Spiral bevel gear composite shot blasting process parameter optimization method and optimization system based on gear tooth surface topography analysis

Abstract

The invention provides a spiral bevel gear composite shot peening process parameter optimization method and optimization system based on gear tooth surface topography analysis, and relates to the technical field of process parameter optimizing.The method comprises the specific steps that machining tests are conducted under different composite shot peening process parameter combinations, a gear tooth surface topography feature prediction model is constructed, and a gear tooth surface topography feature prediction model is constructed; the method comprises the following steps: taking composite shot blasting process parameters as input, carrying out model training, randomly combining the process parameters, generating an initial population, obtaining corresponding gear tooth surface topography characteristic parameters through a prediction model, generating an evaluation index of anti-gluing capability through correlation analysis, comprehensively generating an evaluation coefficient, and taking maximization of the comprehensive evaluation coefficient as a target. And performing iterative optimization on the initial population through a genetic algorithm to obtain an optimal process parameter combination. Through a data-driven prediction model and systematic analysis, the optimization accuracy is improved, the optimal process parameter combination can be quickly positioned, and the test frequency and the time cost are remarkably reduced.

Description

Technical Field

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

[0002] Laser shock and mechanical shot peening strengthening technology can not only induce residual stress on the surface and depth direction of the target material, but also produce equivalent plastic strain on the surface of the material to produce orange peel pits and change its surface morphology. The size and depth of the pits will affect the thickness, viscosity and friction coefficient of the lubricating oil film. The surface morphology of the gear is closely related to its anti-bonding ability.

[0003] When optimizing the composite shot peening process parameters of spiral bevel gears, the existing technology relies on empirical rules to select and adjust the process parameters, lacks scientific data analysis and model prediction. This method is easily affected by subjective factors, resulting in a decrease in the accuracy and reliability of the optimization process. It is also unable to effectively identify and analyze the complex relationship between the composite shot peening process parameters, resulting in the interaction effect of each parameter not being fully utilized during the optimization process, thus affecting the final optimization results.

[0004] 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

[0005] 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 gear tooth surface morphology analysis, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for optimizing process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis, the specific steps comprising:

[0008] S1. Under different combinations of composite shot peening process parameters, spiral bevel gear processing tests were carried out respectively. After the test, several spiral bevel gears were randomly selected. The surface morphological characteristic parameters of the gear teeth included pit diameter, pit depth and roughness. The composite shot peening process parameters included shot diameter, shot velocity, mass flow rate, spot diameter and power density.

[0009] S2. Construct a gear surface morphology feature prediction model, use different composite shot peening process parameter combinations as input, and use gear surface morphology feature parameters as label training models to train the gear surface morphology feature prediction;

[0010] S3. Establishing the constraint conditions of the composite shot peening process parameters, under the constraint conditions of the composite shot peening process parameters, randomly combining the composite shot peening process parameters, constructing individuals of the initial population of composite shot peening process parameters, inputting the individuals of the initial population of composite shot peening process parameters into the gear surface morphology feature prediction model, and obtaining the gear surface morphology feature parameters;

[0011] S4. Process the gear tooth surface morphology characteristic parameters and perform correlation analysis to generate the gear tooth surface friction coefficient and gear tooth surface film thickness ratio for expressing the gear tooth surface anti-adhesion ability, and process the gear tooth surface friction coefficient and gear tooth surface film thickness ratio to generate a gear tooth surface comprehensive evaluation coefficient for comprehensively evaluating the anti-adhesion ability;

[0012] S5. Taking the maximization of the comprehensive evaluation coefficient of the gear tooth surface as the objective function, under the constraints of the composite shot peening process parameters, the individuals of the initial population of composite shot peening process parameters are iteratively optimized through the genetic algorithm to obtain the optimal individuals, and based on the optimal individuals, the optimal values ​​of the composite shot peening process parameters are extracted.

[0013] Furthermore, the composite shot peening process parameters are randomly combined to construct individuals of the initial population of composite shot peening process parameters. The specific process is as follows:

[0014] The initial population is labeled as Q, and the initial population Q={Q1,Q2,…,Q j ,…,Q n}, Q j is the jth individual in the initial population, j is the index of the individual in the initial population, and j∈[1,n], n is the number of individuals in the initial population, Q j ={d j ,v j ,M j ,D j ,P j}, where d j ,v j ,m j ,D j ,P j are the projectile diameter, projectile velocity, mass flow rate, spot diameter and power density of the jth individual respectively.

[0015] Furthermore, the gear surface morphology feature 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;

[0016] The process of training the gear tooth surface topography prediction model is as follows:

[0017] Different combinations of composite shot peening process parameters are used as input, and the gear surface morphology characteristic parameters 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 gear surface morphology characteristic prediction model is completed.

