A method for optimizing the performance of nanomaterial wear-resistant coatings

Abstract

The present invention discloses a method for optimizing the performance of nanomaterial wear-resistant coatings, which belongs to the field of data processing technology. The method includes: reading basic coating information; based on the basic coating information, performing homologous sample retrieval and calling to construct a performance prediction model; based on the homologous samples, performing coating performance failure analysis to determine a failure mechanism diagram; auxiliary failure mechanism diagram to construct an optimization decision module; reading pre-optimized coating information, combining the performance prediction model to determine the performance prediction result, transmitting it to the optimization decision module for hierarchical multi-objective optimization, and determining the target optimization strategy; based on the target optimization strategy, performing coating performance optimization management for the entire coating operation cycle. The present application solves the technical problem in the prior art that the coating performance is unstable and the failure mechanism is unclear, which leads to the inability to efficiently and accurately optimize the nanomaterial wear-resistant coating.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for optimizing the performance of a nano material wear-resistant coating. Background Art

[0002] With the continuous development of modern industrial technology, the operating environment of mechanical equipment and industrial devices is becoming increasingly complex and harsh. In particular, mechanical parts working under harsh conditions such as high wear and high corrosion have higher requirements on the surface performance of materials. In order to extend the service life of equipment and improve work efficiency, wear-resistant coating technology has emerged. Nanomaterials have become a research hotspot in the field of wear-resistant coatings due to their unique physical and chemical properties, such as high strength, high hardness and excellent wear resistance. However, there are some challenges in the preparation and application of nanomaterials, such as the stability of coating performance and the complexity of coating technology. Therefore, how to optimize the performance of nanomaterial wear-resistant coatings has become an important research topic in the field of materials science and engineering.

[0003] Existing nanomaterial wear-resistant coating technologies often face challenges in practical applications, including coating failure and unstable performance. These issues primarily stem from inaccurate control of coating and coating process parameters, as well as inappropriate material ratios. Traditional optimization methods, which rely heavily on experience and trial-and-error, are inefficient and costly.

[0004] In summary, the present application aims to solve the technical problems in the prior art, such as unstable coating performance and unclear failure mechanism, which result in the inability to efficiently and accurately optimize nanomaterial wear-resistant coatings. Summary of the Invention

[0005] This application provides a method for optimizing the performance of nanomaterial wear-resistant coatings, aiming to solve the technical problems in the prior art such as unstable coating performance and unclear failure mechanism, which lead to the inability to efficiently and accurately optimize nanomaterial wear-resistant coatings.

[0006] In view of the above problems, the present application provides a method for optimizing the performance of nanomaterial wear-resistant coatings. The method includes: reading basic coating information, wherein the basic coating information at least includes nano-mixing ratio and process information, wherein the process information includes coating process and coating process; based on the basic coating information, performing homologous sample retrieval and calling, and constructing a performance prediction model, wherein the performance prediction model is constructed based on the extra tree regression principle and outputs the mean as the prediction result; based on the homologous sample, performing coating performance failure analysis, and determining a failure mechanism diagram, wherein the failure mechanism diagram is marked with a failure mitigation feature; assisting the failure mechanism diagram, constructing an optimization decision module, and establishing a communication connection between the optimization decision module and the performance prediction model; reading pre-optimized coating information, combining the performance prediction model to determine the performance prediction result, transmitting it to the optimization decision module for hierarchical multi-objective optimization, and determining the target optimization strategy, wherein the optimization dimension at least includes composite coating, process modification, and material ratio; based on the target optimization strategy, performing coating performance optimization management for the entire coating operation cycle.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Due to the adoption of a technical solution that reads basic coating information (including nano-mixing ratio and coating process, coating process information), performs homologous sample retrieval based on the information, constructs a performance prediction model based on additional tree regression, and outputs the mean prediction result, the technical problem of inaccurate prediction and unclear failure mechanism in the process of coating performance optimization, which leads to insufficient coating reliability and durability, is solved. By performing coating performance failure analysis based on homologous samples, determining the failure mechanism diagram and identifying the failure mitigation characteristics, assisting in the construction of an optimization decision module, and establishing a communication connection with the performance prediction model, the pre-optimized coating information is read, and the performance prediction result is determined in combination with the performance prediction model, which is transmitted to the optimization decision module for hierarchical multi-objective optimization, and the target optimization strategy is determined. The optimization dimensions include at least composite coating, process modification and material ratio. Finally, the coating performance is optimized and managed for the entire coating operation cycle, which solves the technical problem of unstable coating performance and unclear failure mechanism in the existing technology, which leads to the inability to efficiently and accurately optimize the nanomaterial wear-resistant coating. The technical effect of improving the wear resistance, stability and overall performance of the coating is achieved.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A flow chart of a method for optimizing the performance of nanomaterial wear-resistant coatings is provided for an embodiment of the present application.

