An aero-engine wheel disc plasma spraying repair process parameter optimization method, system, electronic device, medium and product

Abstract

The application discloses an aero-engine wheel disc plasma spraying repair process parameter optimization method, system, electronic device, medium and product, relates to the field of aero-engine part surface repair, and comprises the following steps: randomly generating a plasma spraying process parameter combination to form a parent population; regarding each group of plasma spraying process parameter combinations as an individual, regarding the binary number after coding of each group of plasma spraying process parameter combinations as a gene, regarding the binary code formed by arranging the genes in sequence as a chromosome, and regarding the coating performance determined based on a coating performance prediction model as an evaluation basis; performing optimization on each plasma spraying process parameter combination based on the parent population by using an NSGA-II algorithm and the coating performance prediction model, obtaining the optimal numerical value of the plasma spraying process parameter combination, and thus performing plasma spraying repair on the aero-engine wheel disc. The plasma spraying process parameter optimization efficiency is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the field of surface repair of aero-engine parts, in particular to an aero-engine wheel disc plasma spraying repair process parameter optimization method, system, electronic device, medium and product. BACKGROUND

[0002] The aero-engine wheel disc is in a complex environment of high temperature, high rotating speed, vibration and high load, and different wear conditions occur at the positions in contact with other parts. In order to improve the service life and safety of the parts, the size of the wear position needs to be repaired to ensure the long-life requirement of the parts. In addition, the aero-engine wheel disc has high raw material value, long processing cycle and high processing precision. During the processing, the parts may be out of tolerance due to improper processing, or have casting defects (sand holes, air holes), etc., resulting in unqualified parts. If the parts are scrapped, it will cause huge economic losses and seriously delay the development and delivery progress of military aero-engines. Therefore, a suitable maintenance technology means is needed to restore the aero-engine wheel disc itself and its matching features to the level required by the design.

[0003] Plasma spraying is a surface repair technology suitable for aero-engine wheel disc repair tasks. In order to obtain a repair coating with high strength and high thickness, the plasma spraying process parameters need to be optimized. The traditional process parameter optimization usually adopts a multi-round traversal method, which has a long optimization period, a large optimization cost, lacks sufficient theoretical basis, has insufficient flexibility, and lacks a unified optimization process and standard for plasma spraying process parameter optimization, which brings difficulties and challenges to the optimization of the aero-engine wheel disc plasma spraying process parameters.

[0004] Therefore, an efficient, fast and highly applicable aero-engine plasma spraying process parameter optimization method is urgently needed. SUMMARY

[0005] The application aims to provide an aero-engine wheel disc plasma spraying repair process parameter optimization method, system, electronic device, medium and product to solve the problem of low efficiency of plasma spraying process parameter optimization.

[0006] To achieve the above-mentioned purpose, the application provides the following solutions.

[0007] In a first aspect, the application provides an aero-engine wheel disc plasma spraying repair process parameter optimization method, comprising:

[0008] Randomly generating plasma spraying process parameter combinations within the set range of each plasma spraying process parameter of the aircraft engine disk to form a parent population; the plasma spraying process parameter combinations include: each plasma spraying process parameter, the square of each plasma spraying process parameter, and the product of each pair of plasma spraying process parameters;

[0009] Each group of plasma spraying process parameter combinations is regarded as an individual in a population, the binary numbers after the parameters in each group of plasma spraying process parameter combinations are determined as genes, the binary codes formed by sequentially arranging all genes corresponding to each group of plasma spraying process parameter combinations are determined as chromosomes of the corresponding group of plasma spraying process parameter combinations, and the coating performance corresponding to each group of plasma spraying process parameter combinations determined based on a coating performance prediction model is determined as an evaluation basis; wherein the coating performance prediction model is obtained by training a back propagation neural network using a training set; the coating performance includes: hardness and wear loss;

[0010] Utilizing the NSGA-II algorithm and the coating performance prediction model, each plasma spraying process parameter combination is optimized based on the parent population to obtain an optimal value of the plasma spraying process parameter combination;

[0011] The plasma spray repair work of aircraft engine disks is controlled by using the optimal numerical value of plasma spray process parameter combination.