[0018] Furthermore, the gear tooth surface morphology characteristic parameters are processed and correlated to generate the gear tooth surface friction coefficient used to express the anti-adhesion ability, based on the following formula:

[0019] MCx j =α1·wd j +α2·wh j +α3·cr j

[0020] Among them, MCxs j is the friction coefficient of the jth gear tooth surface, wd j is the diameter of the jth individual pit, wh j is the pit depth of the jth individual, cr j is the roughness of the jth individual. On the basis of α1+α2+α3=1, let 0<α2<α3<α1<1.

[0021] Furthermore, the gear tooth surface morphology characteristic parameters are processed and correlation analysis is performed to generate the gear tooth surface film thickness ratio used to express the anti-adhesion ability of the gear tooth surface, based on the following formula:

[0022] MHb j =β1·(wd j ·wh j )+β2·cr j

[0023] Among them, MHbl j is the surface film thickness ratio of the jth individual gear tooth. On the basis of β1+β2=1, let 0<β2<β1<1.

[0024] Furthermore, the gear tooth surface friction coefficient and gear tooth surface film thickness ratio are processed to generate a gear tooth surface comprehensive evaluation coefficient for comprehensive evaluation of anti-adhesion ability, based on the following formula:

[0025] ZGar j =γ1MCxs j +γ2MCbl j

[0026] Among them, ZPxs jis the comprehensive evaluation coefficient of the j-th individual gear tooth surface, γ1 is the weight coefficient of the friction coefficient of the j-th individual gear tooth surface, γ2 is the weight coefficient of the film thickness ratio of the j-th individual gear tooth surface, and the specific values ​​of γ1 and γ2 are determined by the hierarchical analysis method.

[0027] Furthermore, the specific process of step S5 is as follows:

[0028] Find a balance point between the gear surface friction coefficient and the gear surface film thickness ratio to maximize the comprehensive evaluation coefficient. The comprehensive evaluation coefficient ZPxs j The maximization is taken as 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, constraints are set, that is, the maximum and minimum values ​​of the projectile diameter, projectile velocity, mass flow rate, spot diameter, and power density are set respectively. Within the constraints of the projectile diameter, projectile velocity, mass flow rate, spot diameter, and power density, the initial population Q is iteratively optimized. Specifically, the individual with the top comprehensive evaluation coefficient is selected as the parent generation, and the genes of the parent generation individuals are exchanged and combined through the crossover operation to generate new individuals. Then, the genes of the projectile diameter, projectile velocity, mass flow rate, spot diameter, and power density in the newly generated individuals are mutated, and the selection, crossover, and mutation operations are repeated until the predetermined number of iterations is reached;

[0029] After iterative optimization of the initial population Q, the optimal individual is marked as Q j1 ={d j1 ,v j1 ,m j1 ,D j1 ,P j1}, the optimal value of the composite shot peening process parameters for spiral bevel gears is the shot diameter d j1 , projectile velocity v j1 , mass flow rate m j1 , spot diameter D j1 and power density P j1 .

[0030] A system for optimizing composite shot peening process parameters of spiral bevel gears based on gear tooth surface morphology analysis, the system being used to execute any of the above-mentioned methods for optimizing composite shot peening process parameters of spiral bevel gears based on gear tooth surface morphology analysis, comprising:

[0031] The process parameter combination and test module is used to carry out spiral bevel gear processing tests under different composite shot peening process parameter combinations. After the test, several spiral bevel gears are randomly selected. The surface morphology characteristic parameters of the gear teeth include pit diameter, pit depth and roughness. The composite shot peening process parameters include shot diameter, shot velocity, coverage, mass flow rate, spot diameter, power density and overlap rate.

[0032] The morphology feature prediction module is used to build a gear surface morphology feature prediction model, taking different composite shot peening process parameter combinations as input and the gear surface morphology feature parameters as label training models to train the gear surface morphology feature prediction;

[0033] A process parameter population construction 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 composite shot peening process parameters are randomly combined to construct individuals of the initial population of composite shot peening process parameters. The individuals of the initial population of composite shot peening process parameters are input into the gear surface morphology feature prediction model to obtain the gear surface morphology feature parameters.