[0011] Figure 2 A schematic flow chart of constructing a performance prediction model in a method for optimizing the performance of a nanomaterial wear-resistant coating is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The overall idea of ​​the technical solution provided by this application is as follows:

[0013] The embodiment of the present application provides a method for optimizing the performance of nanomaterial wear-resistant coatings. First, the basic coating information including the nano-mixing ratio and process information (coating process and coating process) is read, and this information is used to perform homologous sample retrieval, and a performance prediction model based on additional tree regression is constructed to predict the coating performance by outputting the mean. Then, a coating performance failure analysis is performed based on the homologous samples, a failure mechanism diagram is drawn, and failure mitigation characteristics are identified. Based on the failure mechanism diagram, an optimization decision module is constructed, and a communication connection is established with the performance prediction model. The pre-optimized coating information is read, and the performance prediction results are determined in combination with the performance prediction model, and transmitted to the optimization decision module for hierarchical multi-objective optimization to determine the target optimization strategy, and the optimization dimensions include at least composite coating, process modification, and material ratio. Finally, based on the target optimization strategy, the coating performance optimization management is performed for the entire coating operation cycle to improve the wear resistance and stability of the coating.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced in conjunction with the drawings in the specification.

[0015] like Figure 1 As shown, the embodiment of the present application provides a method for optimizing the performance of nanomaterial wear-resistant coatings, the method comprising:

[0016] Step S100: reading basic coating information, wherein the basic coating information at least includes nano-mixing ratio and process information, wherein the process information includes coating process and coating process.

[0017] Specifically, basic coating information usually comes from experimental records, process documents, product design documents, etc. during the coating preparation process. It can be stored in the form of electronic documents, databases, or paper documents. Reading basic coating information may involve steps such as data extraction, parsing, and conversion. For example, for information stored in a database, it is necessary to write query statements to retrieve relevant data; for paper documents, it is necessary to use OCR (optical character recognition) technology to convert text into an editable digital format. Basic coating information refers to basic information directly related to the coating material, preparation process, and its performance. The basic coating information is crucial for understanding and optimizing the performance of the coating. It includes two aspects: nano-mixing ratio and process information.

[0018] Nano-mixing ratio refers to the ratio of nanomaterials to other components (such as matrix materials, additives, etc.) in the coating. This ratio directly affects the key characteristics of the coating, such as microstructure, mechanical properties and wear resistance.

[0019] Process information covers all technologies and methods used in the coating preparation process, including coating processes and coating processes. Among them, the coating process refers to the technical parameters and steps of the process of mixing, dispersing, and forming nanomaterials and other components. These parameters may include mixing time, temperature, pressure, stirring speed, etc., which together determine the uniformity, density and microstructure of the coating. The coating process refers to the technology and method of applying the prepared coating material to the surface of the substrate. The selection and parameter setting of the coating process directly affect the bonding strength between the coating and the substrate, the thickness distribution of the coating, and the surface morphology. Common coating processes include spraying, brushing, dipping, electrophoretic deposition, etc.

[0020] This step, by acquiring basic coating information, provides a deep understanding of the coating's composition, structure, and preparation process, providing reliable data support for subsequent performance prediction, failure analysis, and optimization decisions. This not only helps identify key factors and potential issues in coating performance, but also guides technicians in targeted improvements and optimization, thereby enhancing the coating's overall performance and service life.

[0021] Step S200: Based on the basic coating information, a homologous sample search and call is performed to construct a performance prediction model. The performance prediction model is constructed based on the extra tree regression principle and outputs the mean as the prediction result.

[0022] Specifically, homologous samples refer to existing coating samples that are similar or close to the current basic coating information in terms of material composition, preparation process, and usage conditions. By retrieving and calling the data of these homologous samples, rich reference information and experience data can be provided for the performance prediction and optimization of the current coating. Specifically, if the homologous sample data is stored in a database, relevant information can be retrieved by writing query statements. The query conditions may include nano-mixing ratio range, process parameter range, usage conditions, etc. For unstructured data or complex query requirements, similarity matching algorithms can be used to find homologous samples that are most similar to the current basic coating information. These algorithms are based on distance metrics (such as Euclidean distance, Manhattan distance), cosine similarity or other complex similarity evaluation methods. After retrieving the homologous samples, the data needs to be preprocessed to ensure data consistency and availability. The preprocessing steps include data cleaning (removing noise and outliers), data conversion (standardization, normalization), feature selection (extracting features useful for performance prediction), etc.

[0023] Furthermore, Extra-Trees Regression is used as the construction principle of the performance prediction model. Extra-Trees Regression is a decision tree-based ensemble learning method that improves the accuracy and stability of predictions by constructing multiple decision trees and averaging their prediction results. Specifically, when constructing each decision tree, a randomization strategy is used to select features and split points to increase the diversity of the model. Each decision tree is trained and predicted independently, and their prediction results are finally merged to obtain the final prediction result. Due to the use of ensemble learning methods, the model's prediction result is usually the average of the prediction results of multiple decision trees, which helps to reduce the bias and noise that may be introduced by a single decision tree.