[0012] Optionally, the process of determining the coating performance prediction model includes:

[0013] Obtaining the plasma spray repair process parameters and corresponding coating properties of an aircraft engine wheel that has been spray repaired;

[0014] Determining a plasma spraying process parameter combination for each of the aircraft engine discs that have been repaired by spraying, based on the plasma spraying repair process parameters of each of the aircraft engine discs that have been repaired by spraying;

[0015] Performing maximum absolute value normalization processing on the plasma spraying process parameter combinations of each aircraft engine wheel that has been spray-repaired to obtain the corresponding processed plasma spraying process parameter combinations;

[0016] The coating properties of each aircraft engine wheel that has been spray-repaired are normalized to the maximum and minimum values ​​to obtain the corresponding coating properties after treatment;

[0017] Constructing the training set based on the plasma spraying process parameter combinations and coating properties of each aircraft engine wheel that has been spray-repaired;

[0018] Constructing the back propagation neural network;

[0019] The back propagation neural network is trained based on the training set using the Adam optimizer to obtain the coating performance prediction model.

[0020] Optionally, the NSGA-II algorithm and the coating performance prediction model are used to optimize each plasma spraying process parameter combination based on the parent population to obtain the optimal value of the plasma spraying process parameter combination, including:

[0021] Determining the coating performance corresponding to each individual in the parent population using the coating performance prediction model;

[0022] Determining a non-dominated hierarchy corresponding to the parent population based on coating properties corresponding to each individual in the parent population; the non-dominated hierarchy includes a plurality of individuals;

[0023] Sort the individuals in the non-dominated hierarchy corresponding to the parent population according to the order of coating performance, and calculate the crowding degree of each individual in the non-dominated hierarchy corresponding to the parent population;

[0024] Based on the individual tournament method, excellent individuals are selected for crossover mutation to generate offspring populations. The parent population and offspring population are merged to obtain the merged population.

[0025] Determining the coating performance corresponding to each individual in the merged population using the coating performance prediction model;

[0026] Based on the coating properties corresponding to each individual in the merged population, the non-dominated level corresponding to the merged population is determined;

[0027] Sort the individuals in the non-dominated hierarchy corresponding to the merged population according to the order of coating performance, and calculate the crowding degree of each individual in the non-dominated hierarchy corresponding to the merged population;

[0028] The individuals with the top 50% of crowding degree in the non-dominated hierarchy corresponding to the merged population are used to form a new parent population, and the process of "using the coating performance prediction model to determine the coating performance corresponding to each individual in the parent population" is returned until the maximum number of iterations is reached to obtain a non-dominated solution for multiple individuals.

[0029] Determining the coating performance corresponding to the non-dominated solution of each individual by using the coating performance prediction model;

[0030] The non-dominated solution of the individual with the best coating performance is determined as the optimal value of the plasma spraying process parameter combination; the optimal coating performance is the maximum hardness and the minimum wear.

[0031] Optionally, each individual in the non-dominated hierarchy is not dominated by any other individual; the domination of individual A by individual B means that the coating performance corresponding to individual B is better than the coating performance corresponding to individual A.

[0032] Optionally, the congestion degree of any current individual in the sorted non-dominated hierarchy is the sum of the first difference and the second difference of the current individual; the first difference is the difference between the coating performance of the current individual and the coating performance of the previous individual, and the second difference is the difference between the coating performance of the current individual and the coating performance of the next individual.

[0033] Optionally, the back propagation neural network comprises: an input layer, a hidden layer and an output layer; the input layer comprises 14 input units, the hidden layer comprises 128 hidden units, and the output layer comprises 2 output units;

[0034] The hidden layer and the output layer both use the ReLU activation function.

