Coating machine control method and device, coating machine

Abstract

A coating machine control method and device, and a coating machine, applied to the coating machine, the method comprising: obtaining a detection surface density corresponding to the slurry in a target detection area during slurry coating by the coating machine; inputting the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determining coating setting information through the coating control model; wherein the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; and adjusting the coating machine according to the coating setting information so that when the adjusted coating machine is coating the slurry, the slurry in the target detection area meets the target surface density. Implementing the embodiments of the present application can automatically and precisely adjust the motor and other related settings of the coating machine, which is conducive to improving the accuracy of the coating machine in slurry coating, thereby improving the efficiency and reliability of production and manufacturing using the coating machine.

Description

Technical Field

[0001] The present application relates to the technical field of coating processes, and in particular to a coating machine control method and device, and a coating machine. Background Art

[0002] The coating process generally involves applying a fluid material (also known as a "slurry") to a substrate. This process can be accomplished using a coating machine and is widely used in various production scenarios, particularly in battery manufacturing. However, in practice, traditional coating machines often require manual adjustment of relevant parameters. Limited by factors such as operator experience, slurry variations, and environmental fluctuations, proper adjustment of the coating machine is often difficult, reducing the accuracy of the coating machine during slurry application and, in turn, the efficiency and reliability of manufacturing using the coating machine. Summary of the Invention

[0003] The embodiments of the present application disclose a coating machine control method and device, and a coating machine, which can automatically and accurately adjust the motor and other related settings of the coating machine, which is beneficial to improving the accuracy of slurry coating by the coating machine, thereby improving the efficiency and reliability of production and manufacturing using the coating machine.

[0004] A first aspect of an embodiment of the present application discloses a coating machine control method, which is applied to a coating machine, and the method includes:

[0005] During the process of slurry coating by the coater, obtaining a detection surface density corresponding to the slurry in the target detection area;

[0006] Inputting the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determining the coating setting information through the coating control model; wherein the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information;

[0007] The coating machine is adjusted according to the coating setting information so that during the slurry coating process of the adjusted coating machine, the slurry in the target detection area meets the target surface density.

[0008] A second aspect of an embodiment of the present application discloses a coating machine control device, which is applied to a coating machine. The coating machine control device includes:

[0009] A detection unit, configured to obtain a detection surface density corresponding to the slurry in a target detection area during the slurry coating process of the coater;

[0010] A model control unit, configured to input the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determine coating setting information through the coating control model; wherein the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information;

[0011] The coating adjustment unit is used to adjust the coating machine according to the coating setting information so that the slurry in the target detection area meets the target surface density during the slurry coating process of the adjusted coating machine.

[0012] A third aspect of the present application discloses a coating machine, comprising:

[0013] a memory storing executable program code;

[0014] a processor coupled to the memory;

[0015] The processor calls the executable program code stored in the memory to execute all or part of the steps in any one of the coating machine control methods disclosed in the first aspect of the embodiment of the present application.

[0016] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0017] In an embodiment of the present application, a coater to which the coater control method is applied can obtain the detection surface density corresponding to the slurry in the target detection area during the process of slurry coating. The coater can input the above-mentioned detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determine the coating setting information through the coating control model. Among them, the coating control model is a model obtained by deep learning training of the first sample data set corresponding to the coater, and the first sample data set may include multiple groups of first sample information, each group of first sample information may respectively include first sample coating setting information and the first sample surface density corresponding to the first sample coating setting information. On this basis, the coater can adjust its coater according to the above-mentioned coating setting information, so that the slurry in the target detection area can meet the target surface density during the process of slurry coating by the adjusted coater. It can be seen that by implementing the embodiment of the present application, the motor and other related settings of the coater can be automatically adjusted based on the coating control model to achieve timely and accurate production regulation and control, ensuring that the slurry coating quickly reaches the target surface density requirements. Such a coating machine control method is conducive to improving the accuracy of the coating machine in slurry coating. At the same time, it can intelligently adjust the control mode and coating control model of the coating machine according to the actual surface density data during the coating process, thereby optimizing the production process and improving the efficiency and reliability of production and manufacturing using the coating machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a schematic diagram of an application scenario of the coating machine disclosed in the embodiment of the present application;

[0020] Figure 2 This is a structural schematic diagram of a coating machine disclosed in an embodiment of the present application;

[0021] Figure 3 This is a flow chart of a coating machine control method disclosed in an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a coating control model disclosed in an embodiment of the present application;

[0023] Figure 5 This is a flow chart of another coating machine control method disclosed in an embodiment of the present application;

[0024] Figure 6AThis is a schematic diagram of a result of a closed-loop simulation using a coating control model disclosed in an embodiment of the present application;

[0025] Figure 6B This is another schematic diagram of the results of closed-loop simulation using the coating control model disclosed in the embodiments of the present application;

[0026] Figure 7 This is a flow chart of another coating machine control method disclosed in an embodiment of the present application;

[0027] Figure 8A This is a schematic diagram of a control panel of a coating machine disclosed in an embodiment of the present application;

[0028] Figure 8B This is another schematic diagram of a control panel of a coating machine disclosed in an embodiment of the present application;

[0029] Figure 8C This is another schematic diagram of a control panel of the coating machine disclosed in the embodiment of the present application;

[0030] Figure 9 This is a timing diagram of a coating machine control method disclosed in an embodiment of the present application;

[0031] Figure 10 This is a modular schematic diagram of a coating machine control device disclosed in an embodiment of the present application;

[0032] Figure 11 A modular schematic diagram of a coating machine disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0034] It should be noted that the terms "including" and "having" in the embodiments of the present application and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0035] The embodiments of the present application disclose a coating machine control method and device, and a coating machine, which can automatically and accurately adjust the motor and other related settings of the coating machine, which is beneficial to improving the accuracy of slurry coating by the coating machine, thereby improving the efficiency and reliability of production and manufacturing using the coating machine.

[0036] The following is a detailed description with reference to the embodiments and drawings.

[0037] See also Figure 1 , Figure 1 1 is a schematic diagram of an application scenario of the coating machine control method disclosed in an embodiment of the present application, which may include a coating machine 10 and a backing roller 20. The backing roller 20 may be used to support a foil (substrate) 21 so that a slurry 30 (usually a fluid material) to be coated may be coated on the foil 21 by the coating machine 10.

