CN111813155A - Fuzzy PID-based target spray system control method, device and storage medium - Google Patents

Abstract

The present application discloses a control method, device and storage medium for a target spraying system based on fuzzy PID. The target spraying system includes a camera, a solenoid valve and a fuzzy PID controller. The fuzzy PID controller is electrically connected to the solenoid valve. The control method includes: obtaining weed images collected by a camera, obtaining weed density information through a preset image recognition algorithm, obtaining the current spray flow rate of the solenoid valve, and reading from a database through the weed density information Target spray flow, obtain flow difference and difference change rate information according to the current spray flow and the target spray flow, send the flow difference and the difference change rate information to the fuzzy PID controller, and obtain The PID control parameters output by the fuzzy PID controller are used to adjust the spray flow of the solenoid valve according to the PID control parameters; using the technical solution of this embodiment, the spray flow of the solenoid valve is adjusted according to the weed density, thereby realizing for precise spraying.

Description

Fuzzy PID-based target spray system control method, device and storage medium

technical field

The present application relates to the technical field of automatic control, in particular to a control method, device and storage medium for a target spray system based on fuzzy PID.

Background technique

In the process of agricultural planting, weeds are harmful to the growth of crops. Weeds are usually removed by spraying herbicides. The traditional manual spraying method can no longer meet today's needs. In order to achieve automation, the common practice is to use drones or weeders for automatic spraying, but the existing solution can only spray evenly over a large area, and weeds do not grow uniformly, and it is easy to spray too little in places with a lot of grass. Or spraying too much herbicide in the place with no grass, the weeding effect is poor.

SUMMARY OF THE INVENTION

In order to overcome the deficiencies of the prior art, the purpose of the present application is to provide a fuzzy PID-based target spray system control method, device and storage medium, which can automatically adjust the spray flow and improve the weeding effect.

The technical scheme adopted by the present application to solve its problems is: firstly, the present application provides a fuzzy PID-based control method for a target spray system, the target spray system includes a control processing unit, a camera, a control device for controlling spray flow A solenoid valve and a fuzzy PID controller, the control processing unit is respectively electrically connected with the fuzzy PID controller, the solenoid valve and the camera, and the control method includes:

obtaining the weed image collected by the camera, and obtaining the weed density information through a preset image recognition algorithm;

Acquiring the current spraying flow of the solenoid valve, reading the target spraying flow from the database through the weed density information, and obtaining the flow difference and the difference change rate information according to the current spraying flow and the target spraying flow;

The flow difference value and the difference value change rate information are sent to the fuzzy PID controller, and the PID control parameters output by the fuzzy PID controller are obtained, and the spray flow of the solenoid valve is adjusted according to the PID control parameters.

Further, the PID control parameters include at least one of the following

Increase the opening signal;

Decrease the opening signal.

Further, the target spray system also includes an overflow valve, and the overflow valve is electrically connected to the fuzzy PID controller. If the PID control parameter includes an increase opening signal, the adjustment of the The spray flow of the solenoid valve specifically includes:

sending an increasing opening signal to the solenoid valve;

Send a reduced overflow signal to the overflow valve.

Further, if the PID control parameter includes a decreasing opening signal, the adjusting the spray flow rate of the solenoid valve according to the PID control parameter specifically includes:

sending a decreasing opening signal to the solenoid valve;

An increased overflow signal is sent to the overflow valve.

Further, the weed density is obtained by a pre-trained neural network algorithm.

Further, the target spray system also includes an ultrasonic sensor, and the control method also includes:

Obtain spraying distance information through the ultrasonic sensor;

The spraying distance information is input into the fuzzy PID controller, so that the fuzzy PID controller adjusts the PID control parameters.

Further, the target spray flow rate is obtained by searching a pre-set comparison table in the database.

Further, the weed image is a video frame in a video collected by the camera.

In a second aspect, the present application provides a fuzzy PID-based target spray system control device, comprising at least one control processing unit and a memory for communicating with the at least one control processing unit; The instruction executed by the at least one control processing unit is executed by the at least one control processing unit, so that the at least one control processing unit can execute the fuzzy PID-based target spray system control method as described above.

In a third aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to make the computer execute the above-mentioned fuzzy PID-based target spray system control method .

In a fourth aspect, the present application also provides a computer program product, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer , to make the computer execute the above-mentioned fuzzy PID-based target spray system control method.