[0035] In a second aspect, the present application provides a system for optimizing process parameters for plasma spray repair of aircraft engine discs, comprising:

[0036] An initialization module is configured to randomly generate plasma spraying process parameter combinations within a set range of plasma spraying process parameters for an aircraft engine disk to form a parent population; the plasma spraying process parameter combinations include: plasma spraying process parameters, squares of plasma spraying process parameters, and products of two plasma spraying process parameters;

[0037] A parameter setting module is configured to treat each plasma spraying process parameter combination as an individual in a population, determine the binary number obtained by encoding the parameters in each plasma spraying process parameter combination as a gene, determine the binary code formed by sequentially arranging all genes corresponding to each plasma spraying process parameter combination as the chromosome of the corresponding plasma spraying process parameter combination, and determine the coating performance corresponding to each plasma spraying process parameter combination determined based on a coating performance prediction model as an evaluation basis; wherein the coating performance prediction model is obtained by training a back propagation neural network using a training set; the coating performance includes hardness and wear loss;

[0038] An optimization module, configured to optimize each plasma spraying process parameter combination based on the parent population using the NSGA-II algorithm and the coating performance prediction model to obtain an optimal value of the plasma spraying process parameter combination;

[0039] A control module is used to control the plasma spray repair work of an aircraft engine wheel disc by utilizing the optimal numerical value of the plasma spray process parameter combination.

[0040] In a third aspect, the present application provides an electronic 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 any of the above-mentioned methods for optimizing process parameters of plasma spray repair of aircraft engine discs.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for optimizing the process parameters of the plasma spray repair of an aircraft engine wheel.

[0042] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for optimizing the process parameters of the aircraft engine wheel plasma spray repair.

[0043] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0044] The present application discloses a method, system, electronic equipment, medium and product for optimizing process parameters of plasma spray repair of aircraft engine wheel discs, proposes a scheme for predicting the effect of plasma spray repair by using BP neural network, adopts feature combination and normalization to process data, adopts multi-layer neural network model and nonlinear activation function, fully considers the coupling effect between plasma spray process parameters and the nonlinear relationship between them and the repair effect; combines NSGA-II algorithm with BP neural network, adopts machine learning method to improve the optimization efficiency of plasma spray process parameters, saves optimization cost, and can complete the optimization of plasma spray repair process parameters in a very short time based on the coating performance prediction model, which can improve the optimization efficiency of plasma spray process parameters, reduce costs, help break through the bottleneck of plasma spray technology, and improve the level of plasma spray technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, 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.

[0046] Figure 1 A schematic flow chart of a method for optimizing process parameters for plasma spray repair of an aircraft engine disc according to one embodiment of the present application;

[0047] Figure 2 Optimization framework for the plasma spray repair process parameters of aircraft engine discs;

[0048] Figure 3 Schematic diagram of the back propagation neural network structure;

[0049] Figure 4 Schematic diagram of the output results of the first test set of the coating performance prediction model;

[0050] Figure 5 Schematic diagram of the output results of the second test set of the coating performance prediction model;

[0051] Figure 6 Schematic diagram of the NSGA-II algorithm optimization process;

[0052] Figure 7 Schematic diagram of chromosome crossing over;

[0053] Figure 8 Schematic diagram of chromosome variation;

[0054] Figure 9 Schematic diagram of the generation process of the new parent population;

[0055] Figure 10 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0056] 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.

[0057] The purpose of this application is to provide a method, system, electronic equipment, medium and product for optimizing the process parameters of aircraft engine wheel plasma spray repair, aiming to improve the efficiency of plasma spray process parameter optimization.

[0058] 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.

[0059] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a method for optimizing process parameters of plasma spray repair of an aircraft engine wheel disc is provided, comprising:

[0060] Step 1: Within the setting range of each plasma spraying process parameter of the aircraft engine wheel, randomly generate plasma spraying process parameter combinations to form a parent population.