[0038] It should be noted that the foil 21 can be attached to the backing roller 20 so that the backing roller 20 can provide support for the foil 21, making it easier for the coating machine 10 to coat the slurry. Figure 1 The gap between the backing roller 20 and the foil 21 is shown only for illustration to distinguish the two. In actual production scenarios, the gap between the two is extremely inconspicuous.

[0039] Please see further Figure 2 , Figure 2 This is a schematic diagram of the structure of the coating machine disclosed in the embodiment of this application. Figure 2 As shown, the coating machine 10 may include at least one motor 11 ( Figure 2 The coating machine 10 comprises a plurality of motors (only one of which is shown) and a feed pump 12. The position of the motor 11 is adjustable, allowing the coating machine 10 to achieve different coating effects. The feed pump 12 is used to supply the coating machine 10, that is, to transfer the slurry 30 to be coated into a cavity (not specifically shown) within the coating machine 10. The coating machine 10 then controls the coating die 13 (the slurry 30 can be discharged through the lip of the coating die 13) to coat the slurry 30 on the foil 21.

[0040] It should be noted that Figure 1 and Figure 2 The shapes of the coater 10, backing roller 20 and foil 21 shown are only examples. In other embodiments, the coater 10, backing roller 20 and foil 21 may also have other different shapes to meet different actual production needs, which are not specifically limited in the embodiments of this application.

[0041] In some embodiments, the coating machine 10 may include a processing module (not specifically shown), which may be used to control the motor 11, feed pump 12, and coating die 13 of the coating machine 10 to adjust the coating effect of the coating machine 10 on the slurry 30. For example, the processing module may include various devices or systems with processing elements, such as a computer, a coating machine control system based on SoC (System-on-a-Chip), etc., which is not specifically limited in the embodiments of the present application.

[0042] In the related art, the control of the coating machine 10 often still requires manual adjustment to set relevant parameters, which is easily affected by various conditions such as different operator experience, differences in the formulation and stability of the slurry 30, and environmental changes, which can easily lead to inaccurate adjustment of the coating machine 10 and reduce the accuracy of the slurry coating by the coating machine 10. In the embodiment of the present application, in order to achieve automatic and precise adjustment of the coating machine 10 to achieve the slurry coating effect required in the actual production scenario, the motor 11, feed pump 12, and coating die head 13 of the coating machine 10 can be adjusted together to avoid manual operation or adjusting only the motor 11, which may lead to poor adjustment effect.

[0043] For example, the coater 10 can obtain the detection surface density corresponding to the slurry in the target detection area during the slurry coating process. The target detection area may include a designated area on the backing roller 20. Sampling and testing the slurry in the target detection area can reflect the slurry coating effect of the coater 10 in real time.

[0044] Furthermore, the coating machine 10 can input the above-mentioned detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determine the coating setting information through the coating control model. The above-mentioned coating control model can be a model obtained by deep learning training of the first sample data set corresponding to the coating machine, and the first sample data set can include multiple groups of first sample information, and each group of first sample information can respectively include first sample coating setting information and the first sample surface density corresponding to the first sample coating setting information. On this basis, the coating machine 10 can be adjusted according to the above-mentioned coating setting information (for example, the position of the above-mentioned motor 11, the pump speed of the feed pump 12, the gap distance between the coating die head 13 and the back roller 20, etc.) so that when the adjusted coating machine 10 is coating the slurry, the slurry in the above-mentioned target detection area can meet the target surface density.

[0045] It can be seen that the coating machine control method of this embodiment can automatically adjust the relevant settings of the motor 11 of the coating machine 10 based on the coating control model to achieve timely and accurate production control, ensuring that the coating of the slurry 30 quickly reaches the target surface density requirement. Such a coating machine control method is conducive to improving the accuracy of the slurry coating performed by the coating machine 10. At the same time, it can intelligently adjust the control method and coating control model of the coating machine 10 according to the actual surface density data during the coating process, thereby optimizing the production process and improving the efficiency and reliability of production and manufacturing using the coating machine 10.

[0046] See also Figure 3 , Figure 3 This is a flow chart of a coating machine control method disclosed in an embodiment of the present application, which can be applied to the coating machine mentioned above. Figure 3 As shown, the coating machine control method may include the following steps:

[0047] 302. During the slurry coating process of the coating machine, obtain the detection surface density corresponding to the slurry in the target detection area.

[0048] In an embodiment of the present application, in order to ensure that the slurry applied by the coater reaches the target surface density, the target detection area where the slurry has been applied can be detected to obtain the detection surface density corresponding to the slurry in the target detection area. The target detection area can include a designated area on the backing roller associated with the coater. That is, when the coater is applying slurry to a foil material mounted on the backing roller, the designated area can be used as the target detection area to detect the surface density of the slurry applied to the foil material in the target detection area.

[0049] In some embodiments, the coating machine may be equipped with a first detection sensor (e.g., a laser thickness gauge, an X-ray thickness gauge, etc.), and the first detection sensor may be used to measure the surface density of the slurry in the target detection area. For example, the first detection sensor may be located near a coating die head controlled by the coating machine, or may be mounted on a backing roller associated with the coating machine, although this is not specifically limited in the present embodiments.

[0050] In other embodiments, the coating machine can also determine the detection surface density corresponding to the slurry in the target detection area based on the discharge conditions corresponding to the coating die head it controls. For example, a second detection sensor can be provided near the coating die head, and the second detection sensor can be used to collect slurry parameters such as the flow rate, density, and mass of the slurry output by the coating die head through its lip. On this basis, the coating machine can synchronously obtain the back roller position information corresponding to the coating die head, and the back roller position information can be used to indicate the position of the slurry output by the coating die head when it is applied to the back roller (the installed foil) at each moment. By matching the back roller position information corresponding to the target detection area with the corresponding slurry parameters, the coating machine can further estimate the detection surface density corresponding to the slurry in the target detection area.

[0051] 304. Input the above-mentioned detection surface density and the target surface density corresponding to the target detection area into the trained coating control model, and determine the coating setting information through the coating control model; wherein, the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, and each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information.

[0052] In an embodiment of the present application, since the surface density of the slurry coated by the coater may not reach the target surface density (for example, when coating has just started, or when there are changes in the slurry or environmental conditions, etc.), the corresponding coating setting information can be determined through the trained coating control model to adjust the coater.

