図4の例では、判定モデル番号Mn)に基づいて適正な判定結果を得ることが可能な判定モデル(図4の例では、判定モデルMDn)を判別することができる。また、対応関係CRに基づいて、判別された判定モデル(図4の例では、判定モデルMDn)に対応するパラメータ値(図4の例では、パラメータ値PRn)を判別することができる。それにより、取得された対応関係CRおよび取得された判定モデル番号(図4の例では、判定モデル番号Mn)に基づいてパラメータ値(図4の例では、パラメータ値PRn)が決定される。したがって、基板処理装置1における構成要素(図4の例では、構成要素C1)を制御するためのパラメータ値が自動的に適切なパラメータ値(図4の例では、パラメータ値PRn)に決定される。同様に、他の構成要素(図4の例では、構成要素C2~Cn)を制御するためのパラメータ値を自動的に適切なパラメータ値に決定することができる。その結果、基板処理装置1の給排気システムAESの構成要素の制御パラメータの値を適切な値に決定するための労力を軽減することが可能になる。
(10-1)上記実施の形態の制御支援装置4においては、インバリアントな関係性に基づいて、判定モデルが生成されるが本発明はこれに限定されない。例えば、制御支援装置4においては、例えば、深層学習等の他の機械学習法を用いることにより、判定モデルが生成されてもよい。
上記実施の形態に係る制御支援装置4は、基板処理装置1の種々の構成要素のうち給排気システムAESの給気部FFUの適正パラメータ値を決定するために用いられるが、上記実施の形態に係る制御支援装置4を、基板処理装置1の他の構成要素に対する適正パラメータ値を決定するために適用することも可能である。例えば、上記実施の形態に係る制御支援装置4は、基板処理装置1の種々の構成要素のうち基板処理ユニットWUの各流量調整バルブの適正パラメータ値を決定するために用いられてもよい。
以下、請求項の各構成要素と実施の形態の各要素との対応の例について説明する。上記実施の形態では、判定モデル番号取得部43が情報取得部の例であり、対応関係記憶部45が記憶部の例であり、適正パラメータ値決定部47が決定部の例である。
Claims (11)
- 基板処理装置の給排気システムにおける構成要素を制御するための制御パラメータの値であるパラメータ値を決定する制御支援装置であって、
前記基板処理装置の基板の処理に関連する動作または状態を示す処理情報から前記構成要素の動作の正常度をそれぞれ判定する複数の判定モデルをそれぞれ識別する複数のモデル識別情報と、複数のパラメータ値との対応関係を取得する対応関係取得部と、
前記複数の判定モデルのうち前記構成要素の動作時の処理情報から適正な判定結果を得ることが可能な判定モデルに対応するモデル識別情報を取得する情報取得部と、
前記対応関係取得部により取得された対応関係および前記情報取得部により取得されたモデル識別情報に基づいて、前記構成要素を制御するための前記パラメータ値を決定する決定部とを備えた、制御支援装置。 - 前記情報取得部は、前記複数の判定モデルの複数の判定結果のうち最も高い正常度を示す判定結果に対応する判定モデルのモデル識別情報を取得する、請求項1記載の制御支援装置。
- 前記基板処理装置は、前記構成要素として、同種の複数の構成要素を含み、
前記複数のパラメータ値は、前記複数の構成要素をそれぞれ制御するための値であり、
前記決定部は、前記対応関係取得部により取得された対応関係および前記情報取得部により取得されたモデル識別情報に基づいて、各構成要素を制御するための前記パラメータ値を決定する、請求項1または2記載の制御支援装置。 - 前記決定部により決定された前記パラメータ値を前記基板処理装置に送信する送信部をさらに備える、請求項1~3のいずれか一項に記載の制御支援装置。
- 前記決定部は、前記基板処理装置の据え付け時、前記基板処理装置の検査時または前記基板処理装置の構成要素が新たな構成要素に交換された場合に、前記据え付け後または交換後の構成要素の制御に用いられる前記パラメータ値を決定する、請求項1~4のいずれか一項に記載の制御支援装置。
- 前記基板処理装置の通常動作時に、前記構成要素の制御に用いられる前記パラメータ値に対応する判定モデルの判定結果が予め定められた異常状態を示す場合に、
前記対応関係取得部は、前記対応関係を取得し、
前記情報取得部は、前記適正な判定結果を得ることが可能な判定モデルに対応するモデル識別情報を取得し、
前記決定部は、前記対応関係取得部により取得された対応関係および前記情報取得部により取得されたモデル識別情報に基づいて、前記構成要素を制御するために新たに用いられるべき前記パラメータ値を決定する、請求項1~5のいずれか一項に記載の制御支援装置。 - 前記複数の判定モデルの各々は、前記基板処理装置の基板の処理に関連する動作または状態を示す複数の前記処理情報間のインバリアントな関係性と前記基板処理装置から実際に収集された複数の処理情報とに基づいて前記構成要素の正常度を判定する、請求項1~6のいずれか一項に記載の制御支援装置。
- 前記対応関係を記憶する記憶部をさらに備え、
前記対応関係取得部は、前記記憶部により記憶された前記対応関係を取得し、
前記決定部は、前記対応関係取得部に記憶された前記対応関係を用いて前記構成要素を制御するための前記パラメータ値を決定する、請求項1~7のいずれか一項に記載の制御支援装置。 - 前記基板処理装置は、基板の処理が行われるチャンバを含み、
前記構成要素は、
前記チャンバ内の給気および排気を行う給気部と、
前記チャンバ内の排気を行う排気部とを含み、
前記パラメータ値は、前記給気部および前記排気部の少なくとも一方の動作に関連する値である、請求項1~8のいずれか一項に記載の制御支援装置。 - 前記制御パラメータは、前記給気部に対応する第1のパラメータと、前記排気部に対応する第2のパラメータとを含み、
前記第1のパラメータのパラメータ値は、前記給気部の動作に関連する値であり、
前記第2のパラメータのパラメータ値は、前記排気部の動作に関連する値である、請求項9記載の制御支援装置。 - 基板処理装置の給排気システムにおける構成要素を制御するための制御パラメータの値であるパラメータ値を決定する制御支援方法であって、
前記基板処理装置の基板の処理に関連する動作または状態を示す処理情報から前記構成要素の動作の正常度をそれぞれ判定する複数の判定モデルをそれぞれ識別する複数のモデル識別情報と、複数のパラメータ値との対応関係を取得するステップと、
前記複数の判定モデルのうち前記構成要素の動作時の処理情報から適正な判定結果を得ることが可能な判定モデルに対応するモデル識別情報を取得するステップと、
前記取得された対応関係および前記取得されたモデル識別情報に基づいて、前記構成要素を制御するための前記パラメータ値を決定するステップとを含む、制御支援方法。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP23763333.4A EP4489057A1 (en) | 2022-03-02 | 2023-02-22 | Control assistance device and control assistance method |
