WO2024041305A1

WO2024041305A1 - Coating control method and apparatus, control device, and storage medium

Info

Publication number: WO2024041305A1
Application number: PCT/CN2023/109701
Authority: WO
Inventors: 陈俊杰; 代爱军; 缪丰; 贾仕勇
Original assignee: 无锡先导智能装备股份有限公司
Priority date: 2022-08-22
Filing date: 2023-07-27
Publication date: 2024-02-29
Also published as: CN115356996A

Abstract

A coating control method and apparatus, a control device, and a storage medium. The coating control method comprises: in an automated coating control mode, acquiring model selection information and the current coating surface density; according to the model selection information, selecting a control model from a plurality of alternative control models to obtain a target control model; by using the target control model, obtaining coating control amount according to the current coating surface density; and outputting a control instruction to a coating control object according to the coating control amount. The present invention can be compatible with various coating control modes, thereby having good compatibility.

Description

Coating control method, device, control equipment and storage medium

This disclosure request is submitted to the China Patent Office on August 22, 2022, with the application number 202211007561.5, and the priority of the Chinese patent application titled "Coating Control Method, Device, Control Equipment and Storage Medium", the entire content of which is incorporated by reference. incorporated in this disclosure.

Technical field

The present application relates to the technical field of pole piece coating, and in particular to a coating control method, device, control equipment and storage medium.

Background technique

The front stage of the lithium battery production process includes the coating process, as shown in Figure 1. It mainly adjusts the size of the slit lip by adjusting the screw, and evenly coats the slurry with good stability, good viscosity and good fluidity on the lithium battery. A process in which the organic solvent in the slurry is dried on the positive and negative electrode foils.

In order to apply the slurry evenly, the slit size needs to be adjusted during the coating process. One type of coating machine currently on the market uses manual mode to adjust the slit, that is, a specialized debugging engineer is arranged to rotate a micrometer installed on the slit by hand to control the adjusting screw, thereby controlling the size of the slit; this manual debugging method This method requires manual adjustment of the micrometer several times every time the slurry is changed in the coating machine and during the coating process, which is time-consuming and labor-intensive. There is also a coating machine that installs a motor (such as a stepper motor) above the adjusting screw, and controls the adjusting screw to adjust the slit size by controlling the movement of the motor. No matter which one of the above is used, the control method is single and has poor compatibility.

Contents of the invention

Based on this, it is necessary to provide a coating control method, device, control equipment and storage medium that can optimize compatibility in response to the above technical problems.

A coating control method including:

In automatic coating control mode, obtain model selection information and current coating surface density;

According to the model selection information, select a control model from multiple alternative control models to obtain a target control model;

Using the target control model and obtaining the coating control amount according to the current coating surface density;

A control instruction is output to the coating control object according to the coating control amount.

A coating control device including:

Information acquisition module, used to obtain model selection information and current coating surface density in automatic coating control mode;

A model selection module, configured to select a control model from multiple alternative control models to obtain a target control model based on the model selection information;

A control quantity acquisition module, used to adopt the target control model and obtain the coating control quantity according to the current coating surface density;

A control module, configured to output control instructions to the coating control object according to the coating control amount.

A control device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it implements the following steps:

A computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

The above-mentioned coating control method, device, control equipment and computer-readable storage medium can select a target control model from multiple control models according to the model selection information, and use the target control model to determine the coating control amount to control the coating control object, so , supports selection and use from multiple control models, supports multiple control models, and can be compatible with multiple control methods. Compared with the existing technology that only allows one control method, the compatibility is better.

Description of drawings

In order to more clearly explain the technical solutions in the embodiments of the present application or the traditional technology, the drawings needed to be used in the description of the embodiments or the traditional technology will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of explaining the embodiments or the technical solutions of the traditional technology. For some embodiments of the application, those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.

