Spiral bevel gear composite shot blasting process parameter optimization method and optimization system based on discrete element-finite element analysis

Abstract

The invention provides a spiral bevel gear composite shot blasting process parameter optimization method and optimization system based on discrete element-finite element analysis, and relates to the technical field of gear parameter optimizing.The method comprises the specific steps that process parameters are generated through random combination and input into a model for simulation; acquiring residual stress distribution, stress gradient and crack characteristic data of the spiral bevel gear; constructing a parameter prediction model, and training the model by using a simulation result; inputting an initial parameter to obtain a performance index; calculating a stress uniformity coefficient and a crack risk coefficient, and generating a comprehensive evaluation coefficient through correlation analysis to evaluate the surface quality of the gear; and with maximization of the comprehensive evaluation coefficient as a target, iterative optimization is carried out on the parameters by using a genetic algorithm, and optimal process parameters are extracted. According to the method, the interaction effect between the composite shot blasting process parameters can be comprehensively considered, then the composite shot blasting process parameters can be optimized, it is ensured that the performance of the spiral bevel gear is optimal in use, and the failure risk is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of gear parameter optimization, and in particular to a method and system for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis. Background Art

[0002] With the increasing demand for high-performance mechanical parts in modern manufacturing, especially in the aerospace and automotive industries, spiral bevel gears are key transmission components, and their surface quality and residual stress distribution are crucial to their service life and performance. Although the traditional shot peening process can improve the surface hardness and load-bearing capacity of the material, it lacks systematic analysis of the optimization of process parameters, which often leads to problems such as uneven film thickness and residual stress concentration, thus affecting the overall performance of spiral bevel gears. Therefore, how to effectively optimize the composite shot peening process parameters to ensure the surface quality of spiral bevel gears after shot peening has become a technical problem that needs to be solved urgently.

[0003] In the prior art, a method and system for optimizing the carburizing and quenching process parameters of aviation steel spiral bevel gears is provided with publication number CN118114562A, which includes the following steps: obtaining the material performance parameters of aviation steel spiral bevel gears, and obtaining the deformation, hardness and other properties of aviation steel spiral bevel gears during the carburizing and quenching process through simulation analysis, effectively making up for the defect that the prior art is difficult to analyze the performance of aviation steel spiral bevel gears during the carburizing and quenching process; designing a four-factor three-level orthogonal test scheme, taking carburizing time, carburizing temperature, quenching temperature, and quenching time as optimization parameters, taking tooth surface hardness and maximum deformation as response indicators, establishing a radial basis function approximation model, and using the improved NSGA-II multi-objective optimization genetic algorithm to obtain the optimal optimization parameter combination, the optimization process has high accuracy, which not only ensures the heat treatment quality, but also improves the engineering efficiency, and significantly reduces the amount of calculation.

[0004] However, there are still some shortcomings. From the above statements, it can be seen that although the existing carburizing and quenching process is effective in some aspects, there is a risk of cracking caused by tensile stress. Relatively speaking, the composite shot peening process can quickly increase the surface compressive stress and fatigue strength, and reduce the risk of crack formation and expansion. However, since the composite shot peening process involves more parameters and complex interactions, the limitations of traditional optimization methods make the overall optimization effect poor.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a method and system for optimizing the process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis, the specific steps include:

[0009] S1. Randomly combine the composite shot peening process parameters, input the randomly combined composite shot peening process parameters into the discrete element-finite element model, conduct simulation experiments, obtain the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear, and obtain the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value on the surface of the spiral bevel gear according to the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear. The composite shot peening process parameters include shot diameter, injection speed, spot diameter, and laser power. According to the composite shot peening process parameters, construct individuals of the initial population;

[0010] S2. Construct a parameter prediction model, take different composite shot peening process parameter combinations as input, and use the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value as label training models to train the parameter prediction model;

[0011] S3. Establishing the constraint conditions of composite shot peening process parameters, under the constraint conditions of composite shot peening process parameters, inputting the individual parameters of the initial population into the parameter prediction model, and obtaining the standard deviation of residual stress, the maximum value of stress gradient, the maximum value of crack area, and the maximum value of crack depth;

[0012] S4. Process the residual stress standard deviation and the maximum value of the stress gradient and perform a correlation analysis to generate a stress uniformity coefficient for evaluating the uniformity of residual stress on the surface of the spiral bevel gear; process the maximum value of the crack area and the maximum value of the crack depth and perform a correlation analysis to generate a crack risk coefficient for evaluating the degree of surface failure risk of the spiral bevel gear; process the stress uniformity coefficient and the crack risk coefficient and perform a correlation analysis to generate a comprehensive evaluation coefficient for comprehensively evaluating the surface quality of the spiral bevel gear;

[0013] S5. Taking the maximization of the comprehensive evaluation coefficient as the objective function, and constructing the constraint conditions of the composite shot peening process parameters, the individuals in the initial population are iteratively optimized through the genetic algorithm under the constraint conditions to obtain the optimal individuals, and based on the optimal individuals, the optimal values ​​of the composite shot peening process parameters are extracted.

[0014] Furthermore, according to the composite shot peening process parameters, the individuals of the initial population are constructed. The specific process is as follows:

[0015] The composite shot peening process parameters of spiral bevel gears are collected, including the spot diameter GL, laser power JP, shot diameter DL and injection velocity PV. The above parameters are combined to construct the initial population, which is calibrated as Q, and the initial population Q = {Q 1 ,Q 2 ,…,Q r ,…,Q R}, Q r is the rth individual in the initial population, r is the index of the individual in the initial population, and r∈[1,R], R is the number of individuals in the initial population, Q r ={GL r ,JP r ,DL r ,PV r};

[0016] Among them, GL r ,JP r ,DL r ,PV r are the spot diameter, laser power, projectile diameter, and injection speed of the laser impact of the rth individual.