[0053] For example, the coating setting information may include at least one or more of motor position information, pump speed information, and gap information. The motor position information may be used to indicate the adjustable position of at least one motor included in the coating machine; the pump speed information may be used to indicate the pumping rate of the feed pump of the coating machine; and the gap information may be used to indicate the gap distance (e.g., the gap distance between the coating die head controlled by the coating machine and the corresponding backing roller) between the coating die head controlled by the coating machine and the corresponding backing roller. Figure 2 shown).

[0054] In some embodiments, the coating machine may input the above-mentioned detection surface density and the target surface density corresponding to the target detection area into a trained coating control model to perform closed-loop simulation through the coating control model to obtain corresponding coating setting information.

[0055] For example, see Figure 4 , Figure 4 This is a schematic diagram of a coating control model disclosed in the embodiment of this application. Figure 4As shown, the coating control model can include a control sub-model and a coating sub-model. The specific method of training the model using the first sample data set will be described in detail later. After receiving the above-mentioned detection area density and target area density, the coating control model can perform pre-processing calculation steps such as subtraction and partial differential calculation to obtain corresponding area density error data, which can be used as input data for the above-mentioned control sub-model. Optionally, the current setting information corresponding to the coating machine can be further used as input data for the control sub-model.

[0056] like Figure 4 As shown, the above-mentioned control sub-model can obtain corresponding simulation setting information based on its input data. Furthermore, the simulation setting information can be input into the above-mentioned coating sub-model to obtain the simulated surface density output by the coating sub-model. On this basis, if the simulated surface density does not meet the target surface density, the coating control model can pass it back to the pre-processing calculation module, that is, based on the simulated surface density and the target surface density, recalculate the surface density error data, thereby completing a single closed-loop simulation; if the simulated surface density meets the target surface density, the coating control model can output the coating setting information for adjusting the coating machine based on the latest simulation setting information, thereby completing the overall process of the closed-loop simulation.

[0057] In other embodiments, the coating machine may also perform a table lookup based on the output of the coating control model to determine the corresponding coating setting information. For example, the coating control model may calculate and output the corresponding coating setting parameters based on the above-mentioned detection surface density and target surface density by specifying a function (e.g., a function constructed using parameters obtained through deep learning training). Optionally, the coating setting parameters may be directly used as coating setting information to instruct the coating machine to make corresponding adjustments; or the coating setting information corresponding to the coating setting parameters may be queried based on a preset parameter lookup table, so that the coating machine can make corresponding adjustments based on the coating setting information in subsequent steps.

[0058] 306. Adjust the coating machine according to the coating setting information so that the slurry in the target detection area meets the target surface density during the slurry coating process of the adjusted coating machine.

[0059] In an embodiment of the present application, the coating machine can adjust at least one motor, feed pump, coating die head and other components included in the coating machine according to the above-mentioned coating setting information (at least including one or more combinations of motor position information, pump speed information and gap information) to make them comply with the instructions of the coating setting information.

[0060] Exemplarily, if the above-mentioned coating setting information includes motor position information, the coater can adjust the position of at least one motor included therein (for example, forward position adjustment or reverse position adjustment, etc.) until it meets the above-mentioned motor position information; if the coating setting information includes pump speed information, the coater can adjust the pump speed of its feed pump (for example, speed up the pump speed or slow down the pump speed, etc.) until it meets the above-mentioned pump speed information; if the coating setting information includes gap information, the coater can adjust the gap distance between its coating die and the corresponding back roller (for example, increase the gap distance or reduce the gap distance, etc.) until it meets the above-mentioned gap information.

[0061] By performing the above adjustments, the adjusted coater can perform subsequent slurry coating using corresponding settings based on the closed-loop simulation results completed by the coating control model, so that the slurry in the target detection area can be as consistent as possible with the above target surface density, thereby achieving the slurry coating effect required in the actual production scenario.

[0062] It can be seen that the implementation of the coating machine control method described in the above embodiment can automatically adjust the motor and other related settings of the coating machine based on the coating control model to achieve timely and accurate production control, ensuring that the slurry coating quickly reaches the target surface density requirements. This is conducive to improving the accuracy of the coating machine in slurry coating. At the same time, it can intelligently adjust the control method and coating control model of the coating machine based on the actual surface density data during the coating process, thereby optimizing the production process and improving the efficiency and reliability of production and manufacturing using the coating machine.

[0063] See also Figure 5 , Figure 5 This is a flow chart of another coating machine control method disclosed in the embodiment of this application, which can be applied to the above coating machine. Figure 5 As shown, the coating machine control method may include the following steps:

[0064] 502. During the slurry coating process of the coating machine, obtain the detection surface density corresponding to the slurry in the target detection area.

[0065] Among them, step 502 is similar to the above step 302 and will not be repeated here.

[0066] 504. Input the above-mentioned detection surface density and the target surface density corresponding to the target detection area into a trained coating control model; wherein, the coating control model is a model obtained by deep learning training of a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, and each group of first sample information includes first sample coating setting information and the first sample surface density corresponding to the first sample coating setting information.

[0067] In an embodiment of the present application, the coating control model may include a control sub-model and a coating sub-model, both of which can be trained based on the first sample data set corresponding to the coating machine. The first sample data set may include multiple groups of first sample information, and each group of first sample information may respectively include first sample coating setting information and the first sample surface density corresponding to the first sample coating setting information. In some embodiments, the first sample data set may be collected by the coating machine during operation, and the coating control model may be directly trained locally by the coating machine through deep learning. Optionally, the coating machine may also transmit the first sample data set to other devices (such as computers, servers, etc.), and the other devices may train the coating control model based on the first sample data set, and then transmit the trained coating control model to the coating machine for direct call by the coating machine.

[0068] For example, during the slurry coating process, the coater can obtain multiple pieces of first sample coating setting information corresponding to the coater, as well as the first sample surface density corresponding to each piece of first sample coating setting information (i.e., the surface density of the slurry in the target detection area when the coater coats the slurry based on the first sample coating setting information). Based on this, the coater can add each piece of first sample coating setting information and the corresponding first sample surface density to the first sample dataset.

[0069] In some embodiments, when the coating sub-model is trained using the first sample data set, the first sample data set can be input into the coating sub-model to be trained so that the coating sub-model to be trained fits the first sample data set and converges to obtain a trained coating sub-model.

[0070] For example, the coating sub-model can be applied by the function To indicate that the function It can be used to characterize the mapping relationship between coating setting information (including motor position information, pump speed information, gap information, etc.) and coating surface density, one form of which can be shown in the following formula 1.