Figure 1 is a cross-sectional view of the slot extrusion coating structure;

Figure 2 is a schematic flow chart of a coating control method in one embodiment;

Figure 3 is a schematic flowchart of selecting a control model from multiple alternative control models to obtain a target control model according to the model selection information in one embodiment;

Figure 4 is a schematic flow chart of a coating control method in another embodiment;

Figure 5 is a modular structural block diagram of a control model selection system in one embodiment;

Figure 6 is a structural block diagram of a coating control device in one embodiment.

Detailed ways

In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are given in the accompanying drawings. However, the present application may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing specific embodiments only and is not intended to limit the application.

As used herein, the singular forms "a," "an," and "the" may include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the terms "comprising" or "having" and the like specify the presence of stated features, integers, steps, operations, components, parts or combinations thereof, but do not exclude the presence or addition of one or more Possibility of other features, integers, steps, operations, components, parts or combinations thereof.

As mentioned in the background art, the coating control of the coating machine in the prior art has the problems of single control method and poor compatibility. Based on this, this application provides a solution that can optimize compatibility and can be used to support control equipment that automatically controls the adjustment screw to adjust the slit size.

As shown in Figure 2, in one embodiment, a coating control method is provided, taking a control device applied to a coating machine as an example. The method includes the following steps:

S110: In the automatic coating control mode, obtain the model selection information and the current coating surface density.

Among them, the automatic coating control mode is a working mode that automatically controls the adjustment screw to adjust the slit size; whether to work in the automatic coating control mode can be manually selected by the user, and the control device can determine whether to work in the automatic coating control mode by identifying the mode selection command input by the user. Work in automatic coating control mode. For example, on the panel of the control device, there are selection buttons for manual coating mode and automatic coating control mode. Clicking the button for manual coating mode allows the user to manually control all the motor adjustment buttons (plus button & minus button) on the panel. ), you can click/edit the coating control amount; when the user When the button in the automatic coating control mode is clicked, the motor adjustment button becomes uneditable, allowing the user to view changes in the coating control volume output by the control model in real time.

Among them, the model selection information is the information used to select the control model, which can be input by the user according to different production requirements. The coating surface density is the surface density obtained by measuring the coated product; for example, the surface density measuring device is used to measure the coated foil to obtain the coating surface density. The control equipment can obtain the coating surface density from the surface density measuring device. Areal density.

S130: According to the model selection information, select a control model from multiple alternative control models to obtain a target control model.

Among them, the control model represents the corresponding relationship between the coating surface density and the coating control quantity; that is, the coating surface density can be used as the input of the control model, and the control model can output the coating control quantity corresponding to the coating surface density. The control device can store multiple alternative control models in advance. Among multiple alternative control models, different control models adopt different control methods.

S150: Use the target control model and obtain the coating control amount based on the current coating surface density.

Input the current coating surface density into the target control model, and the target control model can output the corresponding coating control amount. Specifically, if there is one target control model, the coating control amount output by the target control model can be directly used as the final coating control amount; if there are multiple target control models, the coating control amount output by each target control model can be used. The control amount is processed to obtain the final coating control amount.

S170: Output control instructions to the coating control object according to the coating control amount.

The control instruction is used to control the coating control object to act based on the coating control amount. Among them, the coating control object is a device controlled by the control device and used to adjust the adjusting screw. For example, the coating control object can be a stepper motor. The control device outputs corresponding control instructions to the stepper motor according to the final coating control amount, and controls the stepper motor to adjust the adjustment screw to adjust the slit size.

The above coating control method can select a target control model from multiple control models based on the model selection information, and use the target control model to determine the coating control amount to control the coating control object. In this way, it supports selection and use from multiple control models. It supports multiple control models and can be compatible with multiple control methods. Compared with the existing technology that only allows one control method, the compatibility is better.

In one embodiment, the alternative control models include a control model based on empirical data, a trend closed-loop control model, a machine learning control model, and a constraint learning control model. The control logic of each control model has its own characteristics and adapts to different industrial production needs, as shown in Table 1 below. Among them, model No. 1 is a control model based on empirical data, model No. 2 is a trend closed-loop control model, and model No. 3 is a control model based on empirical data. The model is a machine learning control model, and model No. 4 is a constraint learning control model.