[0017] Furthermore, the parameter prediction model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function;

[0018] The process of training the parameter prediction model is as follows:

[0019] According to the projectile diameter, injection speed, spot diameter and laser power of the individuals in the initial population, the standard deviation of residual stress, the maximum stress gradient, the maximum crack area and the maximum crack depth are used as output labels for training. The mean square error is used as the loss function. When the mean square error is in the range of [0, 0.01], the training of the parameter prediction model is completed.

[0020] Furthermore, the residual stress standard deviation and the maximum value of the stress gradient are processed and correlated to generate the stress uniformity coefficient based on the following formula:

[0021]

[0022] Among them, YJxs ris the stress uniformity coefficient of the rth individual. The stress uniformity coefficient is used to comprehensively evaluate the uniformity of residual stress on the surface of spiral bevel gears from two aspects: the standard deviation of residual stress and the maximum value of stress gradient. r is the standard deviation of residual stress, is the maximum stress gradient of the rth individual, is the combined value of the residual stress standard deviation and the maximum stress gradient of the rth individual, ω 1 is the weight coefficient of the residual stress standard deviation, ω 2 is the weight coefficient of the maximum stress gradient, ω 3 is the weight coefficient of the combined value of the residual stress standard deviation and the maximum stress gradient. 1 +ω 2 +ω 3 =1, let 0<ω 1 <ω 2 <ω 3 <1.

[0023] Furthermore, the maximum crack area and the maximum crack depth are processed and correlated to generate the crack risk coefficient according to the following formula:

[0024]

[0025] Among them, LFxs r is the crack risk coefficient of the rth individual. The crack risk coefficient is used to comprehensively evaluate the surface failure risk of spiral bevel gears from two levels: the maximum crack area and the maximum crack depth. is the maximum crack area of ​​the rth individual, is the maximum crack depth of the rth individual, β 1 is the weight coefficient of the maximum crack area, β 2 is the weight coefficient of the maximum crack depth, in β 1 +β 2 =1, let 0<β 2 <β 1 <1.

[0026] Furthermore, the stress uniformity coefficient and crack risk coefficient are processed and correlated to generate a comprehensive evaluation coefficient based on the following formula:

[0027] ZGar r =α 1 Yj Y r +α 2 LFx r

[0028] Among them, ZPxs ris the comprehensive evaluation coefficient of the rth individual. The comprehensive evaluation coefficient is used to combine the stress uniformity coefficient and the crack risk coefficient to comprehensively evaluate the surface quality of the spiral bevel gear. 1 is the weight coefficient of rock burst coefficient, α 2 is the weight coefficient of rock mass failure coefficient, and α 1 , α 2 The specific value of is determined by the hierarchical analysis method.

[0029] Furthermore, the specific process of step S5 is as follows:

[0030] Seek a balance point between the stress uniformity coefficient and the crack risk coefficient to maximize the comprehensive evaluation coefficient. r Maximization is the optimization goal, and the initial population Q is iteratively optimized, that is, the individuals in the initial population Q are selected, crossed, and mutated. In the iterative optimization process, the constraints of the composite shot peening process parameters should be set, that is, the spot diameter GL is set respectively. r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r The maximum and minimum values ​​of the spot diameter GL r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r Within the constraints of , the initial population Q is iteratively optimized. Specifically, individuals with the highest comprehensive evaluation coefficient are selected as parents. Through crossover operations, the genes of the parent individuals are exchanged and combined to generate new individuals. Then, the spot diameter GL in the newly generated individuals is r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r After the genes are mutated, the selection, crossover, and mutation operations are repeated until the predetermined number of iterations is reached;

[0031] After iterative optimization of the initial population Q, the optimal individual is marked as Q r1 ={GL r1 ,JP r1 ,DL r1 ,PV r1}, the optimal value of the composite shot peening process parameters for spiral bevel gears is the spot diameter GL r1 , Laser power JP r1 、Projectile diameter DL r1 , injection velocity PV r1 .

[0032] To achieve the above object, the present invention also provides the following technical solutions:

[0033] A spiral bevel gear composite shot peening process parameter optimization system based on discrete element-finite element analysis, the system is used to execute any of the above-mentioned spiral bevel gear composite shot peening process parameter optimization methods based on discrete element-finite element analysis, comprising:

[0034] The simulation and population construction module is used to randomly combine the composite shot peening process parameters, input the randomly combined composite shot peening process parameters into the discrete element-finite element model, and conduct simulation experiments to obtain the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear. According to the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear, the residual stress standard deviation, the maximum stress gradient, the maximum crack area, and the maximum crack depth on the surface of the spiral bevel gear are obtained. The composite shot peening process parameters include shot diameter, injection speed, spot diameter, and laser power. According to the composite shot peening process parameters, individuals of the initial population are constructed;

[0035] The prediction model building module is used to build a parameter prediction model. The projectile diameter, injection speed, spot diameter and laser power of the initial population individuals are used as inputs, and the residual stress standard deviation, stress gradient maximum value, crack area maximum value and crack depth maximum value are used as label training models to train the parameter prediction model.

