Design method of high-toughness coating material and related device

Abstract

The invention discloses a design method of a high-toughness coating material and a related device, and relates to the technical field of surface engineering.The method comprises the steps that target coating material information is obtained; inputting the information of the target coating material into the high-toughness coating material prediction model to obtain mechanical property data corresponding to the target coating material; judging whether the target coating material has high strength and toughness or not according to the mechanical property data, and if yes, reserving the target coating material; the determination process of the high-toughness coating material prediction model comprises the following steps: processing a sample coating material system by using a high-throughput first principle to obtain a final stable crystal structure model and corresponding mechanical property data, and constructing a high-toughness coating material database; and training the high-toughness coating material prediction network based on the high-toughness coating material database to obtain a high-toughness coating material prediction model. According to the method, the coating material with high strength and toughness can be screened out through the high strength and toughness coating material prediction model.

Description

Technical Field

[0001] The present application relates to the field of surface engineering technology, and in particular to a design method and related device for a high-strength and tough coating material. Background Art

[0002] In the field of surface engineering, hard coatings, a crucial protective system for mechanical components, are primarily composed of compounds of transition metals and non-metallic elements. These compounds are typically bonded together through strong chemical bonds, such as metallic, covalent, ionic, or mixed bonds, resulting in extremely high hardness and wear resistance. With the rapid development of high-end equipment manufacturing, aerospace, and precision machining, the performance requirements for hard coatings in industrial applications have shifted from single mechanical specifications to stringent, multi-dimensional requirements: maintaining traditional high hardness and wear resistance while also addressing comprehensive properties such as strength-toughness matching and environmental adaptability. While traditional hard coating materials possess a certain degree of hardness, they are susceptible to defects such as brittle fracture and interlayer delamination under high-speed cutting, extreme temperatures, or complex stress conditions, resulting in reduced machining accuracy, shortened tool life, and increased maintenance costs. While traditional experimental methods have yielded a large number of material systems, the complex nonlinear relationships between composition, structure, and performance make it difficult to overcome bottlenecks in comprehensive material performance through empirical trial-and-error research and development. More efficient cross-scale design methods are urgently needed to shorten the development cycle and cost of new hard coating materials.

[0003] In existing materials computing technologies, most computational processes are still tedious and complex, requiring manual processes. For example, alloy system design requires sequential completion of independent operations such as modeling and physical property simulation. However, as the scale of computational systems expands and the complexity of the processes grows, the time cost will increase significantly, and frequent manual intervention can easily introduce operational errors. Summary of the Invention

[0004] The purpose of this application is to provide a design method and related devices for high-strength and toughness coating materials, which can screen out coating materials with high strength and toughness through a high-strength and toughness coating material prediction model.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a design method for a high-strength and tough coating material, comprising:

[0007] Obtaining target coating material information; the target coating material information includes target coating material system constituent elements and solid solution element ratios;

[0008] Inputting the target coating material information into a high-strength and toughness coating material prediction model to obtain mechanical property data corresponding to the target coating material;

[0009] Judging whether the target coating material has high strength and toughness based on the mechanical property data, and retaining the target coating material if so;

[0010] The process of determining the high-strength and toughness coating material prediction model is as follows:

[0011] The obtained sample coating material system is processed using high-throughput first-principles analysis to obtain the final stable crystal structure model and corresponding mechanical property data;

[0012] Based on the final stable crystal structure model and corresponding mechanical property data, a database of high-strength and tough coating materials is constructed;

[0013] Based on the high-strength and toughness coating material database, a high-strength and toughness coating material prediction network is trained to obtain the high-strength and toughness coating material prediction model.

[0014] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for designing a high-strength and tough coating material.

[0015] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for designing a high-strength and tough coating material.

[0016] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above-mentioned method for designing a high-strength and tough coating material.