[0071] Formula 1:

[0072]

[0073] in, Indicates the coating surface density, which may include the detection surface density obtained by actual detection of the slurry in the target detection area, or the simulated surface density obtained in the closed-loop simulation process; Indicates the motor position information, Indicates the pump speed information corresponding to the feed pump. and The subscripts represent the left gap distance and the right gap distance between the coating die head and the backing roller respectively; Used to indicate the closed-loop order during closed-loop simulation.

[0074] According to the first sample coating setting information and the corresponding first sample surface density included in the first sample data set, the above function can be Perform deep learning training and obtain the trained coating sub-model after the training converges.

[0075] On this basis, the control sub-model can also be trained using the first sample data set. According to the first sample data set and the target surface density, a corresponding sample error data set can be generated, which can then be used as input data for the control sub-model.

[0076] Exemplarily, the sample error data set may include multiple sets of sample error information, each set of sample error information may include first sample coating setting information, first sample surface density corresponding to the first sample coating setting information, and sample surface density error between the first sample surface density and the target surface density.

[0077] In some embodiments, by inputting the above-mentioned sample error data set into the control sub-model to be trained, so that the control sub-model to be trained can iteratively learn the functional relationship between the current setting information and the next setting information corresponding to the coating machine based on the above-mentioned trained coating sub-model, a trained control sub-model can be obtained.

[0078] For example, the control sub-model can be controlled by the function To indicate that the function It can be used to characterize the mapping relationship between the current setting information corresponding to the coating machine (including motor position information, pump speed information, gap information, etc.) and the next setting information (i.e., the next simulated setting information obtained through closed-loop simulation).

[0079] The coating setting information required for the final adjustment of the coating machine may include motor position information, pump speed information, gap information, and the like.

[0080] Through iterative learning of the control sub-model and the coating sub-model, a trained control sub-model can be obtained.

[0081] 506. Calculate the surface density error data based on the detection surface density and the target surface density.

[0082] 508. Based on the above-mentioned surface density error data and the current setting information corresponding to the coating machine, a closed-loop simulation is performed through the coating control model to obtain coating setting information.

[0083] In the embodiments of this application, Figure 4 As shown, the coater can utilize a trained coating control model (including a control sub-model and a coating sub-model) by first inputting the aforementioned areal density error data and the coater's corresponding current setting information into the control sub-model, thereby determining simulation setting information through the control sub-model. Furthermore, the simulation setting information can be input into the coating sub-model to determine the simulated areal density through the coating sub-model.

[0084] On this basis, if the simulated surface density meets the target surface density, the closed-loop simulation can be exited, and the latest simulation setting information is determined as the coating setting information.

[0085] If the above-mentioned simulated surface density does not meet the target surface density, the simulated surface density can be used as the new detection surface density, and the latest simulation setting information can be used as the new current setting information (completing a single closed-loop simulation). By re-executing the above-mentioned step 506, that is, recalculating the surface density error data based on the above-mentioned detection surface density and the target surface density, and re-obtaining the simulated surface density based on the surface density error data and the new current setting information, the above-mentioned judgment can be continued until the re-acquired simulated surface density meets the target surface density.

[0086] For example, please refer to Figure 6A and Figure 6B , Figure 6A This is a schematic diagram of the results of a closed-loop simulation using a coating control model disclosed in an embodiment of the present application. Figure 6B This is another result diagram. Figure 6A As shown in , when the initial surface density (i.e., the initial detection surface density) is lower than the target surface density, the error between the real-time surface density (i.e., the simulated surface density) and the target surface density can be reduced to an acceptable range through about 10 closed-loop simulations; similarly, Figure 6B As shown in FIG, when the initial surface density is higher than the target surface density, the error between the real-time surface density and the target surface density can be reduced to an acceptable range through about 7 closed-loop simulations.

[0087] Optionally, during the closed-loop simulation using the coating control model, the coating machine can be adjusted in real time based on the simulation setting information to reflect the adjustment effect as soon as possible; the coating machine can also be adjusted based on the final output coating setting information, thereby reducing the frequency of actual adjustments on the coating machine, which is conducive to shortening the adjustment cycle and reducing material scrap, and further improving the efficiency of production and manufacturing using the coating machine.

[0088] 510. Adjust the coating machine according to the coating setting information so that the slurry in the target detection area meets the target surface density during the slurry coating process of the adjusted coating machine.

[0089] Among them, step 510 is similar to the above step 306 and will not be repeated here.

[0090] As an optional implementation, the coating machine can further adjust the above coating control model during the slurry coating process to optimize the coating control model according to the actual production scenario and further improve the accuracy of the coating machine in slurry coating.

[0091] In some embodiments, the coater may determine a current gain parameter based on the coating setting information. The current gain parameter may vary with system error and error change rate to characterize the possible impact of system error on the coating control model.

[0092] In other embodiments, if the slurry in the target detection area still does not meet the target surface density during the slurry coating process of the adjusted coater, it indicates that there may be a slurry instability problem and the coating control model needs to be updated to adapt to the slurry change.

[0093] For example, the coating machine can obtain multiple historical surface density data corresponding to the target detection area and, based on the historical surface density data and the target surface density, calculate multiple historical error data. If the historical error data does not meet the slurry stability conditions (for example, the mean, standard deviation, variance, etc. corresponding to the multiple historical error data do not meet the specified threshold conditions), the coating machine can obtain multiple second sample coating setting information corresponding to the slurry coating process and the second sample surface density corresponding to each second sample coating setting information. The second sample coating setting information and the corresponding second sample surface density are added to the second sample data set, and the coating control model is updated using the second sample data set.

[0094] Optionally, the coating machine can retrain the coating control model using the second sample data set to obtain a new coating control model; it can also determine the corresponding model adjustment parameters based on the second sample data set, and update the coating control model based on the model adjustment parameters, which is not specifically limited in the embodiments of the present application.

[0095] It can be seen that the coating machine control method described in the above embodiment can automatically adjust the motor and other related settings of the coating machine based on the coating control model to achieve timely and accurate production control, ensuring that the slurry coating quickly reaches the target surface density requirements, thereby helping to improve the accuracy of the coating machine in slurry coating. At the same time, it can also intelligently adjust the control method and coating control model of the coating machine, optimize the production process, and thus improve the efficiency and reliability of production and manufacturing using the coating machine. In addition, by performing closed-loop simulation in the coating control model, it is possible to quickly determine the coating setting information that needs to be adjusted in the current production scenario, reduce the frequency of actual adjustments on the coating machine, thereby helping to shorten the adjustment cycle and reduce material scrap, further improving the efficiency of production and manufacturing using the coating machine.

