A method for automatically coating titanium anode and related equipment

Abstract

The present invention relates to the technical field of titanium anodes, and provides an automatic coating method and related equipment for titanium anodes, including obtaining a target coating area of ​​the titanium anode and coating it, collecting data on the target coating area during the coating process, obtaining coating real-time data, and calculating coating uniformity and thickness variation; evaluating coating uniformity, generating coating quality evaluation results and coating defect distribution; analyzing thickness variation based on the coating quality evaluation results and coating defect distribution, and obtaining thickness optimization parameters; generating a feedback spectrum according to the thickness optimization parameters, and adjusting the coating parameters of the automatic coating equipment based on the feedback spectrum. When improving and controlling the uniformity and thickness in the coating process through the application of automatic coating equipment, sensor arrays, real-time data collection, and coating analysis models, there are problems such as unstable coating quality, uneven coating thickness, and difficulty in real-time monitoring and adjusting coating parameters.

Description

Technical Field

[0001] The present application relates to the technical field of titanium anodes, and in particular to an automatic coating method for titanium anodes and related equipment. Background Art

[0002] With the rapid development of modern industry, titanium anodes are widely used in electrochemistry, electroplating, water treatment and other fields due to their excellent corrosion resistance, conductivity and long life. In order to improve the performance of titanium anodes, it is usually necessary to coat their surfaces. Efficient and uniform coating can not only extend the service life of titanium anodes, but also improve their working efficiency and effectiveness.

[0003] Among the related technical means, the titanium anode coating method mainly relies on manual or semi-automatic equipment. In the prior art, titanium anodes are usually coated by spraying, brushing or dipping. These methods can achieve basic coating effects, but there are certain limitations in coating uniformity and thickness control. For example, manual operation often relies on the experience and skills of workers, resulting in difficulty in controlling the uniformity and thickness of the coating; and although semi-automatic equipment can improve production efficiency, it is still difficult to cover areas with complex shapes or requiring fine coating.

[0004] Regarding the above technical solution, although the titanium anode can be basically coated by manual or semi-automatic equipment, there are problems such as unstable coating quality, uneven coating thickness, and difficulty in real-time monitoring and adjustment of coating parameters when controlling the uniformity and thickness during the coating process. Summary of the invention

[0005] In order to improve the control of uniformity and thickness during the coating process, there are problems such as unstable coating quality, uneven coating thickness, and difficulty in real-time monitoring and adjustment of coating parameters. The present application provides an automatic coating method and related equipment for titanium anodes.

[0006] The present invention provides an automatic coating method for titanium anodes, which is applied to automatic coating equipment, and comprises: obtaining a target coating area of ​​the titanium anode, and coating the target coating area by using the automatic coating equipment; collecting data of the target coating area during the coating process according to a sensor array preset on the automatic coating equipment to obtain real-time coating data; inputting the real-time coating data into a preset coating analysis model, and analyzing the coating uniformity and thickness variation during the coating process of the target coating area by the automatic coating equipment according to the real-time coating data through the coating analysis model; evaluating the coating uniformity by using a preset neural network algorithm to generate a coating quality evaluation result and a coating defect distribution; analyzing the thickness variation based on the coating quality evaluation result and the coating defect distribution to obtain a thickness optimization parameter; generating a feedback map according to the thickness optimization parameter, and adjusting the coating parameters of the automatic coating equipment based on the feedback map, and re-coating the target coating area by the automatic coating equipment after adjusting the coating parameters.

[0007] As a preferred embodiment, the step of obtaining the target coating area of ​​the titanium anode and coating the target coating area using the automatic coating equipment includes: scanning the surface of the titanium anode using laser scanning and computer vision algorithms to identify and mark the target area to be coated to obtain the target coating area; performing a first coating simulation on the target coating area using finite element analysis technology to obtain a first coating path and a first coating strategy; adjusting the first coating path using an optimization algorithm to obtain an adjusted coating path, optimizing the first coating strategy according to the adjusted coating path to obtain an optimized first coating strategy; and optimizing the coating strategy based on the optimized first coating strategy using the The finite element analysis technology is used to perform a second coating simulation on the target coating area to obtain a second coating path and a second coating strategy, and the first coating path is compared with the second coating path to obtain a path difference, and the first coating strategy is compared with the second coating strategy to obtain a strategy difference; the path difference is used to optimize the adjusted coating path to obtain a final coating path; the strategy difference is used to optimize the optimized first coating strategy to obtain a final coating strategy; the final coating path and the final coating strategy are input into the control system of the automatic coating equipment, and the automatic coating equipment is controlled by the control system to coat the target coating area.

[0008] As a preferred embodiment, the step of collecting data from the target coating area during the coating process according to the sensor array preset on the automatic coating equipment to obtain real-time coating data includes: using the laser thickness gauge, the infrared temperature sensor and the coating speed sensor preset on the automatic coating equipment as the sensor array; using the laser thickness gauge to collect data from the target coating area during the coating process to obtain the coating layer thickness; using the infrared temperature sensor to collect data from the target coating area during the coating process to obtain the coating temperature; using the coating speed sensor to collect data from the target coating area during the coating process to obtain the coating speed; using the coating layer thickness, the coating temperature and the coating speed as the real-time coating data.

[0009] As a preferred solution, the step of inputting the real-time coating data into a preset coating analysis model, and analyzing the coating uniformity and thickness change of the target coating area during the coating process of the automatic coating equipment according to the real-time coating data through the coating analysis model, includes: preprocessing the real-time coating data, inputting the preprocessed real-time coating data into the analysis model, extracting features of the real-time coating data using a convolutional neural network algorithm in the analysis model to obtain feature data, and generating a feature map based on the feature data; performing cluster analysis on the feature data according to a statistical analysis method to obtain feature clustering results and a number of feature center points; performing multidimensional scaling analysis on all the feature center points to obtain Feature space coordinates, using the feature space coordinates to segment the feature map, taking all the feature center points as initial segmentation points, marking them on the feature map, calculating the distance between each feature center point, and establishing a neighboring relationship in the feature space; based on the neighboring relationship and a preset distance threshold, dividing the feature map into several regions, each region including feature data; performing statistical analysis on the feature data in each region, calculating the standard deviation and mean of the feature values ​​in the region, and evaluating the coating uniformity in the region based on the standard deviation and mean, and obtaining the overall coating uniformity of the target coating region; modeling the feature clustering results and the coating uniformity according to the multivariate regression analysis method to obtain the thickness change.