[0036] The characteristic parameter output module is used to establish the constraint conditions of the composite shot peening process parameters. Under the constraint conditions of the composite shot peening process parameters, the individual input parameters of the initial population are input into the parameter prediction model to obtain the residual stress standard deviation, the maximum stress gradient, the maximum crack area, and the maximum crack depth;

[0037] A data processing and analysis module is used to process the residual stress standard deviation and the maximum value of the stress gradient and perform correlation analysis to generate a stress uniformity coefficient for evaluating the uniformity of residual stress on the surface of the spiral bevel gear, process the maximum value of the crack area and the maximum value of the crack depth and perform correlation analysis to generate a crack risk coefficient for evaluating the degree of failure risk of the surface of the spiral bevel gear, process the stress uniformity coefficient and the crack risk coefficient and perform correlation analysis to generate a comprehensive evaluation coefficient for comprehensively evaluating the surface quality of the spiral bevel gear;

[0038] The parameter optimization module is used to maximize the comprehensive evaluation coefficient as the objective function and construct the constraint conditions of the composite shot peening process parameters. Under the constraint conditions, the individuals in the initial population are iteratively optimized through the genetic algorithm to obtain the optimal individual. Based on the optimal individual, the optimal value of the composite shot peening process parameters is extracted.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention uses a discrete element-finite element analysis method to perform simulation, randomly generate composite shot peening process parameters (such as projectile diameter, injection speed), input a discrete element-finite element model for simulation, obtain the residual stress distribution, stress gradient, crack area and crack depth of the surface, use the process parameters as input, and use the residual stress and crack characteristics as output. According to the constraints of the process parameters, the initial parameters are input into the prediction model to obtain various performance indicators, calculate the stress uniformity coefficient and the crack risk coefficient, generate a comprehensive evaluation coefficient, comprehensively evaluate the surface quality of the gear, and use a genetic algorithm to iteratively optimize the parameters with the goal of maximizing the comprehensive evaluation coefficient, and extract the optimal process parameters. Therefore, by using simulation, learning algorithms and genetic algorithms, the interaction between composite shot peening process parameters can be comprehensively considered, and then the composite shot peening process parameters can be optimized to ensure the optimal performance of spiral bevel gears in use and reduce the risk of failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0042] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0043] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0044] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0045] Embodiment 1:

[0046] See also Figure 1 , the present invention provides a technical solution:

[0047] A method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis, the specific steps include:

[0048] S1. Randomly combine the composite shot peening process parameters, input the randomly combined composite shot peening process parameters into the discrete element-finite element model, conduct simulation experiments, obtain the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear, and obtain the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value on the surface of the spiral bevel gear according to the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear. The composite shot peening process parameters include shot diameter, injection speed, spot diameter, and laser power. According to the composite shot peening process parameters, construct individuals of the initial population;

[0049] S2. Construct a parameter prediction model, take different composite shot peening process parameter combinations as input, and use the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value as label training models to train the parameter prediction model;

[0050] S3. Establishing the constraint conditions of composite shot peening process parameters, under the constraint conditions of composite shot peening process parameters, inputting the individual parameters of the initial population into the parameter prediction model, and obtaining the standard deviation of residual stress, the maximum value of stress gradient, the maximum value of crack area, and the maximum value of crack depth;

[0051] S4. Process the residual stress standard deviation and the maximum value of the stress gradient and perform a correlation analysis to generate a stress uniformity coefficient for evaluating the uniformity of residual stress on the surface of the spiral bevel gear; process the maximum value of the crack area and the maximum value of the crack depth and perform a correlation analysis to generate a crack risk coefficient for evaluating the degree of surface failure risk of the spiral bevel gear; process the stress uniformity coefficient and the crack risk coefficient and perform a correlation analysis to generate a comprehensive evaluation coefficient for comprehensively evaluating the surface quality of the spiral bevel gear;

[0052] S5. Taking the maximization of the comprehensive evaluation coefficient as the objective function, and constructing the constraint conditions of the composite shot peening process parameters, the individuals in the initial population are iteratively optimized through the genetic algorithm under the constraint conditions to obtain the optimal individuals, and based on the optimal individuals, the optimal values ​​of the composite shot peening process parameters are extracted.

[0053] On the basis of the above embodiment, the randomly combined composite shot peening process parameters are input into the discrete element-finite element model, and a simulation experiment is performed to obtain the relevant parameters of the bevel gear. The specific process is as follows:

[0054] Create a discrete element model, define the physical properties of shot peening particles in the model, including material, density, elastic modulus, etc., set the injection conditions, simulate the motion trajectory and collision behavior of the projectiles during the injection process, and record the interaction between each projectile and the bevel gear surface (such as impact force and contact time);

[0055] Create a three-dimensional geometric model of the spiral bevel gear in the finite element software to form a finite element model, and define material properties, including elastic modulus and yield strength;

[0056] Mesh the geometric model, set appropriate boundary conditions, and input the impact force and energy data from the discrete element model into the finite element model as loads;

[0057] The data from the discrete element model were combined with the finite element model to conduct coupling analysis, run simulation experiments, observe the effects of the shot peening process on the surface stress state and cracks of the spiral bevel gears, and extract simulation results, including residual stress distribution, stress gradient, crack area, and crack depth.

[0058] On the basis of the above embodiment, according to the residual stress distribution, stress gradient, crack area and crack depth, the residual stress standard deviation, the maximum stress gradient, the maximum crack area and the maximum crack depth are obtained. The specific process is as follows:

[0059] The measured value of residual stress is obtained from the simulation experiment, denoted as a 1 ,a 1 ,…,a i ,…,a m ;

[0060] Calculate the mean residual stress:

[0061]

[0062] Where, μ is the mean value of residual stress, a i is the residual stress at the i-th measuring point, i is the index of the measuring point, i∈[1,m], and m is the number of measuring points;

[0063] Calculate the standard deviation of residual stress:

[0064]

[0065] Where, σ is the standard deviation of residual stress;

[0066] Stress gradient is an indicator that describes the rate of change of stress, indicating the degree of stress change within a certain distance;

[0067] Select two adjacent measurement points x i and x i+1 , the corresponding stress value is ai and a i+1 ;

[0068] Stress gradient formula:

[0069]

[0070] G max =max(G i |i∈[1,m-1])

