AI-based coating preparation process regulation and control method and system

Abstract

The invention discloses an AI-based coating preparation process regulation and control method and system, and the method comprises the steps: obtaining the structural characteristic parameters and electrochemical performances of a matrix layer and a functional layer of an electrode coating under different preparation process parameter conditions, building a nonlinear mapping relation through a machine learning model, dividing the nonlinear mapping relation into a plurality of sub-regions, deducing required preparation process parameters and target gradient distribution, and determining a spraying mold category required for preparing a target electrode coating; a conductive material and a nano material are put into a spraying mold of a determined category, spraying is performed according to the obtained required preparation process parameters, a target electrode coating is prepared, and the influence of different process parameters on the structure and performance of the coating can be accurately predicted through combination of experimental data and a machine learning model, so that the preparation parameters are optimized, and the coating quality is improved. The target of gradient distribution is achieved, intelligent regulation and control of the electrode coating preparation process are achieved, and the accuracy and efficiency of the preparation process are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coating preparation, in particular to an AI-based coating preparation process regulation method and system. BACKGROUND

[0002] With the rapid development of modern technology, battery technology plays a crucial role in various industries, especially in electric vehicles, portable electronic devices and energy storage systems. The performance of the battery directly affects the endurance, charging speed and service life of the device, therefore, improving the performance of the battery has become one of the key research directions. The electrode coating, as a core component of the battery, its material selection and preparation process have a decisive influence on the overall performance of the battery. In order to meet the growing demand for high-performance batteries, researchers are constantly exploring and developing new electrode coating materials and their preparation processes.

[0003] In the prior art, the preparation of the electrode coating is usually established by repeated experiments to establish the relationship between the process parameters and the coating performance, these experiments usually involve a large number of variables and complex process flow, researchers need to draw the parameter-performance curve through a large number of experimental data, and intercept the specific point in the curve to obtain the coating material with the required performance. This way not only consumes time and effort, but also has high experimental cost, and it is difficult to achieve precise control. In addition, when optimizing the coating structure and performance, the traditional method often fails to fully consider the complex nonlinear relationship between multiple parameters, resulting in limited improvement of the coating performance, making it difficult to meet the customized needs of different customers for batteries, and the intelligence of the preparation process is insufficient.

[0004] In view of this, it is necessary to improve the preparation process of the electrode coating in the prior art to solve the technical problem of insufficient intelligence of the preparation process. SUMMARY

[0005] The purpose of the present application is to provide an AI-based coating preparation process regulation method and system to solve the above technical problems.

[0006] To achieve this purpose, the present application adopts the following technical solutions: An AI-based coating preparation process regulation method, comprising: Designing a multi-level nano-structured electrode coating, the electrode coating comprising a substrate layer and a functional layer, the substrate layer being a conductive material, the functional layer being a nano-material with electrocatalytic activity, the structural characteristic parameters of the functional layer showing gradient changes along the thickness direction of the coating; Obtaining the structural characteristic parameters of the substrate layer and the functional layer of the electrode coating and its electrochemical performance under different preparation process parameters through experiments, and establishing a nonlinear mapping relationship between the preparation process parameters of the electrode coating and its structural characteristic parameters and electrochemical performance through a machine learning model; According to the electrochemical performance requirements of the target electrode coating, the target electrode coating is divided into several sub-regions, the nonlinear mapping relationship obtained is combined, the preparation process parameters required for preparing the target electrode coating by spraying method in each sub-region are derived, and then the target gradient distribution of the internal structure characteristic parameters of the target electrode coating during preparation is obtained; Taking the preparation process parameters required for each sub-region and the characteristic parameters of the spraying mold as inputs, and taking the target gradient distribution of the corresponding structure characteristic parameters as outputs, numerical simulation is performed to determine the spraying mold required for preparing the target electrode coating; The conductive material and nanomaterial are placed in the spraying mold of the determined category, and spraying is performed according to the obtained required preparation process parameters, so that the target electrode coating is prepared.

[0007] Optionally, the nonlinear mapping relationship between the preparation process parameters of the electrode coating and the structure characteristic parameters and electrochemical performance thereof is established by a machine learning model, and specifically includes: The structure characteristic parameters of the matrix layer and the functional layer of the electrode coating under different preparation process parameters obtained by experiments and the electrochemical performance thereof are sorted to form an experimental data package, and the experimental data package is preprocessed by data cleaning, normalization and feature extraction; A gradient boosting decision tree model is selected, the preprocessed experimental data package is input into the gradient boosting decision tree model, and a preliminary nonlinear mapping relationship between the preparation process parameters and the structure characteristic parameters and electrochemical performance of the electrode coating is established; Optionally, the preliminary nonlinear mapping relationship between the preparation process parameters and the structure characteristic parameters and electrochemical performance of the electrode coating is established, and then further includes: The gradient boosting decision tree model is verified and adjusted by a cross-validation method; Based on the preliminary nonlinear mapping relationship, feature importance analysis is performed to identify the preparation process parameter category that has the greatest impact on the structure characteristic parameters and the electrochemical performance; Combined with the feature importance analysis result, the preparation process parameters are optimized, and an optimized nonlinear mapping relationship model is constructed, which is used to predict the influence of different process parameters on the structure characteristic parameters and the electrochemical performance of the electrode coating, so as to establish the nonlinear mapping relationship.