[0010] As a preferred embodiment, the step of evaluating the coating uniformity using a preset neural network algorithm to generate a coating quality evaluation result and a coating defect distribution comprises: inputting the coating uniformity data into a neural network algorithm, evaluating the coating uniformity using a local sensitivity analysis method in the neural network algorithm to generate an evaluation score and defect characteristic distribution data; classifying the evaluation score into a coating quality grade to obtain a coating quality grade; comparing the coating quality grade with a preset quality standard to obtain a coating quality evaluation result; performing a trend analysis on the coating quality evaluation result to obtain a trend analysis result, and using the trend analysis result to locate defects in the defect characteristic distribution data to obtain a coating defect distribution.

[0011] As a preferred scheme, the step of analyzing the thickness variation based on the coating quality assessment result and the coating defect distribution to obtain thickness optimization parameters includes: using data analysis technology to comprehensively analyze the coating quality assessment result to obtain a comprehensive coating quality analysis result; using data mining technology to extract features of the coating defect distribution to obtain defect feature extraction results; fusing the coating quality comprehensive analysis result and the defect feature extraction result to obtain a fusion analysis result; optimizing the thickness variation based on the fusion analysis result to obtain thickness optimization parameters.

[0012] As a preferred embodiment, the step of generating a feedback map according to the thickness optimization parameters, adjusting the coating parameters of the automatic coating equipment based on the feedback map, and re-coating the target coating area by the automatic coating equipment after adjusting the coating parameters includes: constructing a feedback map according to the thickness optimization parameters and preset map generation rules; wherein the map generation rules include comprehensive evaluation criteria for coating uniformity, thickness consistency and coating efficiency; inputting the feedback map into the control system of the automatic coating equipment, parsing and processing the feedback map by using a control algorithm and model predictive control in the control system to obtain coating parameter adjustment instructions, adjusting the coating parameters of the automatic coating equipment based on the coating parameter adjustment instructions, and re-coating the target coating area by the automatic coating equipment after adjusting the coating parameters; wherein the coating parameters include coating speed, coating pressure, coating temperature, spraying angle, spraying distance and flow control of coating material.

[0013] The present application also provides an automatic coating device for titanium anodes, comprising: an acquisition module, used to acquire a target coating area of ​​the titanium anode, and use the automatic coating equipment to coat the target coating area; an acquisition module, used to collect data on the target coating area during the coating process according to a preset sensor array on the automatic coating equipment, and obtain real-time coating data; a first analysis module, used to input the real-time coating data into a preset coating analysis model, and analyze the coating uniformity and thickness change during the coating process of the target coating area by the automatic coating equipment according to the real-time coating data through the coating analysis model; an evaluation module, used to evaluate the coating uniformity using a preset neural network algorithm, and generate a coating quality evaluation result and a coating defect distribution; a second analysis module, used to analyze the thickness change based on the coating quality evaluation result and the coating defect distribution, and obtain thickness optimization parameters; an adjustment module, used to generate a feedback map according to the thickness optimization parameters, and adjust the coating parameters of the automatic coating equipment based on the feedback map, and re-coat the target coating area by the automatic coating equipment after adjusting the coating parameters.

[0014] The present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the automatic coating method of the titanium anode described in any one of the above is implemented.

[0015] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the automatic coating method for a titanium anode as described in any one of the above.

[0016] Compared with the prior art, the present application has the following beneficial effects: stable quality and uniform thickness. Through precision measurement and image recognition technology, the automatic coating equipment can accurately obtain the target coating area of ​​the titanium anode, and use the sensor array to collect real-time data during the coating process to ensure the controllability of the coating process. After the real-time coating data is input into the coating analysis model, the coating uniformity and thickness changes are analyzed through big data and machine learning algorithms, and the coating quality assessment results and coating defect distribution are generated using a neural network algorithm to optimize the coating parameters. After the thickness optimization parameters generate a feedback map, the control system adjusts the parameters of the automatic coating equipment and re-coats the target coating area to ensure the uniformity and thickness consistency of the final coating, which greatly improves the coating efficiency and quality of the titanium anode. When improving the uniformity and thickness of the coating process, there are problems such as unstable coating quality, uneven coating thickness, and difficulty in real-time monitoring and adjustment of coating parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0019] Figure 1 It is a schematic flow chart of the automatic coating method of titanium anode provided by an embodiment of the present invention;

[0020] Figure 2 is a schematic block diagram of the structure of an automatic coating device for titanium anodes provided in an embodiment of the present invention;

[0021] Figure 3 It is a schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0022] Description of reference numerals:

[0023] 10. Automatic coating device for titanium anode; 11. Acquisition module; 12. Collection module; 13. First analysis module; 14. Evaluation module; 15. Second analysis module; 16. Adjustment module; 20. Electronic device; 21. Memory; 22. Processor. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0026] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0027] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0028] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0029] Embodiment 1:

[0030] like Figure 1 As shown, the automatic coating method of titanium anode provided in the embodiment of the present application is applied to automatic coating equipment, and the automatic coating method of titanium anode includes steps S100 to S600, which are as follows:

[0031] Step S100: acquiring a target coating area of ​​a titanium anode, and coating the target coating area using an automatic coating device.

[0032] In this step, the target coating area of ​​the titanium anode is first determined by precision measurement and image recognition technology. Specifically, a camera or laser rangefinder is used to scan the surface of the titanium anode to generate a detailed three-dimensional model, and the area to be coated is identified through a software algorithm. These data are input into the control system of the automatic coating equipment.

[0033] For example, a laser rangefinder is used to scan the surface of a titanium anode to generate a three-dimensional surface model. The software algorithm analyzes the model data to determine the specific areas on the titanium anode that need to be coated, and transmits the data of these areas to the control system of the automatic coating equipment for coating operations.

[0034] Step S200: collecting data on the target coating area during the coating process according to the sensor array preset on the automatic coating equipment to obtain real-time coating data.