[0017] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0018] The present application provides a design method and related device for high-strength and tough coating materials, the method comprising obtaining target coating material information; inputting the target coating material information into a high-strength and tough coating material prediction model to obtain mechanical property data corresponding to the target coating material; judging whether the target coating material has high strength and toughness based on the mechanical property data, and retaining the target coating material if so; the process of determining the high-strength and tough coating material prediction model is as follows: using high-throughput first-principles to process the obtained sample coating material system to obtain a final stable crystal structure model and corresponding mechanical property data; constructing a high-strength and tough coating material database based on the final stable crystal structure model and the corresponding mechanical property data; training a high-strength and tough coating material prediction network based on the high-strength and tough coating material database to obtain a high-strength and tough coating material prediction model. The present application combines high-throughput first-principles calculations with machine learning models, and can greatly improve the research and development efficiency, accuracy and cost-effectiveness of high-strength and tough coating materials by combining precise physical data with machine learning models, breaking through the limitations of the traditional "trial and error method", and significantly shortening the research and development cycle and development cost of new coating materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is an application environment diagram of the design method for a high-strength and tough coating material in Example 1;

[0021] Figure 2 A schematic flow chart of a method for designing a high-strength and tough coating material provided in Example 1;

[0022] Figure 3 Ti in Example 2 0.5 Al 0.5 Schematic diagram of all possible crystal structure models of N;

[0023] Figure 4 This is a schematic diagram of the hardness prediction results of the nitride coating material in Example 4;

[0024] Figure 5 A schematic diagram of the structure of a computer device provided in Example 5. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0027] The design method of the high-toughness coating material provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the target coating material information to the server 104. After receiving the target coating material information, the server 104 inputs it into the high-strength and toughness coating material prediction model to obtain the mechanical property data corresponding to the target coating material; based on the mechanical property data, it is determined whether the target coating material has high strength and toughness. If so, the target coating material is retained. The server 104 can feedback the obtained high-strength and toughness coating material to the terminal 102.

[0028] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, and IoT devices. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or a cloud server.

[0029] Example 1

[0030] In an exemplary embodiment, Figure 2 As shown, a design method for a high-strength and tough coating material is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 Taking the server 104 in FIG. 1 as an example, the method includes the following steps 201 to 203. In which:

[0031] Step 201 : obtaining target coating material information; the target coating material information includes target coating material system constituent elements and solid solution element ratios.

[0032] Step 202: Input the target coating material information into the high-strength and toughness coating material prediction model to obtain mechanical property data corresponding to the target coating material.

[0033] Step 203: judging whether the target coating material has high strength and toughness based on the mechanical property data, and retaining the target coating material if so.

[0034] Among them, the determination process of the high-strength and toughness coating material prediction model is as follows:

[0035] The obtained sample coating material system is processed using high-throughput first-principles to obtain the final stable crystal structure model and corresponding mechanical property data.

[0036] Based on the final stable crystal structure model and the corresponding mechanical properties data, a high-strength and toughness coating material database is constructed.

[0037] Based on the high-strength and toughness coating material database, the high-strength and toughness coating material prediction network is trained to obtain a high-strength and toughness coating material prediction model.

[0038] By implementing steps 201 to 203 above, this application combines high-throughput first-principles calculations with machine learning models. By combining precise physical data with machine learning models, it can significantly improve the efficiency, accuracy, and cost-effectiveness of the research and development of high-strength and tough coating materials, breaking through the limitations of traditional "trial and error" methods and significantly shortening the research and development cycle and development costs of new coating materials. In addition, further in-depth integration with machine learning technology can form a closed-loop design system of "computationally generated data-data-driven optimization" to achieve accurate prediction and rapid screening of coating material properties.