[0034] A data processing and analysis module is used to process the gear tooth surface morphology characteristic parameters and perform correlation analysis to generate a gear tooth surface friction coefficient and a gear tooth surface film thickness ratio for expressing the gear tooth surface anti-adhesion ability, and to process the gear tooth surface friction coefficient and the gear tooth surface film thickness ratio to generate a gear tooth surface comprehensive evaluation coefficient for comprehensively evaluating the anti-adhesion ability;

[0035] The iterative optimization module is used to iteratively optimize the individuals of the initial population of composite shot peening process parameters by using a genetic algorithm with the maximization of the comprehensive evaluation coefficient of the gear tooth surface as the objective function under the constraints of the composite shot peening process parameters to obtain the optimal individuals, and based on the optimal individuals, extract the optimal values ​​of the composite shot peening process parameters.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention conducts systematic processing tests under different combinations of composite shot peening process parameters, and utilizes a machine learning algorithm to train a model capable of predicting the surface morphology characteristic parameters (pit diameter, pit depth and roughness) of the gear teeth according to the composite shot peening process parameter input. This data-driven method can effectively identify complex parameter relationships, improve the accuracy of optimization, establish the gear surface friction coefficient and film thickness ratio, and comprehensively generate a comprehensive evaluation coefficient for evaluating anti-bonding ability, providing quantitative indicators for performance evaluation. The composite shot peening process parameters are iteratively optimized through a genetic algorithm, and the parameter combination can be flexibly adjusted under multiple constraints to adapt to changing process requirements, effectively improving the global search capability and ensuring that a better parameter combination is obtained. Therefore, through data-driven prediction models and systematic analysis, the optimal process parameter combination can be quickly located, significantly reducing the number of experiments and time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0039] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0040] 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.

[0041] 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.

[0042] Embodiment 1:

[0043] See also Figure 1 , the present invention provides a technical solution:

[0044] A method for optimizing process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis, the specific steps comprising:

[0045] S1. Under different combinations of composite shot peening process parameters, spiral bevel gear processing tests were carried out respectively. After the test, several spiral bevel gears were randomly selected. The surface morphological characteristic parameters of the gear teeth included pit diameter, pit depth and roughness. The composite shot peening process parameters included shot diameter, shot velocity, mass flow rate, spot diameter and power density.

[0046] S2. Construct a gear surface morphology feature prediction model, use different composite shot peening process parameter combinations as input, and use gear surface morphology feature parameters as label training models to train the gear surface morphology feature prediction;

[0047] S3. Establishing the constraint conditions of the composite shot peening process parameters, under the constraint conditions of the composite shot peening process parameters, randomly combining the composite shot peening process parameters, constructing individuals of the initial population of composite shot peening process parameters, inputting the individuals of the initial population of composite shot peening process parameters into the gear surface morphology feature prediction model, and obtaining the gear surface morphology feature parameters;

[0048] S4. Process the gear tooth surface morphology characteristic parameters and perform correlation analysis to generate the gear tooth surface friction coefficient and gear tooth surface film thickness ratio for expressing the gear tooth surface anti-adhesion ability, and process the gear tooth surface friction coefficient and gear tooth surface film thickness ratio to generate a gear tooth surface comprehensive evaluation coefficient for comprehensively evaluating the anti-adhesion ability;

[0049] S5. Taking the maximization of the comprehensive evaluation coefficient of the gear tooth surface as the objective function, under the constraints of the composite shot peening process parameters, the individuals of the initial population of composite shot peening process parameters are iteratively optimized through the genetic algorithm to obtain the optimal individuals, and based on the optimal individuals, the optimal values ​​of the composite shot peening process parameters are extracted.

[0050] Based on the above embodiments, the measuring equipment and method of pit diameter, pit depth and roughness are as follows:

[0051] Scanning the gear surface with a laser beam, obtaining the diameters of a plurality of pits by reflection of the laser, and calculating the average diameter of the plurality of pits as the pit diameter;

[0052] Use a probe of a profilometer to contact the bottom of the pit, measure the depths of multiple pits, and calculate the average depth of the multiple pits as the pit depth;

[0053] The probe of the roughness meter is moved on the surface to record the height changes of the gear tooth surface, so as to calculate the average roughness of the gear tooth as the roughness of the gear tooth surface.

[0054] On the basis of the above embodiments, different projectile diameters, projectile velocities, mass flow rates, spot diameters and power densities are set, and the composite shot peening process parameters are randomly combined to carry out spiral bevel gear processing tests. After the test, the same morphological characteristic parameters of the tooth surface are detected multiple times to obtain the average value of the morphological characteristic parameters.

[0055] On the basis of the above embodiment, the composite shot peening process parameters are randomly combined to construct individuals of the initial population of composite shot peening process parameters. The specific process is as follows:

[0056] The initial population is labeled as Q, and the initial population Q={Q1,Q2,…,Q j ,…,Q n}, Q j is the jth individual in the initial population, j is the index of the individual in the initial population, and j∈[1,n], n is the number of individuals in the initial population, Q j ={d j ,v j ,m j ,D j ,P j}, where d j ,v j ,m j ,D j ,P j are the projectile diameter, projectile velocity, mass flow rate, spot diameter and power density of the jth individual respectively.

[0057] On the basis of the above embodiment, the gear surface morphology feature 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;

[0058] In this embodiment, the input features of the deep learning network of the multilayer perceptron include five features: projectile diameter, projectile velocity, mass flow rate, spot diameter and power density.