[0008] Optionally, according to the electrochemical performance requirements of the target electrode coating, the target electrode coating is divided into several sub-regions, the nonlinear mapping relationship obtained is combined, the preparation process parameters required for preparing the target electrode coating by spraying method in each sub-region are derived, and then the target gradient distribution of the internal structure characteristic parameters of the target electrode coating during preparation is obtained, specifically including: According to the electrochemical performance requirements of the target electrode coating, different functional regions of the electrode coating are determined as high conductivity regions, high catalytic activity regions and high stability regions; According to the determined different functional regions, the target electrode coating is divided into a plurality of sub-regions, so that each sub-region meets the preset electrochemical performance requirements of the corresponding functional region; In combination with the obtained nonlinear mapping relationship model, the preset electrochemical performance requirements of each sub-region are inputted, and the preparation process parameters required by each sub-region are deduced.

[0009] Optionally, the deducing of the preparation process parameters required by each sub-region further includes: Based on the deduced preparation process parameters, the structural characteristic parameters of each sub-region are predicted, so as to obtain the target gradient distribution of each sub-region; In combination with the target gradient distribution of each sub-region, a spraying preparation scheme of the overall target electrode coating is formulated, and the spraying preparation scheme includes a spraying path, a spraying sequence and a spraying condition.

[0010] Optionally, the numerical simulation is performed by taking the preparation process parameters required by each sub-region and the characteristic parameters of the spraying mold as inputs and taking the target gradient distribution of the corresponding structural characteristic parameters as outputs, so as to determine a spraying mold category required for preparing the target electrode coating, and the determining specifically includes: The preparation process parameters required by each sub-region and the characteristic parameters of the spraying mold are collected; A numerical simulation model is established, the preparation process parameters of each sub-region and the characteristic parameters of the spraying mold are inputted, and boundary conditions and initial conditions are set to simulate physical and chemical changes in the spraying process; The spraying process is numerically simulated by using computational fluid dynamics and finite element analysis methods, indexes of flow, deposition, cooling and solidification behaviors of coating materials in the spraying process are calculated, and numerical simulation results are obtained.

[0011] Optionally, the numerical simulation of the spraying process by using computational fluid dynamics and finite element analysis methods, the calculation of the indexes of flow, deposition, cooling and solidification behaviors of coating materials in the spraying process, and the obtaining of the numerical simulation results further include: The numerical simulation results are analyzed, whether the structural characteristic parameters of each sub-region meet the target gradient distribution is evaluated, and key factors affecting the spraying effect are identified; Based on the identified key factors, the characteristic parameters of the spraying mold are optimized, and the numerical simulation is performed again, the optimization process of the characteristic parameters is iterated until the structural characteristic parameters of each sub-region meet the target gradient distribution requirements; Based on the characteristic parameters of the spraying mold in the last iteration in the optimization process, a spraying mold category closest to the spraying mold is matched from a spraying mold library.

[0012] Optionally, the conductive material and nanomaterial are placed in a spray mold of a certain category, and sprayed according to the obtained required preparation process parameters to prepare the target electrode coating, specifically comprising: The conductive material and nanomaterial of a preset particle size are provided, and the conductive material and nanomaterial are mixed and uniformly mixed according to a predetermined ratio; A spray mold of a selected category is installed, the mixed conductive material and nanomaterial are placed in a storage tank of a spraying device, and parameters of the spraying device are set according to the obtained required preparation process parameters; wherein the parameters of the spraying device include nozzle size, spraying speed and spraying angle; The spraying process is started, and the mixed conductive material and nanomaterial are uniformly sprayed on the substrate according to the set spraying preparation scheme to build the target electrode coating layer by layer; Real-time monitoring of key parameters in the spraying process is performed, and after the spraying is completed, the coating is annealed and cooled for post-processing to prepare the target electrode coating; Optionally, the real-time monitoring of key parameters in the spraying process is performed, and after the spraying is completed, the coating is annealed and cooled for post-processing to prepare the target electrode coating, and then further comprising: The target electrode coating prepared is subjected to sampling quality detection and performance evaluation to ensure that its structural characteristic parameters and electrochemical performance meet the expected requirements.

