Speed reducer structure parameter optimization method based on leapfrog algorithm

Through the reduction device structural parameter optimization method based on the frog jump algorithm, the problems of excessive strength and high cost in the existing reducer design are solved, and the effect of reducing costs and improving performance is achieved, improving the overall performance and design flexibility of the automobile.

CN118940405AActive Publication Date: 2024-11-12NORTHEAST AGRICULTURAL UNIVERSITY
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410980889.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

The existing reducer design has problems such as excessive strength, large mass, and large volume, resulting in poor fuel economy, handling and internal space layout, and the traditional optimization method is costly and cannot meet customer needs.

Method used

Using the reducer structural parameter optimization method based on the frog jump algorithm, the reducer structural parameters are optimized to reduce costs and improve through segmented encoding and population initialization, combined with the penalty function method and improved grouping method, variant operation and elite guidance strategy. performance.

Benefits of technology

The reduction gear structure is optimized, production costs are reduced, power transmission efficiency is improved, service life is extended, design flexibility and product quality are improved, and defects of traditional optimization methods are avoided, such as premature convergence and inability to meet customer needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940405A_ABST
    Figure CN118940405A_ABST
Patent Text Reader

Abstract

A speed reducer structure parameter optimization method based on a leapfrog algorithm belongs to the technical field of speed reducer structure design optimization, and comprises the following steps: step 1, individual coding is divided into three parts, the first part is a continuous real number variable, the second part is an integer variable, and the third part is a discrete variable; 2, performing population initialization; 3, changing a constrained optimization problem into an unconstrained optimization problem by using a penalty function, and establishing an objective function of a speed reducer structure optimization problem; step 4, calculating an objective function value of the speed reducer, sorting and grouping, and dividing a population into two groups; 5, updating the first group of individuals; 6, performing combination mutation operation on the first group of individuals; 7, updating the second group of individuals; and 8, combining the first group and the second group as a new population, sorting and recording an optimal solution and an optimal value, continuing iteration until an iteration termination condition is met, and outputting the optimal solution and the optimal value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of reducer structure design optimization, and in particular to a reducer structure parameter optimization method based on a frog leaping algorithm. Background Art

[0002] At present, the replacement of automobiles is accelerating and the R&D cycle is relatively short. In order to reduce material loss, reduce costs and improve vehicle performance, the R&D department usually makes improvements based on the original component models in the later stage of R&D, but this leads to excessive strength in the empirical design in the early stage of R&D. In the past vehicle development, the reducers selected by engineers based on experience had problems such as excessive strength, large mass, and large volume, which had a certain impact on the fuel economy, handling, and layout of the interior space of the car, and could not achieve the ideal state of lightweight. In addition, the use of traditional optimization methods requires re-modeling and optimization on the original design, which is often more complicated in actual situations and cannot minimize the mass. At the same time, the existing reducer optimization methods are costly and cannot meet customer needs. Therefore, it is of great significance to optimize the structural parameters of automobile reducers. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method for optimizing the reducer structure parameters based on the frog leaping algorithm, which can reduce the production cost of the reducer and improve the performance of the reducer, in view of the shortcomings of the prior art.

[0004] The technical problem to be solved by the present invention is achieved by the following technical solution. The present invention is a method for optimizing the structural parameters of a reducer based on a frog leaping algorithm, which is characterized by comprising the following steps: the chromosome is encoded in a segmented manner, and the chromosome is divided into three parts, the first part is a continuous real number variable, the second part is an integer variable, and the third part is a discrete variable;

[0005] Step 2: Population initialization, where the variables include continuous real variables, integer variables and discrete variables, which need to be initialized separately. For the i-th individual Xi in the population, the initialization method is as follows:

[0006] The continuous real number variable initialization method is random generation, that is, X i1 =Lb i +(Ub i -Lb i )×rand(1,DN iv -N dv ), Lb i and Ub i are the lower and upper limit vectors of the value of the ith variable, N iv is the number of integer variables, Ndv is the number of discrete variables, rand is a randomly generated random number uniformly distributed between [0,1];

[0007] The initialization method of the integer variable is random generation, that is, X i2 =Lb i +randperm(Ub i -Lb i ,N iv ), randperm(Ub i -Lb i ,N iv ) is randomly generated [1,Ub i -Lb i ]N without repetition iv integers;

[0008] The initialization method of the discrete variables is as follows: First, the i-th discrete variable X i3 The value set of S i ={s 1 ,s 2 ,…,s Qi}, S i Each number in is mapped to a continuous integer interval Z i , Z i ∈[1,2,…,Q i ],i=1,2,…,N dv ; Then, in set Z i A random integer is generated in the system, and the randomly generated integer is set to k. Then the discrete variable takes S i The kth value s in k ;