[0096] See also Figure 7 , Figure 7 This is a flow chart of another coating machine control method disclosed in the embodiment of this application, which can be applied to the above coating machine. Figure 7 As shown, the coating machine control method may include the following steps:

[0097] 702. In response to a control strategy selection instruction, when the control strategy selection instruction is a fully automatic instruction, obtain an input upper limit of an adjustment time.

[0098] In the embodiment of the present application, the coating machine can be set to apply a variety of different control strategies, such as manual control strategy, semi-automatic control strategy, full-automatic control strategy, etc. Among them, under the manual control strategy, such as Figure 8A As shown, the position of at least one motor included in the coating machine, the pump speed of the feed pump (corresponding to the pump speed information), and the gap distance between the coating die head and the backing roller (corresponding to the gap information) can all be manually adjusted by the user. Optionally, the gap distance can include a left gap distance and a right gap distance ( Figure 8A Not shown, see Figure 8B ), and can be manually adjusted by the user.

[0099] In semi-automatic mode, Figure 8B As shown, the position of the above-mentioned motor cannot be adjusted manually, but the corresponding motor step and overrun times can still be adjusted manually, and the pump speed information and gap information (which may include the left gap distance and the right gap distance) can still be adjusted manually.

[0100] For example, the coating machine can respond to a control strategy selection instruction, where the control strategy selection instruction is a semi-automatic instruction, by obtaining active adjustment information input by the user (including the motor step distance, number of overruns, pump speed information, and gap information, etc.), and then adjust the coating machine based on this active adjustment information. During this process, at least one motor of the coating machine can be adaptively and automatically adjusted based on the preset adjustment strategy to achieve the desired slurry coating effect in actual production scenarios.

[0101] In full automatic mode, if Figure 8C As shown, the user can only set an upper limit on the adjustment time for the coater. For example, the coater can respond to a control strategy selection instruction, and when the control strategy selection instruction is a fully automatic instruction, obtain the upper limit on the adjustment time input by the user. By limiting the coater's adjustment time, it can prevent the coater from consuming excessive time during the subsequent closed-loop simulation of the coating control model, thereby ensuring the efficiency of the coater's adaptive adjustment.

[0102] Alternatively, for the selection of the above different control strategies, please refer to Figure 9 , the corresponding timing will be described in detail later.

[0103] It should be noted that, during the process of slurry coating by the coating machine, if the coating control model has not completed training, the coating machine can be adjusted based on the preset motor setting method (similar to the semi-automatic mode mentioned above), and multiple first sample coating setting information corresponding to the coating machine during the slurry coating process, as well as the first sample surface density corresponding to each first sample coating setting information, can be obtained as the first sample data set corresponding to the coating machine.

[0104] On this basis, the above-mentioned first sample data set can be used to perform deep learning training on the coating control model to be trained. When the coating control model has been trained, the coating machine can execute subsequent step 704 to determine the coating setting information through the trained coating control model.

[0105] 704. Input the above-mentioned detection surface density and the target surface density corresponding to the target detection area into a trained coating control model; wherein, the coating control model is a model obtained by deep learning training of a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, and each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information.

[0106] Among them, step 704 is similar to the above step 504 and will not be repeated here.

[0107] 706. When the upper limit of the adjustment time has not been reached, obtain coating setting information output by the coating control model.

[0108] In the embodiment of the present application, when the coating machine has not reached the upper limit of the adjustment time, the specific implementation method of determining the coating setting information through the coating control model can be referred to the above steps 506 and 508, which will not be repeated here.

[0109] 708. When the upper limit of the adjustment time has been reached and the current simulation surface density does not meet the target surface density, obtain the current simulation setting information corresponding to the current simulation surface density output by the coating control model as the coating setting information.

[0110] In an embodiment of the present application, the coating machine performs closed-loop simulation using a coating control model. The current simulated surface density and the current simulation setting information corresponding to the current simulated surface density are the most recently obtained set of simulation information by the coating control model. If the upper limit of the adjustment time has been reached, the coating machine can extract the current simulation setting information from the most recent set of simulation information (including the current simulated surface density and the corresponding current simulation setting information) obtained before the upper limit of the adjustment time is reached, and output it as the coating setting information, so that the coating machine can complete the adjustment within the specified time.

[0111] It should be noted that step 708 and step 706 may be executed in parallel, and both are executed immediately after step 704. That is, if the upper limit of the adjustment time has not been reached, and the coating control model outputs coating setting information, then step 710 is executed based on the coating setting information; if the upper limit of the adjustment time has been reached and the current simulated surface density does not meet the target surface density, then the current simulation setting information corresponding to the current simulated surface density is used as the coating setting information, and then step 710 is executed.

[0112] 710. Adjust the coating machine according to the coating setting information so that the slurry in the target detection area meets the target surface density during the slurry coating process of the adjusted coating machine.

[0113] Among them, step 710 is similar to the above step 510 and will not be repeated here.

[0114] It can be seen that the coating machine control method described in the above embodiment can be implemented to automatically adjust the motor and other related settings of the coating machine based on the coating control model to achieve timely and accurate production control, ensuring that the slurry coating quickly reaches the target surface density requirements, thereby helping to improve the accuracy of the coating machine in slurry coating. At the same time, it can also intelligently adjust the control method and coating control model of the coating machine, optimize the production process, and thus improve the efficiency and reliability of production and manufacturing using the coating machine. In addition, by adopting appropriate control strategies, the coating machine can be applied to production scenarios corresponding to different instructions such as manual, semi-automatic, and fully automatic. In particular, for fully automatic instructions, appropriate coating control models can be trained and used to adaptively adjust the coating machine, further improving the efficiency of production and manufacturing using the coating machine.

[0115] See also Figure 9 , Figure 9 This is a timing diagram of a coating machine control method disclosed in an embodiment of the present application. Figure 9 As shown, the coating machine control method may include the following steps:

[0116] 902. In response to a control strategy selection instruction, make a judgment on the control strategy selection instruction.

[0117] 904A. When the control strategy selection instruction is a manual instruction, obtain input manual adjustment information.

[0118] For example, the manual adjustment information may include motor position information, pump speed information, clearance information, and the like.

[0119] 904B. When the control strategy selection instruction is a semi-automatic instruction, obtain input active adjustment information.