[0013] The application also provides an AI-based coating preparation process regulation system for realizing the AI-based coating preparation process regulation method as described above, and the regulation system comprises: A data processing unit is configured to sort and form an experimental data package of structural characteristic parameters of the substrate layer and the functional layer of the electrode coating and its electrochemical performance under different preparation process parameter conditions obtained by experiments, and to perform preprocessing; A central control unit is configured to call a machine learning model to establish a nonlinear mapping relationship between the preparation process parameters of the electrode coating and its structural characteristic parameters and electrochemical performance; A region division unit is configured to divide the target electrode coating into a plurality of sub-regions according to the electrochemical performance requirements of the target electrode coating, and to deduce the required preparation process parameters and target gradient distribution of the target electrode coating; A numerical simulation unit is configured to take the required preparation process parameters of each sub-region and the characteristic parameters of the spray mold as input, and take the target gradient distribution of the corresponding structural characteristic parameters as output to perform numerical simulation; A spraying control unit is configured to control the operation of the spraying device according to the set spraying preparation scheme, and to real-time monitor key parameters in the spraying process; A data storage unit is configured to store the preparation process parameters, target gradient distribution, and spray die type for preparing the target electrode coating under different electrochemical performance requirements.

[0014] Compared with the prior art, the present application has the following beneficial effects: the present application can accurately predict the influence of different process parameters on the coating structure and performance by combining experimental data and machine learning models, thereby optimizing the preparation parameters, achieving the target of gradient distribution, and further enhancing the matching degree of process parameters and dies through numerical simulation, ensuring the controllability of the preparation process, not only improving the electrochemical performance of the electrode coating, but also greatly reducing the experimental cost and time, realizing the intelligent regulation and control of the electrode coating preparation process, and significantly improving the accuracy and efficiency of the preparation process. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0016] The structures, proportions, sizes, etc. shown in the drawings of the present specification are only used to cooperate with the content disclosed in the specification, to enable those skilled in the art to understand and read, and are not used to limit the limiting conditions under which the present application can be implemented, so they do not have technical significance. Any modification of structure, change of proportion relationship or adjustment of size, without affecting the effects and purposes that can be achieved by the present application, should still fall within the scope of the technical content disclosed by the present application.

[0017] Figure 1 Figure 1 is a flowchart of the coating preparation process regulation method of the present application; Figure 2 Figure 2 is another flowchart of the coating preparation process regulation method of the present application; Figure 3 Figure 3 is a third flowchart of the coating preparation process regulation method of the present application. DETAILED DESCRIPTION

[0018] In order to make the purposes, features, and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings of the embodiments of the present application. Obviously, the following described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0019] In the description of the present application, it should be understood that the terms "upper", "lower", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. It should be noted that when a component is considered to be "connected" to another component, it can be directly connected to the other component or there can be a component disposed therebetween.

[0020] The technical solutions of the present application will be further illustrated below in conjunction with the drawings and through specific embodiments.

[0021] The embodiment of the present application provides an AI-based coating preparation process regulation method, comprising: S1, designing a multi-level nano-structured electrode coating, the electrode coating comprising a base layer and a functional layer, the base layer being a conductive material, the functional layer being a nano-material with electrocatalytic activity, the structural characteristic parameters of the functional layer presenting gradient changes along the thickness direction of the coating; First, a multi-level nano-structured electrode coating is designed, which includes a base layer and a functional layer. The base layer is composed of conductive material, providing good electrical conductivity. The functional layer is composed of nano-material with electrocatalytic activity, improving the electrochemical performance of the electrode. In order to optimize the performance, the structural characteristic parameters (such as thickness, particle size, morphology) of the functional layer present gradient changes along the thickness direction of the coating. This design enables the coating to meet different electrochemical requirements in different thickness regions, thereby improving the overall performance.

[0022] S2, obtaining the structural characteristic parameters of the base layer and the functional layer of the electrode coating and its electrochemical performance under different preparation process parameters through experiments, and establishing a nonlinear mapping relationship between the preparation process parameters of the electrode coating and its structural characteristic parameters and electrochemical performance through a machine learning model; Through experiments, the structural characteristic parameters of the base layer and the functional layer of the electrode coating and its electrochemical performance (such as electrical conductivity, catalytic activity, cycle stability) under different preparation process parameters (such as temperature, pressure, time) are obtained. Then, a machine learning model (such as gradient boosting decision tree GBDT) is used to establish a nonlinear mapping relationship between the preparation process parameters and the structural characteristic parameters and electrochemical performance of the coating. The specific process includes data preprocessing, model selection, model training, model verification and model optimization. Through this method, the preparation process parameters can be effectively predicted and optimized, thereby obtaining the best coating performance.

[0023] S3, according to the electrochemical performance requirements of the target electrode coating, divide the target electrode coating into several sub-regions, combine the obtained nonlinear mapping relationship, deduce the preparation process parameters required for preparing the target electrode coating by spraying method in each sub-region, and then obtain the target gradient distribution of the internal structure characteristic parameters of the target electrode coating during preparation; According to the electrochemical performance requirements of the target electrode coating, the coating is divided into several sub-regions, such as high conductivity area, high catalytic activity area and high stability area. Using the established nonlinear mapping relationship model, the preparation process parameters required for each sub-region are deduced. By this method, each sub-region can meet the specific electrochemical performance requirements, and then the target gradient distribution of the internal structure characteristic parameters of the entire electrode coating is obtained.