[0035] In this step, multiple sensor arrays on the automatic coating equipment monitor the coating process in real time. Specifically, these sensors include temperature sensors, humidity sensors, pressure sensors and optical sensors, which are used to monitor the coating environment and coating status respectively. The sensor array transmits the collected data to the central processing unit in real time for summary and analysis.

[0036] For example, during the coating process, temperature sensors monitor the temperature of the coating environment, humidity sensors record changes in ambient humidity, and optical sensors measure the thickness and uniformity of the coating through light reflectivity. These data are uploaded to the central processing unit in real time to ensure coating quality.

[0037] Step S300: input the real-time coating data into a preset coating analysis model, and analyze the coating uniformity and thickness variation of the target coating area during the coating process of the automatic coating equipment according to the real-time coating data through the coating analysis model.

[0038] In this step, the real-time coating data is input into a preset coating analysis model, which is built based on big data and machine learning algorithms. Specifically, the analysis model processes and compares the real-time data, evaluates the coating uniformity and thickness variation, and generates a detailed analysis report.

[0039] For example, the coating analysis model uses the input real-time data to evaluate the uniformity and thickness of the current coating by comparing historical coating data with the standard model, and generates a real-time report on the coating quality, including uniformity index and thickness distribution map.

[0040] Step S400: Use a preset neural network algorithm to evaluate coating uniformity and generate coating quality evaluation results and coating defect distribution.

[0041] In this step, a preset neural network algorithm is used to conduct a detailed evaluation of coating uniformity. Specifically, the neural network algorithm generates coating quality evaluation results and coating defect distribution maps by learning and identifying various data patterns that appear during the coating process.

[0042] For example, the neural network algorithm analyzes the input real-time coating data, identifies the tiny unevenness and defects that occur during the coating process, and generates a coating quality assessment report and defect distribution map, detailing the location and type of poor coating.

[0043] Step S500: Analyze the thickness variation based on the coating quality evaluation result and the coating defect distribution to obtain thickness optimization parameters.

[0044] In this step, the coating thickness is optimized and analyzed in combination with the coating quality assessment results and the coating defect distribution. Specifically, by analyzing the coating defect location and coating thickness changes, the optimized thickness parameters are calculated to ensure coating uniformity and thickness consistency.

[0045] For example, if the analysis report shows that the coating thickness in some areas is too thin, the coating parameters in these areas can be adjusted through the optimization algorithm, and new thickness optimization parameters can be calculated to ensure the overall uniformity and quality of the coating.

[0046] Step S600, generating a feedback map according to the thickness optimization parameters, and adjusting the coating parameters of the automatic coating equipment based on the feedback map, and re-coating the target coating area by the automatic coating equipment after adjusting the coating parameters.

[0047] In this step, a feedback map is generated based on the thickness optimization parameters, which shows in detail the coating parameters that need to be adjusted and the corresponding target coating area. Specifically, the control system adjusts the coating speed, coating spray volume, and movement trajectory of the automatic coating equipment based on the feedback map.

[0048] For example, the feedback map shows that certain areas need to increase the amount of paint sprayed and adjust the spray speed. The automatic coating equipment re-coats the target coating area of ​​the titanium anode accurately according to these adjusted parameters to ensure that the coating uniformity and thickness meet the expected standards.

[0049] In the present embodiment, the target coating area of ​​the titanium anode is obtained, and the target coating area is coated by an automatic coating device. During the coating process, a preset sensor array collects data on the target coating area to obtain real-time coating data. The real-time coating data is then input into a preset coating analysis model, and the coating uniformity and thickness variation of the automatic coating device during the coating process are analyzed by the coating analysis model. Next, the coating uniformity is evaluated using a preset neural network algorithm to generate a coating quality evaluation result and a coating defect distribution. Based on the coating quality evaluation result and the coating defect distribution, the thickness variation is analyzed to obtain thickness optimization parameters. Finally, a feedback spectrum is generated according to the thickness optimization parameters, and the coating parameters of the automatic coating device are adjusted based on the feedback spectrum, and the target coating area is re-coated by the automatic coating device after adjusting the coating parameters.

[0050] By utilizing automatic coating equipment and sensor arrays, precise coating of the target coating area of ​​the titanium anode is achieved, and real-time data acquisition and coating analysis models are used to ensure uniformity and thickness consistency during the coating process. The preset neural network algorithm further optimizes the coating quality and generates detailed coating defect distribution and thickness optimization parameters, thereby guiding subsequent coating parameter adjustments, improving coating efficiency and quality, and improving the control of uniformity and thickness during the coating process. However, there are problems such as unstable coating quality, uneven coating thickness, and difficulty in real-time monitoring and adjustment of coating parameters.

[0051] Embodiment 2:

[0052] In step S100, the surface of the titanium anode is scanned using laser scanning and computer vision algorithms to identify and mark the target area to be coated, thereby obtaining a target coating area.

[0053] By using laser scanning technology and computer vision algorithms, it is possible to accurately capture the tiny details of the titanium anode surface and generate a high-definition surface image. Specifically, the laser scanning system emits a laser beam, calculates the three-dimensional data of the titanium anode surface by the time and angle of the reflected light, and the computer vision algorithm processes the scanned data to identify and mark the target area to be coated. The data of these marked areas are stored in the control system for reference in the subsequent coating process.

[0054] For example, a laser scanning device is used to perform a full coverage scan of the titanium anode surface and generate a three-dimensional model. The model is analyzed through an image processing algorithm to determine the area that needs to be coated and mark it on the three-dimensional model to ensure that the coating equipment can accurately identify the target area.

[0055] The finite element analysis technology is used to perform a first coating simulation on the target coating area to obtain a first coating path and a first coating strategy.

[0056] By using finite element analysis technology to accurately simulate the coating process, it is possible to predict the behavior and effect of the coating under different conditions. Specifically, by establishing a finite element model of the target coating area and simulating the process of coating flow and curing on the surface, the optimal coating path and coating strategy can be obtained to ensure the uniformity and adhesion of the coating.

[0057] For example, finite element analysis software is used to simulate the coating of the target area, simulating the distribution of the coating under different temperature, pressure and speed conditions, and obtaining the first coating path and strategy, including parameters such as spraying angle, spraying speed and coating amount.

[0058] The first coating path is adjusted by using an optimization algorithm to obtain an adjusted coating path, and the first coating strategy is optimized according to the adjusted coating path to obtain an optimized first coating strategy.