[0059] The structure of the deep learning network of multi-layer perceptron is:

[0060] Input layer: receives input of 5 features;

[0061] The first hidden layer has 128 neurons and uses ReLU as the activation function.

[0062] The second hidden layer has 64 neurons and also uses the ReLU activation function.

[0063] The third hidden layer has 32 neurons and uses the ReLU activation function.

[0064] Output layer: has 1 neuron, gear tooth surface morphology characteristic parameters.

[0065] The process of training the gear tooth surface topography prediction model is as follows:

[0066] Different combinations of composite shot peening process parameters are used as input, and the gear surface morphology characteristic parameters 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 gear surface morphology characteristic prediction model is completed.

[0067] Based on the above embodiments, the correlation between the pit diameter, pit depth and roughness and the anti-adhesion ability of the gear tooth surface is as follows:

[0068] Within a certain range, the increase in the pit diameter can increase the microscopic roughness of the gear tooth surface, thereby improving the ability to retain the lubricating oil film, reducing direct contact between metals, and thus enhancing the anti-adhesion ability. Therefore, the pit diameter is positively correlated with the anti-adhesion ability of the gear tooth surface.

[0069] Within a certain range, the increase in pit depth can accommodate more lubricating oil and form an oil film on the gear tooth surface, thereby enhancing the anti-adhesion ability. Therefore, the pit depth is positively correlated with the anti-adhesion ability of the gear tooth surface.

[0070] Within a certain range, increasing the surface roughness can enhance the lubrication effect, increase the small gap between the friction surfaces, promote the formation of oil film, reduce metal contact, and enhance the anti-adhesion ability. Therefore, the roughness and the anti-adhesion ability of the gear tooth surface are positively correlated.

[0071] According to the correlation between the pit diameter, pit depth and roughness and the anti-adhesion ability of the gear tooth surface, the gear tooth surface morphology characteristic parameters are processed and correlation analysis is performed to generate the gear tooth surface friction coefficient used to express the anti-adhesion ability. The formula is as follows:

[0072] MCx j =α1·wd j +α2·wh j +α3·cr j

[0073] Among them, MCxs j is the friction coefficient of the jth gear tooth surface. The friction coefficient of the gear tooth surface is used to comprehensively evaluate the anti-adhesion ability of the gear tooth surface from three aspects: pit diameter, pit depth and roughness. The larger the friction coefficient of the gear tooth surface, the greater the anti-adhesion ability of the gear tooth surface.

[0074] Where wd j is the diameter of the jth individual pit, wh j is the pit depth of the jth individual, cr j is the roughness of the jth individual;

[0075] The reason for setting the above function form to express the functional relationship between the friction coefficient of the gear surface and the pit diameter, pit depth and roughness is as follows:

[0076] First, the friction coefficient of the gear tooth surface is not the result of a single parameter, but the joint effect of multiple parameters. By weighted summing up multiple parameters, the logical relationship between the pit diameter, pit depth, roughness and the gear tooth surface friction coefficient can be truly characterized, reflecting the influence of each parameter on the gear tooth surface friction coefficient.

[0077] Second, the pit diameter, pit depth and roughness represent the microscopic characteristics of the surface, reflecting the surface lubrication performance, contact characteristics and friction characteristics, and have clear physical meanings. Through linear combination, we can better understand the influence of these parameters on the friction coefficient.

[0078] Third, the weight coefficients (α1, α2, α3) are used to adjust the different parameters on the tooth surface friction coefficient MCxs j These weights reflect the difference in the impact of pit diameter, pit depth and roughness on the friction coefficient of the gear tooth surface.

[0079] Wherein, α1, α2, and α3 are all preset weight coefficients, α1 is specifically the weight of the influence of the pit diameter on the friction coefficient of the gear tooth surface, α2 is specifically the weight of the influence of the pit depth on the friction coefficient of the gear tooth surface, and α3 is specifically the weight of the influence of the roughness on the friction coefficient of the gear tooth surface;

[0080] The pit diameter plays an important role in the friction characteristics of the gear tooth surface. A larger pit diameter can provide more lubricant storage space, thereby effectively reducing the direct contact between metal surfaces. Good lubrication conditions can significantly reduce the friction coefficient and improve the anti-adhesion ability, so α1 is usually the largest;

[0081] Roughness directly affects the friction characteristics. Moderate roughness can improve the ability to retain lubricating oil, but if the roughness is too high, it may increase friction. The influence of roughness is relatively complex. It not only depends on the characteristics of the surface itself, but also on the combined effects of friction materials, lubrication conditions, working environment and other factors. Its weight is after the pit diameter, so α3 is usually lower than α1.

[0082] The effect of pit depth on friction characteristics is relatively small. Although the depth can increase the thickness of the lubricating oil film, if the depth is too large, it will lead to increased friction, which will in turn affect the anti-adhesion ability. The effect of pit depth on friction coefficient is not as significant as the pit diameter and roughness, so α2 is the lowest.