[0061] The plasma spraying process parameter combination includes: each plasma spraying process parameter, the square of each plasma spraying process parameter, and the product of each pair of plasma spraying process parameters.

[0062] In fact, the plasma spraying process parameters include but are not limited to: aging, current, nozzle speed and air flow; at this time, the plasma spraying process parameter combination includes: aging, current, nozzle speed, air flow, the square of aging, the square of current, the square of nozzle speed, the square of air flow and the product of each plasma spraying process parameter.

[0063] Specifically, the setting ranges of various plasma spraying process parameters are shown in Table 1.

[0064] Table 1 Plasma spraying process parameter setting range

[0065] Process parameters Value range step length Time limita 200-500 5 Current b 100-200 5 Nozzle speed c 50-300 5 Air flow d 0-50 1

[0066] In addition to the above parameters, plasma spraying process parameters may also include: voltage, power and spraying distance.

[0067] Step 2: Each group of plasma spraying process parameter combinations is regarded as an individual in the population, the binary numbers after the parameters in each group of plasma spraying process parameter combinations are determined as genes, the binary codes formed by sequentially arranging all genes corresponding to each group of plasma spraying process parameter combinations are determined as the chromosomes of the corresponding group of plasma spraying process parameter combinations, and the coating performance corresponding to each group of plasma spraying process parameter combinations determined based on the coating performance prediction model is determined as the evaluation basis.

[0068] Among them, the coating performance prediction model is obtained by training the back propagation neural network using the training set; the coating performance includes: hardness and wear amount.

[0069] As an optional implementation, the process of determining the coating performance prediction model includes:

[0070] Step 21: Obtain the plasma spray repair process parameters and corresponding coating properties of the aircraft engine wheel that has been spray repaired.

[0071] Step 22: Based on the plasma spraying repair process parameters of each aircraft engine wheel that has been sprayed and repaired, determine the plasma spraying process parameter combination of each aircraft engine wheel that has been sprayed and repaired.

[0072] Step 23: performing maximum absolute value normalization processing on the plasma spraying process parameter combinations of each aircraft engine wheel that has been spray-repaired to obtain the corresponding processed plasma spraying process parameter combinations.

[0073] Step 24: Perform maximum and minimum value normalization processing on the coating properties of each aircraft engine wheel that has been spray-repaired to obtain the corresponding coating properties after processing.

[0074] Step 25: Construct a training set based on the plasma spraying process parameter combinations and coating properties of each aircraft engine wheel that has been spray-repaired.

[0075] Step 26: Build a back-propagation neural network.

[0076] Step 27: Using the Adam optimizer, the back propagation neural network is trained based on the training set to obtain a coating performance prediction model.

[0077] As an optional implementation, Figure 3 As shown in FIG, the back propagation neural network includes: an input layer, a hidden layer and an output layer; the input layer includes 14 input units, the hidden layer includes 128 hidden units, and the output layer includes 2 output units.

[0078] Both the hidden layer and the output layer use the ReLU activation function.

[0079] After training the coating performance prediction model, the coating performance prediction model was tested using the first test set and the second test set. The results are as follows: Figure 4 and Figure 5 As shown in the figure, the prediction error is basically within 5%.

[0080] Step 3: Using the NSGA-II algorithm and the coating performance prediction model, the plasma spraying process parameter combinations are optimized based on the parent population to obtain the optimal values ​​of the plasma spraying process parameter combinations.

[0081] As an optional implementation, Figure 6 As shown, step 3 includes:

[0082] Step 301: Using the coating performance prediction model, determine the coating performance corresponding to each individual in the parent population.

[0083] Step 302: Based on the coating properties corresponding to each individual in the parent population, determine a non-dominated hierarchy corresponding to the parent population; the non-dominated hierarchy includes multiple individuals.

