Pressing rivet quality optimization method based on genetic algorithm and grey correlation analysis

Abstract

The invention relates to a pressing rivet quality optimization method based on a genetic algorithm and grey correlation analysis. According to the pressing rivet quality optimization method based on the genetic algorithm and the grey correlation analysis, a genetic algorithm model is established by taking a quality optimization target as a maximum optimization target quality set Nx as an optimization target and taking a parameter set K as a definition parameter; carrying out an interaction test on the parameter set K to obtain a parameter set F having a great influence on the optimization target quality Nx, carrying out a Taguchi test and grey correlation analysis on the parameter set F to obtain a grey correlation value, building a fitness value of a genetic algorithm model according to the grey correlation value, judging whether the parameters of the genetic algorithm individual q belong to the set F, and if yes, carrying out the optimization of the target quality Nx. And establishing a mapping function according to the value of the grey relational degree to adjust the variation rate of the genetic algorithm model, performing variation iteration on the individual q according to the adjusted variation rate, controlling the genetic algorithm model to perform repeated calculation on the parameter set K until the maximum iteration is achieved, and outputting an optimal solution at the moment.

Description

Technical Field

[0001] The invention relates to the technical field of press riveting optimization, in particular to a press riveting quality optimization method based on genetic algorithm and grey correlation analysis. Background Art

[0002] Compression riveting is a riveting method. Specifically, it refers to the process of using external pressure to squeeze the compression riveted parts (such as rivets, nuts or studs, etc.) into the body material, causing the body material to undergo plastic deformation, so that they enter the special prefabricated grooves in the riveted screw and nut structure, thereby achieving a reliable connection between two or more parts.

[0003] Riveting strength is an important indicator to measure the quality of riveting, which mainly includes push-out force, twist-out force and maximum installation torque. Optimizing the riveting quality can ensure a stronger connection between riveted parts and reduce problems such as loosening and falling off caused by insufficient riveting strength. The methods for optimizing the riveting quality in the prior art mainly use the Taguchi method and the grey correlation algorithm to optimize the riveting quality. This method may rely on traditional experimental design, statistical analysis or empirical rules in the optimization process. These methods do not consider the influence of parameters on the optimization target during optimization, so all parameters need to be comprehensively evaluated. When solving complex optimization problems, the amount of calculation is large and the optimization efficiency is low. At the same time, during the optimization process, different parameter combinations are often tried one by one in the solution space, which is not targeted at important influencing parameters and is easy to fall into local optimal solutions.

[0004] In view of the above problems, the present invention provides a press riveting quality optimization method based on genetic algorithm and grey correlation analysis, which can quickly and accurately find the optimal press riveting quality optimization solution, thereby significantly improving the press riveting quality. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for optimizing the press riveting quality based on genetic algorithm and grey correlation analysis, which has the advantages of being able to quickly evaluate the optimal parameter group from a large number of parameters to optimize the press riveting quality, and solves the problem caused by the traditional technology failing to screen the parameters when optimizing the press riveting and directly evaluating the parameters through the algorithm.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for optimizing the quality of press riveting based on genetic algorithm and grey relational analysis, comprising the following steps: S1, determining the optimized target quality Nx of press riveting and the parameter set K that affects the riveting quality, wherein the parameter set K includes an adjustable design parameter set Ami and a riveting press control parameter set Bnj; establishing a genetic algorithm model with maximizing the optimized target quality set Nx as the optimization target and the parameter set K as the definition parameter; S2. Encode the parameter set K, and encode all parameter combinations in the parameter set K as X, X = (Ami, Bnj), where m and n are parameter types, and i and j are parameter levels; S3, set the population size to P, and randomly generate q individuals; S4, conducting interactive experiments on the adjustable design parameter set Ami and the riveting press control parameter Bnj to obtain the parameter set F that has a significant impact on the optimization target mass set Nx; S5. The parameter set F obtained through the interactive experiment is used to design an orthogonal experiment through the Taguchi method, the signal-to-noise ratio is calculated, and the signal-to-noise ratio is normalized and standardized; S6. Using the grey correlation analysis method to evaluate the grey correlation degree of each parameter in the parameter set F to the target quality of press riveting quality optimization, the signal-to-noise ratio after normalization and standardization is used; S7, taking the value of grey correlation as the fitness value, establishing the fitness function, taking the fitness function as the evaluation standard of the genetic algorithm model, and obtaining the fitness value of individual q; S8. Calculate the selection probability of each individual using the roulette wheel selection method according to the fitness value of the individual q, randomly select multiple individuals q from the population P to form a mating pool based on the selection probability, randomly select two individuals from the mating pool and generate two new offspring individuals in a single-point crossover manner; S9, set the initial mutation rate to W1, and establish a mapping function based on the parameter set F and the grey correlation degree of the parameter set F. , according to the mapping function To judge individual q, determine the mutation rate W of the offspring of individual q, randomly select a parameter of the offspring to mutate with the mutation rate W, merge the mutated offspring individuals into population P, and generate a new population P1; S10, taking the maximum number of iterations as the termination condition, repeatedly run S7-S9 until the termination condition is met to stop the calculation and generate the final population, select the individual with the highest fitness from the final population as the optimal solution, and finally output the parameter combination of the optimal individual and the corresponding optimization target quality Nx value.