[0039] Furthermore, the high-throughput first-principles calculation refers to the integration and automation of the calculation process through computer codes such as Bash, Python, C / C++ and Java. In the present application, the calculation process includes: construction of a crystal structure model, structural optimization of the model, and calculation of mechanical properties. Specifically, when the obtained sample coating material system (i.e., the alloy system to be screened) is processed using high-throughput first-principles, a final stable crystal structure model and corresponding mechanical property data are obtained, including: constructing all possible initial crystal structure models corresponding to the sample coating material system according to the obtained sample coating material system, that is, there are multiple initial crystal structure models; based on a first threshold value of a preset calculation accuracy control parameter, the initial crystal structure model is optimized in the first stage to obtain a crystal structure model optimized in the first stage and corresponding energy information, and based on the energy information corresponding to the crystal structure model optimized in the first stage, an initial stable crystal structure model is screened; based on a second threshold value of a preset calculation accuracy control parameter, the initial stable crystal structure model is optimized in the second stage to obtain a crystal structure model optimized in the second stage and corresponding energy information, and based on the energy information corresponding to the crystal structure model optimized in the second stage, a final stable crystal structure model is screened; and the final stable crystal structure model is calculated using a mechanical property calculation method to obtain mechanical property data corresponding to the final stable crystal structure model. The automated management mentioned above refers to high-throughput automatic submission and real-time monitoring of tasks, automated screening of thermodynamically stable structures, batch submission of mechanical property calculation tasks and monitoring of task progress, and screening of high-strength and toughness mechanical performance data.

[0040] Furthermore, the sample coating material system includes carbides, nitrides, borides, and metal coatings; and this application has no special requirements for the types and contents of other elements in carbides, nitrides, borides, and metal coating materials, including all elements in the periodic table and element proportions of 0-100%. Among them, the structural models of carbides, nitrides, borides, and common titanium-based, nickel-based, and other metal coatings are matrix material structural models, and all possible initial crystal structure models are constructed by dissolving elements in the matrix material structural model and traversing the position of the dissolved elements in the matrix material crystal structure.

[0041] Furthermore, in the process of structural optimization of the initial crystal structure model until the final stable crystal structure model is obtained, the structural optimization is specifically achieved by using density functional theory. First, based on a preset first threshold value of a calculation accuracy control parameter, the initial crystal structure model is optimized in the first stage to obtain a crystal structure model optimized in the first stage and corresponding energy information. Specifically, the optimization includes: optimizing the crystal structure model before optimization based on the first threshold value of the calculation accuracy control parameter to obtain an optimized crystal structure model and corresponding energy information; the crystal structure model before optimization is any initial crystal structure model before optimization; determining whether the atomic force value in the optimized crystal structure model is less than the preset first threshold value; if so, obtaining the crystal structure model optimized in the first stage and corresponding energy information; if not, returning to the step of "optimizing the crystal structure model before optimization based on the first threshold value of the calculation accuracy control parameter to obtain an optimized crystal structure model and corresponding energy information". Then, based on the energy information corresponding to the crystal structure model optimized in the first stage, the crystal structure model corresponding to the minimum energy information is screened and the crystal structure model corresponding to the minimum energy information is used as the initial stable crystal structure model. The more negative the energy information corresponding to the crystal structure model, the better its stability.

[0042] In addition, the second-stage optimization process of the crystal structure model and the basis for screening to obtain the final stable crystal structure model are the same as the first-stage optimization process and the basis for screening to obtain the initial stable crystal structure model; that is, based on the second threshold value of the preset calculation accuracy control parameter, the crystal structure model before optimization is optimized to obtain the optimized crystal structure model and the corresponding energy information; at this time, the crystal structure model before optimization is the initial stable crystal structure model before optimization; it is determined whether the atomic force value in the optimized crystal structure model is less than the preset second threshold value; if so, the crystal structure model after the second-stage optimization and the corresponding energy information are obtained; if not, the optimization is continued. And based on the energy information corresponding to the crystal structure model after the second-stage optimization, the crystal structure model corresponding to the minimum energy information is screened, and the crystal structure model corresponding to the minimum energy information is used as the final stable crystal structure model.