One or more technical solutions provided in the embodiments of the present application have at least the following beneficial effects: the control method of the present application is applied to a target spraying system, and the target spraying system includes a camera, a solenoid valve and a fuzzy PID controller, and the fuzzy The PID controller is electrically connected to the solenoid valve, and the control method includes: acquiring weed images collected by a camera, acquiring weed density information by a preset image recognition algorithm, acquiring the current spray flow of the solenoid valve, and The weed density information reads the target spray flow rate from the database, obtains the flow difference value and the difference value change rate information according to the current spray flow rate and the target spray flow rate, and changes the flow difference value and the difference value. The rate information is sent to the fuzzy PID controller, and the PID control parameters output by the fuzzy PID controller are obtained, and the spray flow of the solenoid valve is adjusted according to the PID control parameters; using the technical solution of this embodiment, through the flow difference value And the difference change rate information realizes fuzzy PID control, and adjusts the spray flow of the solenoid valve according to the weed density, so as to achieve precise spraying.

Description of drawings

The present application will be further described below with reference to the accompanying drawings and examples.

Fig. 1 is the module structure diagram of the target spray system provided by an embodiment of the present application;

Fig. 2 is the flow chart of a kind of target spray system control method based on fuzzy PID provided by another embodiment of the present application;

3 is a flow chart of increasing spray flow in a fuzzy PID-based target spray system control method provided by another embodiment of the present application;

4 is a flow chart of reducing spray flow in a fuzzy PID-based target spray system control method provided by another embodiment of the present application;

5 is a detailed flow chart of obtaining PID control information in a fuzzy PID-based target spray system control method provided by another embodiment of the present application;

FIG. 6 is a schematic diagram of a device for implementing a fuzzy PID-based control method for a target spray system provided by another embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

It should be noted that, if there is no conflict, various features in the embodiments of the present application may be combined with each other, which are all within the protection scope of the present application. In addition, although the functional modules are divided in the schematic diagram of the device, and the logical sequence is shown in the flowchart, in some cases, the modules in the device may be divided differently, or the sequence shown in the flowchart may be performed. or the described steps.

Referring to FIG. 1 , FIG. 1 is a schematic structural module diagram of a target spraying system 10 . The target spraying system 10 includes but is not limited to a control processing unit 20 , a camera 30 , a solenoid valve 40 , a fuzzy PID controller 50 , and a relief valve 60 .

In one embodiment, the control processing unit 20 may be a common control chip, such as an FPGA, a single-chip microcomputer, etc., or may be a computer or other equipment mounted on the target spraying system, which can be selected according to actual needs. It should be noted that the control processing unit 20 is respectively electrically connected with the fuzzy PID controller 50, the solenoid valve 40, the camera 30 and the ultrasonic sensor 70, and can obtain the PID control parameters sent by the fuzzy PID controller 50, and control the control according to the PID control parameters. The opening degree of the solenoid valve 40 is increased or decreased. It should be noted that the solenoid valve may be an electric pulse electronically controlled solenoid valve, and this embodiment does not involve the improvement of the specific solenoid valve structure, and the related technology in the prior art may be used, which will not be repeated here. It should be noted that the camera 30 and the fuzzy PID controller 50 in this embodiment can also adopt the hardware structure in the prior art. This embodiment does not involve the improvement of hardware, but only improves the control method. Repeat. It should be noted that the relief valve 60 can be connected to the medicine box containing medicines. When the opening and closing degree of the solenoid valve 50 changes, the pressure on the relief valve 60 changes, so as to control the amount of medicine flowing back to the medicine box. It should be noted that, the ultrasonic sensor 70 in this embodiment may adopt any model in the prior art, as long as it can realize ultrasonic ranging, which will not be repeated here.

2, the first embodiment of the present application provides a fuzzy PID-based target spray system control method, applied to the target spray system shown in FIG. 1, the control method comprises the following steps:

Step S100, obtaining the weed image collected by the camera, and obtaining the weed density information through a preset image recognition algorithm;

Step S200, obtaining the current spray flow rate of the solenoid valve, reading the target spray flow rate from the database through the weed density information, and obtaining the flow difference value and the difference change rate information according to the current spray flow rate and the target spray flow rate;

In step S300, the flow difference value and the difference value change rate information are sent to the fuzzy PID controller, and the PID control parameters output by the fuzzy PID controller are obtained, and the spray flow rate of the solenoid valve is adjusted according to the PID control parameters.

In one embodiment, since the images collected by the camera include weeds and crops at the same time, weeds can be identified through a preset image recognition algorithm, and weed density information can be obtained according to the identified weeds. Density information reflects the number of weeds and facilitates control of the amount of herbicide sprayed.

In one embodiment, the target spray flow rate can be obtained in any form, such as looking up a table, or calculating through a preset formula, and a specific method may be selected according to actual needs, which will not be repeated here.