Table 1

Among them, model No. 1 is a control model established based on the corresponding relationship data between coating surface density and coating control volume given by expert experience. On-site surface density debugging experts can output their empirical rules to form a set of control parameters based on expert experience. Adjust tables or control variable flow charts. When experts have sufficient experience and the working conditions such as on-site slurry and coating speed are stable, the control strategy of this control model can often achieve optimal control effects. Its disadvantages are that it relies heavily on the support of expert experience and the model is not transferable. Poor.

Among them, model No. 2 is a control model that collects the current coating surface density and performs closed-loop control based on the deviation between the current coating surface density and the preset target value. The control strategy is mainly trend closed-loop, and its principle is to set extremely conservative settings. The safety control boundary (preset target value), when the coating surface density exceeds the safety control boundary and does not reach the alarm line, and when the coating surface density changes show a partial trend, the control model will output the corresponding coating control amount, which is equivalent to It is used to perform closed-loop control based on the changing trend of coating surface density. The control strategy of model No. 2 can replace manual real-time monitoring and debugging, without the need for accumulated data training, and can be put into use immediately. The disadvantage is that the control logic needs to be adjusted multiple times to achieve a better control result, which will cause a lot of slurry waste.

Model No. 3 is a control model established by machine learning on a period of production data to represent the corresponding relationship between coating surface density and coating control volume. For example, it is necessary to accumulate at least one month of production data, and then use a machine learning algorithm to establish a fitting model based on the relationship between the motor position and the coating surface density in the actual production data. Use the fitting model, and then combine it with MPC (Model Predictive Control) ) and other advanced control models can complete the entire set of control closed-loop logic. The control accuracy of this control model is high, but it requires data storage for stable production in the early stage.

Model No. 4 is a control model established by adding constraints on the basis of learning and training production data. It requires the accumulation of at least 3 months of production data. The main idea is to directly replace the controller with a reinforcement learning model, because reinforcement The output of the learning model is unpredictable, so it is necessary to reserve enough historical data for training, and hard constraints need to be added to ensure the stability of production. This control model has good control effect and adaptability, but requires a large amount of historical operating data storage.

Specifically, the control equipment can control the display device to display the description information and applicable scope of each alternative control model in the automatic coating control mode, and the user can input model selection information based on the understanding of current production conditions and model applicability.

In one embodiment, as shown in Figure 3, step S130 includes steps S131 to step S137.

S131: Select multiple control models corresponding to the model selection information from multiple candidate control models.

S133: Obtain the historical coating surface density within the preset historical time period.

The historical coating surface density within the preset historical time period includes the coating surface density corresponding to multiple time points within the preset historical time period.

S135: Use each selected control model to conduct simulation tests based on historical coating surface density.

Specifically, the simulation test is to input the historical coating surface density into each selected control model, obtain the coating control quantity corresponding to the output of each control model, and generate a control instruction based on the coating control quantity of each control model to obtain the simulation control instruction.

S137: Select the final control model as the target control model based on the results of the simulation test of each control model.

The results of the control model simulation test may include the coating control amount of the simulation output, the number of simulation tests (the number of times simulation control instructions are generated), etc. Specifically, the control device can control the display device to output the results of the simulation test, and the user can judge which control model is more suitable by viewing the results and combining experience and then select. Alternatively, the control device can further process the results of the simulation test and then select the final control model. By combining historical data for simulation and selecting a target control model based on the simulation results, the selection can be optimized.

For example, the user can select the coating surface density at any historical time period, select the corresponding control model, and start the simulation logic calculation after the selection is completed. The control model output for the surface density curve change in the historical time period can be obtained. The number of quantity changes and the overall error of the surface density; the display effect is shown in Table 2 below, where the overall error is the difference between the coating surface density after controlling the coating control quantity output from each simulation test and the expected value of the coating surface density. Deviation is obtained.

Table 2

In one embodiment, step S137 includes step (a1) and step (a2).