[0024] During the model prediction phase, the extra tree regression model generates predictions from multiple decision trees for the input base coating information. The final prediction is the average of these results, which serves as the coating performance prediction.

[0025] This step utilizes homologous samples and an extra-tree regression algorithm to construct an accurate performance prediction model. This model predicts the coating's performance based on the input base coating information. It leverages existing empirical data and advanced machine learning techniques to predict and optimize the performance of new coatings, thereby improving the overall performance and service life of the coating.

[0026] Step S300: performing coating performance failure analysis based on the homologous sample to determine a failure mechanism diagram, wherein the failure mechanism diagram is marked with a failure mitigation feature.

[0027] Specifically, data related to coating failure is collected from homologous samples, including coating performance parameters before and after failure, environmental conditions, usage history, etc. The collected data is organized to ensure its completeness and accuracy.

[0028] Analyze the specific manifestations of coating failure, such as wear, corrosion, cracking, and flaking, to identify different failure modes. Classify and statistically analyze each failure mode to understand its distribution and frequency across homogenous samples. In-depth research is conducted on the various factors that contribute to coating failure, including the properties of the material itself (e.g., nano-mixing ratio, component purity), preparation process (e.g., coating process, coating process), operating environment (e.g., temperature, humidity, medium, etc.), and external stress. Through comparative analysis, experimental verification, and other methods, determine the contribution of each factor to coating failure and the interaction relationship.

[0029] Based on the analysis of failure modes and failure factors, construct a failure mechanism diagram for the coating. This diagram should clearly demonstrate the coating's evolution from normal to failed state, along with the key influencing factors and failure characteristics at each stage. In the failure mechanism diagram, pay particular attention to features that can delay or prevent failure (i.e., failure-mitigating features), such as specific nanomaterial additions, optimized preparation process parameters, and enhanced interfacial bonding.

[0030] This step, analyzing coating performance failures based on homologous samples and determining failure mechanism diagrams, is a crucial step in optimizing coating performance and improving product reliability. This step provides a deeper understanding of coating failure patterns and influencing factors, providing strong support for subsequent improvements and optimization efforts.

[0031] Step S400: Assisting the failure mechanism diagram, constructing an optimization decision module, and establishing a communication connection between the optimization decision module and the performance prediction model.

[0032] Specifically, the optimization decision module is an intelligent system based on algorithms and rules. It automatically generates decision recommendations for coating performance optimization based on the output of the performance prediction model, the analysis results of the failure mechanism diagram, and the preset optimization goals. By automating the analysis and decision-making process, human intervention is reduced, optimization efficiency is improved, and coating performance is ensured to meet or exceed expectations.

[0033] Specifically, the failure mechanism diagram is used to identify the main failure modes and mitigation features that affect coating performance. The key information and failure mitigation features in the failure mechanism diagram are mapped to the data structure of the optimization decision module for reference and utilization in the decision-making process. As an important auxiliary tool for the optimization decision module, the failure mechanism diagram provides an intuitive display and analysis of failure causes, influencing factors, and potential solutions during the decision-making process. For example, for wear failure, the mixing ratio of nanomaterials can be optimized; for corrosion failure, the coating process can be improved. With the addition of new data and the continuous improvement of the failure mechanism diagram, the optimization decision module should be able to dynamically update its decision logic and strategy library to adapt to new optimization needs.

[0034] Specifically, pre-optimized coating data is read from the base coating information as input. A performance prediction model is used to predict coating performance outcomes, and the results are transmitted to the optimization decision module. Within this module, multi-dimensional, multi-objective optimization calculations are performed. Optimization dimensions include at least composite coatings, process modifications, and material ratios. Based on the performance prediction results and failure mechanism diagrams, a hierarchical multi-objective optimization search is performed to determine the optimal optimization strategy. This optimization strategy is then output for reference in actual production and application.

[0035] Design a data interface between the optimization decision module and the performance prediction model to ensure smooth data exchange between the two. Establish an information transmission mechanism so that the performance prediction model's prediction results can be transmitted to the optimization decision module in real time. Simultaneously, the optimization decision module's decision results can be fed back to the performance prediction model for verification and adjustment. Ensure that the optimization decision module receives the latest failure mechanism analysis results and performance prediction results in real time to enable dynamic optimization adjustments.

[0036] This step builds an optimization decision module and establishes a communication link between it, the performance prediction model, and the failure mechanism diagram to form a closed-loop coating performance optimization system. This system automatically analyzes coating performance data, identifies failure causes, generates optimization decisions, and tracks implementation results, thereby achieving continuous improvement and enhancement of coating performance.

[0037] Step S500: Read the pre-optimized coating information, determine the performance prediction results in combination with the performance prediction model, and transmit them to the optimization decision module for hierarchical multi-objective optimization to determine the target optimization strategy, wherein the optimization dimensions at least include composite coating, process modification, and material ratio.