[0071] Among them, G i is the stress gradient at the ith measuring point, G max is the maximum value of stress gradient, x i is the coordinate of the ith measurement point, x i+1 is the coordinate of the i+1th measurement point, a i is the measurement point x i The stress value at a i+1 is the measurement point x i+1 The stress value at ;

[0072] Multiple cracks are obtained from the simulation experiment, the main axis of the crack is extracted using the minimum circumscribed rectangle, the length of each crack is calculated, the width is measured through the contour line of the crack, and then the area of ​​the crack is calculated, which is recorded as A 1 ,A 2 ,…,A j ,…,A n ;

[0073] Find the maximum value among all crack area data:

[0074] A max =max(A j |j∈[1,n])

[0075] Among them, A max is the maximum crack area, A j is the area of ​​the jth crack, j is the index of the crack, j∈[1,n], and n is the number of cracks;

[0076] Multiple cracks are obtained from the simulation experiment, and the depth values ​​of all cracks are accurately extracted by laser measurement, which is recorded as D 1 ,D 2 ,…,D j ,…,D n ;

[0077] Find the maximum value among all crack depth data:

[0078] D max =max(D j |j∈[1,n])

[0079] Among them, D max is the maximum crack depth, D j is the depth of the jth crack.

[0080] On the basis of the above embodiment, according to the composite shot peening process parameters, individuals of the initial population are constructed, and the specific process is as follows:

[0081] The composite shot peening process parameters of spiral bevel gears are collected, including the spot diameter GL, laser power JP, shot diameter DL and injection velocity PV. The above parameters are combined to construct the initial population, which is calibrated as Q, and the initial population Q = {Q 1 ,Q 2 ,…,Q r ,…,Q R}, Q r is the rth individual in the initial population, r is the index of the individual in the initial population, and r∈[1,R], R is the number of individuals in the initial population, Q r ={GL r ,JP r ,DL r ,PV r};

[0082] Among them, GL r ,JP r ,DL r ,PV r are the spot diameter, laser power, projectile diameter, and injection speed of the laser impact of the rth individual.

[0083] Based on the above embodiment, the parameter prediction model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

[0084] In this embodiment, the input features of the deep learning network of the multilayer perceptron include four features: projectile diameter, injection speed, spot diameter and laser power.

[0085] The structure of the deep learning network of multi-layer perceptron is:

[0086] Input layer: receives input of 4 features;

[0087] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0088] The second hidden layer has 32 neurons and also uses the ReLU activation function.

[0089] The third hidden layer has 16 neurons and uses the ReLU activation function.

[0090] Output layer: has 4 neurons, standard deviation of residual stress, maximum stress gradient, maximum crack area, and maximum crack depth.

[0091] The process of training the parameter prediction model is as follows:

[0092] According to the projectile diameter, injection speed, spot diameter and laser power of the individuals in the initial population, the standard deviation of residual stress, the maximum stress gradient, the maximum crack area and the maximum crack depth are used as output labels for training. The mean square error is used as the loss function. When the mean square error is in the range of [0, 0.01], the training of the parameter prediction model is completed.

[0093] Based on the above embodiment, the correlation between the residual stress standard deviation, the maximum value of the stress gradient and the uniformity of the residual stress on the bevel gear surface is as follows:

[0094] The standard deviation of residual stress reflects the degree of dispersion of stress distribution after statistical analysis of the residual stress values ​​at multiple measurement points. The smaller the standard deviation, the smaller the variation of residual stress at different positions and the better the uniformity.

[0095] When the standard deviation of residual stress is small, it means that the residual stress is distributed more evenly on the surface of the bevel gear, which indicates that the processing or forming process of the bevel gear surface is relatively stable; a large standard deviation indicates that the stress distribution is uneven, which may cause local overload or fatigue problems on the bevel gear surface during use.

[0096] In summary, the standard deviation of residual stress is positively correlated with the uniformity of residual stress on the surface of bevel gears.

[0097] The maximum stress gradient refers to the largest value among the stress gradients calculated at adjacent positions. It indicates the rate of change of stress in space, especially the stress change within a short distance.

[0098] A smaller maximum value of stress gradient usually means that the stress on the material surface changes gently, indicating that the residual stress distribution is relatively uniform; on the contrary, a larger maximum value of stress gradient indicates that the stress changes dramatically within a short distance, which is usually related to the inhomogeneity of residual stress.

[0099] In summary, the maximum value of stress gradient and the uniformity of residual stress on the bevel gear surface are positively correlated.

[0100] According to the correlation between the residual stress standard deviation, the maximum value of the stress gradient and the uniformity of the residual stress on the bevel gear surface, the residual stress standard deviation and the maximum value of the stress gradient are processed and correlated to generate the stress uniformity coefficient. The formula is as follows:

[0101]

[0102] Among them, YJxs r is the stress uniformity coefficient of the rth individual. The stress uniformity coefficient is used to comprehensively evaluate the uniformity of residual stress on the surface of spiral bevel gears from two aspects: the standard deviation of residual stress and the maximum value of stress gradient. The smaller the stress uniformity coefficient, the better the uniformity of residual stress on the surface of spiral bevel gears, and then the better the surface quality of spiral bevel gears.

[0103] It should be noted that the smaller the residual stress standard deviation, the smaller the stress uniformity coefficient, the better the residual stress uniformity; the smaller the maximum value of the stress gradient, the smaller the stress uniformity coefficient, the better the residual stress uniformity;

[0104] In the formula, σ r is the standard deviation of residual stress, is the maximum stress gradient of the rth individual, is the combined value of the residual stress standard deviation and the maximum stress gradient of the rth individual;

[0105] In the formula, ω 1 is the weight coefficient of the residual stress standard deviation, ω 2 is the weight coefficient of the maximum stress gradient, ω 3 is the weight coefficient of the combined value of the residual stress standard deviation and the maximum stress gradient;

[0106] The reason why the above functional form is used to express the functional relationship between the stress uniformity coefficient and the residual stress standard deviation and the maximum stress gradient is as follows:

[0107] First, (ω 1 ·σ r ), which partly reflects the influence of the residual stress standard deviation on the stress uniformity coefficient. r This will reduce the TJxs value, indicating that the stress uniformity is better, which is consistent with the actual logic.