[0083] To summarize, on the basis of α1+α2+α3=1, let 0<α2<α3<α1<1.

[0084] As an implementation mode, the value range of α1 is 0.4-0.5, the value range of α2 is 0.2-0.25, and the value range of α3 is 0.3-0.35. The specific values ​​are set by technicians according to actual conditions and are not limited here.

[0085] Based on the above embodiment, a higher film thickness ratio means that the lubricating oil film can effectively cover and isolate the gear tooth surface, reduce direct contact between metals, reduce the friction coefficient, and thus improve the anti-adhesion ability. Therefore, there is a positive correlation between the film thickness ratio and the anti-adhesion ability;

[0086] A larger pit diameter can provide a larger lubricating oil storage space. According to the principles of fluid mechanics, the larger the pit diameter, the thicker the oil film that can be formed on the surface. This is because a larger pit can effectively capture and retain lubricants, reducing the risk of oil film rupture, thereby increasing the film thickness ratio. At the same time, a larger pit diameter can reduce the actual contact area of ​​the gear tooth surface, reduce local contact pressure, and thus reduce the possibility of wear and adhesion, and improve anti-adhesion ability;

[0087] When the pit depth is larger, a more stable oil film can be formed on the gear tooth surface. The deep pit can effectively hold the lubricating oil. Even under high load conditions, the oil film is not easily squeezed out, thereby maintaining a high film thickness ratio. At the same time, a moderate depth is crucial to improving anti-adhesion ability. Increasing the pit depth can help disperse pressure, optimize load distribution, and reduce fatigue wear.

[0088] Surface roughness directly affects the fluidity and adhesion of lubricating oil. Appropriate roughness can increase the adhesion area of ​​the oil film, which is helpful for the distribution and stability of the lubricating oil. When the roughness is moderate, it can enhance the formation of the lubricating oil film, thereby increasing the film thickness ratio. At the same time, moderate roughness can improve the anti-adhesion ability.

[0089] On this basis, there is a positive correlation between the pit diameter, pit depth, roughness and film thickness ratio, and there is a positive correlation between the pit diameter, pit depth, roughness and anti-adhesion ability.

[0090] According to the correlation between the pit diameter, pit depth, roughness and film thickness ratio, the gear surface morphology characteristic parameters are processed and the correlation analysis is performed to generate the gear surface film thickness ratio used to express the anti-bonding ability of the gear surface. The formula is as follows:

[0091] MHb j =β1·(wd j ·wh j )+β2·cr j

[0092] Among them, MHbl j is the gear tooth surface film thickness ratio of the jth individual. The gear tooth surface film thickness ratio is used to comprehensively evaluate the anti-adhesion ability of the gear tooth surface from three aspects: pit diameter, pit depth and roughness. The larger the gear tooth surface film thickness ratio, the greater the gear tooth surface anti-adhesion ability;

[0093] The reasons for setting the above function form to express the functional relationship between the gear surface film thickness ratio and the pit diameter, pit depth and roughness are as follows:

[0094] First, the gear tooth surface film thickness ratio is not the result of a single parameter, but the joint effect of multiple parameters. By weighted summing up multiple parameters, the logical relationship between pit diameter, pit depth, roughness and gear tooth surface film thickness ratio can be truly characterized, reflecting the influence of each parameter on the gear tooth surface film thickness ratio.

[0095] Second, (wd j ·wh j ) This item jointly considers the oil storage capacity and oil film stability of the pit, reflecting the positive effect of the pit characteristics on the anti-adhesion ability. The larger the pit diameter and the deeper the pit, the more effective it is to store lubricating oil and maintain a stable oil film, reduce the possibility of metal contact, and improve the anti-adhesion ability.

[0096] Third, roughness cr j In this formula, as a separate weighted item, its effect on the adhesion and fluidity of the lubricating oil film is highlighted. Moderate roughness can increase the adhesion area of ​​the lubricating oil, enhance the stability of the oil film, and thus improve the anti-adhesion ability.

[0097] Fourth, the weight coefficients (β1, β2) are used to adjust the effect of different parameters on the gear surface film thickness ratio MHbl j These weights reflect the combination of pit diameter and pit depth, and the difference in the effect of roughness on the film thickness ratio on the gear tooth surface.

[0098] Wherein, β1 and β2 are both preset weight coefficients, β1 is specifically the weight of the combination of pit diameter and pit depth on the gear tooth surface film thickness ratio, and β2 is specifically the weight of the roughness on the gear tooth surface film thickness ratio.

[0099] The pit diameter and pit depth directly affect the storage capacity of lubricating oil and the formation of oil film, and the combined characteristics of the pits largely determine the thickness and stability of the oil film.