In one embodiment, the flow difference value may be the absolute value of the value obtained by subtracting the target spray flow rate from the current spray flow rate, and the difference change rate information may be the trend of the difference value change, and the value needs to be obtained through the flow difference values obtained several times. , for example, the flow difference for three consecutive times is getting smaller and smaller, then the difference change rate information can be the decreasing trend of the flow difference, and the selection method of the specific value can be determined according to the actual demand. It should be noted that, because the flow difference and difference rate of change information used to obtain the PID control parameters are different each time, they are used as two-dimensional input items of the PID fuzzy controller, and the above parameters are input into the fuzzy PID controller. , the PID control parameters can be obtained by substituting the PID formula in the prior art, and the specific PID formula is not an improvement made by this embodiment, and will not be repeated here.

In another embodiment of the present application, the PID control parameters include at least one of the following

Increase the opening signal;

Decrease the opening signal.

In one embodiment, since the solenoid valve is usually connected between the spray head and the spray pump, the spray flow rate can be changed by controlling the solenoid valve through the electrical pulse point control. In this embodiment, it is preferable to control the opening of the solenoid valve to achieve precise control. .

Referring to FIG. 3 , in another embodiment of the present application, if the PID control parameter includes the increasing opening signal, step S300 further includes but is not limited to the following refinement steps:

Step S311, sending an increase opening signal to the solenoid valve;

Step S312, sending a reducing overflow signal to the overflow valve.

In one embodiment, if the PID control parameter includes an increasing opening signal, then when the increasing opening signal is sent to the solenoid valve, a reducing overflow signal can also be sent to the relief valve, and the pressure received by the relief valve is If it is reduced, the amount of medicine that overflows back to the medicine box is also reduced, and more medicine can be sprayed, so as to better realize the increase of the spray flow.

Referring to FIG. 4 , in another embodiment of the present application, if the PID control parameter includes a decreasing opening signal, step S300 further includes but is not limited to the following refinement steps:

Step S321, sending a decreasing opening signal to the solenoid valve;

Step S322, sending an increased overflow signal to the overflow valve.

It should be noted that the principle of reducing the spray flow rate is similar to that of the embodiment shown in FIG. 3 , and the control direction may be reversed, which will not be repeated here.

In another embodiment of the present application, the weed density is obtained by a pre-trained neural network algorithm.

In one embodiment, the weed density can be obtained in any way. In this embodiment, it is preferably obtained by a pre-trained neural network algorithm. The neural network algorithm has the characteristics of fast calculation speed and high accuracy, and can quickly obtain the weed density. At the same time, because the camera can also be used to obtain video information, the target spraying system can continuously collect weed images during the moving process. Therefore, the timeliness of the neural network algorithm can meet the real-time acquisition of weed density, so as to adjust the spray flow in real time and improve the degree of automation.

5 , in another embodiment of the present application, the target spray system further includes an ultrasonic sensor, and step S200 also includes but is not limited to the following refinement steps:

Step S210, obtaining spraying distance information through an ultrasonic sensor;

Step S220, the spraying distance information is input into the fuzzy PID controller, so that the fuzzy PID controller adjusts the PID control parameters.

In one embodiment, when the spraying flow rate meets the weed density, the distance between the target spraying system and the weeds also needs to be considered. In the pan/tilt, the target spraying system is in the process of constant movement. In order to achieve a better spraying effect, this embodiment preferably uses an ultrasonic sensor for ultrasonic ranging, which has the characteristics of fast measurement speed and high accuracy.

It should be noted that, after the spraying distance information is input to the fuzzy PID controller, on the basis of the existing PID control parameters, the larger the spraying distance is, the opening of the solenoid valve can be increased, or the spray pump can be increased. Power, and vice versa, select a specific control method according to the actual demand, which can realize the compensation of the spraying distance.

In another embodiment of the present application, the target spray flow rate is obtained by searching a pre-set comparison table in the database.

In one embodiment, the target spray flow rate is stored as a preference in this embodiment through a comparison table, which can reduce the amount of calculation. It should be noted that the directly used target spraying flow can be saved in the comparison table, and the incremental value can also be saved. For example, adding the incremental value to the current spraying flow, the value obtained is the target spraying flow. The specific method You can choose according to actual needs.

In another embodiment of the present application, the weed image is a video frame in a video captured by a camera.

In one embodiment, the video captured by the camera can provide a data basis for realizing real-time control of the spraying flow. Since the target spraying system is usually in motion and the spraying area is large, the video is captured by the camera, and the specific video is obtained from the video. The frame is used as a weed image, and the spraying flow can be adjusted in real time according to the currently acquired weed image, and the accuracy of herbicide spraying can be improved.

Referring to FIG. 6 , another embodiment of the present application also provides a fuzzy PID-based target spray system control device 6000 , including: a memory 6100 , a control processor 6200 , and a control device 6200 stored in the memory 6200 and available on the control processor 6200 The computer program that runs, when the control processing unit executes the computer program, the fuzzy PID-based target spray system control method in any of the above embodiments is realized, for example, the method steps S100 to S300 in the above-described Fig. 2 are executed, and in Fig. 3 method steps S311 to S312 in FIG. 4 , method steps S321 to S322 in FIG. 4 , and method steps S210 to S220 in FIG. 5 .