[0108] second, This item reflects the maximum stress gradient effect on YJxs r The effect of smaller G max Will make YJxs r Lower, further indicating that the residual stress uniformity is better, which is consistent with the actual logic.

[0109] third, Since the residual stress standard deviation and the maximum stress gradient are interrelated, this term combines the interaction between the standard deviation and the maximum stress gradient, and represents the combined effect of the residual stress standard deviation and the maximum stress gradient, which can more comprehensively reflect their influence on stress uniformity. When both are small, this term will significantly reduce YJxs r value, indicating better uniformity, which is also consistent with the actual logic.

[0110] Fourth, different residual stress parameters have different effects on the residual stress on the surface of spiral bevel gears. Therefore, it is necessary to set the weight coefficient of the residual stress parameter. By setting the weight coefficient ω 1 ,ω 2 ,ω 3 , which can more accurately reflect the influence of residual stress parameters on the residual stress on the surface of spiral bevel gears and emphasize the interaction between various parameters.

[0111] Among them, ω 3 Represents the interaction between the standard deviation of residual stress and the maximum value of stress gradient. Because there is a complex relationship between the two, considering their interaction can more comprehensively reflect the influence of stress uniformity on the performance of spiral bevel gears. When both are small, their combined effect may significantly reduce the stress uniformity coefficient (YJxs r ), indicating better uniformity. Therefore, the weight coefficient of the interaction ω 3 Usually set to highest.

[0112] Among them, ω 2 Represents the influence of the maximum value of stress gradient. The change of stress gradient is directly related to the fatigue and fracture risk of spiral bevel gears. In many application scenarios, the influence of stress gradient is often considered to be a key factor; ω 1 Represents the influence of the residual stress standard deviation on the stress uniformity coefficient. Although the standard deviation reflects the unevenness of stress distribution, it only describes the degree of dispersion of residual stress at different positions and lacks a direct reflection of the stress change rate. In the performance evaluation of spiral bevel gears, the focus is usually on the local stress concentration and deformation that the spiral bevel gears may encounter during actual use. The change in stress gradient is directly related to the failure mechanism of the spiral bevel gears, while the standard deviation mainly reflects the distribution characteristics of the overall stress and lacks a direct indication of local stress changes. Therefore, compared with the stress gradient and interaction, the influence of the residual stress standard deviation is relatively small, so the weight coefficient of the stress gradient ω 2 The weight factor ω is usually higher than the standard deviation of residual stress 1 .

[0113] In summary, in ω 1 +ω2 +ω 3 =1, let 0<ω 1 <ω 2 <ω 3 <1.

[0114] As an implementation method, 1 The value range is an open interval of 0.2-0.3, ω 2 The value range is an open interval of 0.3-0.4, ω 3 The value range is an open interval of 0.4-0.5. The specific value is set by the technicians according to the actual situation and is not limited here.

[0115] Based on the above embodiment, the correlation between the maximum crack area, the maximum crack depth and the surface failure risk of the spiral bevel gear is as follows:

[0116] The maximum crack area refers to the crack with the largest area among the cracks detected on the surface of the spiral bevel gear. This indicator reflects the severity of the defects on the surface of the spiral bevel gear. The larger the crack area, the more significant the defects on the surface, which may lead to stress concentration and increase the failure risk of the spiral bevel gear during use.

[0117] Therefore, the maximum crack area is positively correlated with the degree of surface failure risk of spiral bevel gears.

[0118] The maximum crack depth refers to the crack with the largest depth among the cracks detected on the surface of the spiral bevel gear. This indicator is directly related to the internal structural integrity of the spiral bevel gear. A larger crack depth usually means that the crack has penetrated deep into the interior, which may cause a significant reduction in the load-bearing capacity of the spiral bevel gear and increase the risk of fatigue failure.

[0119] Therefore, the maximum crack depth is positively correlated with the surface failure risk of spiral bevel gears.

[0120] In summary, the maximum crack area and the maximum crack depth are positively correlated with the degree of surface failure risk of spiral bevel gears.

[0121] According to the correlation between the maximum crack area, the maximum crack depth and the risk of surface failure of spiral bevel gears, the maximum crack area and the maximum crack depth are processed and correlated to generate the crack risk coefficient. The formula is as follows:

[0122]

[0123] Among them, LFxs ris the crack risk coefficient of the rth individual. The crack risk coefficient is used to comprehensively evaluate the surface failure risk of the spiral bevel gear from two levels: the maximum crack area and the maximum crack depth. The smaller the crack risk coefficient, the lower the surface failure risk of the spiral bevel gear, and then the better the surface quality of the spiral bevel gear.

[0124] It should be noted that the smaller the maximum value of the crack area, the smaller the crack risk coefficient, the lower the failure risk, and the smaller the maximum value of the crack depth, the smaller the crack risk coefficient, and the smaller the maximum value of the crack depth;

[0125] In the formula, is the maximum crack area of ​​the rth individual, is the maximum crack depth of the rth individual;

[0126] In the formula, β 1 is the weight coefficient of the maximum crack area, β 2 is the weight coefficient of the maximum crack depth;

[0127] The reason why the above function form is used to express the functional relationship between the crack risk coefficient and the maximum crack area and the maximum crack depth is as follows:

[0128] First, the crack area usually increases with the degree of damage, but its effect on the overall strength of the spiral bevel gear is not linear. Using the square root The form can better capture this nonlinear relationship, making risk assessment more accurate.