[0038] Specifically, pre-optimized coating information refers to existing coating-related data and parameters prior to optimization, including nano-mixing ratios, coating processes, and application techniques. Composite coatings are composed of multiple materials combined to enhance their performance. Process modification refers to improvements to the coating's manufacturing and application processes to improve coating performance. Material ratio refers to the proportions of different materials in a coating.

[0039] Existing coating-related data, including the nanomaterial mixing ratio, coating process, and coating process details, is read from a database or preset parameter set. The pre-optimized coating information is input into the performance prediction model. The performance prediction model calculates and determines the coating's performance results. The performance prediction model uses an additional tree regression algorithm based on homologous sample data to output predicted coating performance values. The performance prediction results are transmitted to the optimization decision module via a data interface. The optimization decision module receives and integrates the results from the performance prediction model and the pre-optimized coating information to prepare for multi-objective optimization analysis.

[0040] Identify the key dimensions for optimization, including at least composite coatings, process modifications, and material ratios. Use a hierarchical multi-objective optimization algorithm to systematically analyze and optimize the optimization objectives of different dimensions. Generate an initial optimization strategy based on the current coating information and performance prediction results. Through iterative calculations, gradually adjust the parameters of each dimension to seek the globally optimal optimization strategy. Layer the optimization objectives, prioritize solving key issues, and then gradually optimize secondary issues to ensure the best overall optimization results. Ultimately, determine the optimal optimization strategy through hierarchical multi-objective optimization. This strategy includes the optimal material combination for the composite coating, specific measures for process modifications, and the optimal material ratio.

[0041] Through the above steps, hierarchical multi-objective optimization is performed using the pre-optimized coating information and performance prediction model, and the optimal coating optimization strategy is finally determined to improve the wear resistance and stability of the coating.

[0042] Step S600: Based on the target optimization strategy, coating performance optimization management is performed for the entire coating operation cycle.

[0043] Specifically, adjustments and improvements are made to the coating's material combination, process modification, and material ratio based on the defined target optimization strategy. Composite coating optimization: Select the optimal material combination to improve the coating's wear resistance and other key performance indicators. Process modification: Improve the coating and curing processes to ensure coating uniformity and stability. Material ratio optimization: Adjust the proportion of nanomaterials to achieve optimal performance.

[0044] Prepare the required nanomaterials and substrates according to the material ratios in the target optimization strategy. Ensure the quality and purity of the materials to avoid the impact of impurities on the coating performance. Select a suitable coating method (such as spraying, brushing, dipping, etc.) according to the process modification measures in the optimization strategy. Control the coating parameters (such as coating speed, thickness, temperature, etc.) to ensure the uniformity and adhesion of the coating. Curing treatment (such as heat treatment, light curing, etc.) of the coating according to the curing process requirements in the optimization strategy. Perform necessary post-processing operations (such as polishing, cleaning, etc.) to improve the surface quality and performance of the coating.

[0045] During actual use, follow the usage requirements in the optimization strategy to ensure the stability and durability of the coating in the working environment. Regularly perform coating performance testing and maintenance to promptly identify and resolve potential problems and extend the coating's service life.

[0046] This step is based on the target optimization strategy to conduct comprehensive performance optimization management of the coating throughout its entire operation cycle to ensure that the nanomaterial wear-resistant coating always maintains excellent performance and stability throughout its entire life cycle.

[0047] Furthermore, if Figure 2As shown, the construction of the performance prediction model also includes: traversing the homologous samples, randomly extracting a preset number of N groups of sample data, and there is repetitiveness between the N groups of sample data; based on the N groups of sample data, constructing N decision trees that meet the convergence conditions; integrating the N decision trees to generate the performance prediction model.

[0048] Specifically, historical sample data similar to the current coating's basic information is extracted from a homologous sample library. This includes different nano-mixing ratios, process information, and corresponding coating performance results. A preset number of N groups of sample data are randomly extracted from the homologous sample library, and each group of data is used to construct a decision tree. To improve the model's generalization and stability, these sample data can be repeated between groups, meaning that the same sample can be used by multiple decision trees.

[0049] For each set of sample data, a decision tree is constructed based on its characteristics and the corresponding coating performance results. The decision tree recursively partitions the data space to find the optimal split point between the characteristics and the target value (coating performance). During the decision tree construction process, convergence conditions, such as minimum error or maximum depth, are set. When the decision tree optimization goal reaches the preset convergence condition, further tree splitting stops, completing the decision tree construction.

[0050] N independent decision trees are integrated to form an ensemble model. Specifically, ensemble learning methods, such as random forest or extra-tree regression, are used to combine the predictions of multiple decision trees. For each input data point, the ensemble model combines the predictions of the N decision trees by voting or averaging to generate a final prediction.