[0009] The i-th individual X in the population generated by the above method i =[X i1 ,X i2 ,X i3 ], repeat the above steps N times to generate an initial population of N individuals;

[0010] Step 3: Construct the objective function of reducer optimization, establish the objective function according to the sum of the volumes of the shaft system components, and the objective function is to find the minimum value; use the penalty function method to deal with the constraints;

[0011] Step 4: Calculate the individual fitness values ​​and arrange them in descending order according to the fitness values. Group the individuals in the population according to the improved grouping method, and divide the individuals into two groups, the first N / 2 individuals into one group, and the last N / 2 individuals into another group;

[0012] The improved grouping method sorts by the fitness and divides into two groups according to the predation method. The individuals with better fitness are in the first group and prey by local search in place, simulating local development. The individuals with poorer fitness are in the second group and move by jumping towards places with more food to prey, simulating global exploration.

[0013] Step Five: Update the positions of the individuals in the first group and adopt an elitist retention evolutionary strategy.

[0014] Step Six: Perform a combined mutation operation on the individuals in the first group, including the following steps:

[0015] First Step: Set the mutation probability p m = 0.8, randomly select the individuals in the first group except the optimal individual, and randomly generate a random number r 1 between [0, 1]. When r 1 ≤ p m , perform the mutation operation on the selected individual.

[0016] Second Step: Set the dynamically adaptive adjustment transition probability p, p(t) = p max -(p max -p min )×Rt(t) / MaxRt, let p max = 1, p min = 0, where Rt(t) is the running time from the start to the t-th iteration, and MaxRt is the maximum running time.

[0017] Third Step: Randomly generate a random number r 2 between [0, 1]. When r 2 < p, perform Cauchy mutation; otherwise, perform Lévy mutation.

[0018] Step Seven: Update the individuals in the second group. First, set the step size adjustment coefficient c i , Then, perform an elite-guided strategy to update the positions of the individuals in the second group.

[0019] Step Eight: Combine the individuals in the first group and the second group as a new population, sort and record the optimal solution and the optimal value. Determine whether the iteration termination condition is satisfied. If satisfied, stop the iteration and output the optimal solution and the optimal value. If not satisfied, repeat Steps Four to Eight until the iteration termination condition is satisfied.

[0020] The technical problem to be solved by the present invention can also be further realized by the following technical solution. The update formula in Step Five is:

[0021] NewXli =N D (Xl i ,σ 2 )

[0022]

[0023] In the formula, NewXl i is the offspring generated after the update of the i-th frog in the first group, Xl i,j is the jth component of the ith frog, N D (Xl i ,σ 2 ) is Xl i is the mean, σ 2 is the variance, a D-dimensional random row vector that follows a normal distribution;

[0024] The updated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

[0025] The technical problem to be solved by the present invention can be further achieved by the following technical solution. In step 6, the random individuals in the first group move to a new position after Cauchy mutation, which is represented as:

[0026] NewXl rand =Xl rand +δ×s Cauchy

[0027] After Lévy mutation, the movement to the new position is expressed as:

[0028] NewXl rand =Xl rand +δ×s Lévy

[0029] Where Xl rand is the individual other than the best individual randomly selected from the first group, δ is the adjustment parameter and takes 1;

[0030] The mutated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

[0031] The technical problem to be solved by the present invention can be further achieved by the following technical solution. The elite guidance strategy in step seven includes the following steps: first, the individuals in the first group and the second group are evenly divided into two parts, that is, the individuals in the first group are divided into [1, 2, ..., 0.5N 1 ] and [0.5N1 +1,0.5N 1 +2,…,N 1 ], the individuals in the second group are divided into [1,2,…,0.5N 2 ] and [0.5N 2 +1,0.5N 2 +2,…,N 2 ]; Then, when [1,2,…,0.5N in the second group 2 ]When an individual updates its position, it starts from the first group [1,2,…,0.5N 1 ] to randomly select an elite individual to guide the second group [1,2,…,0.5N 2 ]An individual updates its position, and the position update formula of the second individual is:

[0032]

[0033] The updated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] (1) The reducer structure was optimized. Based on theoretical research, the reducer structural parameter optimization method based on the frog leaping algorithm was applied to the production of various types of reducers. This has important significance in many aspects for improving the overall performance of the automobile and saving costs and increasing efficiency. It can reduce production costs, improve the power transmission efficiency of the automobile, extend its service life, enhance design flexibility, save production materials, and improve product quality.