[0024] S4, taking the preparation process parameters required for each sub-region and the characteristic parameters of the spraying mold as input, and taking the target gradient distribution of the corresponding structure characteristic parameters as output, numerical simulation is carried out to determine the type of spraying mold required for preparing the target electrode coating; Taking the preparation process parameters required for each sub-region and the characteristic parameters of the spraying mold (such as nozzle size, spraying speed, spraying angle) as input, and taking the target gradient distribution of the corresponding structure characteristic parameters as output, numerical simulation is carried out. Using computational fluid dynamics (CFD) and finite element analysis (FEA) methods, the physical and chemical changes during spraying process are simulated, and the spraying effect is evaluated. Through iterative optimization, the most suitable spraying mold type is finally determined to ensure that the expected structure characteristic parameters and electrochemical performance can be achieved in the actual spraying process.

[0025] S5, put the conductive material and nanomaterial into the determined type of spraying mold, and spray according to the obtained required preparation process parameters to prepare the target electrode coating.

[0026] After mixing the conductive material and nanomaterial in a predetermined ratio, put them into the determined spraying mold. Spray according to the preparation process parameters deduced in step S3 to build the target electrode coating layer by layer. Real-time monitor the key parameters during the spraying process to ensure the stability and consistency of the spraying process. After spraying, carry out necessary post-processing (such as annealing, cooling) on the coating, and carry out quality detection and performance evaluation to ensure that it meets the expected structure characteristic parameters and electrochemical performance.

[0027] The working principle of the present application is as follows: first, a multi-level nano-structured electrode coating is designed, including a base layer and a functional layer, wherein the structural characteristic parameters of the functional layer change in a gradient along the thickness direction of the coating, the structural characteristic parameters of the base layer and the functional layer and the electrochemical performance of the electrode coating under different preparation process parameters are obtained through experiments, and a nonlinear mapping relationship between the preparation process parameters and the structural characteristic parameters and the electrochemical performance is established by using a machine learning model, according to the electrochemical performance requirements of the target electrode coating, the target electrode coating is divided into several sub-regions, and the required preparation process parameters of each sub-region are deduced by combining the nonlinear mapping relationship, so as to realize the target gradient distribution, then numerical simulation is used, the required preparation process parameters of each sub-region and the mold characteristic parameters are used as input to determine the type of spraying mold required for preparing the electrode coating, the conductive material and the nano material are put into the determined spraying mold, and spraying is carried out according to the obtained spraying process parameters, so that the target electrode coating is prepared.

[0028] The present application can accurately predict the influence of different process parameters on the structure and performance of the coating by combining experimental data and a machine learning model, so as to optimize the preparation parameters and realize the target of gradient distribution. The numerical simulation further enhances the matching degree of the process parameters and the mold, ensures the controllability of the preparation process, improves the electrochemical performance of the electrode coating, greatly reduces the experimental cost and time, realizes the intelligent control of the electrode coating preparation process, and significantly improves the accuracy and efficiency of the preparation process.

[0029] In the present embodiment, it is specifically explained that step S2 specifically comprises: S21, obtaining the structural characteristic parameters of the base layer and the functional layer and the electrochemical performance of the electrode coating under different preparation process parameters through experiments.

[0030] S22, arranging the structural characteristic parameters of the base layer and the functional layer and the electrochemical performance of the electrode coating under different preparation process parameters obtained through experiments to form an experimental data package, and performing data cleaning, normalization and feature extraction preprocessing on the experimental data package; The electrode coating data obtained under different preparation process parameters are arranged to form an experimental data package, and then data cleaning, normalization and feature extraction preprocessing are performed on the experimental data package. Data cleaning includes removing outliers and missing values, normalization is to eliminate the influence between different dimensions, and feature extraction is to extract useful information for the model. The preprocessing step ensures data quality and consistency, which is a prerequisite for effective training of the machine learning model.

[0031] S23, selecting a gradient boosting decision tree model, inputting the preprocessed experimental data package into the gradient boosting decision tree model, and establishing a preliminary nonlinear mapping relationship between the preparation process parameters and the structural characteristic parameters and the electrochemical performance of the electrode coating.

[0032] Gradient Boosting Decision Tree (GBDT) model is selected, and the pre-processed experimental data package is input into the GBDT model to establish a preliminary nonlinear mapping relationship between the preparation process parameters and the structural characteristic parameters and electrochemical performance of the electrode coating. The GBDT model has the ability to process nonlinear relationships and high-dimensional data, and is suitable for modeling the relationship between complex process parameters and coating performance. The preliminary mapping relationship provides a basis for subsequent optimization and verification.

[0033] In this embodiment, it is further illustrated that after step S23, it further includes: S24, verifying and adjusting the gradient boosting decision tree model through a cross-validation method; ensuring that the model has good prediction performance. Regarding the specific method of cross-validation, such as the selection of K value of K-fold cross-validation, the selection and calculation method of verification indicators (such as mean square error, R^2 value, etc.).