[0007] Furthermore, the interactive test in S4 includes the following sub-steps: S4.1. There are m design parameters A, and each parameter has multiple levels , control parameters There are n, and each control parameter has multiple levels , establish an orthogonal array based on the number of factors and levels.

[0008] S4.2. According to the parameter combination determined by the orthogonal table, set the control parameter B of the riveting press and the design parameter A of the busbar, assign different levels of each parameter to each test and perform the riveting operation, and record the response variable value of each test, that is, optimize the target quality Nx.

[0009] S4.3. Calculate the average value of the optimized target quality Nx, use variance analysis to evaluate the influence of each parameter and its interaction on the optimized target quality Nx, and establish a variance analysis model: in , is the corresponding variable value under the combination of the i-th level of the m-th design parameter and the j-th level of the n-th control parameter, i.e., the optimized target quality, is the population mean, and are the main effects of design parameters and control parameters, is the interaction effect, is the error term.

[0010] ANOVA Model The p value in the output value is judged to determine whether P satisfies If yes, it means that this parameter combination has a significant impact on the optimization target quality N. The parameter combination that meets the conditions is used to establish the parameter F, where .

[0011] Further, the Taguchi method in S5 includes the following steps: S5.1. Determine the target quality Nx that needs to be optimized, establish an orthogonal table based on the number of parameter types (m+n) in the parameter set F and the number of levels i and j of each parameter, and conduct an orthogonal test.

[0012] S5.2. Measure and record the data of each quality characteristic Nx under each test condition.

[0013] S5.3. For each quality target Nx, calculate its signal-to-noise ratio according to the formula: Where n is the number of trials, is the value of the optimized target mass Nx measured in the lth test, is the target value for optimizing the target quality Nx, is the signal-to-noise ratio.

[0014] Furthermore, the signal-to-noise ratio in S5.3 is normalized by the formula: Where min and max Respectively The minimum and maximum values ​​of .

[0015] The signal-to-noise ratio in S5.3 is normalized by the formula: in yes The mean of yes The standard deviation of .

[0016] Furthermore, the grey correlation analysis in S6 also includes the following sub-steps: S6.1. Select X normalization and standardization As a reference sequence .

[0017] S6.2. Use the grey correlation analysis formula to calculate the corresponding The value of The correlation coefficient is given by the formula: in is the kth element of the reference sequence, xi(k) is the kth quality characteristic value under the ith test condition, is the resolution coefficient.

[0018] S6.3 Calculate the grey relational degree using the formula: Where X is the quantity of the optimization target quality, It is the grey relational degree between the i-th parameter combination and the optimal value of the optimization target.