[0036] (2) In the study of the improved hybrid frog leaping algorithm, adding mutation operations and improving the update strategy can reduce the occurrence of premature convergence, increase population diversity, and improve global search capabilities. For such complex engineering optimization problems, it can avoid the defects of the traditional optimization method's own architecture. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the present invention;

[0038] Figure 2 It is a schematic diagram of the individual structure of the population;

[0039] Figure 3 This is a simplified diagram of the structure and dimensions of the reducer shaft system components;

[0040] Figure 4 The schematic diagram of the structure size of the reducer is shown in Figure 1. DETAILED DESCRIPTION

[0041] The specific technical solutions of the present invention are further described below to help those skilled in the art further understand the present invention without limiting the rights thereof.

[0042] Reference Figure 1-Figure 4 , a method for optimizing reducer structural parameters based on frog leaping algorithm, comprising:

[0043] Step 1: Reference Figure 2 The individuals are encoded using segmented coding. The optimization problem has D variables, including N iv integer variable, N dv discrete variables, and the remaining variables are continuous real variables. The individuals are coded using segmented coding. Each individual is divided into three parts. The first part is a continuous real variable, the second part is an integer variable, and the third part is a discrete variable. The i-th individual X in the population i The structure is represented as (X i1 ,…,X i(D-Niv-Ndv) ,X i(D-Niv-Ndv+1) ,…,X i(D-Ndv) ,X i(D-Ndv+1) ,…,X iD );

[0044] Step 2: Population initialization. Different types of variables use different initialization methods. The variables include continuous real variables, integer variables, and discrete variables.

[0045] The i-th individual X i The continuous real variable X i1 The initialization method is randomly generated, that is, X i1 =Lb i +(Ub i -Lb i )×rand(1,DN iv -N dv ), Lb i and Ub i are the lower and upper limit vectors of the value of the ith variable, N iv is the number of integer variables, N dv is the number of discrete variables, rand is a randomly generated random number uniformly distributed between [0,1];

[0046] The initialization method of the integer variable is random generation, that is, X i2 =Lb i +randperm(Ub i -Lb i ,N iv ), randperm(Ub i -Lb i,N iv ) is randomly generated [1,Ub i -Lb i ]N without repetition iv integers;

[0047] The initialization method of the discrete variables is as follows: First, let the i-th discrete variable X i3 The value set of S i ={s 1 ,s 2 ,…,s Qi}, S i Each number in is mapped to a continuous integer interval Z i , Z i ∈[1,2,…,Q i ],i=1,2,…,N dv ; Then, in set Z i A random integer is generated in the system, and the randomly generated integer is set to k. Then the discrete variable takes S i The kth value s in k ;

[0048] The i-th individual X in the population generated by the above method i =[X i1 ,X i2 ,X i3 ], repeat the above steps N times to generate an initial population containing N individuals.

[0049] Step 3: Construct the objective function of reducer optimization. The smaller the volume of the shaft system components, the smaller the mass of the reducer. First, establish the objective function according to the sum of the volumes of the shaft system components. The objective function is to find the minimum value. Then, process the constraints and use the penalty function method to punish the solutions that do not meet the constraints, and finally turn the infeasible solution into a feasible solution.

[0050] Step 4: Calculate the fitness values ​​of all N individuals in the population and arrange them in descending order. Group them according to the improved grouping method. The first N individuals in the sorted population 1 The individuals are the first group, denoted as Xl, and the N 2 The second group is composed of individuals, denoted as Xfo, where N 1 and N 2 Equal, equal to N / 2;

[0051] The improved grouping method is to sort by fitness and divide them into two groups according to the predation method. The individuals with better fitness are in the first group, which prey by searching in situ to simulate local development; the individuals with poorer fitness are in the second group, which jump and move towards places with more food to simulate global exploration.

[0052] Step 5: Update the individuals in the first group according to the position update formula and adopt the elite retention strategy; the update formula generates offspring through a normal distribution, with the position of the individual to be updated as the mean, and controls the distance of the individual's updated position by controlling the value of the variance. As the number of iterations increases, the variance value changes from large to small, and the exploration ability of the algorithm gradually weakens while the development ability gradually increases;

[0053] Step 6: Perform a combined mutation operation on the individuals in the first group. The combined mutation operation includes the following steps:

[0054] The first step: Set the mutation probability p m , randomly select individuals in the first group except the optimal individual, and randomly generate a random number r between [0, 1] 1 , when r 1 ≤p m , perform a mutation operation on the selected individual;

[0055] The second step: Set the dynamic adaptive adjustment transformation probability p, p(t) = p max -(p max -p min )×Runtime(t) / MaxRuntime, let p max = 1, p min = 0, Runtime(t) is the running time from the start to the t-th iteration, and MaxRuntime is the maximum running time;