[0034] The GBDT model is verified and adjusted through the cross-validation method. The cross-validation method divides the training set and the test set multiple times to evaluate the stability and generalization ability of the model. According to the verification result, the model parameters (such as the number of trees, depth, learning rate, etc.) are adjusted to improve the prediction accuracy of the model.

[0035] S25, based on the preliminary nonlinear mapping relationship, performing feature importance analysis to identify the preparation process parameter category that has the greatest impact on the structural characteristic parameters and the electrochemical performance; Based on the preliminary nonlinear mapping relationship, feature importance analysis is performed to identify the preparation process parameter category that has the greatest impact on the structural characteristic parameters and the electrochemical performance. Feature importance analysis can be realized through feature importance scores in the GBDT model. The purpose of this step is to find the most critical process parameters to provide a basis for subsequent parameter optimization.

[0036] S26, combining the feature importance analysis result, optimizing the preparation process parameters, constructing an optimized nonlinear mapping relationship model, and using the optimized nonlinear mapping relationship model to predict the influence of different process parameters on the structural characteristic parameters and the electrochemical performance of the electrode coating, so as to establish a nonlinear mapping relationship.

[0037] The optimized nonlinear mapping relationship model can accurately predict the influence of different process parameters on the structural characteristic parameters and the electrochemical performance of the electrode coating. The final optimized nonlinear mapping relationship is used to guide the selection and optimization of the preparation process parameters of the electrode coating to achieve the target electrochemical performance.

[0038] Based on the feature importance analysis results, the preparation process parameters are optimized, and an optimized nonlinear mapping relationship model is constructed. The optimized nonlinear mapping relationship model is used to predict the influence of different process parameters on the electrode coating structure feature parameters and electrochemical performance. Through multiple iterations and optimization, a nonlinear mapping relationship model that can accurately predict and optimize the preparation process parameters is finally established.

[0039] In this embodiment, it is specifically explained that step S3 specifically includes: S31, according to the electrochemical performance requirements of the target electrode coating, determining different functional regions of the electrode coating as high conductivity region, high catalytic activity region and high stability region; According to the electrochemical performance requirements of the target electrode coating, the different functional regions of the coating are determined. For example, the high conductivity region needs to have excellent conductivity, the high catalytic activity region needs to have high catalytic performance, and the high stability region needs to remain stable under long-term working conditions. The purpose of this step is to clarify the specific performance requirements of each region, so as to facilitate the subsequent sub-region division and process parameter optimization.

[0040] S32, according to the determined different functional regions, the target electrode coating is divided into several sub-regions, so that each sub-region meets the preset electrochemical performance requirements of the corresponding functional region.

[0041] According to the determined different functional regions, the target electrode coating is divided into several sub-regions, each sub-region corresponds to a functional region and needs to meet the preset electrochemical performance requirements. When dividing the sub-regions, the thickness direction and surface distribution of the coating need to be considered to ensure that each sub-region can play its specific function in actual application.

[0042] S33, combining the obtained nonlinear mapping relationship model, inputting the preset electrochemical performance requirements of each sub-region, deducing the required preparation process parameters of each sub-region.

[0043] Combining the nonlinear mapping relationship model obtained in step S2, inputting the preset electrochemical performance requirements of each sub-region, deducing the required preparation process parameters of each sub-region. Through the nonlinear mapping relationship model, the influence of different process parameters (such as temperature, pressure, time) on the coating structure feature parameters and electrochemical performance can be determined, so as to deduce the optimal preparation process parameters.

[0044] In this embodiment, it is further explained that step S33 further includes: S34, based on the derived preparation process parameters, predict the structural feature parameters of each sub-region, thereby obtaining the target gradient distribution of each sub-region; based on the derived preparation process parameters, predict the structural feature parameters of each sub-region, thereby obtaining the target gradient distribution of each sub-region. The purpose of this step is to ensure that the structural feature parameters of each sub-region meet the expectations through model prediction, so as to achieve the target electrochemical performance.

[0045] S35, combined with the target gradient distribution of each sub-region, formulate the spraying preparation scheme of the whole target electrode coating, which includes spraying path, spraying sequence and spraying condition. To ensure that each sub-region reaches the expected structural feature parameters and electrochemical performance in the actual preparation process.

[0046] Combined with the target gradient distribution of each sub-region, the spraying preparation scheme of the whole target electrode coating is formulated. The spraying preparation scheme includes spraying path, spraying sequence and spraying condition. The spraying path and sequence need to ensure the uniform distribution of different sub-region materials, while the spraying condition (such as spraying speed, nozzle size, spraying angle) needs to be set according to the derived process parameters to achieve the expected structural feature parameters and electrochemical performance.

[0047] In this embodiment, it is specified that step S4 specifically includes: S41, collect the preparation process parameters required by each sub-region and the feature parameters of the spraying mold (including nozzle size, spraying speed, spraying angle).