[0043] Furthermore, the high-throughput first-principles calculation software is preferably commercial and open-source software such as VASP, Materials Studio, Quantum Espresso, and more preferably VASP software. The present application has no special restrictions on the calculation accuracy control parameters used for structural optimization of the crystal structure model. The calculation accuracy control parameters can be adjusted accordingly according to different material systems and convergence tests. In the present application, the calculation accuracy control parameters include K-point density, cutoff energy, energy and force convergence criteria (i.e., the convergence threshold of atomic force), etc.; the first threshold of the preset calculation accuracy control parameters is preferably K-point density of (a is the lattice constant), cutoff energy ≥ 350eV, energy 10 -5 ~10 - 6eV / atom and the force convergence criterion is More preferably, the K-point density is 6×6×6, the cutoff energy is 400 eV, and the -5 Energy in eV / atom and The force convergence criterion can satisfy the structural optimization calculation of most coating material systems.

[0044] Furthermore, the mechanical property calculation method includes the stress-strain method, the energy-strain method and the direct calculation method, and the stress-strain method with simple calculation steps and high result accuracy is preferred. In the present application, the mechanical property calculation process requires high-precision structural optimization. Therefore, the second threshold value of the preset calculation accuracy control parameter selects a denser K-point grid and a higher cutoff energy, etc. In the present application, the second threshold value of the preset calculation accuracy control parameter is preferably a K-point density ≥ 18×18×18, a cutoff energy ≥ 400eV, and more preferably a K-point density of 20×20×20 and a cutoff energy of 500eV. The mechanical property calculation process needs to set a plurality of strain numbers and strain amplitudes. There is no special limitation on the strain number and strain amplitude. The more strain numbers, the higher the calculation accuracy, but the corresponding calculation time is also longer. In the present application, the strain number is preferably 7, and the strain amplitude is preferably This application focuses on the first-principles calculation of the mechanical properties of coating materials. Different convergence standards have a huge impact on the final mechanical property calculation results. Selecting a high convergence accuracy can ensure the accuracy of the calculation results.

[0045] In addition, the coating material system also needs to consider the magnetic material alloy system. The structural optimization of the magnetic material alloy system also needs to consider the influence of calculation accuracy control parameters such as spin and atomic magnetic moment. In this application, the calculation software is preferably VASP software. For the magnetic material alloy system, the ISPIN parameter is set to 2, and the MAGMOM parameter is set according to the magnetic atomic magnetic moment value.

[0046] Furthermore, the establishment of the high-strength and toughness coating material database requires the integration of relevant information of the coating material system, and the data is structured and stored after screening based on stability standards. In this application, the relevant information of the coating material system includes specific composition, lattice parameters, space groups, mechanical properties data (elastic constants, bulk modulus, Young's modulus, shear modulus and Poisson's ratio, etc.); the structured storage of the data includes standardized formats such as JSON and CSV. In this application, the screening criteria for the high-strength and toughness coating material database must meet the following conditions: formation energy is less than 0; C 11 -C 12 >0,C 11 +2C 12 >0,C 44 >0(C 11 、C 12 、C 44 is the elastic constant of the coating material). The structured storage of the data includes standardized formats such as JSON and CSV.

[0047] Furthermore, the machine learning screening and prediction process includes: pre-processing of the high-strength and toughness coating material database, model training and optimization, and high-performance material design and prediction. This application will perform pre-processing operations on the constructed high-strength and toughness coating material database to obtain a pre-processed high-strength and toughness coating material database. The pre-processing operations include Pearson correlation coefficient analysis, data segmentation, and normalization operations to meet the data format required by the subsequent machine learning algorithm.