Step (a1): Calculate the simulation evaluation value corresponding to each control model based on the results of the simulation test of each control model.

Step (a2): Select the control model as the target control model based on the simulation evaluation value of each control model.

The simulation evaluation value is used to reflect the quality of the control model. For example, if the larger the simulation evaluation value is, the better the control model is, then the control model corresponding to the largest simulation evaluation value is selected as the target control model. By further imitating The results of real tests are evaluated to select the target control model. Compared with selecting based on user experience, subjectivity can be avoided and the selection is more accurate.

In one embodiment, the results of the control model simulation test include the control instruction calculation time, the number of simulation tests, and the control error; where the control instruction calculation time refers to the time required to generate the simulation control instruction during the control model simulation test process; The number of simulation tests is equal to the number of simulation control instructions generated during the control model simulation test; the control error is the surface density deviation between the coating surface density after being controlled by the coating control amount output by each simulation test and the expected value of the coating surface density. Obtained, for example, can be the average value of the areal density deviations of multiple simulation tests.

Specifically, step (a1) includes: calculating the variance and steady-state error according to the control error of each control model simulation test; calculating the time consumption, number of simulation tests, and preset variance proportion and preset error according to the variance, steady-state error, and control instructions. Assuming the steady-state error proportion, the preset time-consuming proportion and the preset times proportion, calculate the simulation evaluation value of the corresponding control model.

Each control model corresponds to its own indicators, which include control instruction calculation time, number of simulation tests, variance and steady-state error; for a control model, according to its corresponding control instruction calculation time, number of simulation tests, variance and steady-state error The state error and the proportion of each indicator are calculated to obtain the simulation evaluation value of the control model. The time taken to calculate the control instructions reflects the timeliness of the control, the variance reflects the control stability, and the steady-state error reflects the control effect. The number of simulation tests is the number of control steps until the coating surface density reaches the preset target value; by calculating the time consuming based on the control instructions , the number of simulation tests and the control error define the evaluation indicators of the control model to achieve a comprehensive evaluation of each control model from many aspects such as control timeliness, control stability, and control effect, and the evaluation effect is good.

Among them, the preset variance proportion is the proportion corresponding to the variance parameter, the preset steady-state error proportion is the proportion corresponding to the steady-state error parameter, and the preset time-consuming proportion is the control instruction calculation time The proportion corresponding to this parameter, the preset number of times is the proportion corresponding to the number of simulation tests. For example, simulation evaluation value = preset time-consuming proportion * control instruction calculation time + preset number of times proportion * number of simulation tests + preset variance proportion * variance + preset steady-state error proportion * steady-state error. By default, the preset variance proportion, preset steady-state error proportion, preset time-consuming proportion and preset times proportion can be equal to 25%; if the user considers different tendencies under different working conditions, it can be based on The proportions of each item need to be changed.

In another embodiment, there may be multiple target control models. Step S130 includes: selecting multiple control models corresponding to the model selection information from multiple candidate control models to obtain multiple target control models.

Correspondingly, step S150 includes: obtaining the coating control amount output by each target control model according to the current coating surface density; and performing a weighted average of the coating control amount of each target control model to obtain the final coating control amount. Specifically, step S170 outputs a control instruction according to the final coating control amount.

Each control model has its own advantages and disadvantages. This embodiment selects multiple target control models and obtains the final coating control amount based on the multiple target control models, so that it can support customized model combinations and facilitate users' own combinations. Multiple control models enable multiple control models at the same time to achieve a relatively balanced control effect.

In one embodiment, after step S150 and before step S170, the method further includes: outputting the coating control quantity; if a control quantity approval instruction is received, executing step S170; if a control quantity disapproval instruction is received, returning to step S110 .

To output the coating control quantity, the control device may control the output device to output the coating control quantity, for example, by controlling the display device to display. Among them, the control amount approval instruction and the control amount disapproval instruction can be input by the user based on the output coating control amount. The control volume approval instruction indicates that the coating control volume is approved and the next step can be performed; the control volume disapproval instruction indicates that the coating control volume is not approved and the model needs to be selected again. Determine whether the control quantity approval instruction is received. If so, execute step S170; otherwise, return to step S110. In this way, before controlling the coating control object based on the coating control quantity, a manual confirmation step is added to facilitate the user to perform the process according to the production working conditions. confirm.