[0048] S42, establish a numerical simulation model, input the preparation process parameters of each sub-region and the feature parameters of the spraying mold, set boundary conditions and initial conditions to simulate the physical and chemical changes in the spraying process; Based on the collected preparation process parameters and the feature parameters of the spraying mold, a numerical simulation model is established. Input the preparation process parameters of each sub-region and the feature parameters of the spraying mold, set boundary conditions and initial conditions to simulate the physical and chemical changes in the spraying process. The setting of boundary conditions and initial conditions needs to be adjusted according to the actual spraying environment to ensure the reliability and accuracy of the simulation results.

[0049] S43, through computational fluid dynamics and finite element analysis method, numerical simulation is carried out on the spraying process, the index of the flow, deposition, cooling and solidification behavior of the coating material in the spraying process is calculated, and the numerical simulation result is obtained.

[0050] The numerical simulation results are obtained by simulating the flow, deposition, cooling and solidification behavior of the coating material during the spraying process using computational fluid dynamics (CFD) and finite element analysis (FEA) methods. The CFD method can simulate the flow and deposition process of the material, while the FEA method can simulate the cooling and solidification process of the material. By combining the two methods, a comprehensive understanding of the various behaviors during the spraying process can be achieved.

[0051] In this embodiment, it is further specified that after step S43, the following steps are further included: S44, analyze the numerical simulation results to evaluate whether the structural characteristic parameters (such as thickness, particle size, and morphology) of each sub-region meet the target gradient distribution, and identify the key factors affecting the spraying effect.

[0052] S45, based on the identified key factors, optimize the feature parameters of the spraying mold, and re-perform numerical simulation, iterate the optimization process of the feature parameters, until the structural characteristic parameters of each sub-region meet the target gradient distribution requirements; Based on the identified key factors, the feature parameters of the spraying mold are optimized, and numerical simulation is re-performed, and the optimization process of the feature parameters is iterated, until the structural characteristic parameters of each sub-region meet the target gradient distribution requirements. Through multiple simulation and optimization, the feature parameters of the spraying mold can be gradually adjusted to ensure that the spraying effect meets the expected requirements.

[0053] S46, based on the feature parameters of the spraying mold in the last iteration of the optimization process, the closest spraying mold category is matched from the spraying mold library.

[0054] Based on the feature parameters of the spraying mold in the last iteration of the optimization process, the closest spraying mold category is matched from the spraying mold library. The purpose of this step is to ensure that the selected spraying mold can meet the optimized feature parameter requirements in the actual spraying process, and to ensure that the final prepared electrode coating meets the expected structural characteristic parameters and electrochemical performance.

[0055] In this embodiment, it is specifically specified that step S5 specifically includes: S51, provide conductive material and nanomaterial of a predetermined particle size, and mix and uniformly mix the conductive material and nanomaterial according to a predetermined ratio; ensure that the purity and particle size meet the required electrode coating performance requirements; mix the conductive material and nanomaterial according to a predetermined ratio to ensure uniform mixing of the materials and avoid agglomeration.

[0056] S52, install the selected category of spraying mold, place the mixed conductive material and nanomaterial into the storage tank of the spraying equipment, and set the parameters of the spraying equipment according to the obtained required preparation process parameters; wherein the parameters of the spraying equipment include nozzle size, spraying speed and spraying angle; The mixed conductive material and nanomaterial are placed in the storage tank of the spraying equipment, and the parameters of the spraying equipment are set according to the preparation process parameters obtained in step S3. These parameters include nozzle size, spraying speed and spraying angle. Ensure that the equipment parameter settings are accurate to achieve the best spraying effect and coating performance.

[0057] S53, start the spraying process, and uniformly spray the mixed conductive material and nanomaterial on the substrate according to the set spraying preparation scheme to build the target electrode coating layer by layer; Start the spraying process, and uniformly spray the mixed conductive material and nanomaterial on the substrate according to the spraying preparation scheme (including spraying path, spraying sequence and spraying condition) formulated in step S3. Build the target electrode coating layer by layer to ensure uniform distribution and good adhesion of each layer of material. The purpose of this step is to build an electrode coating layer with expected structural characteristic parameters by precisely controlling the spraying process.

[0058] S54, real-time monitoring of key parameters during the spraying process, after the spraying is completed, the coating is annealed and cooled for post-processing to prepare the target electrode coating layer; (key parameters such as temperature, pressure, spraying speed) to ensure the stability and consistency of the spraying process; after the spraying is completed, the coating is post-processed, such as annealing, cooling or other necessary processing steps, to further optimize the structural characteristic parameters and electrochemical performance of the coating.

[0059] Annealing can eliminate stress in the coating, improve adhesion and stability of the coating; cooling helps to solidify and stabilize the performance of the coating. The purpose of this step is to optimize the structure and electrochemical performance of the coating through post-processing.

[0060] S55, sample quality detection and performance evaluation of the prepared target electrode coating layer to ensure that its structural characteristic parameters and electrochemical performance meet the expected requirements.

[0061] Sample quality detection and performance evaluation of the prepared target electrode coating layer. The detection content includes the thickness, particle size, morphology, electrical conductivity, catalytic activity and cycle stability of the coating. Through quality detection and performance evaluation, it is ensured that the structural characteristic parameters and electrochemical performance of the coating meet the expected requirements. If the detection result does not meet the requirements, the problem needs to be analyzed and corresponding adjustment and optimization is needed.