[0120] For example, the active adjustment information may include motor step size, number of overruns, pump speed information, and clearance information.

[0121] 904C. When the control strategy selection instruction is a fully automatic instruction, obtain the input adjustment time upper limit.

[0122] Steps 904A, 904B, and 904C are in parallel (corresponding to manual mode, semi-automatic mode, and fully automatic mode, respectively). Different steps can be executed based on the specific control strategy. After executing step 904C, i.e., the coating machine is in fully automatic mode, the subsequent step 906 can be executed.

[0123] 906. During the slurry coating process of the coating machine, if the coating control model has not completed training, the coating machine is adjusted based on the preset motor setting method, and a first sample data set corresponding to the coating machine during the slurry coating process is obtained. The first sample data set is used to perform deep learning training on the coating control model to be trained.

[0124] The first sample data set may include a plurality of first sample coating setting information and first sample surface densities corresponding to each piece of first sample coating setting information.

[0125] Optionally, when the coating control model has not been trained, the coating machine may repeatedly perform step 906 until the coating control model training is completed.

[0126] 908. When the coating control model has been trained, the detection surface density and the target surface density corresponding to the target detection area are input into the trained coating control model, and the coating setting information is determined through the coating control model.

[0127] 910. Adjust the coating machine according to the coating setting information.

[0128] 912. If the slurry in the target detection area does not meet the target surface density during the slurry coating process of the adjusted coating machine, obtain historical surface density data corresponding to the target detection area.

[0129] 914. Calculate historical error data based on the above historical surface density data and target surface density.

[0130] 916. When the historical error data does not meet the slurry stability condition, obtain a second sample data set corresponding to the coating machine during the slurry coating process, and update the coating control model using the second sample data set.

[0131] The second sample data set may include a plurality of second sample coating setting information and second sample surface densities corresponding to each piece of second sample coating setting information.

[0132] It should be noted that, when the coating machine updates the coating control model, the above step 906 may be executed again, and at this time, the second sample data set may be used as the first sample data set in step 906 .

[0133] Optionally, when the historical error data meets the slurry stability condition, the coating machine can determine the corresponding simulation adjustment parameters to adjust the closed-loop simulation process of the coating control model in step 908 according to the simulation adjustment parameters.

[0134] See also Figure 10 , Figure 10This is a modular schematic diagram of a coating machine control device disclosed in an embodiment of the present application, which can be applied to the coating machine mentioned above. Figure 10 As shown, the coating machine control device may include a detection unit 1001, a model control unit 1002 and a coating adjustment unit 1003, wherein:

[0135] The detection unit 1001 is used to obtain the detection surface density corresponding to the slurry in the target detection area during the slurry coating process of the coater;

[0136] The model control unit 1002 is configured to input the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determine coating setting information through the coating control model; wherein the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information;

[0137] The coating adjustment unit 1003 is used to adjust the coating machine according to the coating setting information, so that the slurry in the target detection area meets the target surface density during the slurry coating process of the adjusted coating machine.

[0138] It can be seen that the coating machine control device described in the above embodiment can automatically adjust the motor and other related settings of the coating machine based on the coating control model to achieve timely and accurate production control and ensure that the slurry coating quickly reaches the target surface density requirements. This is conducive to improving the accuracy of the coating machine in slurry coating. At the same time, it can intelligently adjust the control method and coating control model of the coating machine based on the actual surface density data during the coating process, thereby optimizing the production process and improving the efficiency and reliability of production and manufacturing using the coating machine.

[0139] In one embodiment, the coating setting information may include at least one or more of motor position information, pump speed information, and gap information. The gap information may be used to indicate the gap distance between the coating die head controlled by the coater and the corresponding backing roller.

[0140] In one embodiment, when the model control unit 1002 is used to determine the coating setting information through the coating control model, it may specifically include:

[0141] According to the detection surface density and the target surface density, the surface density error data is calculated;

[0142] Based on the surface density error data and the current setting information corresponding to the coating machine, a closed-loop simulation is performed through the coating control model to obtain the coating setting information.

[0143] In one embodiment, the coating control model may include a coating sub-model and a control sub-model, and the model control unit 1002 may be specifically configured to:

[0144] The areal density error data and the current setting information corresponding to the coating machine are input into the control sub-model, and the simulation setting information is determined by the control sub-model;

[0145] Inputting simulation setting information into the coating sub-model, and determining the simulation surface density through the coating sub-model;

[0146] If the simulated surface density meets the target surface density, the simulated setting information is determined as the coating setting information; if the simulated surface density does not meet the target surface density, the simulated surface density is used as the new detection surface density, the simulated setting information is used as the new current setting information, and the step of calculating the surface density error data based on the detection surface density and the target surface density is re-executed until the re-acquired simulated surface density meets the target surface density.

[0147] In one embodiment, the target surface density may include a target surface density interval, and the model control unit 1002 may be specifically configured to:

[0148] If the simulated area density falls within the target area density range, the simulation setting information is determined as coating setting information.

[0149] In one embodiment, the coating machine control device may further include a model training unit (not shown), which may be used to:

[0150] During the process of slurry coating by the coating machine, a plurality of first sample coating setting information corresponding to the coating machine and a first sample surface density corresponding to each of the first sample coating setting information are obtained, and each of the first sample coating setting information and the corresponding first sample surface density are added to a first sample data set; wherein the first sample surface density corresponding to the first sample coating setting information is used to represent the surface density corresponding to the slurry in the target detection area when the coating machine coats the slurry based on the first sample coating setting information; and

[0151] The first sample data set is input into the coating sub-model to be trained, so that the coating sub-model to be trained fits the first sample data set and converges to obtain a trained coating sub-model.

[0152] On this basis, the above model training unit can also be used for:

[0153] Generate a sample error data set based on the first sample data set and the target area density, the sample error data set including multiple sets of sample error information, each set of sample error information including first sample coating setting information, a first sample area density corresponding to the first sample coating setting information, and a sample area density error between the first sample area density and the target area density; and

[0154] The sample error data set is input into the control sub-model to be trained, so that the control sub-model to be trained iteratively learns the functional relationship between the current setting information and the next setting information corresponding to the coating machine based on the trained coating sub-model to obtain the trained control sub-model.