[0019] Further, the output value of the grey relational degree As the fitness value, and establish the fitness function , where the fitness function is: ; Further, the roulette selection formula in S8 is: in Represents an individual The probability of being selected, represents the fitness value of an individual, represents the sum of the fitness values ​​of all individuals in the population, where p is the population size, Indicates the population Individual.

[0020] Furthermore, the formula for establishing the mutation rate W(q) in S9 according to the parameter set F and the grey relational degree of the parameter set F is as follows: Where w1 is the initial mutation rate.

[0021] Compared with the prior art, the technical solution of this application has the following beneficial effects: 1. The riveting quality optimization method based on genetic algorithm and grey correlation analysis can obtain the parameter set F that has the greatest impact on the riveting quality from among many evaluation parameters by interactively testing the original evaluation parameters, thereby reducing the blindness of the genetic algorithm in the search space and greatly narrowing the search space in the subsequent optimization process, thereby improving the optimization efficiency of the genetic algorithm.

[0022] 2. This riveting quality optimization method based on genetic algorithm and grey correlation analysis uses the grey correlation degree obtained by the Taguchi method and grey correlation analysis of the parameter set F as the fitness function of the genetic algorithm and the basis for adjusting the mutation rate, so that the genetic algorithm can more intelligently adjust the mutation rate and selection strategy of different parameters during the evolution process, better reflect the actual impact of the parameters, and thus improve the optimization effect; this method effectively balances efficiency and accuracy by first screening the significantly influencing parameters and then performing in-depth optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of the press riveting quality optimization of the present invention; Figure 2 It is the interactive test flow chart of the present invention; Figure 3 It is the flow chart of Taguchi test and grey relational analysis of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] See also Figure 1 In this embodiment, a method for optimizing the quality of riveting based on genetic algorithm and grey relational analysis comprises the following steps: S1, determining the optimized target quality Nx of press riveting and the parameter set K that affects the riveting quality, wherein the parameter set K includes an adjustable design parameter set Ami and a riveting press control parameter set Bnj; establishing a genetic algorithm model with maximizing the optimized target quality set Nx as the optimization target and the parameter set K as the definition parameter; In the actual evaluation process, the staff can use the push-out force, twist-out force and limit installation torque of the rivet after riveting as the optimized target quality Nx of riveting. The adjustable design parameter Ami in actual use includes the design parameters of the busbar, such as hole diameter, material, thickness, etc., and the design parameters of the rivet, such as diameter, length, material, etc. The control parameters of the riveting press include the pressing loading force, pressing speed, pressing holding time and the distance between the center line of the hole and the edge, etc. The above design parameters and control parameters are used as the parameter set K, and the optimization target quality Nx is used as the optimization target to establish a genetic algorithm model. The genetic algorithm is used to calculate the best combination from the above parameters to achieve the best riveting quality. Compared with traditional algorithms, it has a strong global optimization capability and can search for the global optimal solution or a solution close to the global optimal solution in a complex parameter space. This means that it can not only find the local optimal solution, but also explore the possible solution space in a larger range, thereby increasing the chance of finding the true optimal solution.

[0026] S2. Encode the parameter set K, and encode all the parameter combinations in the parameter set K as X, X=(Ami, Bnj), where m and n are parameter types, and i and j are parameter levels; where m and n include the design parameters of the busbar, such as hole diameter, material, thickness, etc., and the design parameters of the rivet, such as the diameter, length, material, etc. of the rivet, and the control parameters of the riveting press include the pressing load force, pressing speed, pressing holding time, and the distance between the center line of the hole and the edge, etc. i and j can represent the levels of different parameters, such as different materials, different lengths, etc.

[0027] S3, set the population size to P, and randomly generate q individuals; See also Figure 2 : S4. Interactive experiments are conducted on the adjustable design parameter set A and the riveting press control parameter B to obtain the parameter set F that has a significant impact on the optimization target quality set Nx; S4.1. There are m design parameters A, and each parameter has multiple levels , control parameters There are n, and each control parameter has multiple levels , establish an orthogonal array based on the number of factors and levels.