[0084] As an optional embodiment, each individual in the non-dominated level is not dominated by any other individual; the domination of individual A by individual B means that the coating performance corresponding to individual B is better than the coating performance corresponding to individual A.

[0085] Step 303: Sort the individuals in the non-dominated level corresponding to the parent population according to the order of the coating performance from good to bad, and calculate the crowding degree of the individuals in the non-dominated level corresponding to the parent population.

[0086] As an optional implementation, the crowding degree of any current individual in the sorted non-dominated level is the sum of the first difference value and the second difference value of the current individual; the first difference value is the difference between the coating performance of the current individual and the coating performance of the previous individual, and the second difference value is the difference between the coating performance of the current individual and the coating performance of the next individual.

[0087] In fact, the greater the crowding degree of the individuals in the same non-dominated level, the better the individual.

[0088] Step 304: Select excellent individuals for cross and mutation to generate a child population based on the individuals, combine the parent population and the child population, and obtain a combined population.

[0089] Specifically, as shown in Figure 7 , the crossover is a random exchange of a segment between two chromosomes. As shown in Figure 8 , the mutation is a change in a random binary number on the chromosome.

[0090] Step 305: Determine the coating performance corresponding to each individual in the combined population by using the coating performance prediction model.

[0091] Step 306: Determine the non-dominated level corresponding to the combined population based on the coating performance corresponding to each individual in the combined population.

[0092] Step 307: Sort the individuals in the non-dominated level corresponding to the combined population according to the order of the coating performance from good to bad, and calculate the crowding degree of the individuals in the non-dominated level corresponding to the combined population.

[0093] Step 308: Form a new parent population from the individuals with a crowding degree in the top 50% in the non-dominated level corresponding to the combined population, and return to step 301 until the maximum number of iterations is reached, to obtain multiple non-dominated solutions of individuals.

[0094] Specifically, the generation process of the new parent population is as shown in Figure 9 .

[0095] Step 309: Determine the coating performance corresponding to the non-dominated solution of each individual by using the coating performance prediction model.

[0096] Step 310: Determine the non-dominated solution of the individual with the optimal coating performance as the optimal value of the plasma spraying process parameter combination. The optimal coating performance is the maximum hardness and the minimum wear amount.

[0097] Specifically, the optimal values ​​of each plasma spraying process parameter in the plasma spraying process parameter combination are shown in Table 2.

[0098] Table 2 Optimal values ​​of various plasma spraying process parameters

[0099]

[0100]

[0101] Step 4: Use the optimal numerical value of the plasma spraying process parameter combination to control the plasma spraying repair work of the aircraft engine wheel.

[0102] In an exemplary embodiment, a system for optimizing process parameters for plasma spray repair of an aircraft engine disk is provided, comprising:

[0103] An initialization module is used to randomly generate plasma spraying process parameter combinations to form a parent population within the set range of various plasma spraying process parameters for aircraft engine disks; the plasma spraying process parameters include: aging, current, nozzle speed, and gas flow; the plasma spraying process parameter combinations include: various plasma spraying process parameters, the square of various plasma spraying process parameters, and the product of each pair of plasma spraying process parameters.

[0104] A parameter setting module is used to treat each group of plasma spraying process parameter combinations as an individual in a population, determine the binary numbers after the parameters in each group of plasma spraying process parameter combinations are encoded as genes, determine the binary codes formed by sequentially arranging all genes corresponding to each group of plasma spraying process parameter combinations as chromosomes of the corresponding group of plasma spraying process parameter combinations, and determine the coating performance corresponding to each group of plasma spraying process parameter combinations determined based on a coating performance prediction model as an evaluation basis; wherein the coating performance prediction model is obtained by training a back propagation neural network using a training set; the coating performance includes: hardness and wear amount.

[0105] The optimization module is used to optimize each plasma spraying process parameter combination based on the parent population using the NSGA-II algorithm and the coating performance prediction model to obtain the optimal value of the plasma spraying process parameter combination.