[0059] By applying optimization algorithms (such as genetic algorithms or particle swarm optimization algorithms) to adjust the initial coating path and strategy, the coating efficiency and quality can be further improved; specifically, the optimization algorithm iteratively optimizes the first simulation results and adjusts the nodes and strategy parameters of the coating path to minimize coating defects and improve coating uniformity.

[0060] For example, a genetic algorithm is used to optimize the first coating path, and through continuous iteration and selection of the best path, an adjusted optimal coating path and an optimized coating strategy are finally obtained. These strategies include an adjusted spray angle and paint flow rate.

[0061] Based on the optimized first coating strategy, a second coating simulation is performed on the target coating area using finite element analysis technology to obtain a second coating path and a second coating strategy. The first coating path is compared with the second coating path to obtain a path difference, and the first coating strategy is compared with the second coating strategy to obtain a strategy difference.

[0062] By conducting a second finite element analysis simulation based on the optimized strategy, the coating path and strategy are verified and further improved; specifically, by comparing the paths and strategies of the two simulations, calculating their differences, analyzing the optimization effects, and ensuring the reliability and effectiveness of the coating path and strategy.

[0063] For example, in the second simulation, it was found that some areas were unevenly coated. By comparing the coating paths of the first and second times and calculating the path difference, the spraying angle and paint amount were further optimized to ensure the uniformity and consistency of the final coating effect.

[0064] The adjusted coating path is optimized using the path difference and the strategy difference to obtain the final coating path; the optimized first coating strategy is optimized using the strategy difference to obtain the final coating strategy.

[0065] By combining the path difference and the strategy difference, the coating path and strategy are further optimized to ensure the best final coating effect; specifically, the spraying parameters and path nodes are adjusted according to the difference to eliminate the unevenness and defects in the coating process, and finally the optimal coating path and strategy are determined.

[0066] For example, the path difference is used to adjust the spraying speed and spraying trajectory, and the strategy difference is used to adjust the paint flow and spraying angle, and finally the optimal coating path and strategy are determined to ensure coating uniformity and quality.

[0067] The final coating path and the final coating strategy are input into the control system of the automatic coating equipment, and the automatic coating equipment is controlled by the control system to coat the target coating area.

[0068] By inputting the optimized coating path and strategy into the control system of the automatic coating equipment, the automatic coating equipment can accurately coat the target area according to the predetermined path and strategy; specifically, the control system adjusts the spraying parameters such as coating speed, coating pressure and spraying angle according to the input path and strategy to ensure the uniformity and adhesion of the coating.

[0069] For example, after receiving the final coating path and strategy, the control system automatically adjusts the nozzle position and spraying speed of the spraying equipment, and starts precise coating of the target coating area to ensure that the coating thickness and uniformity meet the preset requirements.

[0070] In step S200, a laser thickness gauge, a preset infrared temperature sensor and a preset coating speed sensor on the automatic coating equipment are used as a sensor array.

[0071] By installing a variety of sensors on the automatic coating equipment, key parameters of the coating process can be monitored in real time; specifically, the laser thickness gauge is used to measure the coating thickness, the infrared temperature sensor monitors the temperature changes in the coating area, and the coating speed sensor records the spraying speed. The data of all sensors are synchronously transmitted to the control system.

[0072] For example, a laser thickness gauge is installed next to the spray head to measure the coating thickness in real time, an infrared temperature sensor is installed above the spraying area to monitor temperature changes during the coating process, and a coating speed sensor is installed on the moving parts of the coating equipment to record the spraying speed.

[0073] The laser thickness gauge is used to collect data on the target coating area during the coating process to obtain the coating layer thickness.

[0074] Non-contact measurement is performed using a laser thickness gauge to ensure real-time acquisition of coating thickness data; specifically, the laser thickness gauge emits a laser beam to the coating surface, calculates the coating thickness by the time and intensity changes of the reflected light, and transmits the data to the control system in real time for analysis and adjustment.

[0075] For example, a laser thickness gauge collects thousands of thickness data points per second, generating a real-time map of coating thickness, ensuring that spraying parameters are adjusted at any time during the coating process to achieve the desired thickness.

[0076] The infrared temperature sensor is used to collect data of the target coating area during the coating process to obtain the coating temperature.

[0077] The temperature change of the coating area is measured by an infrared temperature sensor to ensure that the coating process is carried out within the appropriate temperature range; specifically, the infrared temperature sensor performs non-contact temperature measurement of the coating area, and the data is transmitted to the control system in real time to adjust the coating parameters and prevent uneven curing of the coating.

[0078] For example, the infrared temperature sensor collects temperature data every second and compares it with the preset temperature range. If the temperature is out of range, the control system will automatically adjust the spraying speed or spraying angle to ensure that the coating process is carried out within the optimal temperature range.

[0079] The coating speed sensor is used to collect data of the target coating area during the coating process to obtain the coating speed.

[0080] The coating speed sensor monitors the spraying speed to ensure the stability and uniformity of the coating process; specifically, the coating speed sensor records the movement speed of the spray head and the spraying speed of the paint, and the data is transmitted to the control system in real time for dynamic adjustment of the spraying parameters to ensure the coating quality.

[0081] For example, the coating speed sensor monitors the spraying speed in real time. If the speed fluctuation exceeds the set range, the control system will immediately adjust the motion parameters of the spraying equipment to ensure a stable and uniform coating process.

[0082] The coating thickness, coating temperature and coating speed are used as real-time coating data.

[0083] The above three key parameters are used as real-time coating data to comprehensively evaluate the quality of the coating process. Specifically, the control system summarizes and analyzes the real-time data to ensure that each stage of the coating process is within the optimal parameter range and adjusts the coating strategy in real time.

[0084] For example, the control system receives thousands of data points per second, comprehensively analyzes the coating thickness, temperature and speed data, and generates real-time coating quality reports to ensure the continuous stability of the coating effect.

[0085] In step S300, the real-time coating data is preprocessed, and the preprocessed real-time coating data is input into the analysis model. In the analysis model, a convolutional neural network algorithm is used to extract features of the real-time coating data to obtain feature data, and a feature map is generated based on the feature data.