In one of the embodiments, after step S170, it also includes: recording control instructions, counting the number of control times and the number of overruns when the obtained coating surface density exceeds the preset target value; and regularly generating according to the control instructions, the number of control times, and the number of times overruns. Control reporting.

The number of control times is the number of times the control model outputs control instructions based on the coating control amount; the number of over-limit times is the number of times the coating surface density exceeds the preset target value, where the preset target value can be set according to the actual required surface density. After each control instruction is output to control the coating control object, the number of control times and the number of overruns are counted, the control instructions are recorded, and control reports are regularly generated for users to review and understand, allowing users to evaluate the effectiveness of the control model and give feedback, thereby continuously Optimize control logic.

Specifically, in addition to the control instructions, control times, and overrun times, the content of the control report can also record other content as needed. For example, it can also include indicators and icons that users may care about, such as control error, number of manual confirmations, etc.

In one embodiment, the above-mentioned coating control method further includes: when receiving the real-time simulation command, using each alternative control model to obtain the coating control amount according to the current coating surface density; The coating control quantities obtained by the model generate simulation control instructions; the simulation control instructions corresponding to each alternative control model are output.

Specifically, when receiving a real-time simulation command, the control device can access the current real-time coating surface density, and each control model will calculate the coating control amount that the coating control object needs to do based on the coating surface density. The control quantity generates control instructions and obtains simulation control instructions. The control command can be output in the form of "motor number: motor displacement". At the same time, the control command calculation time can also be output for reference by on-site engineers, as shown in Table 3 below.

table 3

The above coating control method can be used by users to select control models based on different production conditions and select a better control model from multiple control models. For example, when pursuing production quality, switch to a control model with more control times and low errors; when pursuing output and relaxing quality requirements, switch to a control model with less control times; by default, multiple control models can be prioritized for multiple models. The coating control quantities output from the control model are weighted and averaged to achieve a relatively balanced control method.

For better explanation, a detailed embodiment is provided. As shown in Figure 4, the user selects automatic coating control mode or manual coating mode. If it is a manual coating mode, the on-site debugging engineer will intervene and perform manual control; if it is an automatic coating control mode, it will enter the control model selection system and select the target control model. The user can further confirm the selected control model and output The coating control amount obtained based on the target control model. When the user checks the manual confirmation mode, the coating control volume is manually confirmed. If the manual confirmation mode is not checked, the coating control volume is directly used to generate control instructions to control the coating control object to implement the control model. Assisted production. The control instructions of each control operation can be recorded and backed up locally, and the control effect is regularly (user-defined) outputted as a control report and fed back to the user. The control report can include the number of over-limit coating surface density, control times, and control deviations. , number of manual confirmations, etc.

Among them, the modular structure of the control model selection system is shown in Figure 5. It mainly has four modules, namely "Multiple control model display module", "Model simulation module (history/real-time)", "Model evaluation module", " Model Customization Module". The multi-control model display module is used to display the description information and applicable scope of each control module; the model simulation module (historical/real-time) is used to perform historical simulation based on the historical coating surface density and real-time simulation based on the real-time coating surface density; model The evaluation module is used to calculate simulation evaluation values based on historical simulation results; the model customization module is used to enable multiple control models at the same time, and then weight the results of each control model as the final output.

It should be understood that although various steps in the flowcharts of FIGS. 2 to 4 are shown in sequence as indicated by arrows, these steps are not necessarily executed in the order indicated by arrows. Unless explicitly stated in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in Figures 2 to 4 may include multiple steps or stages. These steps or stages are not necessarily executed at the same time, but may be executed at different times. The order of execution is not necessarily sequential, but may alternate with other steps or at least part of steps or stages in other steps. Or do it alternately.