[0106] A control module is used to control the plasma spray repair work of an aircraft engine wheel disc by utilizing the optimal numerical value of the plasma spray process parameter combination.

[0107] In an exemplary embodiment, an electronic device is provided, 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 a method for optimizing process parameters of plasma spray repair of an aircraft engine wheel.

[0108] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for optimizing process parameters of a plasma spray repair of an aircraft engine wheel is implemented.

[0109] In an exemplary embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements a method for optimizing process parameters of a plasma spray repair of an aircraft engine wheel.

[0110] 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 10 As 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, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through 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 computer program in the non-volatile storage medium. 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 through a network connection. When the computer program is executed by the processor, a method for optimizing the process parameters of plasma spray repair of an aircraft engine wheel is realized.

[0111] Those skilled in the art will understand that Figure 10 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.

[0112] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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 method for optimizing process parameters of plasma spray repair of aircraft engine discs, characterized in that: The method for optimizing process parameters of aircraft engine disk plasma spray repair comprises: Randomly generating plasma spraying process parameter combinations within the set range of each plasma spraying process parameter of the aircraft engine disk to form a parent population; the plasma spraying process parameter combinations include: each plasma spraying process parameter, the square of each plasma spraying process parameter, and the product of each pair of plasma spraying process parameters; Each group of plasma spraying process parameter combinations is regarded as an individual in a population, the binary numbers after the parameters in each group of plasma spraying process parameter combinations are determined as genes, the binary codes formed by sequentially arranging all genes corresponding to each group of plasma spraying process parameter combinations are determined as chromosomes of the corresponding group of plasma spraying process parameter combinations, and the coating performance corresponding to each group of plasma spraying process parameter combinations determined based on a coating performance prediction model is determined as an evaluation basis; wherein the coating performance prediction model is obtained by training a back propagation neural network using a training set; the coating performance includes: hardness and wear loss; Utilizing the NSGA-II algorithm and the coating performance prediction model, each plasma spraying process parameter combination is optimized based on the parent population to obtain an optimal value of the plasma spraying process parameter combination; Utilize the optimal numerical control of plasma spraying process parameter combination to repair the aircraft engine disk by plasma spraying; Utilizing the NSGA-II algorithm and the coating performance prediction model, each plasma spraying process parameter combination is optimized based on the parent population to obtain the optimal value of the plasma spraying process parameter combination, including: Determining the coating performance corresponding to each individual in the parent population using the coating performance prediction model; Determining a non-dominated hierarchy corresponding to the parent population based on coating properties corresponding to each individual in the parent population; the non-dominated hierarchy includes a plurality of individuals; Sort the individuals in the non-dominated hierarchy corresponding to the parent population according to the order of coating performance, and calculate the crowding degree of each individual in the non-dominated hierarchy corresponding to the parent population; Based on the individual tournament method, excellent individuals are selected for crossover mutation to generate offspring populations. The parent population and offspring population are merged to obtain the merged population. Determining the coating performance corresponding to each individual in the merged population using the coating performance prediction model; Based on the coating properties corresponding to each individual in the merged population, the non-dominated level corresponding to the merged population is determined; Sort the individuals in the non-dominated hierarchy corresponding to the merged population according to the order of coating performance, and calculate the crowding degree of each individual in the non-dominated hierarchy corresponding to the merged population; The individuals in the top 50% of the crowding degree in the non-dominated hierarchy corresponding to the merged population are used to form a new parent population. The process of "using the coating performance prediction model to determine the coating performance corresponding to each individual in the parent population" is returned until the maximum number of iterations is reached to obtain a non-dominated solution for multiple individuals. Determining the coating performance corresponding to the non-dominated solution of each individual by using the coating performance prediction model; The non-dominated solution of the individual with the best coating performance is determined as the optimal value of the plasma spraying process parameter combination; the optimal coating performance is the maximum hardness and the minimum wear.