[0086] By preprocessing the real-time coating data, removing noise and outliers, the accuracy and consistency of the data are ensured; specifically, the original data is processed using filtering algorithms and data cleaning techniques to obtain clean real-time coating data, which is then input into a convolutional neural network for feature extraction to generate a feature map for analysis.

[0087] For example, during the preprocessing process, the filtering algorithm removes high-frequency noise in the sensor data, the data cleaning technology eliminates outliers, and the convolutional neural network performs multi-level feature extraction on the processed data to generate a feature map that reflects the quality of the coating.

[0088] The characteristic data is clustered according to the statistical analysis method to obtain the characteristic clustering results and several characteristic center points.

[0089] By using statistical analysis methods to cluster the feature data, patterns and trends in the data are identified; specifically, the K-means clustering algorithm or the DBSCAN algorithm is used to group the feature data to obtain feature clustering results, and the feature center points are determined based on the feature clustering results to reflect the changes in key parameters in the coating process.

[0090] For example, the K-means clustering algorithm is used to divide the feature data into several groups, each group represents a specific coating condition, and the feature center point identifies the center position of each group of data, reflecting the average coating state of the group.

[0091] Perform multidimensional scaling analysis on all feature center points to obtain feature space coordinates, use the feature space coordinates to segment the feature map, use all feature center points as initial segmentation points, mark them on the feature map, calculate the distance between each feature center point, and establish the proximity relationship in the feature space.

[0092] High-dimensional data is mapped to low-dimensional space through multidimensional scaling analysis, which facilitates the segmentation and analysis of feature maps. Specifically, the MDS algorithm is used to convert the high-dimensional data of the feature center points into low-dimensional coordinates, which are used as feature space coordinates and marked on the feature map to segment the feature map. Finally, the distance between each center point is calculated to determine the proximity relationship between data points.

[0093] For example, the MDS algorithm is used to reduce the high-dimensional data of feature center points to a two-dimensional space to form a two-dimensional representation of the feature map. Each center point is marked and the distance between adjacent center points is calculated to establish a proximity relationship matrix.

[0094] Based on the proximity relationship and the preset distance threshold, the feature map is divided into several regions, each of which includes feature data.

[0095] By utilizing the proximity relationship and the distance threshold, the feature map is divided into several regions, each region representing a coating state; specifically, the feature map is divided according to the proximity relationship matrix and the preset distance threshold to ensure that the data in each region has similar characteristics.

[0096] For example, a distance threshold is set, and points whose distances between feature center points are less than the threshold are divided into a region, and finally a plurality of regions representing different coating states are formed.

[0097] The characteristic data in each area are statistically analyzed, the standard deviation and mean of the characteristic values ​​in the area are calculated, and the coating uniformity in the area is evaluated based on the standard deviation and mean to obtain the overall coating uniformity of the target coating area.

[0098] The coating uniformity is evaluated by performing a detailed statistical analysis on the characteristic data in each area; specifically, the standard deviation and mean of the characteristic data in each area are calculated to evaluate the coating uniformity in the area, determine the overall coating quality, and obtain the overall coating uniformity of the target coating area.

[0099] For example, the standard deviation and mean of each area are calculated. The smaller the standard deviation, the more uniform the coating. The mean reflects the average thickness of the coating layer. The overall coating uniformity can be evaluated by combining these data.

[0100] The characteristic clustering results and coating uniformity were modeled according to the multivariate regression analysis method to obtain the thickness variation.

[0101] By establishing a multivariate regression model, the relationship between the feature clustering results and coating uniformity is analyzed to predict the thickness change. Specifically, the multivariate regression analysis method is used to construct a mathematical model between the feature data and coating uniformity to predict the thickness change under different coating conditions.

[0102] For example, a model is established using multivariate regression analysis, with the feature clustering results as the independent variable and coating uniformity as the dependent variable. The model outputs the thickness variation of the coating layer in different areas.

[0103] In step S400, the coating uniformity data is input into a neural network algorithm, and the coating uniformity is evaluated using a local sensitivity analysis method in the neural network algorithm to generate an evaluation score and defect feature distribution data.

[0104] The coating quality is evaluated by inputting the coating uniformity data into a neural network algorithm; specifically, the local sensitivity analysis method is used to analyze the changes in the coating uniformity data under different conditions, and an evaluation score and defect distribution data are generated to identify problems in the coating process.

[0105] For example, convolutional neural networks are used to evaluate coating uniformity data and generate evaluation scores for each area. Local sensitivity analysis methods are used to identify possible defect locations in the coating process and generate defect feature distribution maps.

[0106] The evaluation scores are classified into coating quality grades to obtain coating quality grades.

[0107] The coating quality level is determined by classifying the evaluation scores; specifically, the evaluation scores are divided into different levels according to the preset quality standards, and the coating quality is evaluated to ensure that the coating process meets the quality requirements.

[0108] For example, the evaluation scores are divided into Grade A (excellent), Grade B (qualified) and Grade C (needs improvement) according to preset standards, and a coating quality grade report is generated to reflect the coating quality of different areas.

[0109] The coating quality grade is compared with the preset quality standard to obtain the coating quality assessment result.

[0110] By comparing the coating quality grade with the quality standard, the overall quality of the coating process is evaluated; specifically, based on the comparison results, it is determined whether the coating quality meets the expected requirements, and a detailed evaluation report is generated to guide subsequent process adjustments.

[0111] For example, compare the coating quality level with the standard quality requirements, generate an evaluation report, point out the areas that need improvement and improvement suggestions, and ensure that the coating quality meets the expected goals.

[0112] Perform trend analysis on the coating quality assessment results to obtain trend analysis results, use the trend analysis results to locate defects on defect feature distribution data, and obtain coating defect distribution conditions.

[0113] By performing trend analysis on the evaluation results, defects that may occur in the coating process can be identified; specifically, trend analysis technology is used to perform time series analysis on the evaluation results to identify abnormal trends in the coating process and locate defects.

[0114] For example, trend analysis can be used to identify quality fluctuations that occur during certain time periods during the coating process, and these fluctuations can be combined with defect distribution data to determine the specific location and type of defects and generate a coating defect distribution map.

[0115] In step S500, the coating quality evaluation results are comprehensively analyzed using data analysis technology to obtain a comprehensive coating quality analysis result.