[0155] In one embodiment, the coating machine control device may further include a gain parameter determination unit and a model adjustment unit (not shown), wherein:

[0156] a gain parameter determining unit, configured to determine a current gain parameter according to the coating setting information after the model control unit 1002 determines the coating setting information through the coating control model;

[0157] The model adjustment unit is used to calculate the iterative gain parameter based on the current gain parameter and the surface density error data between the detected surface density and the target surface density. The iterative gain parameter is used to adjust the parameters of the coating control model.

[0158] In one embodiment, the coating machine control device may further include a historical data acquisition unit, a calculation unit, a sample data acquisition unit, and a model update unit (not shown), wherein:

[0159] a historical data acquisition unit for acquiring historical surface density data corresponding to the target detection area if, after the coating adjustment unit 1003 adjusts the coating machine according to the coating setting information, the slurry in the target detection area does not meet the target surface density during the slurry coating process performed by the adjusted coating machine;

[0160] A calculation unit, configured to calculate historical error data based on historical surface density data and target surface density;

[0161] a sample data acquisition unit, configured to acquire, when the historical error data does not meet the slurry stability condition, a plurality of second sample coating setting information corresponding to the coating machine during the slurry coating process, and a second sample surface density corresponding to each second sample coating setting information, and add each second sample coating setting information and the corresponding second sample surface density to a second sample data set;

[0162] The model updating unit is used to update the coating control model through the second sample data set.

[0163] In one embodiment, the coating machine control device may further include a strategy selection unit (not shown), wherein:

[0164] a strategy selection unit configured to obtain input active adjustment information in response to a control strategy selection instruction before the detection unit 1001 obtains the detection surface density corresponding to the slurry in the target detection area, if the control strategy selection instruction is a semi-automatic instruction;

[0165] The coating adjustment unit 1003 is further configured to adjust the coating machine according to the active adjustment information.

[0166] In one embodiment, the strategy selection unit is further configured to, in response to a control strategy selection instruction, obtain an inputted upper limit of the adjustment time when the control strategy selection instruction is a fully automatic instruction;

[0167] The coating adjustment unit 1003 is further used to:

[0168] When the upper limit of the adjustment time is not reached, obtaining coating setting information output by the coating control model;

[0169] When the upper limit of the adjustment time has been reached and the current simulation surface density does not meet the target surface density, the current simulation setting information corresponding to the current simulation surface density output by the coating control model is obtained as the coating setting information; wherein, the current simulation surface density and the current simulation setting information corresponding to the current simulation surface density are the latest set of simulation information obtained by the coating control model before the upper limit of the adjustment time is reached during the closed-loop simulation process.

[0170] In one embodiment, the sample data acquisition unit is further configured to adjust the coating machine based on a preset motor setting mode if the coating control model has not completed training during the coating process of the coating machine applying the slurry, and obtain a plurality of first sample coating setting information corresponding to the coating machine during the coating process of the slurry, as well as first sample surface densities corresponding to each first sample coating setting information, as first sample data sets corresponding to the coating machine, and the first sample data sets are used to perform deep learning training on the coating control model to be trained;

[0171] The above-mentioned model control unit 1002 can be specifically used to input the detection surface density and the target surface density corresponding to the target detection area into the trained coating control model when the coating control model has been trained, and determine the coating setting information through the coating control model.

[0172] It can be seen that the coating machine control device described in the above embodiment can be used to automatically adjust the motor and other related settings of the coating machine based on the coating control model to achieve timely and accurate production control and ensure that the slurry coating quickly reaches the target surface density requirements. This is conducive to improving the accuracy of the coating machine in slurry coating. At the same time, it can intelligently adjust the control method and coating control model of the coating machine according to the actual surface density data during the coating process, so as to optimize the production process and improve the efficiency and reliability of the coating machine for production. In addition, by performing closed-loop simulation in the coating control model, the coating setting information required for adjustment in the current production scenario can be quickly determined, reducing the frequency of actual adjustment on the coating machine, which is conducive to shortening the adjustment cycle and reducing material scrap, further improving the efficiency of production and manufacturing using the coating machine. In addition, by adopting a suitable control strategy, the coating machine can be applied to production scenarios corresponding to different instructions such as manual, semi-automatic, and fully automatic. In particular, for fully automatic instructions, a suitable coating control model can be trained and used to adaptively adjust the coating machine, further improving production efficiency.

[0173] See also Figure 11 , Figure 11 This is a modular schematic diagram of a coating machine disclosed in an embodiment of the present application. The coating machine may include a processing module (such as a computer, a coating machine control system based on SoC, etc.). Figure 11 As shown, the coating machine (specifically, the processing module included in the coating machine) may include:

[0174] A memory 1101 storing executable program code; a processor 1102 coupled to the memory 1101; wherein the processor 1102 calls the executable program code stored in the memory 1101 and can execute all or part of the steps in any one of the coating machine control methods described in the above embodiments.

[0175] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0176] The above is a detailed introduction to a coating machine control method and device, and a coating machine disclosed in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A coating machine control method, characterized in that, Applied to a coating machine, the method comprises: During the process of slurry coating by the coater, obtaining a detection surface density corresponding to the slurry in the target detection area; Inputting the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determining the coating setting information through the coating control model; wherein the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information; adjusting the coating machine according to the coating setting information so that the slurry in the target detection area meets the target surface density during the slurry coating process of the adjusted coating machine; The coating setting information includes at least one or more of motor position information, pump speed information, and gap information, wherein the gap information is used to indicate the gap distance between the coating die head controlled by the coater and the corresponding backing roller; The determining of coating setting information by the coating control model includes: Calculating surface density error data based on the detection surface density and the target surface density; Based on the areal density error data and current setting information corresponding to the coating machine, a closed-loop simulation is performed through the coating control model to obtain coating setting information; The coating control model includes a coating sub-model and a control sub-model, the target surface density includes a target surface density interval, and based on the surface density error data and the current setting information corresponding to the coating machine, a closed-loop simulation is performed through the coating control model to obtain coating setting information, including: Inputting the areal density error data and current setting information corresponding to the coating machine into the control sub-model, and determining simulation setting information through the control sub-model; Inputting the simulation setting information into the coating sub-model, and determining the simulation surface density through the coating sub-model; If the simulated surface density meets the target surface density range, the simulated setting information is determined as the coating setting information; if the simulated surface density does not meet the target surface density range, the simulated surface density is used as the new detection surface density, the simulated setting information is used as the new current setting information, and the step of calculating the surface density error data based on the detection surface density and the target surface density is re-executed until the re-acquired simulated surface density meets the target surface density.