[0051] This step uses homogenous sample data to construct N decision trees that meet convergence criteria. These trees are then integrated to generate a performance prediction model. This model accurately predicts coating performance based on input basic coating information, providing a scientific basis and support for coating performance optimization.

[0052] Furthermore, the determination of the failure mechanism diagram also includes: traversing the homologous samples to locate the sample failure points; clustering the sample failure points based on the failure location and failure driving force to determine multiple cluster clusters; traversing the multiple cluster clusters, pruning them based on the preset number of clusters, and determining effective hierarchical clustering results; and mining the failure mechanism diagram based on the effective hierarchical clustering results.

[0053] Specifically, historical sample data similar to the current coating's basic information is extracted from a homologous sample library. The failure point of each sample is determined, that is, the specific location or link where the coating has problems during use.

[0054] Cluster analysis is performed on failure points with similar characteristics based on their location and failure driving forces. Cluster analysis identifies multiple clusters, each containing similar failure points. The failure location refers to the specific physical location or system component where the failure occurred. The failure driving force is the root cause or factor that leads to the failure, such as material fatigue, design flaws, and environmental factors.

[0055] Based on pre-set criteria (such as the number of samples within each cluster), the clustering results are pruned to remove unimportant or noisy data. Valid clustering results are retained to form a hierarchical clustering structure. In other words, when the number of samples within a cluster falls below a certain threshold, the cluster is considered insufficiently significant or valid and needs to be pruned. Based on the valid hierarchical clustering results, the failure mechanism of each cluster is analyzed. The failure mechanism corresponding to each cluster is determined, forming the preliminary structure of the failure mechanism diagram.

[0056] A failure mechanism diagram is a graphical representation used to demonstrate the cause-effect relationships and paths of product or system failure. Leveraging data mining techniques, key information, such as failure modes, causes, and influencing factors, is extracted from valid hierarchical clustering results to construct a failure mechanism diagram. This intuitive presentation, through charts, flow charts, and other formats, helps engineers and designers quickly understand the root causes of failures and possible solutions.

[0057] This step utilizes homogenous sample data to locate failure points and perform cluster analysis, ultimately uncovering and generating a failure mechanism diagram. This process provides detailed failure cause analysis and mitigation measures for coating performance optimization, thereby improving the overall performance and reliability of the coating.

[0058] Furthermore, mining the failure mechanism diagram based on the effective hierarchical clustering result also includes: mining failure mechanisms based on the effective hierarchical clustering result, wherein the failure mechanisms correspond one-to-one to cluster clusters; traversing the failure mechanisms to determine failure mitigation characteristics, wherein the failure mitigation characteristics are defined based on failure driving forces; mapping the failure mechanism-failure driving force-failure mitigation characteristics, determining multiple mechanism sequences and performing occasional associations to generate the failure mechanism diagram.

[0059] Specifically, based on the results of effective hierarchical clustering, we conduct an in-depth analysis of the characteristics and content of each cluster. We identify the specific failure mechanisms within each cluster, specifically the failure points within each cluster that share a common failure cause and process. We conduct a detailed analysis of each cluster to identify the specific mechanisms that lead to failure, such as material wear, corrosion, and thermal stress. We document and categorize each failure mechanism to ensure a comprehensive understanding of the failure causes within each cluster.

[0060] Further analyze each failure mechanism to identify features or measures that can mitigate or delay failure. Based on the failure driving force, determine corresponding mitigation features. For example, mechanical wear failures can be mitigated by increasing material hardness or applying lubricants. Record and categorize each failure mitigation feature to ensure that appropriate mitigation measures are available for each failure mechanism.

[0061] Map each failure mechanism to its corresponding failure driving force to identify the primary driver of failure. Map each failure mechanism to its corresponding failure mitigation feature to identify mitigation measures. Form multiple mechanism sequences, each consisting of a failure mechanism, a failure driving force, and a failure mitigation feature. Analyze the relationships between mechanism sequences to identify interrelated mechanisms and features, ensuring a comprehensive understanding of the failure process.

[0062] Visualize all mechanism sequences and create a failure mechanism diagram. The failure mechanism diagram should demonstrate the specific process, driving forces, and mitigation characteristics of each failure mechanism, and clearly indicate the relationships between the mechanisms. Ensure the accuracy and comprehensiveness of the failure mechanism diagram, providing a clear framework for demonstrating coating failure modes and optimization options. Use the mechanism diagram to guide the development and implementation of coating performance optimization strategies.

[0063] This step leverages the results of effective hierarchical clustering to deeply explore the coating's failure mechanism, identify failure mitigation characteristics, and generate a detailed failure mechanism diagram. This failure mechanism diagram not only illustrates the cause and process of coating failure but also provides specific mitigation measures, providing a scientific basis and guidance for optimizing coating performance.