[0116] Through data analysis technology, the coating quality assessment results are comprehensively analyzed to identify potential problems in the coating process; specifically, statistical analysis and data mining technology are used to comprehensively process the assessment results and generate an analysis report on the overall coating quality.

[0117] For example, statistical software can be used to conduct multi-dimensional analysis of the evaluation results, identify the main problems in the coating process, generate a comprehensive analysis report, and provide data support for process improvement.

[0118] Data mining technology is used to extract features of coating defect distribution and obtain defect feature extraction results.

[0119] Through data mining technology, the coating defect distribution data is deeply analyzed to extract key features; specifically, cluster analysis, association rule mining and other technologies are used to identify patterns and laws in defect distribution and generate feature extraction results.

[0120] For example, cluster analysis is used to group defect data, identify the distribution patterns of different types of defects, and generate defect feature extraction reports that describe the types, locations, and frequencies of defects in detail.

[0121] The comprehensive analysis results of coating quality and the defect feature extraction results are fused and analyzed to obtain fusion analysis results.

[0122] By integrating the analysis of coating quality and defect characteristics, the overall performance of the coating process can be comprehensively evaluated. Specifically, the quality analysis results and defect characteristic data are combined to identify key issues in the coating process and provide improvement suggestions.

[0123] For example, fusion analysis shows that certain defects are related to specific process parameters, and by adjusting these parameters, the coating quality can be significantly improved, generating a detailed report with improvement recommendations.

[0124] Based on the fusion analysis results, the thickness variation is optimized to obtain the thickness optimization parameters.

[0125] By integrating the analysis results, the thickness variation is optimized and the best thickness control parameters are determined; specifically, the optimization algorithm is used to adjust the process parameters to ensure the consistency and uniformity of the coating thickness.

[0126] For example, genetic algorithms are used to optimize thickness control parameters to ensure thickness consistency under different coating conditions, generate optimized parameter reports, and guide process adjustments.

[0127] In step S600, a feedback map is constructed according to the thickness optimization parameters and preset map generation rules; wherein the map generation rules include comprehensive evaluation criteria for coating uniformity, thickness consistency and coating efficiency.

[0128] By optimizing parameters and generating rules, a feedback map for control is constructed; specifically, the thickness optimization parameters are organized to include the thickness range of the target coating layer, the allowable error range in the coating process, the optimized coating path, etc. These parameters are the basic data for constructing the feedback map. The map generation rules are composed of multiple coating evaluation criteria, including the coating uniformity standard: evaluate the uniformity of the coating layer in the target coating area, including calculating the standard deviation and mean of the coating thickness. Thickness consistency standard: evaluate the thickness consistency of the coating layer at different locations to ensure that the thickness at each location meets the predetermined optimization parameters. Coating efficiency standard: evaluate the speed and efficiency of the coating process, including the coating area and coating quality completed per unit time.

[0129] According to the thickness optimization parameters and the map generation rules, the data structure of the feedback map is designed. The feedback map is usually represented in the form of a two-dimensional or three-dimensional grid, in which each cell represents a part of the target coating area, and each cell contains the following data: current position coordinates, actual coating thickness, theoretical coating thickness, coating uniformity evaluation value, coating efficiency evaluation value, and data filling: using the real-time coating data, the actual measured coating thickness and other related data are filled into each cell of the feedback map. At the same time, using the thickness optimization parameters and preset standards, the theoretical coating thickness, coating uniformity evaluation value and coating efficiency evaluation value of each cell are calculated, and the corresponding data are filled. According to the filled data, the feedback map is converted into a visual image, usually in the form of a heat map, contour map or 3D surface map. In the visual image, different colors and heights represent different coating thickness and uniformity evaluation results, so that the operator can intuitively see the coating quality and the area that needs to be adjusted, so as to realize the use of thickness optimization parameters and coating evaluation standards, generate feedback maps, and guide real-time adjustment of the coating process.

[0130] For example, based on the optimized parameters, a feedback map is generated, which contains information such as coating uniformity, thickness consistency and efficiency, providing real-time adjustment reference for the coating equipment.

[0131] The feedback map is input into the control system of the automatic coating equipment, and the control system uses the control algorithm and model predictive control to analyze and process the feedback map to obtain coating parameter adjustment instructions.

[0132] The coating parameters are adjusted in real time by inputting the feedback map into the control system; specifically, the feedback map is analyzed by using model predictive control and feedback control algorithms, adjustment instructions are generated, and the coating process is optimized.

[0133] For example, the control system automatically adjusts parameters such as spraying speed, pressure and temperature based on the feedback map to ensure a stable and efficient coating process.

[0134] The coating parameters of the automatic coating equipment are adjusted based on the coating parameter adjustment instructions, and the target coating area is re-coated by the automatic coating equipment after the coating parameters are adjusted; wherein the coating parameters include coating speed, coating pressure, coating temperature, spraying angle, spraying distance and flow control of coating material.

[0135] Optimize coating quality by adjusting coating parameters in real time; specifically, reset various parameters of coating equipment according to adjustment instructions to ensure accurate control of coating process and improve coating quality.

[0136] For example, automatic coating equipment adjusts the spraying angle and distance according to the instructions of the control system, controls the material flow, ensures uniform thickness of the coating layer, and improves the coating effect.

[0137] In this embodiment, the surface of the titanium anode is scanned by using laser scanning and computer vision algorithms to identify and mark the target coating area to ensure the accuracy of the coating. The first coating simulation is performed using finite element analysis technology to obtain the first coating path and strategy. The path and strategy are adjusted by the optimization algorithm to improve the coating accuracy and quality. Finite element analysis is performed again to obtain the second coating path and strategy, and comparison and optimization are performed to ensure the accuracy and consistency of the coating process. The final coating path and strategy are input into the control system of the automatic coating equipment to ensure high-quality coating.

[0138] Embodiment 3:

[0139] like Figure 2 As shown, the present application also provides an automatic coating device 10 for titanium anodes, and the automatic coating device 10 for titanium anodes includes an acquisition module 11, a collection module 12, a first analysis module 13, an evaluation module 14, a second analysis module 15 and an adjustment module 16.

[0140] The acquisition module 11 is mainly used to acquire the target coating area of ​​the titanium anode and coat the target coating area using automatic coating equipment.