[0048] Furthermore, the training and optimization of the high-strength and toughness coating material prediction model includes the following contents: composition-performance mapping, structure-performance prediction and balance between multi-objective optimization. In this application, interpretable symbolic expressions are established by using algorithms such as SISSO, random forest (RF) and gradient boosting tree (XGBoost), thereby realizing the mapping relationship between composition and performance; graph neural network (GNN), convolutional neural network (CNN) and other algorithms are used to process crystal structure diagrams to capture the interaction between atoms to achieve structure-to-performance prediction; and algorithms such as NSGA-II, MOEA / DD are used to balance conflicting indicators such as hardness, toughness and cost. In this application, the reverse design and prediction of high-performance materials generate coating candidates for a variety of high-performance materials through machine learning and perform high-throughput computational verification on the generated candidates. This application samples in the composition-process space through the trained machine learning model, and outputs materials that meet the mechanical properties database standards as coating candidates for high-performance materials. The generated candidates are screened again in combination with the high-throughput first-principle calculation code, and the new data is fed back to the model for retraining, forming a "computational prediction → experimental verification → data update" closed loop.

[0049] Example 2

[0050] The high-throughput first-principles calculation method for the design of high-strength and tough coating materials, which uses nitride as the matrix material structure model, consists of the following steps:

[0051] Step (1) executes the high-throughput first-principles calculation code, and inputs the calculated alloy system elements and the corresponding solid solution ratios in the command line interactive interface in sequence according to the prompts. Taking the ternary TiAlN nitride coating material as an example, input Ti, Al, N and 0, 0.25, 0.5, 0.75, 1 in sequence, and then the code will automatically traverse all possible occupancy situations of the solid solution elements in the atomic structure of the matrix material, and then construct all possible crystal structure models. Taking Ti0.5Al0.5N as an example, the crystal structure model of all possible occupancy situations in the atomic structure is shown in the figure below. Figure 3 shown.

[0052] Step (2) is to optimize the crystal structure model obtained in step (1) based on the VASP first principle calculation software. The calculation accuracy control parameters are controlled by a unified standard to improve the comparability of the data, while satisfying the convergence of most material systems. The calculation accuracy control parameters are selected as follows: K point density is 6×6×6, cutoff energy is 400eV, and the energy convergence standard of two adjacent iterations is 10 -5 The convergence criteria for eV / atom and the forces per atom are Crystal structure optimization tasks are submitted in batches by the code and monitored in real time.

[0053] Step (3) After the structural optimization calculation process is completed, a static calculation is performed on the initial stable crystal structure model obtained by optimization (with fixed atomic positions). The convergence standard of the calculation accuracy control parameters is consistent with the structural optimization process. After the static calculation is completed, energy information is extracted to screen for thermodynamically stable structures. The more negative the energy information of the crystal structure model, the better the thermodynamic stability. Taking Bash code as an example, the code can extract the energy information of the static calculation results through the command "grep entropy = OUTCAR | grep -oP'\d*\.\d+' | head-1".

[0054] Step (4) requires a more accurate convergence standard for mechanical property calculations. The K-point density is adjusted to 20×20×20 and the cutoff energy is increased to 500eV. The stress-strain method with simple steps and high result accuracy is used for calculations. The code generates -0.015, -0.01, -0.005, 0, 0.005, 0.01, 7 different strain amplitudes are calculated and submitted in batches. After the calculation is completed, the code calls the vaspkit program to post-process the results and filter the calculated data according to the mechanical performance standards, finally obtaining the high-strength and toughness coating material data.

[0055] Example 3

[0056] The only difference between Example 3 and Example 2 is that the coating material system contains magnetic elements. Therefore, during the structural optimization and mechanical property calculation process, it is necessary to enable spin and set the magnetic moment. All other changes are the same as in Example 2. Taking the TiCoN ternary nitride coating material containing the magnetic element Co as an example, the following changes are made to the calculation parameter modification and element magnetic moment setting: the spin-enabling ISIF parameter is changed from 1 to 2; based on the Co atomic magnetic moment value, the MAGMOM parameter is added, and the magnetic moment value will change during the crystal structure optimization process and should be adjusted accordingly.