[0028] S4.2. According to the parameter combination determined by the orthogonal table, set the control parameter B and design parameter A of the riveting press, assign different levels of each parameter to each test and perform the riveting operation, and record the response variable value of each test, that is, optimize the target quality Nx.

[0029] S4.3. Calculate the average value of the optimized target quality Nx, use variance analysis to evaluate the influence of each parameter and its interaction on the optimized target quality Nx, and establish a variance analysis model: in , is the corresponding variable value under the combination of the i-th level of the m-th design parameter and the j-th level of the n-th control parameter, i.e., the optimized target quality, is the population mean, and are the main effects of design parameters and control parameters, is the interaction effect, is the error term.

[0030] ANOVA Model The p value in the output value is judged to determine whether P satisfies If yes, it means that this parameter combination has a significant impact on the optimization target quality Nx. The parameter combination that meets the conditions is used to establish the parameter F, where .

[0031] By establishing an orthogonal table of the above parameters and obtaining the parameter set F for optimizing the target quality through variance analysis, the parameters and interactions that have a significant impact on the system performance can be preliminarily screened out, thereby reducing unnecessary test combinations in subsequent Taguchi tests and reducing test costs and time.

[0032] The results of the interactive experiment can guide how to adjust the parameter levels in the Taguchi experiment to maximize the system performance and improve its robustness. For example, if a parameter is found to have a significant impact on system performance and has an optimal level, then in the Taguchi experiment, this parameter can be fixed at this level to optimize other parameters.

[0033] It is worth mentioning that the riveting operation in the above experiment can be replaced by a simulation model, which can reduce the experimental cost on the one hand and increase work efficiency on the other.

[0034] By using the variance analysis method to obtain the parameter set F that has a greater impact on the target quality Nx, compared with other methods, it can more comprehensively consider the influence of all parameters and their interactions, thereby drawing more accurate conclusions.

[0035] Set the threshold of the p-value in the ANOVA results to It can make statistically significant judgments. The p-value represents the probability of observing the current data or more extreme data when the null hypothesis (that is, the parameter has no significant effect on the optimization target) is true. Setting the p-value threshold to 0.05 means that if the p-value is less than 0.05, we have 95% confidence to reject the null hypothesis, that is, we believe that the parameter has a significant effect on the optimization target. This provides a clear statistical standard to determine which parameters are important.

[0036] See also Figure 3 : S5, the parameter set F obtained through the interactive experiment is used to design an orthogonal experiment through the Taguchi method, the signal-to-noise ratio is calculated, and the signal-to-noise ratio is normalized and standardized; The Taguchi method in S5 includes the following steps: S5.1. Determine the target quality Nx that needs to be optimized, establish an orthogonal table based on the number of parameter types (m+n) in the parameter set F and the number of levels i and j of each parameter, and conduct an orthogonal test.

[0037] S5.2. Measure and record the data of each target mass Nx under each test condition.

[0038] S5.3. For each quality target Nx, calculate its signal-to-noise ratio according to the formula: Where n is the number of trials, is the value of the optimized target mass Nx measured in the lth test, is the target value for optimizing the target quality Nx, is the signal-to-noise ratio.

[0039] The signal-to-noise ratio in S5.3 is normalized by the formula: Where min and max Respectively The minimum and maximum values ​​of .

[0040] The signal-to-noise ratio in S5.3 is normalized by the formula: in yes The mean of yes The standard deviation of .

[0041] By using the Taguchi method to establish an orthogonal test table, the number of experiments can be systematically reduced while maintaining a certain ability to evaluate the interaction between parameters. This means that with limited resources, more parameter combinations can be covered more quickly, thereby accelerating the optimization process.

[0042] The signal-to-noise ratio is a quantitative indicator used to evaluate the degree of influence of each parameter or parameter combination on the optimization target. A high SNR value indicates that the parameter or combination has a significant and stable influence on the optimization target, while a low SNR value may indicate a small or unstable influence.