[0100] Although surface roughness also has an important influence on the formation and stability of the lubricating oil film, its role is more limited than the influence of the pit characteristics. In many cases, moderate roughness does help the adhesion and distribution of the lubricating oil, but if the pit characteristics are insufficient, the generation and maintenance of the oil film will still be limited. Therefore, the influence of the geometric characteristics of the pit on the anti-adhesion ability is usually greater than the influence of roughness, that is, β1 as the combined weight of the pit characteristics is greater than β2.

[0101] To sum up, on the basis of β1+β2=1, let 0<β2<β1<1.

[0102] As an implementation mode, the value range of β1 is 0.55-0.6, and the value range of β2 is 0.4-0.45. The specific values ​​are set by technicians according to actual conditions and are not limited here.

[0103] On the basis of the above embodiment, the gear tooth surface friction coefficient and the gear tooth surface film thickness ratio are processed to generate a gear tooth surface comprehensive evaluation coefficient for comprehensive evaluation of anti-adhesion ability, according to the following formula:

[0104] ZGar j =γ1MCxs j +γ2MHbl j

[0105] Among them, ZPxs j is the comprehensive evaluation coefficient of the jth individual gear tooth surface. The comprehensive evaluation coefficient of the individual gear tooth surface is used to combine the individual gear tooth surface friction coefficient and gear tooth surface film thickness ratio to comprehensively evaluate the anti-bonding ability of the gear tooth surface. The comprehensive evaluation coefficient ZPxs j The larger it is, the greater the anti-bonding ability of the gear tooth surface;

[0106] It should be noted that, as can be seen from the above description, the friction coefficient of the individual gear tooth surface MCxs j The larger the gear tooth surface is, the greater the anti-bonding ability of the gear tooth surface is. The individual gear tooth surface film thickness is greater than MHbl j The larger the gear tooth surface is, the greater the gear tooth surface anti-bonding ability is. Therefore, the individual gear tooth surface comprehensive evaluation coefficient ZPxs j Friction coefficient with gear tooth surface MHxsj , gear tooth surface film thickness ratio MHbl j Therefore, the gear surface comprehensive evaluation coefficient ZPxs in the form of weighted summation is set as j Calculation formula;

[0107] In the formula, γ1 is the weight coefficient of the friction coefficient of the j-th individual gear tooth surface, γ2 is the weight coefficient of the film thickness ratio of the j-th individual gear tooth surface, and the specific values ​​of γ1 and γ2 are determined by the hierarchical analysis method. The specific logic is as follows:

[0108] The two indicators of gear tooth surface friction coefficient and gear tooth surface film thickness ratio are marked, and the relative importance between the two indicators is determined by the nine-scale method to construct a judgment matrix, in which the index of gear tooth surface friction coefficient is marked as 1, and the index of gear tooth surface film thickness ratio is marked as 2. The constructed judgment matrix [q uv ] 2×2 for:

[0109]

[0110] Where u and v are the indices of the coefficients, and u∈[1,2], v∈[1,2], indicating the importance of the coefficient with index u to the comprehensive evaluation coefficient of the gear tooth surface 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 than the coefficient with index v for the comprehensive evaluation coefficient of the gear tooth surface. uv =1 means that the coefficient with index u is extremely unimportant to the comprehensive evaluation coefficient of the gear tooth surface compared with the coefficient with index v;

[0111] Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the weight coefficient of the individual gear tooth surface friction coefficient, and the mean of the element values ​​in the second row is used as the weight coefficient of the individual gear tooth surface film thickness ratio. With the constraint that the sum of the scaled values ​​is equal to 1, the two weight coefficients are scaled proportionally, and the values ​​obtained after scaling are used as the weights of the corresponding coefficients.

[0112] Based on the above embodiment, the specific process of step S5 is as follows:

[0113] Find a balance point between the gear surface friction coefficient and the gear surface film thickness ratio to maximize the comprehensive evaluation coefficient. The comprehensive evaluation coefficient ZPxs jThe maximization is taken as 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, constraints are set, that is, the maximum and minimum values ​​of the projectile diameter, projectile speed, coverage rate, mass flow rate, spot diameter, power density, and overlap rate are set respectively. Within the constraints of the projectile diameter, projectile speed, mass flow rate, spot diameter, and power density, the initial population Q is iteratively optimized. Specifically, individuals with a comprehensive evaluation coefficient in the front column are selected as parents. The front column refers to individuals in the first 50% of the comprehensive evaluation coefficient. Through the crossover operation, the genes of the parent individuals are exchanged and combined to generate new individuals. Then, after the genes of the projectile diameter, projectile speed, mass flow rate, spot diameter, and power density in the newly generated individuals are mutated, the selection, crossover, and mutation operations are repeated until the predetermined number of iterations is reached;

[0114] After iterative optimization of the initial population Q, the optimal individual is marked as Q j1 ={d j1 ,v j1 ,m j1 ,D j1 ,P j1}, the optimal value of the composite shot peening process parameters for spiral bevel gears is the shot diameter d j1 , projectile velocity v j1 , mass flow rate m j1 , spot diameter D j1 and power density P j1 .