[0141] The acquisition module 12 is mainly used to acquire data of the target coating area during the coating process according to the sensor array preset on the automatic coating equipment to obtain real-time coating data.

[0142] The first analysis module 13 is mainly used to input the real-time coating data into a preset coating analysis model, and analyze the coating uniformity and thickness variation of the automatic coating equipment during the coating process of the target coating area according to the real-time coating data through the coating analysis model.

[0143] The evaluation module 14 is mainly used to evaluate the coating uniformity using a preset neural network algorithm to generate coating quality evaluation results and coating defect distribution.

[0144] The second analysis module 15 is mainly used to analyze the thickness variation based on the coating quality evaluation result and the coating defect distribution to obtain the thickness optimization parameters.

[0145] The adjustment module 16 is mainly used to generate a feedback map according to the thickness optimization parameters, and adjust the coating parameters of the automatic coating equipment based on the feedback map, and re-coat the target coating area through the automatic coating equipment after adjusting the coating parameters.

[0146] In this embodiment, through the collaborative work of various modules, precise control of the titanium anode coating process is achieved. The acquisition module 11 first uses the automatic coating equipment to accurately identify and coat the target coating area to ensure the initial accuracy of the coating. The acquisition module 12 uses the sensor array to monitor the coating process in real time, collects key data such as coating thickness, temperature and speed, and forms real-time coating data. The first analysis module 13 performs a deep analysis of the real-time data through the coating analysis model, evaluates the coating uniformity and thickness variation, and provides real-time feedback of the coating process. The evaluation module 14 further uses the neural network algorithm to perform a detailed evaluation of the coating uniformity, generates the coating quality evaluation results and defect distribution, and ensures the high standard of coating quality. The second analysis module 15 analyzes the thickness variation based on the evaluation results and defect distribution, proposes thickness optimization parameters, and optimizes the coating effect. Finally, the adjustment module 16 generates a feedback spectrum according to the optimization parameters, and adjusts the coating parameters of the automatic coating equipment to achieve adaptive optimization of the coating process, thereby improving the overall coating quality and efficiency.

[0147] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned embodiment of the automatic coating method of titanium anode, and will not be repeated here.

[0148] Embodiment 4:

[0149] like Figure 3 As shown, the present application also provides an electronic device 20, including a memory 21 and a processor 22, wherein the memory 21 stores a computer program that can be run on the processor 22, and when the processor 22 executes the computer program, the automatic coating method of the titanium anode of Example 1 is implemented.

[0150] In this embodiment, the memory 21 and the processor 22 of the electronic device 20 are coordinated to ensure the efficient execution of the automatic coating method of the titanium anode. The computer program stored in the memory 21 includes the complete steps of obtaining the target coating area, collecting real-time coating data, analyzing coating uniformity and thickness variation, evaluating coating quality, analyzing thickness optimization parameters, and adjusting coating equipment parameters. When the processor 22 executes the program, it first identifies and marks the target coating area to ensure the accuracy of the coating. Subsequently, the coating process is monitored in real time through the sensor array, and the real-time coating data is collected and processed. The program further analyzes these data, evaluates the coating quality, generates optimization parameters, and adjusts the operating parameters of the coating equipment in real time to ensure the dynamic optimization of the coating process. In this way, the electronic device 20 realizes the full automation and high-precision control of the titanium anode coating process, which significantly improves the coating efficiency and quality.

[0151] Embodiment 5:

[0152] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the automatic coating method of the titanium anode as described in Example 1.

[0153] In this embodiment, through the computer program on the computer-readable storage medium, the processor can efficiently execute the automatic coating method of the titanium anode. The program stored in the storage medium includes the steps of obtaining the target coating area, data collection, analysis and evaluation, optimizing the thickness parameters, and adjusting the coating equipment. When the processor runs the program, it first accurately obtains the target coating area and performs preliminary coating. Then, the coating data is collected in real time through the sensor array, and the coating analysis model is input to analyze the coating uniformity and thickness variation. The program uses a neural network algorithm to evaluate the coating quality, generate defect distribution and optimization parameters. According to the optimization parameters, the program generates a feedback map and adjusts the coating equipment parameters to ensure that each coating can achieve the best effect. In this way, the computer-readable storage medium provides strong technical support for realizing the intelligent and efficient titanium anode coating process.

[0154] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic coating method for titanium anodes, characterized in that: The automatic coating method of the titanium anode is applied to an automatic coating device, and the automatic coating method of the titanium anode comprises: Acquire a target coating area of ​​the titanium anode, and coat the target coating area using the automatic coating equipment; Collecting data of the target coating area during the coating process according to a sensor array preset on the automatic coating equipment to obtain real-time coating data; The real-time coating data is input into a preset coating analysis model, and the coating uniformity and thickness change of the automatic coating equipment during the coating process of the target coating area are analyzed by the coating analysis model according to the real-time coating data; including: preprocessing the real-time coating data, inputting the preprocessed real-time coating data into the analysis model, using a convolutional neural network algorithm in the analysis model to extract features of the real-time coating data to obtain feature data, and generating a feature map based on the feature data; clustering analysis is performed on the feature data according to a statistical analysis method to obtain feature clustering results and a number of feature center points; multi-dimensional scaling analysis is performed on all the feature center points to obtain feature space coordinates , segment the feature map using the feature space coordinates, take all the feature center points as initial segmentation points, mark them on the feature map, calculate the distance between each feature center point, and establish a neighbor relationship in the feature space; divide the feature map into several regions based on the neighbor relationship and a preset distance threshold, each region includes feature data; perform statistical analysis on the feature data in each region, calculate the standard deviation and mean of the feature values ​​in the region, and evaluate the coating uniformity in the region based on the standard deviation and mean, and obtain the overall coating uniformity of the target coating region; model the feature clustering results and the coating uniformity according to the multivariate regression analysis method to obtain the thickness change; The coating uniformity is evaluated by using a preset neural network algorithm to generate a coating quality evaluation result and a coating defect distribution; including: inputting the coating uniformity data into the neural network algorithm, evaluating the coating uniformity by using a local sensitivity analysis method in the neural network algorithm to generate an evaluation score and defect feature distribution data; classifying the evaluation score into a coating quality grade to obtain a coating quality grade; comparing the coating quality grade with a preset quality standard to obtain a coating quality evaluation result; performing a trend analysis on the coating quality evaluation result to obtain a trend analysis result, and using the trend analysis result to locate defects on the defect feature distribution data to obtain a coating defect distribution; Based on the coating quality evaluation result and the coating defect distribution, a fusion analysis is performed on the thickness variation to obtain thickness optimization parameters; A feedback map is generated according to the thickness optimization parameters, and coating parameters of an automatic coating device are adjusted based on the feedback map, and the target coating area is re-coated by the automatic coating device after the coating parameters are adjusted.