[0062] Example two: The application also provides an AI-based coating preparation process control system for realizing the AI-based coating preparation process control method of example one. The control system comprises: a data processing unit configured to sort and form an experimental data package of structural characteristic parameters of the base layer and the functional layer of the electrode coating obtained under different preparation process parameter conditions and electrochemical performance thereof, and to perform preprocessing; a central control unit configured to call a machine learning model to establish a nonlinear mapping relationship between preparation process parameters of the electrode coating and structural characteristic parameters and electrochemical performance thereof; a region division unit configured to divide the target electrode coating into a plurality of sub-regions according to the electrochemical performance requirement of the target electrode coating, and to derive the required preparation process parameters and target gradient distribution of the target electrode coating; a numerical simulation unit configured to take the required preparation process parameters of each sub-region and the characteristic parameters of the spraying mold as input, and take the target gradient distribution of the corresponding structural characteristic parameters as output, to perform numerical simulation; a spraying control unit configured to control the operation of the spraying equipment according to the set spraying preparation scheme, and to monitor the key parameters in the spraying process in real time; a data storage unit configured to store the preparation process parameters, target gradient distribution and spraying mold category of the target electrode coating prepared under different electrochemical performance requirements.

[0063] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An AI-based coating preparation process regulation method, characterized by, The application relates to a multi-level nano-structured electrode coating, and relates to a method for preparing the electrode coating. The electrode coating comprises a substrate layer and a functional layer, the substrate layer is made of conductive material, the functional layer is made of nano-material with electrocatalytic activity, and structural characteristic parameters of the functional layer change in a gradient manner along a thickness direction of the coating; Structural characteristic parameters and electrochemical performances of the substrate layer and the functional layer of the electrode coating under different preparation process parameters are obtained through experiments, and a nonlinear mapping relationship between the preparation process parameters of the electrode coating and the structural characteristic parameters and the electrochemical performances of the electrode coating is established through a machine learning model; According to an electrochemical performance requirement of a target electrode coating, the target electrode coating is divided into a plurality of sub-regions, the nonlinear mapping relationship is combined, preparation process parameters required for preparing the target electrode coating by using a spraying method in each sub-region are deduced, and a target gradient distribution of structural characteristic parameters in the target electrode coating is obtained when the target electrode coating is prepared; The preparation process parameters required in each sub-region and characteristic parameters of a spraying mold are taken as inputs, and the target gradient distribution of the corresponding structural characteristic parameters is taken as output, numerical simulation is carried out, and a spraying mold type required for preparing the target electrode coating is determined; The conductive material and the nano-material are placed in the spraying mold of the determined type, and spraying is carried out according to the obtained required preparation process parameters, so that the target electrode coating is prepared.

2. The AI-based coating preparation process regulation method of claim 1, wherein, The nonlinear mapping relationship between the preparation process parameters of the electrode coating and the structural characteristic parameters and the electrochemical performances of the electrode coating is established through a machine learning model, and specifically includes the following steps: Experimental data packets of structural characteristic parameters and electrochemical performances of the substrate layer and the functional layer of the electrode coating under different preparation process parameters are obtained through experiments, and the experimental data packets are preprocessed through data cleaning, normalization and feature extraction; A gradient boosting decision tree model is selected, the preprocessed experimental data packets are input into the gradient boosting decision tree model, and a preliminary nonlinear mapping relationship between the preparation process parameters and the structural characteristic parameters and the electrochemical performances of the electrode coating is established.

3. The AI-based coating preparation process regulation method of claim 2, wherein, The preliminary nonlinear mapping relationship between the preparation process parameters and the structural characteristic parameters and the electrochemical performances of the electrode coating is established, and then the following steps are further included: The gradient boosting decision tree model is verified and adjusted through a cross-validation method; Based on the preliminary nonlinear mapping relationship, feature importance analysis is carried out, and a preparation process parameter type with the greatest influence on the structural characteristic parameters and the electrochemical performances is identified; Based on the feature importance analysis result, the preparation process parameters are optimized, an optimized nonlinear mapping relationship model is constructed, and the optimized nonlinear mapping relationship model is used for predicting influences of different process parameters on the structural characteristic parameters and the electrochemical performances of the electrode coating, so as to establish the nonlinear mapping relationship.

4. The AI-based coating preparation process regulation method of claim 1, wherein, The target electrode coating is divided into a plurality of sub-regions according to an electrochemical performance requirement of the target electrode coating, the nonlinear mapping relationship is combined, preparation process parameters required for preparing the target electrode coating by using a spraying method in each sub-region are deduced, and a target gradient distribution of structural characteristic parameters in the target electrode coating is obtained when the target electrode coating is prepared, and specifically includes the following steps: According to the electrochemical performance requirements of the target electrode coating, different functional regions of the electrode coating are determined as high conductivity regions, high catalytic activity regions and high stability regions; According to the determined different functional regions, the target electrode coating is divided into a plurality of sub-regions, so that each sub-region meets the preset electrochemical performance requirements of the corresponding functional region; In combination with the obtained nonlinear mapping relationship model, the preset electrochemical performance requirements of each sub-region are inputted, and the required preparation process parameters of each sub-region are deduced.