[0057] The test data calculated according to the methods of Examples 2 and 3 are shown in Tables 1 and 2.

[0058] Table 1 Some ternary Ti 1-x M x N system coating material Young's modulus, elastic modulus, shear modulus, Poisson's ratio and other toughness data

[0059]

[0060]

[0061] Table 2 Some ternary Ti containing magnetic elements 1-x M x N system coating material Young's modulus, elastic modulus, shear modulus, Poisson's ratio and other toughness data

[0062]

[0063]

[0064] Example 4

[0065] After obtaining a database of high-strength and tough coating materials, a preliminary screening and prediction process using the random forest (RF) algorithm is performed for machine learning, which consists of the following steps:

[0066] Step (1), data import: After obtaining a database of high-strength and tough coating materials stored in CSV format through high-throughput first-principles calculations, the read_csv function in the pandas library is used to read the CSV file and load it into a pandas dataFrame to facilitate subsequent data analysis and processing.

[0067] Step (2), data processing: using atomic ratio, thermodynamic parameters, geometric parameters and electronic structure parameters as input variables, and Vickers hardness and Poisson's ratio as output variables, the database is subjected to Pearson correlation coefficient analysis, and strong correlation features (i.e., Pearson correlation coefficient greater than 0.95) are removed; the data set is divided into a training set and a test set using the train_test_split function, where the test set accounts for 10% of the total data set and the remaining 90% is the training set.

[0068] Step (3), model training and optimization: A high-strength and tough coating material prediction model was constructed using the random forest (RF) algorithm, and the RepeatedKFold class was imported. The model's hyperparameters (i.e., n_estimators, max_depth, min_samples_split, min_samples_leaf, and max_features) were optimized through 10-fold cross-validation. During the 10-fold cross-validation process, the training set was divided into 10 small sets, one of which was used for validation and the remaining nine for training. During cross-validation, a mean absolute error (MAE) was generated for each cycle, and the MAEs of all cycles were then averaged to obtain a comprehensive evaluation of the overall performance of the model.

[0069] In step (4), the model with the best parameters (i.e., the lowest MAE) is selected, and the machine learning model is trained to predict the mechanical properties of the nitride coating material. The hardness prediction results of the nitride coating material are as follows: Figure 4 shown.

[0070] In summary, the above embodiment is based on a method for obtaining the mechanical properties of materials by high-throughput first-principles calculations. Using a high-throughput computing code, the coating material is first modeled, and the model is thoroughly optimized and calculated. The thermodynamically stable structural model is screened out, and the mechanical properties of the structural model are subsequently calculated using the stress-strain method. Finally, the data is screened according to the mechanical performance indicators. The crystal structure model that meets the requirements will be used to establish a subsequent database and help discover potential new hard coating materials. The method provided in this application can save time and improve computing efficiency. At the same time, by combining quantitative calculations with data-driven methods, it breaks through the limitations of the traditional "trial and error method" and can significantly shorten the research and development cycle and development costs of new coating materials.

[0071] Example 5

[0072] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a design method for a high-strength and toughness coating material is realized.

[0073] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0074] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0075] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0076] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0077] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0078] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0079] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A design method for a high-strength and tough coating material, characterized in that: The design method of the high-toughness coating material includes: Obtaining target coating material information; the target coating material information includes target coating material system constituent elements and solid solution element ratios; Inputting the target coating material information into a high-strength and toughness coating material prediction model to obtain mechanical property data corresponding to the target coating material; Judging whether the target coating material has high strength and toughness according to the mechanical property data, and retaining the target coating material if so; The process of determining the high-strength and toughness coating material prediction model is as follows: The obtained sample coating material system is processed using high-throughput first-principles analysis to obtain the final stable crystal structure model and corresponding mechanical property data; Based on the final stable crystal structure model and corresponding mechanical property data, a database of high-strength and tough coating materials is constructed; Based on the high-strength and toughness coating material database, a high-strength and toughness coating material prediction network is trained to obtain the high-strength and toughness coating material prediction model.