2. The automatic coating method of titanium anode according to claim 1, characterized in that: The step of obtaining a target coating area of ​​the titanium anode and coating the target coating area using the automatic coating equipment comprises: Use laser scanning and computer vision algorithms to scan the surface of the titanium anode, identify and mark the target area to be coated, and obtain the target coating area; Performing a first coating simulation on the target coating area using finite element analysis technology to obtain a first coating path and a first coating strategy; Using an optimization algorithm to adjust the first coating path to obtain an adjusted coating path, and optimizing the first coating strategy according to the adjusted coating path to obtain an optimized first coating strategy; Based on the optimized first coating strategy, using the finite element analysis technology to perform a second coating simulation on the target coating area to obtain a second coating path and a second coating strategy, comparing the first coating path with the second coating path to obtain a path difference, and comparing the first coating strategy with the second coating strategy to obtain a strategy difference; Utilizing the path difference and optimizing the adjusted coating path to obtain a final coating path; utilizing the strategy difference to optimize the optimized first coating strategy to obtain a final coating strategy; The final coating path and the final coating strategy are input into a control system of the automatic coating equipment, and the automatic coating equipment is controlled by the control system to coat the target coating area.

3. The automatic coating method of titanium anode according to claim 1, characterized in that: The step of collecting data from the target coating area during the coating process according to the sensor array preset on the automatic coating equipment to obtain real-time coating data includes: Using a laser thickness gauge, a preset infrared temperature sensor and a preset coating speed sensor preset on the automatic coating equipment as a sensor array; Using the laser thickness gauge to collect data on the target coating area during the coating process to obtain the coating layer thickness; Using the infrared temperature sensor to collect data from the target coating area during the coating process to obtain the coating temperature; Using the coating speed sensor to collect data from the target coating area during the coating process to obtain the coating speed; The coating layer thickness, the coating temperature and the coating speed are used as coating real-time data.

4. The automatic coating method of titanium anode according to claim 1, characterized in that: The step of performing a fusion analysis on the thickness variation based on the coating quality assessment result and the coating defect distribution to obtain thickness optimization parameters comprises: Comprehensively analyzing the coating quality evaluation results using data analysis technology to obtain a comprehensive coating quality analysis result; Using data mining technology to extract features of the coating defect distribution to obtain defect feature extraction results; Performing a fusion analysis on the coating quality comprehensive analysis result and the defect feature extraction result to obtain a fusion analysis result; The thickness variation is optimized based on the fusion analysis result to obtain thickness optimization parameters.

5. The automatic coating method of titanium anode according to claim 1, characterized in that: The step of generating a feedback map according to the thickness optimization parameters, adjusting the coating parameters of the automatic coating equipment based on the feedback map, and re-coating the target coating area by the automatic coating equipment after adjusting the coating parameters includes: Constructing a feedback map according to the thickness optimization parameters and the preset map generation rules; wherein the map generation rules include comprehensive evaluation criteria for coating uniformity, thickness consistency and coating efficiency; The feedback map is input into the control system of the automatic coating equipment, and the feedback map is analyzed and processed by the control system using a control algorithm and model predictive control to obtain a coating parameter adjustment instruction, and the coating parameters of the automatic coating equipment are adjusted based on the coating parameter adjustment instruction, and the target coating area is re-coated by the automatic coating equipment after the coating parameters are adjusted; wherein the coating parameters include coating speed, coating pressure, coating temperature, spraying angle, spraying distance and flow control of coating material.

6. An automatic coating device for titanium anodes, characterized in that: include: An acquisition module, used for acquiring a target coating area of ​​the titanium anode, and coating the target coating area using an automatic coating device; An acquisition module, used for acquiring data of the target coating area during the coating process according to a sensor array preset on the automatic coating equipment, to obtain real-time coating data; The first analysis module is used to input the real-time coating data into a preset coating analysis model, and analyze the coating uniformity and thickness change of the automatic coating equipment during the coating process of the target coating area according to the real-time coating data through the coating analysis model; including preprocessing the real-time coating data, inputting the preprocessed real-time coating data into the analysis model, using a convolutional neural network algorithm in the analysis model to extract features of the real-time coating data to obtain feature data, and generating a feature map based on the feature data; performing cluster analysis on the feature data according to a statistical analysis method to obtain feature clustering results and a number of feature center points; performing multidimensional scaling analysis on all the feature center points to obtain feature The method comprises the following steps: first, determining the feature map of the coating layer and the coating uniformity of the target coating area; second, determining the feature map of the coating layer; third, determining the coating uniformity of the target coating area; fourth, determining the coating uniformity of the target coating area; fifth ... An evaluation module is used to evaluate the coating uniformity using a preset neural network algorithm to generate a coating quality evaluation result and a coating defect distribution; including: inputting the coating uniformity data into the neural network algorithm, evaluating the coating uniformity using a local sensitivity analysis method in the neural network algorithm, generating an evaluation score and defect feature distribution data; classifying the evaluation score into a coating quality grade to obtain a coating quality grade; comparing the coating quality grade with a preset quality standard to obtain a coating quality evaluation result; performing a trend analysis on the coating quality evaluation result to obtain a trend analysis result, and using the trend analysis result to locate defects on the defect feature distribution data to obtain a coating defect distribution; A second analysis module is used to perform a fusion analysis on the thickness variation based on the coating quality evaluation result and the coating defect distribution to obtain thickness optimization parameters; The adjustment module is used to generate a feedback map according to the thickness optimization parameters, and adjust the coating parameters of the automatic coating equipment based on the feedback map, so that the target coating area is re-coated by the automatic coating equipment after the coating parameters are adjusted.

7. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the automatic coating method of the titanium anode according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the processor is caused to perform the automatic coating method for a titanium anode as claimed in any one of claims 1 to 5.

Images