[0064] Furthermore, determining the performance prediction result in combination with the performance prediction model also includes: identifying the pre-optimized coating information, randomly matching a first number of decision trees based on the performance prediction model, performing parallel decision analysis, and determining M decision results; traversing the M decision results, screening the results and calculating the mean based on a preset discreteness, and determining the performance prediction result; based on the expected performance standard, mapping and differential measurement are performed with the performance prediction result to determine the performance optimization target.

[0065] Specifically, pre-optimized coating information, including the mixing ratio of nanomaterials, coating process, and coating process details, is read from a database or preset parameter set. This information is used as input to prepare for performance prediction analysis.

[0066] From the constructed decision tree model, a first number of decision trees are randomly selected for parallel decision analysis. This involves running multiple decision trees simultaneously for predictive analysis to improve the model's prediction accuracy and stability. The pre-optimized coating information is then input into each selected decision tree for parallel predictive analysis. Each decision tree runs independently, generating a prediction result. Together, these M decision results form a collection of prediction results from the multiple independent decision trees.

[0067] The M decision results are traversed and filtered according to a preset discreteness threshold to remove outliers or results with large discrepancies. The filtered decision results are averaged to obtain the final performance prediction. Average calculation can smooth the impact of individual outliers on the overall prediction result, improving the stability and accuracy of the prediction result.

[0068] Map and compare performance predictions against expected performance standards to identify discrepancies. Quantify these discrepancies and identify specific performance parameters that require optimization. This measurement provides a clear direction and goal for subsequent optimization. Based on the results of the differential measurement, determine performance optimization goals and identify specific areas and metrics that require improvement. Performance optimization goals should be specific and quantifiable to facilitate subsequent optimization implementation and effectiveness evaluation.

[0069] This step combines the performance prediction model with pre-optimized coating information to conduct parallel decision analysis, screen and calculate the mean of the predicted results, map them to the expected performance standards, and measure the difference, ultimately determining a clear performance optimization target. This process ensures the scientific and feasible optimization target and provides a solid foundation for further improving coating performance.

[0070] Furthermore, the hierarchical multi-objective optimization search also includes: identifying the pre-optimized coating information, determining the hierarchical finite element optimization target, the hierarchical finite element optimization target is an iterative optimization variable, including at least one optimization dimension layer and at least one optimization target within the dimension; based on the hierarchical finite element optimization target, a first optimization strategy set is determined using target-based variation and crossover as the optimization method; iterative optimization is performed until the maximum number of iterations is met, and the global optimal strategy is selected as the target optimization strategy.

[0071] Specifically, the pre-optimized coating information is read from a database or preset parameter set, including the mixing ratio of nanomaterials, coating process, and detailed information of the coating process. This information is used as input to prepare for hierarchical multi-objective optimization. Based on the pre-optimized coating information, the optimization goals are determined, and these goals are set hierarchically to gradually optimize each dimension. The optimization goals at each level can include one or more specific performance indicators, such as hardness, wear resistance, adhesion, etc. Set the variables that need to be optimized, and these variables will be iteratively adjusted during the optimization process to gradually approach the optimal solution. Variables can include material ratios, coating parameters, curing conditions, etc.

[0072] A goal-based mutation and crossover method, an operation in the genetic algorithm, is used to generate new optimal solutions. Existing solutions are randomly modified to explore new solution spaces. New solutions are generated by combining partial features of two solutions. The mutation and crossover operations generate a first set of optimization strategies, which serve as initial solutions for subsequent optimization iterations.

[0073] In each iteration, mutation and crossover operations are performed on the current set of optimization strategies to generate new optimization strategies. The performance of each new strategy is evaluated, the optimal strategy is selected, and the optimization strategy set is updated. A maximum number of iterations is set, and the iteration process continues until the maximum number of iterations is reached or another convergence condition is met, such as performance indicators meeting the expected standards. During the iteration process, the performance of each optimization strategy is continuously evaluated, and the strategy with the best performance is selected as the global optimal strategy. The global optimal strategy is then used as the final target optimization strategy to guide coating performance optimization in actual production processes.

[0074] This step utilizes a hierarchical multi-objective optimization approach, combining pre-optimized coating information with performance prediction models. Mutation and crossover operations are performed to gradually generate and screen optimization strategies, ultimately determining the global optimal strategy. This process ensures the scientific and feasible nature of the optimization strategy, providing strong support for comprehensively improving coating performance.

[0075] Furthermore, the method further includes: setting an optimization degree threshold; if the optimization degree of the optimization strategy is greater than the optimization degree threshold, performing taboo locking on the optimization method corresponding to the optimization strategy, and setting a preset number of iterations as a taboo unlocking method.

[0076] Specifically, the optimization degree of each optimization strategy is calculated using performance indicators. These indicators can include specific coating performance parameters such as hardness, wear resistance, and adhesion. The optimization degree is typically a comprehensive metric used to assess the overall effectiveness of each strategy. Based on historical data and optimization goals, a threshold is set to distinguish between high-performing strategies and those requiring further optimization.