The control processor 6200 and the memory 6100 may be connected through a bus or in other ways, and the connection through a bus is taken as an example in FIG. 6 .

As a non-transitory computer-readable storage medium, the memory 6100 can be used to store non-transitory software programs and non-transitory computer-executable programs. Additionally, memory 6100 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 6100 may optionally include a memory located remotely relative to the control processor 6200, and these remote memories may be connected to the fuzzy PID-based target spray system control apparatus 6000 through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The apparatus embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, another embodiment of the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more control processing units, for example, Executed by a control processor 6200 in FIG. 6 , the above-mentioned one or more control processors 6200 can be made to execute the fuzzy PID-based target spray system control method in the above method embodiment, for example, execute the above-described method in FIG. 2 . Method steps S100 to S300, method steps S311 to S312 in FIG. 3 , method steps S321 to S322 in FIG. 4 , method steps S210 to S220 in FIG. 5 .

It should be noted that, because the device for executing the fuzzy PID-based target spray system control method in this embodiment and the above-mentioned fuzzy PID-based target spray system control method are based on the same inventive concept, therefore, the method in the embodiment is based on the same inventive concept. Corresponding contents are also applicable to the embodiments of the apparatus, and will not be described in detail here.

From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform. Those skilled in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed , which may include the flow of an embodiment of the above-mentioned method. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ReadOnly Memory, ROM), or a random access memory (Random Access Memory, RAM) or the like.

The above is a specific description of the preferred implementation of the application, but the application is not limited to the above-mentioned embodiments. Those skilled in the art can also make various equivalent deformations or replacements on the premise of not violating the spirit of the application. These Equivalent modifications or substitutions are included within the scope defined by the claims of the present application.

Claims (10)

1. a target spray system control method based on fuzzy PID, is characterized in that, for target spray system, described target spray system comprises control processing unit, camera, solenoid valve and fuzzy PID controller for controlling spray flow, The control processing unit is respectively electrically connected with the fuzzy PID controller, the solenoid valve and the camera, and the control method includes: The control processing unit obtains the weed image collected by the camera, and obtains the weed density information through a preset image recognition algorithm; Acquiring the current spraying flow of the solenoid valve, reading the target spraying flow from the database through the weed density information, and obtaining the flow difference and the difference change rate information according to the current spraying flow and the target spraying flow; The flow difference value and the difference value change rate information are sent to the fuzzy PID controller, and the PID control parameters output by the fuzzy PID controller are obtained, and the spray flow of the solenoid valve is adjusted according to the PID control parameters. 2. a kind of target spray system control method based on fuzzy PID according to claim 1, is characterized in that, described PID control parameter comprises at least one of following Increase the opening signal; Decrease the opening signal. 3. a kind of target spray system control method based on fuzzy PID according to claim 2, is characterized in that, described target spray system also comprises overflow valve, and described overflow valve is electrically connected with described fuzzy PID controller , if the PID control parameter includes an increase opening signal, the adjusting the spray flow rate of the solenoid valve according to the PID control parameter specifically includes: sending an increasing opening signal to the solenoid valve; Send a reduced overflow signal to the overflow valve. 4. a kind of target spray system control method based on fuzzy PID according to claim 3, it is characterized in that, if described PID control parameter comprises reducing opening signal, described adjusting described solenoid valve according to PID control parameter. The spray flow specifically includes: sending a decreasing opening signal to the solenoid valve; An increased overflow signal is sent to the overflow valve. 5 . The fuzzy PID-based target spraying system control method according to claim 1 , wherein the weed density is obtained by a pre-trained neural network algorithm. 6 . 6. a kind of target spray system control method based on fuzzy PID according to claim 1, is characterized in that, described target spray system also comprises ultrasonic sensor, and described control method also comprises: Obtain spraying distance information through the ultrasonic sensor; The spraying distance information is input into the fuzzy PID controller, so that the fuzzy PID controller adjusts the PID control parameters. 7 . A fuzzy PID-based target spray system control method according to claim 1 , wherein the target spray flow rate is obtained by searching a comparison table preset in a database. 8 . 8 . The fuzzy PID-based target spray system control method according to claim 1 , wherein the weed image is a video frame in a video collected by the camera. 9 . 9. A target spray system control device based on fuzzy PID, characterized in that it comprises at least one control processing unit and a memory for communicating with the at least one control processing unit; An instruction executed by a control processing unit, the instruction is executed by the at least one control processing unit, so that the at least one control processing unit can execute the fuzzy PID-based target spraying according to any one of claims 1 to 8 System control method. 10. A computer-readable storage medium, characterized in that: the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute any one of claims 1 to 8. The control method of target spray system based on fuzzy PID.

Images