In one embodiment, as shown in FIG. 6 , a coating control device is provided, including: an information acquisition module 610 , a model selection module 630 , a control quantity acquisition module 650 and a control module 670 .

The information acquisition module 610 is used to acquire model selection information and the current coating surface density in the automatic coating control mode; the model selection module 630 is used to select a control model from multiple alternative control models according to the model selection information to obtain Target control model; the control quantity obtaining module 650 is used to adopt the target control model and obtain the coating control quantity according to the current coating surface density; the control module 670 is used to output control instructions to the coating control object according to the coating control quantity.

The above-mentioned coating control device can select a target control model from multiple control models based on the model selection information, and use the target control model to determine the coating control amount to control the coating control object. In this way, it supports selection and use from multiple control models. It supports multiple control models and can be compatible with multiple control methods. Compared with the existing technology that only allows one control method, the compatibility is better.

In one embodiment, the model selection module 630 includes a model selection unit, a historical data acquisition unit, a simulation unit and a model determination unit.

The model selection unit is used to select multiple control models corresponding to the model selection information from multiple alternative control models. The historical data acquisition unit is used to acquire the historical coating surface density within a preset historical time period. The simulation unit is used to conduct simulation tests based on the historical coating surface density using each selected control model. The model determination unit is used to select the final control model as the target control model based on the results of simulation tests of each control model. By combining historical data for simulation and selecting a target control model based on the simulation results, the selection can be optimized.

In one embodiment, the model determination unit is configured to calculate the simulation evaluation value corresponding to each control model based on the simulation test results of each control model; and select the control model as the target control model based on the simulation evaluation value of each control model.

By further evaluating based on the results of simulation tests to select the target control model, subjectivity can be avoided and the selection is more accurate than selecting based on user experience.

In one embodiment, the results of the control model simulation test include control instruction calculation time, number of simulation tests, and control error. The model determination unit calculates the variance and steady-state error based on the control errors of each control model simulation test; calculates the time consumption, number of simulation tests, and preset variance proportions and preset steady-state error proportions based on the variance, steady-state error, and control instructions. , the preset time-consuming proportion and the preset number of times proportion, and calculate the simulation evaluation value of the corresponding control model.

In another embodiment, there may be multiple target control models. The model selection module 630 selects multiple control models corresponding to the model selection information from multiple candidate control models to obtain multiple target control models. Correspondingly, the control quantity obtaining module 650 obtains the coating control quantity output by each target control model according to the current coating surface density; The coating control amount of each target control model is weighted and averaged to obtain the final coating control amount. In this way, custom model combinations can be supported, allowing users to combine multiple control models by themselves to enable multiple control models at the same time to achieve a relatively balanced control effect.

In one embodiment, the above-mentioned coating control device also includes a control quantity approval module (not shown) for outputting the coating control quantity; when receiving the control quantity approval instruction, the control module 670 performs the corresponding function; When the control quantity disapproval instruction is received, the information acquisition module 610 executes the corresponding function again.

In one embodiment, the above-mentioned coating control device also includes a reporting module (not shown) for recording control instructions, counting the number of control times and the number of times the obtained coating surface density exceeds the preset target value; according to the control Regularly generate control reports on instructions, control times and limit violations.

In one embodiment, the above-mentioned coating control device also includes a real-time simulation module (not shown), which is used to use each alternative control model to obtain coating according to the current coating surface density when receiving a real-time simulation command. Control volume; generate simulation control instructions based on the coating control variables obtained from each alternative control model; output simulation control instructions corresponding to each alternative control model.

For specific limitations on the coating control device, please refer to the above limitations on the coating method, which will not be described again here. Each module in the above-mentioned coating control device can be realized in whole or in part by software, hardware and combinations thereof. Each of the above modules can be embedded in or independent of the processor in the control device in the form of hardware, or can be stored in the memory of the control device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. In actual implementation, there may be other division methods.

In one embodiment, a control device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the steps in the above method embodiments.