[0129] Second, in the early stage of crack occurrence, the crack area may be small, but even a small crack, if deep, may lead to serious failure. The square root function can reduce the impact of large crack area on the risk factor, making the impact of crack depth more prominent, thereby more reasonably reflecting the actual failure risk.

[0130] Third, for crack depth, a linear relationship is used This is because crack depth is usually a key factor that directly affects the strength and integrity of spiral bevel gears. An increase in depth usually means a direct increase in the risk of failure, so a linear relationship can more directly evaluate its impact.

[0131] Fourth, β 1 and β 2 It reflects the importance of these two parameters to the overall risk assessment by setting the weight coefficient β 1 and β 2 , which can more accurately reflect the influence of the maximum crack area and the maximum crack depth on the surface failure risk of spiral bevel gears, and emphasize the interaction between various parameters.

[0132] Among them, the crack area is usually closely related to the load-bearing capacity of the spiral bevel gear. A larger crack area means that the spiral bevel gear is weakened to a greater extent, which may lead to more serious failure. In risk assessment, the impact of the crack area on the overall strength may be more significant than the crack depth.

[0133] The expansion of cracks is usually caused by stress concentration at the crack tip, and stress concentration is not only related to the crack depth, but also closely related to the area and shape of the crack. A larger crack area means there are more stress concentration points, which may accelerate the expansion of the crack.

[0134] Therefore, an increase in crack area often means a higher risk of failure, and the weight coefficient β of the maximum crack area is 1 The weight factor β is usually higher than the maximum crack depth. 2 .

[0135] In summary, in β 1 +β 2 =1, let 0<β 2 <β 1 <1.

[0136] As an embodiment, β 1 The value range is an open interval of 0.5-0.6, β 2 The value range is an open interval of 0.4-0.5. The specific value is set by the technicians according to the actual situation and is not limited here.

[0137] On the basis of the above embodiment, the stress uniformity coefficient and the crack risk coefficient are processed and correlation analysis is performed to generate a comprehensive evaluation coefficient, based on the following formula:

[0138] ZGar r =α 1 Yj Y r +α 2 LFx r

[0139] Among them, ZPxs r is the comprehensive evaluation coefficient of the rth individual. The comprehensive evaluation coefficient is used to combine the stress uniformity coefficient and the crack risk coefficient to comprehensively evaluate the surface quality of the spiral bevel gear. The comprehensive evaluation coefficient ZPxs r The smaller it is, the better the surface quality of the spiral bevel gear is;

[0140] It should be noted that, from the above description, the stress uniformity coefficient YJxs r The smaller it is, the better the uniformity of residual stress on the surface of the spiral bevel gear is, and the better the surface quality of the spiral bevel gear is; the crack risk factor LFxsr The smaller it is, the lower the risk of surface failure of the spiral bevel gear and the better the surface quality of the spiral bevel gear. Therefore, the comprehensive evaluation coefficient ZPxs r and stress uniformity coefficient YJxs r , crack risk factor LFxs r Therefore, the comprehensive evaluation coefficient ZPxs in the form of weighted summation is set as r The calculation formula of

[0141] In the formula, α 1 is the weight coefficient of rock burst coefficient, α 2 is the weight coefficient of rock mass failure coefficient, and α 1 , α 2 The specific value of is determined by the hierarchical analysis method, and the specific logic is as follows:

[0142] The stress uniformity coefficient YJxs r , crack risk factor LFxs r , two indicators are marked, and the relative importance values ​​between the two are determined by the nine-scale method to construct a judgment matrix, in which the index of the stress uniformity coefficient is marked as 1, and the index of the crack risk coefficient is marked as 2. The constructed judgment matrix [q uv ] 2×2 for:

[0143]

[0144] Among them, u and v both represent the index of the coefficient, and u∈[1,2], v∈[1,2], indicating the importance of the coefficient with index u to the comprehensive evaluation coefficient relative to the coefficient with index v, q uv The specific value of q is determined by relevant experts using a 1-9 scoring method. uv =9 means that the coefficient with index u is more important to the comprehensive evaluation coefficient than the coefficient with index v. uv =1 means that the coefficient with index u is extremely unimportant to the comprehensive evaluation coefficient compared with the coefficient with index v;

[0145] Divide each element value in the judgment matrix by the sum of its columns to obtain a normalized judgment matrix, calculate the mean of each row of element values ​​in the normalized judgment matrix, and use the mean of the first row of element values ​​as the stress uniformity coefficient YJxs r The proportionality coefficient of the second row is the mean of the element values ​​as the crack risk coefficient LFxs r The proportional coefficients are scaled in equal proportions with the constraint that the sum of the scaled values ​​is 1, and the values ​​obtained after scaling are used as the weights of the corresponding coefficients.

[0146] Based on the above embodiment, the specific process of step S5 is as follows:

[0147] Seek a balance point between the stress uniformity coefficient and the crack risk coefficient to maximize the comprehensive evaluation coefficient. r Maximization is the optimization goal, and the initial population Q is iteratively optimized, that is, the individuals in the initial population Q are selected, crossed, and mutated. In the iterative optimization process, the constraints of the composite shot peening process parameters should be set, that is, the spot diameter GL is set respectively. r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r The maximum and minimum values ​​of the spot diameter GL r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r Within the constraints of , the initial population Q is iteratively optimized. Specifically, individuals with the top comprehensive evaluation coefficients are selected as parents. The top refers to individuals in the top 50% of the comprehensive evaluation coefficients. Through crossover operations, the genes of the parent individuals are exchanged and combined to generate new individuals. Then, the spot diameter GL in the newly generated individuals is r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r After the genes are mutated, the selection, crossover, and mutation operations are repeated until the predetermined number of iterations is reached;

[0148] After iterative optimization of the initial population Q, the optimal individual is marked as Q r1 ={GL r1 ,JP r1 ,DL r1 ,PV r1}, the optimal value of the composite shot peening process parameters for spiral bevel gears is the spot diameter GL r1 , Laser power JP r1 、Projectile diameter DL r1 , injection velocity PV r1 .