5. The AI-based coating preparation process regulation method according to claim 4, characterized in that, After the required preparation process parameters of each sub-region are deduced, the following steps are further included: Based on the deduced preparation process parameters, the structural characteristic parameters of each sub-region are predicted, so as to obtain the target gradient distribution of each sub-region; In combination with the target gradient distribution of each sub-region, a spraying preparation scheme of the overall target electrode coating is formulated, and the spraying preparation scheme includes a spraying path, a spraying sequence and spraying conditions.

6. The AI-based coating preparation process regulation method of claim 1, wherein, In combination with the required preparation process parameters of each sub-region and the characteristic parameters of the spraying die, numerical simulation is performed with the target gradient distribution of the corresponding structural characteristic parameters as the output, so as to determine the spraying die category required for preparing the target electrode coating, and the specific steps include: The required preparation process parameters of each sub-region and the characteristic parameters of the spraying die are collected; A numerical simulation model is established, the preparation process parameters of each sub-region and the characteristic parameters of the spraying die are inputted, and boundary conditions and initial conditions are set to simulate the physical and chemical changes in the spraying process; By means of computational fluid dynamics and finite element analysis method, the spraying process is numerically simulated, the indices of the flow, deposition, cooling and solidification behaviors of the coating material in the spraying process are calculated, and numerical simulation results are obtained.

7. The AI-based coating preparation process regulation method of claim 6, wherein, After the spraying process is numerically simulated by means of computational fluid dynamics and finite element analysis method, the indices of the flow, deposition, cooling and solidification behaviors of the coating material in the spraying process are calculated, and numerical simulation results are obtained, the following steps are further included: The numerical simulation results are analyzed, whether the structural characteristic parameters of each sub-region meet the target gradient distribution is evaluated, and key factors affecting the spraying effect are identified; Based on the identified key factors, the characteristic parameters of the spraying die are optimized, and numerical simulation is performed again, the optimization process of the characteristic parameters is iterated until the structural characteristic parameters of each sub-region meet the target gradient distribution requirements; Based on the characteristic parameters of the spraying die in the last iteration in the optimization process, the closest spraying die category is matched from the spraying die library.

8. The AI-based coating preparation process regulation method of claim 5, wherein, The conductive material and the nanomaterial are put into the spraying die of the determined category, and are sprayed according to the obtained required preparation process parameters, so as to prepare the target electrode coating, and the specific steps include: The conductive material and the nanomaterial with a preset particle size are provided, and the conductive material and the nanomaterial are mixed and uniformly mixed according to a predetermined ratio; The selected category of the spraying die is installed, the mixed conductive material and nanomaterial are put into a storage tank of a spraying device, and parameters of the spraying device are set according to the obtained required preparation process parameters; wherein, the parameters of the spraying device include nozzle size, spraying speed and spraying angle; Starting the spraying process, spraying the mixed conductive material and nanomaterial on the substrate according to the set spraying preparation scheme, and building the target electrode coating layer by layer; Real-time monitoring of key parameters during the spraying process, annealing and cooling of the coating after spraying, and preparation of the target electrode coating.

9. The AI-based coating preparation process regulation method of claim 8, wherein, The real-time monitoring of key parameters during the spraying process, annealing and cooling of the coating after spraying, and preparation of the target electrode coating, and then further comprising: Sampling quality detection and performance evaluation of the prepared target electrode coating to ensure that its structural characteristic parameters and electrochemical performance meet the expected requirements.

10. An AI-based coating preparation process regulation system, characterized by, The AI-based coating preparation process regulation method according to any one of claims 1-9, wherein the regulation system comprises: A data processing unit for arranging and preprocessing experimental data packets of the structural characteristic parameters of the substrate layer and the functional layer of the electrode coating and its electrochemical performance under different preparation process parameters obtained by experiments; A central control unit for calling a machine learning model to establish a nonlinear mapping relationship between the preparation process parameters of the electrode coating and its structural characteristic parameters and electrochemical performance; A region division unit for dividing the target electrode coating into several sub-regions according to the electrochemical performance requirements of the target electrode coating, and deriving the required preparation process parameters and target gradient distribution of the target electrode coating; A numerical simulation unit for taking the required preparation process parameters of each sub-region and the characteristic parameters of the spraying mold as input, and taking the target gradient distribution of the corresponding structural characteristic parameters as output to perform numerical simulation; A spraying control unit for controlling the operation of the spraying equipment according to the set spraying preparation scheme, and real-time monitoring of key parameters during the spraying process; A data storage unit for storing the preparation process parameters, target gradient distribution and spraying mold category of the target electrode coating prepared under different electrochemical performance requirements.

Images