Since the above control device can implement the steps in each of the above method embodiments, it can also support a variety of coating control methods and has better compatibility.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

Since the above-mentioned computer-readable storage medium can implement the steps in each of the above-mentioned method embodiments, it can also support a variety of coating control methods and has better compatibility.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. That , any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM).

In the description of this specification, reference to the terms "some embodiments," "other embodiments," "ideal embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included herein. In at least one embodiment or example of the invention. In this specification, schematic descriptions of the above terms do not necessarily refer to the same embodiment or example.

The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.

The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

A coating control method, characterized by including:

In automatic coating control mode, obtain model selection information and current coating surface density;

According to the model selection information, select a control model from multiple alternative control models to obtain a target control model;

Using the target control model and obtaining the coating control amount according to the current coating surface density;

A control instruction is output to the coating control object according to the coating control amount.
The method according to claim 1, characterized in that, according to the model selection information, selecting a control model from a plurality of alternative control models to obtain a target control model includes:

Select a plurality of control models corresponding to the model selection information from a plurality of alternative control models;

Obtain the historical coating surface density within the preset historical time period;

Each selected control model is used to conduct simulation tests based on the historical coating surface density;

The final control model is selected as the target control model based on the simulation test results of each control model.
The method according to claim 2, characterized in that selecting the final control model as the target control model based on the results of simulation tests of each control model includes:

Calculate the simulation evaluation value corresponding to each control model based on the results of the simulation test of each control model;

The control model is selected as the target control model based on the simulation evaluation value of each control model.
The method according to claim 3, characterized in that the results of the control model simulation test include the control instruction calculation time, the number of simulation tests and the control error; the calculation of each control is based on the results of the simulation test of each control model. The simulation evaluation values corresponding to the model include:

Calculate the variance and steady-state error respectively based on the control errors of each control model simulation test;

According to the variance, the steady-state error, the control instruction calculation time, the number of simulation tests, and the preset variance proportion, the preset steady-state error proportion, the preset time-consuming proportion, and the preset number of times Ratio, calculate the simulation evaluation value of the corresponding control model.
The method according to claim 1, characterized in that, according to the model selection information, selecting a control model from a plurality of alternative control models to obtain a target control model includes:

Select multiple control models corresponding to the model selection information from multiple alternative control models to obtain multiple target control models;

The method of using the target control model and obtaining the coating control amount based on the current coating surface density includes:

Obtain the coating control amount output by each target control model based on the current coating surface density;

The coating control amount of each target control model is weighted and averaged to obtain the final coating control amount.
The method according to claim 1, characterized in that, after using the target control model and obtaining the coating control amount according to the current coating surface density, the control instruction is output to the coating according to the coating control amount. Before placing control objects, also include:

Output the coating control amount;

If the control quantity approval instruction is received, then execute the step of outputting the control instruction to the coating control object according to the coating control quantity;

If the control quantity disapproval instruction is received, return to the step of obtaining the model selection information and the current coating surface density in the automatic coating control mode.
The method according to claim 1, characterized in that after outputting the control instruction to the coating control object according to the coating control amount, it further includes:

Record the control instructions, count the number of times of control and the number of times the obtained coating surface density exceeds the preset target value;

Control reports are periodically generated based on the control instructions, the number of times of control, and the number of times of overruns.
The method of claim 1, further comprising:

When receiving the real-time simulation command, each alternative control model is used to obtain the coating control amount based on the current coating surface density;

Generate simulation control instructions based on the coating control quantities obtained from each alternative control model;

Output the simulation control instructions corresponding to each alternative control model.
A coating control device, characterized by including:

Information acquisition module, used to obtain model selection information and current coating surface density in automatic coating control mode;

A model selection module, configured to select a control model from multiple alternative control models to obtain a target control model based on the model selection information;

A control quantity acquisition module, used to adopt the target control model and obtain the coating control quantity according to the current coating surface density;

A control module, configured to output control instructions to the coating control object according to the coating control amount.
A control device, including a memory and a processor, the memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the method described in any one of claims 1 to 8 are implemented. steps.
A computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.