| KR1020247032897A KR20240158950A (ko) | 2022-03-02 | 2023-02-22 | 제어 지원 장치 및 제어 지원 방법 |
| CN202380024596.6A CN118805244A (zh) | 2022-03-02 | 2023-02-22 | 控制辅助装置以及控制辅助方法 |
| US18/839,682 US20250147493A1 (en) | 2022-03-02 | 2023-02-22 | Control assistance device and control assistance method |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022031944A JP7750775B2 (ja) | 2022-03-02 | 2022-03-02 | 制御支援装置および制御支援方法 |
| JP2022-031944 | 2022-03-02 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023167074A1 true WO2023167074A1 (ja) | 2023-09-07 |
Family
ID=87883583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2023/006489 Ceased WO2023167074A1 (ja) | 2022-03-02 | 2023-02-22 | 制御支援装置および制御支援方法 |
Country Status (7)
| Country | Link |
|---|---|
| US (1) | US20250147493A1 (ja) |
| EP (1) | EP4489057A1 (ja) |
| JP (1) | JP7750775B2 (ja) |
| KR (1) | KR20240158950A (ja) |
| CN (1) | CN118805244A (ja) |
| TW (1) | TWI867452B (ja) |
| WO (1) | WO2023167074A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2025205452A1 (ja) * | 2024-03-29 | 2025-10-02 | 日本碍子株式会社 | 基板支持体を有する基板処理装置の運用支援システム及び運用支援方法 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000003206A (ja) * | 1998-06-12 | 2000-01-07 | Hitachi Ltd | 制御対象モデル変更装置 |
| JP2006091937A (ja) * | 2004-09-16 | 2006-04-06 | Canon System Solutions Inc | データ分析装置及びその方法、プログラム |
| JP2008187139A (ja) * | 2007-01-31 | 2008-08-14 | Hitachi High-Technologies Corp | 減圧処理室の圧力制御装置 |
| WO2018151215A1 (ja) * | 2017-02-20 | 2018-08-23 | 株式会社安川電機 | 制御装置及び制御方法 |
| JP2018186610A (ja) * | 2017-04-25 | 2018-11-22 | 株式会社安川電機 | システムおよび評価装置ならびに評価方法 |
| WO2020179729A1 (ja) * | 2019-03-04 | 2020-09-10 | Sppテクノロジーズ株式会社 | 基板処理装置の製造プロセス判定装置、基板処理システム、基板処理装置の製造プロセス判定方法、学習モデル群、学習モデル群の生成方法及びプログラム |
| JP2021168364A (ja) * | 2020-04-13 | 2021-10-21 | キヤノン株式会社 | 情報処理装置、検出方法、プログラム、基板処理システム、及び物品の製造方法 |
| JP2021190530A (ja) | 2020-05-28 | 2021-12-13 | 株式会社Screenホールディングス | 基板処理装置、基板処理方法、学習用データの生成方法、学習方法、学習装置、学習済モデルの生成方法、及び学習済モデル |
| JP2022015151A (ja) | 2020-07-08 | 2022-01-21 | 株式会社Screenホールディングス | 基板処理方法 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210073610A1 (en) * | 2017-12-27 | 2021-03-11 | Semiconductor Energy Laboratory Co., Ltd. | Thin film manufacturing apparatus and thin film manufacturing apparatus using neural network |
| US10832979B2 (en) * | 2018-02-22 | 2020-11-10 | Lam Research Corporation | Feedback control system for iterative etch process |
| CN114207776A (zh) * | 2019-09-24 | 2022-03-18 | 株式会社国际电气 | 基板处理装置、半导体装置的制造方法以及预兆检测程序 |
-
2022
- 2022-03-02 JP JP2022031944A patent/JP7750775B2/ja active Active
-
2023
- 2023-02-22 CN CN202380024596.6A patent/CN118805244A/zh active Pending
- 2023-02-22 US US18/839,682 patent/US20250147493A1/en active Pending
- 2023-02-22 WO PCT/JP2023/006489 patent/WO2023167074A1/ja not_active Ceased
- 2023-02-22 EP EP23763333.4A patent/EP4489057A1/en active Pending
- 2023-02-22 KR KR1020247032897A patent/KR20240158950A/ko active Pending
- 2023-03-01 TW TW112107212A patent/TWI867452B/zh active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000003206A (ja) * | 1998-06-12 | 2000-01-07 | Hitachi Ltd | 制御対象モデル変更装置 |