[0043] In order to facilitate the subsequent grey correlation analysis of the signal-to-noise ratio value, the signal-to-noise ratio value needs to be processed.

[0044] S6. Using the grey correlation analysis method to evaluate the grey correlation degree of each parameter in the parameter set F to the target quality of press riveting quality optimization, the signal-to-noise ratio after normalization and standardization is used; The grey relational analysis in S6 also includes the following sub-steps: S6.1. Select X normalization and standardization As a reference sequence .

[0045] S6.2. Use the grey correlation analysis formula to calculate the corresponding The value of The correlation coefficient is given by the formula: in is the kth element of the reference sequence, xi(k) is the kth quality characteristic value under the ith test condition, is the resolution coefficient.

[0046] S6.3 Calculate the grey relational degree using the formula: Where X is the quantity of the optimization target quality, is the grey relational degree between the i-th parameter combination and the optimal value of the optimization target. The value range is The normalized and standardized signal-to-noise ratio allows the results from different parameters or different experimental conditions to be compared on the same scale. This helps to identify which parameters are critical, which parameters have negligible effects, and their relative importance.

[0047] For this solution, in multi-objective optimization problems such as optimizing the push-out force, twist-out force, and limit installation torque at the same time, the normalized and standardized signal-to-noise ratio can be used as the weight or priority indicator of each objective function. This helps to find a balance between multiple optimization objectives, thereby obtaining a riveting solution with better comprehensive performance.

[0048] Output value of grey relational degree As the fitness value, and establish the fitness function , where the fitness function is: ; Taking the value of grey correlation as the fitness function of the genetic algorithm can effectively optimize the genetic algorithm. The genetic algorithm itself is a search algorithm based on natural selection and genetic mechanism, with global search capability. Taking grey correlation as the fitness function can further guide the algorithm to search more widely in the solution space, because grey correlation analysis can consider the degree of correlation between multiple factors and the target, which helps to find the potential global optimal solution. At the same time, it can reduce the impact of these parameters on the performance of the algorithm to a certain extent, because grey correlation analysis itself has a certain anti-interference ability and robustness, and can more stably evaluate the pros and cons of individuals.

[0049] S7, taking the value of grey correlation as the fitness value, establishing the fitness function, taking the fitness function as the evaluation standard of the genetic algorithm model, and obtaining the fitness value of individual q; S8. Calculate the selection probability of each individual using the roulette wheel selection method according to the fitness value of the individual q, randomly select multiple individuals q from the population P to form a mating pool based on the selection probability, randomly select two individuals from the mating pool and generate two new offspring individuals in a single-point crossover manner; The roulette selection formula in S8 is: in Represents an individual The probability of being selected, represents the fitness value of an individual, represents the sum of the fitness values ​​of all individuals in the population, where p is the population size, Indicates the population Individual.

[0050] The roulette wheel selection method is directly based on the individual fitness, which is evaluated and selected by the grey relational degree in this scheme. Since the grey relational degree has been normalized or standardized, the consistency and comparability of the data are ensured, making the fitness evaluation more accurate and efficient.

[0051] Furthermore, although the roulette wheel selection method itself is random, some strategies can be used to reduce the impact of its randomness on the performance of the algorithm. For example, in this scheme, an elite retention strategy can be combined, that is, the best individuals in each generation are directly retained to the next generation, or the roulette wheel selection method can be appropriately improved, such as introducing nonlinear transformations, to better meet the needs of specific problems.

[0052] S9, set the initial mutation rate to W1, and establish a mapping function based on the parameter set F and the grey correlation degree of the parameter set F. , according to the mapping function To judge individual q, determine the mutation rate W of the offspring of individual q, randomly select a parameter of the offspring to mutate with the mutation rate W, merge the mutated offspring individuals into population P, and generate a new population P1; The formula for establishing the mutation rate W(F) in S9 according to the parameter set F and the grey relational degree of the parameter set F is as follows: Where w1 is the initial mutation rate, and W is the mutation rate during the genetic algorithm calculation process.