[0149] See also Figure 2 , the present invention also provides a technical solution:

[0150] A spiral bevel gear composite shot peening process parameter optimization system based on discrete element-finite element analysis, the system is used to execute any of the above-mentioned spiral bevel gear composite shot peening process parameter optimization methods based on discrete element-finite element analysis, comprising:

[0151] The simulation and population construction module is used to randomly combine the composite shot peening process parameters, input the randomly combined composite shot peening process parameters into the discrete element-finite element model, and conduct simulation experiments to obtain the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear. According to the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear, the residual stress standard deviation, the maximum stress gradient, the maximum crack area, and the maximum crack depth on the surface of the spiral bevel gear are obtained. The composite shot peening process parameters include shot diameter, injection speed, spot diameter, and laser power. According to the composite shot peening process parameters, individuals of the initial population are constructed;

[0152] The prediction model building module is used to build a parameter prediction model, taking different composite shot peening process parameter combinations as input, and the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value as label training models to train the parameter prediction model;

[0153] The parameter output module is used to establish the constraint conditions of the composite shot peening process parameters. Under the constraint conditions of the composite shot peening process parameters, the individuals of the initial population are input into the parameter prediction model to obtain the standard deviation of residual stress, the maximum value of stress gradient, the maximum value of crack area, and the maximum value of crack depth;

[0154] A data processing and analysis module is used to process the residual stress standard deviation and the maximum value of the stress gradient and perform correlation analysis to generate a stress uniformity coefficient for evaluating the uniformity of residual stress on the surface of the spiral bevel gear, process the maximum value of the crack area and the maximum value of the crack depth and perform correlation analysis to generate a crack risk coefficient for evaluating the degree of failure risk of the surface of the spiral bevel gear, process the stress uniformity coefficient and the crack risk coefficient and perform correlation analysis to generate a comprehensive evaluation coefficient for comprehensively evaluating the surface quality of the spiral bevel gear;

[0155] The parameter optimization module is used to maximize the comprehensive evaluation coefficient as the objective function and construct the constraint conditions of the composite shot peening process parameters. Under the constraint conditions, the individuals in the initial population are iteratively optimized through the genetic algorithm to obtain the optimal individual. Based on the optimal individual, the optimal value of the composite shot peening process parameters is extracted.

[0156] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0157] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis, characterized in that: The specific steps include: S1. Randomly combine the composite shot peening process parameters, input the randomly combined composite shot peening process parameters into the discrete element-finite element model, conduct simulation experiments, obtain the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear, and obtain the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value on the surface of the spiral bevel gear according to the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear. The composite shot peening process parameters include shot diameter, injection speed, spot diameter, and laser power. According to the composite shot peening process parameters, construct individuals of the initial population; S2. Construct a parameter prediction model, take different composite shot peening process parameter combinations as input, and use the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value as label training models to train the parameter prediction model; S3. Establishing the constraint conditions of composite shot peening process parameters, under the constraint conditions of composite shot peening process parameters, inputting the individual parameters of the initial population into the parameter prediction model, and obtaining the standard deviation of residual stress, the maximum value of stress gradient, the maximum value of crack area, and the maximum value of crack depth; S4. Process the residual stress standard deviation and the maximum value of the stress gradient and perform a correlation analysis to generate a stress uniformity coefficient for evaluating the uniformity of residual stress on the surface of the spiral bevel gear; process the maximum value of the crack area and the maximum value of the crack depth and perform a correlation analysis to generate a crack risk coefficient for evaluating the degree of surface failure risk of the spiral bevel gear; process the stress uniformity coefficient and the crack risk coefficient and perform a correlation analysis to generate a comprehensive evaluation coefficient for comprehensively evaluating the surface quality of the spiral bevel gear; S5. Taking the maximization of the comprehensive evaluation coefficient as the objective function, and constructing the constraint conditions of the composite shot peening process parameters, the individuals in the initial population are iteratively optimized through the genetic algorithm under the constraint conditions to obtain the optimal individuals, and based on the optimal individuals, the optimal values ​​of the composite shot peening process parameters are extracted.

2. The method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis according to claim 1 is characterized in that: According to the composite shot peening process parameters, the individuals of the initial population are constructed. The specific process is as follows: The composite shot peening process parameters of spiral bevel gears are collected, including the spot diameter GL, laser power JP, shot diameter DL and injection velocity PV. The above parameters are combined to construct the initial population, which is calibrated as Q, and the initial population Q = {Q1, Q2, …, Q r ,…,Q R }, Q r is the rth individual in the initial population, r is the index of the individual in the initial population, and r∈[1,R], R is the number of individuals in the initial population, Q r ={GL r ,JP r ,DL r ,PV r }; Among them, GL r ,JP r ,DL r ,PV r are the spot diameter, laser power, projectile diameter, and injection speed of the laser impact of the rth individual.

3. The method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis according to claim 1 is characterized in that: The parameter prediction model is composed of a deep learning network based on a multilayer perceptron, wherein the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, wherein the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function; The process of training the parameter prediction model is as follows: According to the projectile diameter, injection speed, spot diameter and laser power of the individuals in the initial population, the standard deviation of residual stress, the maximum stress gradient, the maximum crack area and the maximum crack depth are used as output labels for training. The mean square error is used as the loss function. When the mean square error is in the range of [0, 0.01], the training of the parameter prediction model is completed.