| JP2006091937A (ja) * | 2004-09-16 | 2006-04-06 | Canon System Solutions Inc | データ分析装置及びその方法、プログラム |
| JP2008187139A (ja) * | 2007-01-31 | 2008-08-14 | Hitachi High-Technologies Corp | 減圧処理室の圧力制御装置 |
| WO2018151215A1 (ja) * | 2017-02-20 | 2018-08-23 | 株式会社安川電機 | 制御装置及び制御方法 |
| JP2018186610A (ja) * | 2017-04-25 | 2018-11-22 | 株式会社安川電機 | システムおよび評価装置ならびに評価方法 |
| WO2020179729A1 (ja) * | 2019-03-04 | 2020-09-10 | Sppテクノロジーズ株式会社 | 基板処理装置の製造プロセス判定装置、基板処理システム、基板処理装置の製造プロセス判定方法、学習モデル群、学習モデル群の生成方法及びプログラム |
| JP2021168364A (ja) * | 2020-04-13 | 2021-10-21 | キヤノン株式会社 | 情報処理装置、検出方法、プログラム、基板処理システム、及び物品の製造方法 |
| JP2021190530A (ja) | 2020-05-28 | 2021-12-13 | 株式会社Screenホールディングス | 基板処理装置、基板処理方法、学習用データの生成方法、学習方法、学習装置、学習済モデルの生成方法、及び学習済モデル |
| JP2022015151A (ja) | 2020-07-08 | 2022-01-21 | 株式会社Screenホールディングス | 基板処理方法 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2025205452A1 (ja) * | 2024-03-29 | 2025-10-02 | 日本碍子株式会社 | 基板支持体を有する基板処理装置の運用支援システム及び運用支援方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118805244A (zh) | 2024-10-18 |
| TW202343538A (zh) | 2023-11-01 |
| JP7750775B2 (ja) | 2025-10-07 |
| KR20240158950A (ko) | 2024-11-05 |
| US20250147493A1 (en) | 2025-05-08 |
| TWI867452B (zh) | 2024-12-21 |
| EP4489057A1 (en) | 2025-01-08 |
| JP2023127946A (ja) | 2023-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7494342B2 (ja) | 処理装置、装置管理コントローラ、及びプログラム並びに半導体装置の製造方法 | |
| US7580767B2 (en) | Methods of and apparatuses for maintenance, diagnosis, and optimization of processes | |
| JP2005536887A (ja) | 製造中にデバイスの電気パラメータを予測する方法および装置 | |
| KR20020047215A (ko) | 통계적인 공정 제어를 이용하여 제어기 성능을 모니터하는방법 및 장치 | |
| CN1816905A (zh) | 用于刻蚀工艺的前馈和反馈晶片到晶片控制方法 | |
| WO2023167074A1 (ja) | 制御支援装置および制御支援方法 | |
| JP5042225B2 (ja) | 熱処理システムのビルトイン・セルフテスト | |
| JP5096335B2 (ja) | 熱処理システムのビルトイン・セルフテスト | |
| US20240096657A1 (en) | Etching control system and etching control method | |
| WO2023166804A1 (ja) | 制御支援装置および制御支援方法 | |
| WO2023140005A1 (ja) | 支援装置、支援方法および支援プログラム | |
| US20250390066A1 (en) | Control assistance device and control assistance method | |
| EP4492429A1 (en) | Substrate processing device management system, management device, substrate processing device, substrate processing device management method, and substrate processing device management program | |
| US20240096658A1 (en) | Etching control device, etching control method, and etching control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23763333 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18839682 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202380024596.6 Country of ref document: CN |
|
| ENP | Entry into the national phase |
Ref document number: 20247032897 Country of ref document: KR Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 1020247032897 Country of ref document: KR Ref document number: 2023763333 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2023763333 Country of ref document: EP Effective date: 20241002 |
|
| WWP | Wipo information: published in national office |
Ref document number: 18839682 Country of ref document: US |