[0115] See also Figure 2 , the present invention also provides a technical solution:

[0116] A system for optimizing composite shot peening process parameters of spiral bevel gears based on gear tooth surface morphology analysis, the system being used to execute any of the above-mentioned methods for optimizing composite shot peening process parameters of spiral bevel gears based on gear tooth surface morphology analysis, comprising:

[0117] The process parameter combination and test module is used to carry out spiral bevel gear processing tests under different composite shot peening process parameter combinations. After the test, several spiral bevel gears are randomly selected. The surface morphology characteristic parameters of the gear teeth include pit diameter, pit depth and roughness. The composite shot peening process parameters include shot diameter, shot velocity, mass flow rate, spot diameter and power density.

[0118] The morphology feature prediction module is used to build a gear surface morphology feature prediction model, taking different composite shot peening process parameter combinations as input and the gear surface morphology feature parameters as label training models to train the gear surface morphology feature prediction;

[0119] A process parameter population construction 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 composite shot peening process parameters are randomly combined to construct individuals of the initial population of composite shot peening process parameters. The individuals of the initial population of composite shot peening process parameters are input into the gear surface morphology feature prediction model to obtain the gear surface morphology feature parameters.

[0120] A data processing and analysis module is used to process the gear tooth surface morphology characteristic parameters and perform correlation analysis to generate a gear tooth surface friction coefficient and a gear tooth surface film thickness ratio for expressing the gear tooth surface anti-adhesion ability, and to process the gear tooth surface friction coefficient and the gear tooth surface film thickness ratio to generate a gear tooth surface comprehensive evaluation coefficient for comprehensively evaluating the anti-adhesion ability;

[0121] The iterative optimization module is used to iteratively optimize the individuals of the initial population of composite shot peening process parameters by using a genetic algorithm with the maximization of the comprehensive evaluation coefficient of the gear tooth surface as the objective function under the constraints of the composite shot peening process parameters to obtain the optimal individuals, and based on the optimal individuals, extract the optimal values ​​of the composite shot peening process parameters.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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 the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis, characterized in that: The specific steps include: S1. Under different combinations of composite shot peening process parameters, spiral bevel gear processing tests were carried out respectively. After the test, several spiral bevel gears were randomly selected. The surface morphological characteristic parameters of the gear teeth included pit diameter, pit depth and roughness. The composite shot peening process parameters included shot diameter, shot velocity, mass flow rate, spot diameter and power density. S2. Construct a gear surface morphology feature prediction model, use different composite shot peening process parameter combinations as input, and use gear surface morphology feature parameters as label training models to train the gear surface morphology feature prediction; S3. Establishing the constraint conditions of the composite shot peening process parameters, under the constraint conditions of the composite shot peening process parameters, randomly combining the composite shot peening process parameters, constructing individuals of the initial population of composite shot peening process parameters, inputting the individuals of the initial population of composite shot peening process parameters into the gear surface morphology feature prediction model, and obtaining the gear surface morphology feature parameters; S4. Process the gear tooth surface morphology characteristic parameters and perform correlation analysis to generate the gear tooth surface friction coefficient and gear tooth surface film thickness ratio for expressing the gear tooth surface anti-adhesion ability, and process the gear tooth surface friction coefficient and gear tooth surface film thickness ratio to generate a gear tooth surface comprehensive evaluation coefficient for comprehensively evaluating the anti-adhesion ability; S5. Taking the maximization of the comprehensive evaluation coefficient of the gear tooth surface as the objective function, under the constraints of the composite shot peening process parameters, the individuals of the initial population of composite shot peening process parameters are iteratively optimized through the genetic algorithm 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 the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to claim 1 is characterized in that: The composite shot peening process parameters are randomly combined to construct individuals of the initial population of composite shot peening process parameters. The specific process is as follows: The initial population is labeled as Q, and the initial population Q={Q1,Q2,…,Q j ,…,Q n }, Q j is the jth individual in the initial population, j is the index of the individual in the initial population, and j∈[1,n], n is the number of individuals in the initial population, Q j ={d j ,v j ,m j ,D j ,P j }, where d j ,v j ,m j ,D j ,P j are the projectile diameter, projectile velocity, mass flow rate, spot diameter and power density of the jth individual respectively.

3. The method for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to claim 1 is characterized in that: The gear surface morphology feature prediction model is composed of a deep learning network based on a multi-layer perceptron, wherein the deep neural network of the multi-layer 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 gear tooth surface topography prediction model is as follows: Different combinations of composite shot peening process parameters are used as input, and the gear surface morphology characteristic parameters 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 gear surface morphology characteristic prediction model is completed.