[0077] In each iteration, all optimization strategies are evaluated and their optimization degree is calculated. If the optimization degree of an optimization strategy exceeds the preset optimization degree threshold, the strategy is taboo-locked. The taboo-locked strategy will no longer participate in mutation and crossover operations in subsequent iterations to maintain its current excellent performance.

[0078] Set a preset number of iterations as the condition for tabu unlocking. After reaching the preset number of iterations, the tabu-locked strategy is unlocked and can re-engage in mutation and crossover operations. The preset number of iterations should be appropriately set based on the complexity and goals of the optimization process. This number should be large enough to ensure that the tabu-locked strategy maintains its excellent performance during the locking period, but not too large to avoid missing opportunities for further optimization.

[0079] This step can effectively control the strategy quality during the optimization process by setting the optimization threshold and taboo locking mechanism, preventing premature convergence. At the same time, the taboo locking strategy is unlocked by presetting the number of iterations to ensure the continuity and comprehensiveness of the optimization process, thereby finding the optimal coating performance optimization strategy.

[0080] Furthermore, the method also includes: determining a fuzzy decision function for determining the degree of optimization, wherein the fuzzy decision function is used to determine the degree of optimization in the iterative optimization process; performing performance prediction verification based on the target optimization strategy and the performance prediction model, and generating iterative optimization instructions if the performance optimization criteria are not met.

[0081] Specifically, fuzzy logic is used to address uncertainty in the optimization process, defining fuzzy sets and membership functions. A fuzzy decision function is designed to comprehensively evaluate multiple performance indicators, such as hardness, wear resistance, and adhesion. The function inputs include the measured values ​​of each performance indicator, and the output is a fuzzy evaluation of the degree of optimization. The actual values ​​of each performance indicator are input into the fuzzy decision function to calculate the degree of optimization. The resulting degree of optimization is then used to evaluate the effectiveness of the current optimization strategy.

[0082] Combined with the performance prediction model, the performance of the identified target optimization strategy is predicted. The performance prediction model inputs the parameters of the target optimization strategy and predicts the coating's performance. The predicted results are compared with the preset performance optimization criteria to confirm whether the strategy meets the requirements. If the predicted results meet or exceed the performance criteria, the strategy is considered effective. If the predicted results do not meet the performance criteria, further optimization is required.

[0083] If the performance prediction verification fails, meaning the target optimization strategy does not meet the performance optimization criteria, iterative optimization instructions are generated. These instructions include the optimization variables that need to be adjusted and the recommended adjustment directions. Specific instructions include resetting material ratios and adjusting process parameters. Based on the iterative optimization instructions, the optimization strategy is adjusted and the optimization iteration is repeated. Optimization degree determination and performance prediction verification continue until an optimization strategy that meets the criteria is found.

[0084] This step uses a fuzzy decision function to determine the degree of optimization, combined with a performance prediction model for verification, and generates iterative optimization instructions if the criteria are not met. This process ensures the scientific and feasible optimization strategy, ultimately finding the optimal coating performance optimization solution.

[0085] In summary, the method for optimizing the performance of nanomaterial wear-resistant coatings provided by the embodiments of the present application has the following technical effects:

[0086] 1. By reading the basic coating information and combining it with homologous samples, a performance prediction model based on extra tree regression is constructed to achieve accurate prediction of coating performance, thereby providing a scientific basis to guide the optimal design of the coating.

[0087] 2. Conduct coating performance failure analysis based on homologous sample data, determine the failure mechanism diagram and failure mitigation characteristics, systematically identify and address coating failure causes, and improve coating durability and stability.

[0088] 3. By combining the performance prediction model and failure mechanism diagram, an optimization decision module is constructed to conduct hierarchical multi-objective optimization. Optimization is carried out from multiple dimensions such as composite coating, process modification and material ratio to ensure comprehensive improvement of coating performance.

[0089] 4. Set the optimization threshold, lock the efficient strategies, and unlock them through the preset number of iterations to avoid local optimality, improve the global optimization effect, and ensure the diversity and comprehensiveness of strategies in the optimization process.

[0090] 5. Use fuzzy decision functions to determine the degree of optimization, and combine them with performance prediction models to verify performance predictions. If the performance optimization standards are not met, generate iterative optimization instructions to ensure the scientificity and accuracy of the optimization process.

[0091] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0092] Furthermore, the terms "first" or "second" as described above may not only represent an order relationship but may also represent a specific concept and / or refer to the selection of multiple elements individually or collectively. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, if such modifications and variations fall within the scope of this application and its equivalents, this application is intended to include such modifications and variations.