2. The design method of high-toughness coating material according to claim 1, characterized in that: The obtained sample coating material system is processed using high-throughput first-principles methods to obtain the final stable crystal structure model and corresponding mechanical property data, including: According to the obtained sample coating material system, constructing an initial crystal structure model corresponding to the sample coating material system; the initial crystal structure model is multiple; Based on a first threshold value of a preset calculation accuracy control parameter, the initial crystal structure model is optimized in the first stage to obtain a crystal structure model optimized in the first stage and corresponding energy information, and an initial stable crystal structure model is screened based on the energy information corresponding to the crystal structure model optimized in the first stage; Based on a second threshold value of a preset calculation accuracy control parameter, the initial stable crystal structure model is optimized in the second stage to obtain a crystal structure model optimized in the second stage and corresponding energy information, and the final stable crystal structure model is screened based on the energy information corresponding to the crystal structure model optimized in the second stage; The final stable crystal structure model is calculated using a mechanical property calculation method to obtain mechanical property data corresponding to the final stable crystal structure model.

3. The design method of the high-toughness coating material according to claim 2, characterized in that: According to the obtained sample coating material system, an initial crystal structure model corresponding to the sample coating material system is constructed, specifically including: The occupation of the solid solution elements in the obtained sample coating material system within the crystal structure of the base material is traversed to obtain an initial crystal structure model corresponding to the sample coating material system.

4. The design method of the high-toughness coating material according to claim 2, characterized in that: Based on the first threshold value of the preset calculation accuracy control parameter, the initial crystal structure model is optimized in the first stage to obtain the crystal structure model after the first stage optimization and the corresponding energy information, specifically including: Based on a first threshold value of a preset calculation accuracy control parameter, the crystal structure model before optimization is optimized to obtain an optimized crystal structure model and corresponding energy information; the crystal structure model before optimization is any initial crystal structure model when not optimized; Determining whether the atomic force value in the optimized crystal structure model is less than the first threshold; If so, the crystal structure model after the first stage optimization and the corresponding energy information are obtained; if not, return to the step "based on the first threshold of the preset calculation accuracy control parameter, the crystal structure model before optimization is optimized to obtain the optimized crystal structure model and the corresponding energy information".

5. The design method of high-toughness coating material according to claim 2, characterized in that: According to the energy information corresponding to the crystal structure model optimized in the first stage, the initial stable crystal structure model is screened, including: According to the energy information corresponding to the crystal structure model after the optimization in the first stage, the crystal structure model corresponding to the minimum energy information is screened and obtained, and the crystal structure model corresponding to the minimum energy information is used as the initial stable crystal structure model.

6. The design method of high-toughness coating material according to claim 1, characterized in that: The sample coating material systems include carbides, nitrides, borides, and metal coatings.

7. The design method of high-toughness coating material according to claim 1, characterized in that: Based on the high-strength and tough coating material database, a high-strength and tough coating material prediction network is trained to obtain the high-strength and tough coating material prediction model, specifically including: Performing a preprocessing operation on the high-strength and toughness coating material database to obtain a preprocessed high-strength and toughness coating material database; the preprocessing operation includes a Pearson correlation coefficient analysis operation, a data segmentation operation, and a normalization operation; The high-strength and tough coating material prediction network is trained using the preprocessed high-strength and tough coating material database to obtain the high-strength and tough coating material prediction model; the high-strength and tough coating material prediction network includes a random forest algorithm, a support vector machine algorithm or a deep learning algorithm.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for designing a high-strength and tough coating material according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for designing a high-strength and tough coating material according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for designing a high-strength and tough coating material according to any one of claims 1 to 7 is implemented.

Images