[0053] In actual use, the initial mutation rate W1 can be set between 0.01 and 0.05. A lower initial mutation rate helps maintain the stability of the population in the early stages of the algorithm. In the initial stages of a genetic algorithm, individuals in the population are often generated randomly or based on some heuristic method, and their quality may vary. A lower mutation rate can reduce the damage to excellent individuals in the early stages of the algorithm, which helps the algorithm converge to a better solution more quickly. The staff can determine the specific value of the initial mutation rate W1 based on actual usage.

[0054] By combining the correlation analysis between the parameters of individual q and set F with the adjustment of the mutation rate, the algorithm can more intelligently select the direction and intensity of mutation. When the correlation between individual parameters and the target is high, the mutation rate can be appropriately reduced to maintain the stability of the solution; when the correlation is low, the mutation rate is increased to explore a wider solution space. This strategy helps the algorithm avoid falling into the local optimal solution while maintaining search efficiency.

[0055] S10, taking the maximum number of iterations as the termination condition, repeatedly run S7-S9 until the termination condition is met to stop the calculation and generate the final population, select the individual with the highest fitness from the final population as the optimal solution, and finally output the parameter combination of the optimal individual and the corresponding optimization target quality Nx value.

[0056] In the actual evaluation process, through repeated operations, the genetic algorithm can search the solution space more comprehensively and increase the possibility of finding the global optimal solution. The crossover and mutation operations in the genetic algorithm help to jump out of the local optimal solution and explore a wider solution space. Repeated operations can reduce the uncertainty of the results of a single operation and improve the stability and reliability of the algorithm. By statistically analyzing the results of multiple operations, the performance and effect of the algorithm can be evaluated. After reaching the maximum number of iterations, the algorithm can output the optimal parameter combination after multiple iterations. These parameter combinations usually have better performance.

[0057] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing the quality of press riveting based on genetic algorithm and grey relational analysis, characterized in that: The steps include: S1, determining the optimized target quality Nx of press riveting and the parameter set K that affects the riveting quality, wherein the parameter set K includes an adjustable design parameter set Ami and a riveting press control parameter set Bnj; establishing a genetic algorithm model with maximizing the optimized target quality set Nx as the optimization target and the parameter set K as the definition parameter; S2. Encode the parameter set K, and encode all parameter combinations in the parameter set K as X, X = (Ami, Bnj), where m and n are parameter types, and i and j are parameter levels; S3, set the population size to P, and randomly generate q individuals; S4, conducting interactive experiments on the adjustable design parameter set Ami and the riveting press control parameter Bnj to obtain the parameter set F that has a significant impact on the optimization target mass set Nx; S5. The parameter set F obtained through the interactive experiment is used to design an orthogonal experiment through the Taguchi method, the signal-to-noise ratio is calculated, and the signal-to-noise ratio is normalized and standardized; S6. Using the grey correlation analysis method to evaluate the grey correlation degree of each parameter in the parameter set F to the target quality of press riveting quality optimization, the signal-to-noise ratio after normalization and standardization is used; S7, taking the value of grey correlation as the fitness value, establishing the fitness function, taking the fitness function as the evaluation standard of the genetic algorithm model, and obtaining the fitness value of individual q; S8. Calculate the selection probability of each individual using the roulette wheel selection method according to the fitness value of the individual q, randomly select multiple individuals q from the population P to form a mating pool based on the selection probability, randomly select two individuals from the mating pool and generate two new offspring individuals in a single-point crossover manner; S9, set the initial mutation rate to W1, and establish a mapping function based on the parameter set F and the grey correlation degree of the parameter set F. , according to the mapping function To judge individual q, determine the mutation rate W of the offspring of individual q, randomly select a parameter of the offspring to mutate with the mutation rate W, merge the mutated offspring individuals into population P, and generate a new population P1; S10, taking the maximum number of iterations as the termination condition, repeatedly run S7-S9 until the termination condition is met to stop the calculation and generate the final population, select the individual with the highest fitness from the final population as the optimal solution, and finally output the parameter combination of the optimal individual and the corresponding optimization target quality Nx value.