Claims

1. A method for optimizing the performance of nanomaterial wear-resistant coatings, characterized in that: The method comprises: Reading basic coating information, wherein the basic coating information at least includes a nano-mixing ratio and process information, wherein the process information includes a coating process and a coating process; Based on the basic coating information, homologous sample retrieval and calling are performed to construct a performance prediction model, wherein the performance prediction model is constructed based on the extra tree regression principle and the output mean is the prediction result; Based on the homologous samples, a coating performance failure analysis is performed to determine a failure mechanism diagram, wherein the failure mechanism diagram is marked with a failure mitigation feature. The failure mechanism diagram shows the evolution of the coating from a normal state to a failure state, as well as the key influencing factors and failure mitigation features at each stage. The failure mitigation features refer to features that can delay or prevent the occurrence of failure, including specific nanomaterial additions, optimized preparation process parameters, and enhanced interfacial bonding strength. Assisting the failure mechanism diagram to construct an optimization decision module, that is, mapping the key influencing factors and failure mitigation characteristics in the failure mechanism diagram to the data structure of the optimization decision module, and establishing a communication connection between the optimization decision module and the performance prediction model, wherein the optimization decision module is an intelligent system based on algorithms and rules, which automatically generates decision recommendations for coating performance optimization based on the output of the performance prediction model, the analysis results of the failure mechanism diagram, and the preset optimization goals; Read the pre-optimized coating information, determine the performance prediction results in combination with the performance prediction model, and transmit them to the optimization decision module for hierarchical multi-objective optimization to determine the target optimization strategy, wherein the optimization dimensions at least include composite coating, process modification, and material ratio; the hierarchical multi-objective optimization includes: identifying the pre-optimized coating information, determining the hierarchical finite element optimization targets, these targets are set hierarchically to gradually optimize each dimension, the hierarchical finite element optimization target is an iterative optimization variable, including at least one optimization dimension layer and at least one optimization target within the dimension; based on the hierarchical finite element optimization target, determine the first optimization strategy set using target-based variation and crossover as the optimization method; perform iterative optimization until the maximum number of iterations is met, and select the global optimal strategy as the target optimization strategy; Based on the target optimization strategy, coating performance optimization management is carried out for the entire coating operation cycle.

2. The method for optimizing the performance of nanomaterial wear-resistant coating according to claim 1, characterized in that: The constructing of the performance prediction model comprises: Traversing the homologous samples, randomly extracting a preset number of N groups of sample data, where the N groups of sample data have inter-group repetitiveness; Based on the N groups of sample data, constructing N decision trees that meet convergence conditions; The N decision trees are integrated to generate the performance prediction model.

3. The method for optimizing the performance of nanomaterial wear-resistant coating according to claim 1, characterized in that: The determining of the failure mechanism diagram comprises: Traversing the homologous samples to locate sample failure points; Clustering the sample failure points based on failure locations and failure driving forces to determine a plurality of clusters, wherein the failure driving forces are root causes or factors leading to failure, including material fatigue, design defects, and environmental factors; Traversing the plurality of clusters, performing pruning based on a preset number of clusters, and determining a valid hierarchical clustering result; Based on the effective hierarchical clustering results, the failure mechanism graph is mined.

4. A method for optimizing the performance of nanomaterial wear-resistant coatings according to claim 3, characterized in that: Mining the failure mechanism diagram based on the effective hierarchical clustering result includes: Based on the effective hierarchical clustering results, mining failure mechanisms, wherein the failure mechanisms correspond one to one with cluster clusters; Traversing the failure mechanism to determine a failure mitigation characteristic, the failure mitigation characteristic being defined based on a failure driving force; The failure mechanism-failure driving force-failure mitigation characteristics are mapped, multiple mechanism sequences are determined and occasionally correlated, and the failure mechanism diagram is generated, wherein the occasionally correlated indicator indicates the correlation between the various mechanisms.

5. The method for optimizing the performance of nanomaterial wear-resistant coating according to claim 2, characterized in that: Determining a performance prediction result in combination with the performance prediction model includes: Identifying the pre-optimized coating information, randomly matching a first number of decision trees based on the performance prediction model, performing parallel decision analysis, and determining M decision results; Traversing the M decision results, filtering the results and calculating the mean based on a preset discreteness, and determining the performance prediction result; Based on the expected performance standards, mapping and differential measurement are performed with the performance prediction results to determine the performance optimization target.

6. The method for optimizing the performance of nanomaterial wear-resistant coating according to claim 1, characterized in that: An optimization degree threshold is set. If the optimization degree of the optimization strategy is greater than the optimization degree threshold, the optimization method corresponding to the optimization strategy is taboo locked, and a preset number of iterations is set as the taboo unlocking method. Taboo locking means that when the optimization degree of the optimization strategy exceeds the preset optimization degree threshold, it will no longer participate in mutation and crossover operations in subsequent iterations.

7. The method for optimizing the performance of nanomaterial wear-resistant coating according to claim 6, characterized in that: The method further comprises: Determine a fuzzy decision function for determining the degree of optimization, wherein the fuzzy decision function is used to determine the degree of optimization in an iterative optimization process; A performance prediction check is performed based on the target optimization strategy and the performance prediction model. If the performance optimization criteria are not met, an iterative optimization instruction is generated.

Images