4. The method for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to claim 2, characterized in that: The gear tooth surface morphology characteristic parameters are processed and correlated to generate the gear tooth surface friction coefficient used to express the anti-adhesion ability. The formula is as follows: MCxs j =α1·wd j +α2·wh j +α3·cr j Among them, MCxs j is the friction coefficient of the jth gear tooth surface, wd j is the pit diameter of the jth individual, wh j is the pit depth of the jth individual, cr j is the roughness of the j-th individual. On the basis of α1+α2+α3=1, let 0<α2<α3<α1<1.

5. The method for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to claim 4 is characterized in that: The gear tooth surface morphology characteristic parameters are processed and correlated to generate the gear tooth surface film thickness ratio used to express the anti-bonding ability of the gear tooth surface. The formula is as follows: MHbl j =β1·(wd j ·wh j )+β2·cr j Among them, MHbl j is the surface film thickness ratio of the jth individual tooth. On the basis of β1+β2=1, let 0<β2<β1<1.

6. The method for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to claim 5, characterized in that: The gear tooth surface friction coefficient and gear tooth surface film thickness ratio are processed to generate a gear tooth surface comprehensive evaluation coefficient for comprehensive evaluation of anti-adhesion ability, based on the following formula: ZPxs j =γ1MCxs j +γ2MHbl j Among them, ZPxs j is the comprehensive evaluation coefficient of the j-th individual gear tooth surface, γ1 is the weight coefficient of the friction coefficient of the j-th individual gear tooth surface, γ2 is the weight coefficient of the film thickness ratio of the j-th individual gear tooth surface, and the specific values ​​of γ1 and γ2 are determined by the hierarchical analysis method.

7. The method for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to claim 6, characterized in that: The specific process of step S5 is as follows: Find a balance point between the gear surface friction coefficient and the gear surface film thickness ratio to maximize the comprehensive evaluation coefficient. The comprehensive evaluation coefficient ZPxs j The maximization is taken as 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, constraints are set, that is, the maximum and minimum values ​​of the projectile diameter, projectile velocity, mass flow rate, spot diameter, and power density are set respectively. Within the constraints of the projectile diameter, projectile velocity, mass flow rate, spot diameter, and power density, the initial population Q is iteratively optimized. Specifically, the individual with the top comprehensive evaluation coefficient is selected as the parent generation, and the genes of the parent generation individuals are exchanged and combined through the crossover operation to generate new individuals. Then, the genes of the projectile diameter, projectile velocity, mass flow rate, spot diameter, and power density in the newly generated individuals are mutated, and 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 j1 ={d j1 ,v j1 ,m j1 ,D j1 ,P j1 }, the optimal value of the composite shot peening process parameters for spiral bevel gears is the shot diameter d j1 , projectile velocity v j1 , mass flow rate m j1 , spot diameter D j1 and power density P j1 .

8. A system for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis, the system being used to execute the method for optimizing the process parameters of spiral bevel gear composite shot peening based on gear tooth surface morphology analysis according to any one of claims 1 to 7, characterized in that: include: The process parameter combination and test module is used to carry out spiral bevel gear processing tests under different composite shot peening process parameter combinations. After the test, several spiral bevel gears are randomly selected. The surface morphology characteristic parameters of the gear teeth include pit diameter, pit depth and roughness. The composite shot peening process parameters include shot diameter, shot velocity, mass flow rate, spot diameter and power density. The morphology feature prediction module is used to build a gear surface morphology feature prediction model, taking different composite shot peening process parameter combinations as input and the gear surface morphology feature parameters as label training models to train the gear surface morphology feature prediction; A process parameter population construction 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 composite shot peening process parameters are randomly combined to construct individuals of the initial population of composite shot peening process parameters. The individuals of the initial population of composite shot peening process parameters are input into the gear surface morphology feature prediction model to obtain the gear surface morphology feature parameters. A data processing and analysis module is used to process the gear tooth surface morphology characteristic parameters and perform correlation analysis to generate a gear tooth surface friction coefficient and a gear tooth surface film thickness ratio for expressing the gear tooth surface anti-adhesion ability, and to process the gear tooth surface friction coefficient and the gear tooth surface film thickness ratio to generate a gear tooth surface comprehensive evaluation coefficient for comprehensively evaluating the anti-adhesion ability; The iterative optimization module is used to iteratively optimize the individuals of the initial population of composite shot peening process parameters by using a genetic algorithm with the maximization of the comprehensive evaluation coefficient of the gear tooth surface as the objective function under the constraints of the composite shot peening process parameters to obtain the optimal individuals, and based on the optimal individuals, extract the optimal values ​​of the composite shot peening process parameters.

Images