2. The method for optimizing riveting quality based on genetic algorithm and grey relational analysis according to claim 1, characterized in that: The interactive test in S4 includes the following sub-steps: S4.

1. There are m design parameters A, and each parameter has multiple levels , control parameters There are n, and each control parameter has multiple levels , establish an orthogonal array according to the number of factors and levels; S4.

2. According to the parameter combination determined by the orthogonal table, set the control parameter B of the riveting press and the design parameter A of the busbar, assign different levels of each parameter to each test and perform the riveting operation, and record the response variable value of each test, that is, optimize the target quality Nx; S4.

3. Calculate the average value of the optimized target quality Nx, use variance analysis to evaluate the influence of each parameter and its interaction on the optimized target quality Nx, and establish a variance analysis model: in , is the corresponding variable value under the combination of the i-th level of the m-th design parameter and the j-th level of the n-th control parameter, i.e., the optimized target quality, is the population mean, and are the main effects of design parameters and control parameters, is the interaction effect, is the error term; ANOVA Model The p value in the output value is judged to determine whether P satisfies If yes, it means that this parameter combination has a significant impact on the optimization target quality N. The parameter combination that meets the conditions is used to establish the parameter F, where .

3. The method for optimizing riveting quality based on genetic algorithm and grey relational analysis according to claim 1, characterized in that: The Taguchi method in S5 includes the following steps: S5.

1. Determine the target quality Nx to be optimized, establish an orthogonal table based on the number of parameter types (m+n) in the parameter set F and the number of levels i and j of each parameter, and conduct an orthogonal test; S5.

2. Measure and record the data of each quality characteristic Nx under each test condition; S5.

3. For each quality target Nx, calculate its signal-to-noise ratio according to the formula: Where n is the number of trials, is the value of the optimized target mass Nx measured in the lth test, is the target value for optimizing the target quality Nx, is the signal-to-noise ratio.

4. The method for optimizing riveting quality based on genetic algorithm and grey relational analysis according to claim 3, characterized in that: The signal-to-noise ratio in S5.3 is normalized by the formula: Where min and max Respectively The minimum and maximum values ​​of ; The signal-to-noise ratio in S5.3 is normalized by the formula: in yes The mean of yes The standard deviation of .

5. The method for optimizing the riveting quality based on genetic algorithm and grey relational analysis according to claim 1 or 4, characterized in that: The grey relational analysis in S6 also includes the following sub-steps: S6.

1. Select X normalization and standardization As a reference sequence ; S6.

2. Use the grey correlation analysis formula to calculate the corresponding The value of The correlation coefficient is given by the formula: in is the kth element of the reference sequence, xi(k) is the kth quality characteristic value under the ith test condition, is the resolution coefficient; S6.3 Calculate the grey relational degree using the formula: Where X is the quantity of the optimization target quality, It is the grey relational degree between the i-th parameter combination and the optimal value of the optimization target.

6. The method for optimizing riveting quality based on genetic algorithm and grey relational analysis according to claim 5, characterized in that: Output value of grey relational degree As the fitness value, and establish the fitness function , where the fitness function is: .

7. The method for optimizing riveting quality based on genetic algorithm and grey relational analysis according to claim 1, characterized in that: The roulette selection formula in S8 is: in Represents an individual The probability of being selected, represents the fitness value of an individual, represents the sum of the fitness values ​​of all individuals in the population, where p is the population size, Indicates the population Individual.

8. The method for optimizing riveting quality based on genetic algorithm and grey relational analysis according to claim 1, characterized in that: The formula for establishing the mutation rate W(q) in S9 according to the parameter set F and the grey relational degree of the parameter set F is as follows: Where w1 is the initial mutation rate.

Images