2. The method for optimizing process parameters of aircraft engine disk plasma spray repair according to claim 1, characterized in that: The process of determining the coating performance prediction model includes: Obtaining the plasma spray repair process parameters and corresponding coating properties of an aircraft engine wheel that has been spray repaired; Determining a plasma spraying process parameter combination for each of the aircraft engine discs that have been repaired by spraying, based on the plasma spraying repair process parameters of each of the aircraft engine discs that have been repaired by spraying; Performing maximum absolute value normalization processing on the plasma spraying process parameter combinations of each aircraft engine wheel that has been spray-repaired to obtain the corresponding processed plasma spraying process parameter combinations; The coating properties of each aircraft engine wheel that has been spray-repaired are normalized to the maximum and minimum values ​​to obtain the corresponding coating properties after treatment; Constructing the training set based on the plasma spraying process parameter combinations and coating properties of each aircraft engine wheel that has been spray-repaired; Constructing the back propagation neural network; The back propagation neural network is trained based on the training set using the Adam optimizer to obtain the coating performance prediction model.

3. The method for optimizing process parameters of aircraft engine disk plasma spray repair according to claim 1, characterized in that: Each individual in the non-dominated level is not dominated by any other individual; the meaning of individual A being dominated by individual B is that the coating performance corresponding to individual B is better than the coating performance corresponding to individual A.

4. The method for optimizing process parameters of aircraft engine disk plasma spray repair according to claim 1, characterized in that: The crowding degree of any current individual in the sorted non-dominated hierarchy is the sum of the first difference and the second difference of the current individual; The first difference is the difference between the coating performance of the current individual and the coating performance of the previous individual, and the second difference is the difference between the coating performance of the current individual and the coating performance of the next individual.

5. The method for optimizing process parameters of aircraft engine disk plasma spray repair according to claim 2, characterized in that: The back propagation neural network comprises: an input layer, a hidden layer and an output layer; the input layer comprises 14 input units, the hidden layer comprises 128 hidden units, and the output layer comprises 2 output units; The hidden layer and the output layer both use the ReLU activation function.

6. A system for optimizing process parameters of an aircraft engine disk plasma spray repair, for implementing the method for optimizing process parameters of an aircraft engine disk plasma spray repair according to any one of claims 1 to 5, characterized in that: The aircraft engine wheel plasma spray repair process parameter optimization system includes: An initialization module is configured to randomly generate plasma spraying process parameter combinations within a set range of plasma spraying process parameters for an aircraft engine disk to form a parent population; the plasma spraying process parameter combinations include: plasma spraying process parameters, squares of plasma spraying process parameters, and products of two plasma spraying process parameters; A parameter setting module is configured to treat each plasma spraying process parameter combination as an individual in a population, determine the binary number obtained by encoding the parameters in each plasma spraying process parameter combination as a gene, determine the binary code formed by sequentially arranging all genes corresponding to each plasma spraying process parameter combination as the chromosome of the corresponding plasma spraying process parameter combination, and determine the coating performance corresponding to each plasma spraying process parameter combination determined based on a coating performance prediction model as an evaluation basis; wherein the coating performance prediction model is obtained by training a back propagation neural network using a training set; the coating performance includes hardness and wear loss; An optimization module, configured to optimize each plasma spraying process parameter combination based on the parent population using the NSGA-II algorithm and the coating performance prediction model to obtain an optimal value of the plasma spraying process parameter combination; A control module is used to control the plasma spray repair work of an aircraft engine wheel disc by utilizing the optimal numerical value of the plasma spray process parameter combination.

7. An electronic 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 optimizing process parameters of plasma spray repair of an aircraft engine wheel as described in any one of claims 1 to 5.

8. 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 optimizing the process parameters of the plasma spray repair of an aircraft engine disk as claimed in any one of claims 1 to 5 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for optimizing the process parameters of the plasma spray repair of an aircraft engine disk as claimed in any one of claims 1 to 5 is implemented.

Images