2. The method according to claim 1, characterized in that The coating control model includes a coating sub-model, and the method further includes: During the process of the coating machine coating the slurry, a plurality of first sample coating setting information corresponding to the coating machine and a first sample surface density corresponding to each of the first sample coating setting information are obtained, and each of the first sample coating setting information and the corresponding first sample surface density are added to a first sample data set; wherein the first sample surface density corresponding to the first sample coating setting information is used to represent the surface density corresponding to the slurry in the target detection area when the coating machine coats the slurry based on the first sample coating setting information; The first sample data set is input into the coating sub-model to be trained, so that the coating sub-model to be trained is fitted to the first sample data set and converged to obtain a trained coating sub-model.

3. The method according to claim 2, characterized in that The coating control model further includes a control sub-model. After inputting the first sample data set into the coating sub-model to be trained so that the coating sub-model fits the first sample data set and converges to obtain a trained coating sub-model, the method further includes: generating a sample error dataset based on the first sample dataset and the target areal density, the sample error dataset comprising multiple sets of sample error information, each set of sample error information comprising first sample coating setting information, a first sample areal density corresponding to the first sample coating setting information, and a sample areal density error between the first sample areal density and the target areal density; The sample error data set is input into the control sub-model to be trained, so that the control sub-model to be trained iteratively learns the functional relationship between the current setting information and the next setting information corresponding to the coating machine based on the trained coating sub-model to obtain the trained control sub-model.

4. The method according to any one of claims 1 to 3, characterized in that After inputting the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model and determining coating setting information by the coating control model, the method further includes: Determining a current gain parameter according to the coating setting information; An iterative gain parameter is calculated based on the current gain parameter and the surface density error data between the detected surface density and the target surface density. The iterative gain parameter is used to adjust the parameters of the coating control model.

5. The method according to any one of claims 1 to 3, characterized in that After adjusting the coating machine according to the coating setting information, the method further includes: If the slurry in the target detection area does not meet the target surface density during the slurry coating process of the adjusted coater, obtaining historical surface density data corresponding to the target detection area; Calculating historical error data based on the historical area density data and the target area density; When the historical error data does not meet the slurry stability condition, obtaining a plurality of second sample coating setting information corresponding to the coating machine during the slurry coating process, and a second sample surface density corresponding to each second sample coating setting information, and adding each second sample coating setting information and the corresponding second sample surface density to the second sample data set; The coating control model is updated using the second sample data set.

6. The method according to any one of claims 1 to 3, characterized in that During the process of coating the slurry on the coater, before obtaining the detection surface density corresponding to the slurry in the target detection area, the method further includes: In response to a control strategy selection instruction, if the control strategy selection instruction is a semi-automatic instruction, obtaining input active adjustment information; The coating machine is adjusted according to the active adjustment information.

7. The method according to any one of claims 1 to 3, characterized in that During the process of coating the slurry on the coater, before obtaining the detection surface density corresponding to the slurry in the target detection area, the method further includes: In response to a control strategy selection instruction, when the control strategy selection instruction is a fully automatic instruction, obtaining an inputted upper limit of an adjustment time; The determining of coating setting information by the coating control model includes: When the upper limit of the adjustment time is not reached, obtaining coating setting information output by the coating control model; When the upper limit of the adjustment time has been reached and the current simulation surface density does not meet the target surface density, the current simulation setting information corresponding to the current simulation surface density output by the coating control model is obtained as the coating setting information; wherein, the current simulation surface density and the current simulation setting information corresponding to the current simulation surface density are the latest set of simulation information obtained by the coating control model before the upper limit of the adjustment time is reached during the closed-loop simulation process.

8. The method according to claim 7, characterized in that Before inputting the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model and determining coating setting information by the coating control model, the method further includes: During the process of slurry coating by the coating machine, if the coating control model has not completed training, the coating machine is adjusted based on a preset motor setting mode, and a plurality of first sample coating setting information corresponding to the coating machine during the slurry coating process and a first sample surface density corresponding to each of the first sample coating setting information are obtained as a first sample data set corresponding to the coating machine, and the first sample data set is used to perform deep learning training on the coating control model to be trained; The step of inputting the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model and determining coating setting information through the coating control model includes: When the coating control model has been trained, the detection surface density and the target surface density corresponding to the target detection area are input into the trained coating control model, and the coating setting information is determined by the coating control model.

9. A coating machine control device, characterized in that: Applied to a coating machine, the coating machine control device includes: A detection unit, configured to obtain a detection surface density corresponding to the slurry in a target detection area during the slurry coating process of the coater; A model control unit, configured to input the detection surface density and the target surface density corresponding to the target detection area into a trained coating control model, and determine coating setting information through the coating control model; wherein the coating control model is a model obtained by deep learning training using a first sample data set corresponding to the coating machine; the first sample data set includes multiple groups of first sample information, each group of first sample information includes first sample coating setting information and a first sample surface density corresponding to the first sample coating setting information; a coating adjustment unit, configured to adjust the coating machine according to the coating setting information so that, during the slurry coating process of the adjusted coating machine, the slurry in the target detection area meets the target surface density; the coating setting information includes at least one or more of motor position information, pump speed information, and gap information, wherein the gap information is used to indicate a gap distance between a coating die head controlled by the coating machine and a corresponding backing roller; The model control unit is used to determine the coating setting information through the coating control model, including: calculating the surface density error data according to the detected surface density and the target surface density; performing closed-loop simulation through the coating control model based on the surface density error data and the current setting information corresponding to the coating machine to obtain the coating setting information; the coating control model includes a coating sub-model and a control sub-model, the target surface density includes a target surface density interval, and the surface density error data and the current setting information corresponding to the coating machine are used to perform closed-loop simulation through the coating control model to obtain the coating setting information, including: converting the surface density error data and the current setting information corresponding to the coating machine into a target surface density interval. The corresponding current setting information is input into the control sub-model, and the simulation setting information is determined by the control sub-model; the simulation setting information is input into the coating sub-model, and the simulation surface density is determined by the coating sub-model; if the simulation surface density meets the target surface density interval, the simulation setting information is determined as the coating setting information; if the simulation surface density does not meet the target surface density interval, the simulation surface density is used as the new detection surface density, the simulation setting information is used as the new current setting information, and the step of calculating the surface density error data based on the detection surface density and the target surface density is re-executed until the re-acquired simulation surface density meets the target surface density.

10. A coating machine, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 8.

Images