4. The method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis according to claim 2 is characterized in that: The residual stress standard deviation and the maximum value of the stress gradient are processed and correlated to generate the stress uniformity coefficient. The formula is as follows: Among them, YJxs r is the stress uniformity coefficient of the rth individual. The stress uniformity coefficient is used to comprehensively evaluate the uniformity of residual stress on the surface of spiral bevel gears from two aspects: the standard deviation of residual stress and the maximum value of stress gradient. r is the standard deviation of residual stress, is the maximum stress gradient of the rth individual, is the combined value of the residual stress standard deviation and the maximum stress gradient of the rth individual, v1 is the weight coefficient of the residual stress standard deviation, v2 is the weight coefficient of the maximum stress gradient, ω3 is the weight coefficient of the combined value of the residual stress standard deviation and the maximum stress gradient, on the basis of ω1+ω2+ω3=1, let 0<ω1<ω2<ω3<1.

5. The method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis according to claim 4 is characterized in that: The maximum crack area and the maximum crack depth are processed and correlated to generate the crack risk coefficient based on the following formula: Among them, LFxs r is the crack risk coefficient of the rth individual. The crack risk coefficient is used to comprehensively evaluate the surface failure risk of spiral bevel gears from two levels: the maximum crack area and the maximum crack depth. is the maximum crack area of ​​the rth individual, is the maximum crack depth of the rth individual, β1 is the weight coefficient of the maximum crack area, β2 is the weight coefficient of the maximum crack depth, and on the basis of β1+β2=1, let 0<β2<β1<1.

6. The method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis according to claim 5, characterized in that: The stress uniformity coefficient and crack risk coefficient are processed and correlated to generate a comprehensive evaluation coefficient based on the following formula: ZPxs r =α1YJxs r +α2LFxs r Among them, ZPxs r is the comprehensive evaluation coefficient of the rth individual. The comprehensive evaluation coefficient is used to combine the stress uniformity coefficient and the crack risk coefficient to comprehensively evaluate the surface quality of the spiral bevel gear. α1 is the weight coefficient of the rock burst coefficient, and α2 is the weight coefficient of the rock destruction coefficient. The specific values ​​of α1 and α2 are determined by the hierarchical analysis method.

7. The method for optimizing process parameters of spiral bevel gear composite shot peening based on discrete element-finite element analysis according to claim 6, characterized in that: The specific process of step S5 is as follows: Seek a balance point between the stress uniformity coefficient and the crack risk coefficient to maximize the comprehensive evaluation coefficient. r Maximization is the optimization goal, and the initial population Q is iteratively optimized, that is, the individuals in the initial population Q are selected, crossed, and mutated. In the iterative optimization process, the constraints of the composite shot peening process parameters should be set, that is, the spot diameter GL is set respectively. r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r The maximum and minimum values ​​of the spot diameter GL r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r Within the constraints of , the initial population Q is iteratively optimized. Specifically, individuals with the highest comprehensive evaluation coefficient are selected as parents. Through crossover operations, the genes of the parent individuals are exchanged and combined to generate new individuals. Then, the spot diameter GL in the newly generated individuals is r , Laser power JP r 、Projectile diameter DL r , injection velocity PV r After the genes are mutated, the selection, crossover, and mutation operations are repeated until the predetermined number of iterations is reached; After iterative optimization of the initial population Q, the optimal individual is marked as Q r1 ={GL r1 ,JP r1 ,DL r1 ,PV r1 }, the optimal value of the composite shot peening process parameters for spiral bevel gears is the spot diameter GL r1 , Laser power JP r1 、Projectile diameter DL r1 , injection velocity PV r1 .

8. A spiral bevel gear composite shot peening process parameter optimization system based on discrete element-finite element analysis, the system is used to execute a spiral bevel gear composite shot peening process parameter optimization method based on discrete element-finite element analysis according to any one of claims 1 to 7, characterized in that: include: The simulation and population construction module is used to randomly combine the composite shot peening process parameters, input the randomly combined composite shot peening process parameters into the discrete element-finite element model, and conduct simulation experiments to obtain the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear. According to the residual stress distribution, stress gradient, crack area, and crack depth on the surface of the spiral bevel gear, the residual stress standard deviation, the maximum stress gradient, the maximum crack area, and the maximum crack depth on the surface of the spiral bevel gear are obtained. The composite shot peening process parameters include shot diameter, injection speed, spot diameter, and laser power. According to the composite shot peening process parameters, individuals of the initial population are constructed; The prediction model building module is used to build a parameter prediction model, taking different composite shot peening process parameter combinations as input, and the residual stress standard deviation, stress gradient maximum value, crack area maximum value, and crack depth maximum value as label training models to train the parameter prediction model; The characteristic parameter output module is used to establish the constraint conditions of the composite shot peening process parameters. Under the constraint conditions of the composite shot peening process parameters, the individual input parameters of the initial population are input into the parameter prediction model to obtain the residual stress standard deviation, the maximum stress gradient, the maximum crack area, and the maximum crack depth; A data processing and analysis module is used to process the residual stress standard deviation and the maximum value of the stress gradient and perform correlation analysis to generate a stress uniformity coefficient for evaluating the uniformity of residual stress on the surface of the spiral bevel gear, process the maximum value of the crack area and the maximum value of the crack depth and perform correlation analysis to generate a crack risk coefficient for evaluating the degree of failure risk of the surface of the spiral bevel gear, process the stress uniformity coefficient and the crack risk coefficient and perform correlation analysis to generate a comprehensive evaluation coefficient for comprehensively evaluating the surface quality of the spiral bevel gear; The parameter optimization module is used to maximize the comprehensive evaluation coefficient as the objective function and construct the constraint conditions of the composite shot peening process parameters. Under the constraint conditions, the individuals in the initial population are iteratively optimized through the genetic algorithm to obtain the optimal individual. Based on the optimal individual, the optimal value of the composite shot peening process parameters is extracted.

Images