[0056] The third step: Randomly generate a random number r between [0, 1] 2 , when r 2 <p, perform Cauchy mutation; otherwise, perform Lévy mutation;

[0057] Step 7: Update the individuals in the second group according to the update formula. First, set the step size adjustment coefficient c i , the step size has a great influence on the performance of the algorithm. In order to better balance the global exploration ability and the local development ability, an adaptive step size adjustment coefficient c that is independent of the maximum number of iterations and the maximum running time and changes continuously is set i , c i is used in the update formula for the individuals in the second group, so that the algorithm conducts global search with a high probability and local search with a low probability in the early stage of iteration, and vice versa in the later stage of iteration, but the global search ability at this time is weaker than that in the early stage of iteration. The calculation formula of c i is: α 1 、α 2 and α 3 are adjustment coefficients, α 1 = 0.9, α 2is a random vector of 1 row and D columns uniformly distributed between [0.2, 0.8], α 3 =2, bF(t) is the fitness value of the best individual in the second group at the tth iteration, wF(t) is the fitness value of the worst individual in the second group at the tth iteration, f i (t) is the fitness value of the i-th individual in the second group in the t-th iteration; then, the elite guidance strategy is executed to update the individuals in the second group;

[0058] The position update formula of the individuals in the second group is:

[0059]

[0060] In the formula, c i is the step length adjustment coefficient, Xfo i is the i-th individual in the second group, Xl r is an individual randomly selected from the first group, Xl elite is an individual randomly selected from the first 20% of the individuals in the first group, and Xl elite ≠Xl r , N 2 is the number of individuals in the second group;

[0061] Step 8: Merge the first group and the second group as a new population, sort them from small to large according to the individual fitness values ​​and record the optimal solution and the optimal value; determine whether the iteration termination condition is met. If so, stop the iteration and give the optimal value and the optimal solution; if not, repeat steps 4 to 7 until the iteration termination condition is met.

[0062] The technical problem to be solved by the present invention can be further achieved by the following technical solution: the i-th individual X in step 2 i The continuous real variable X i1 The initialization method is random generation, that is, X i1 =Lb i +(Ub i -Lb i )×rand(1,DN iv -N dv ), Lb i and Ub i are the lower and upper limit vectors of the value of the ith variable, N iv is the number of integer variables, N dv is the number of discrete variables, rand is a randomly generated random number uniformly distributed between [0,1];

[0063] The i-th integer variable X i2 The initialization method is random generation, that is, X i2 =Lbi +randperm(Ub i -Lb i ,N iv ), randperm(Ub i -Lb i ,N iv ) is randomly generated [1,Ub i -Lb i ]N without repetition iv integers;

[0064] The i-th discrete variable X i3 The initialization method is: First, if the i-th discrete variable X i3 The value set of S i ={s 1 ,s 2 ,…,s Qi}, S i Each number in is mapped to a continuous integer interval Z i , Z i ∈[1,2,…,Q i ],i=1,2,…,N dv ; Then, in set Z i A random integer is generated in the system, and the randomly generated integer is set to k. Then the discrete variable takes S i The kth value s in k ;

[0065] The i-th individual X in the population generated by the above method i =[X i1 ,X i2 ,X i3 ], repeat the above steps N times to generate an initial population containing N individuals;

[0066] The updated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

[0067] The technical problem to be solved by the present invention can also be further achieved by the following technical solution. The penalty function method in step 3 includes: when processing the constraint conditions of the mixed discrete variable problem, the equality constraint is converted into an inequality constraint. At the same time, in order to avoid the failure of the penalty function due to the small penalty term, the formula of the penalty function method is as follows:

[0068]

[0069] Where M 1 、M 2 Take a sufficiently large constant, f(Xc ) is the objective function term, G i (X c )=max(0,g i (X c )), H i (X c )=max(0,|h j (X c )|-ξ), ξ=10 -4 , g i (X c ) is the inequality constraint penalty term, h i (X c ) is the equality constraint penalty term.

[0070] The technical problem to be solved by the present invention can also be further achieved by the following technical solution, and the objective function in step three is:

[0071]

[0072] The variables include: the transmission ratio i of the first gear set 1 、Number of teeth of pinion of primary gear set z 1 、Number of teeth of pinion of secondary gear set z 3 , first gear module m n1 , Secondary gear set module m n2 、Helix angle of helical gear of primary gear set β 1 、Helix angle of helical gear of secondary gear set β 2 , tooth width coefficient of primary gear set Secondary gear set tooth width coefficient Input shaft diameter d' 1 、Intermediate shaft diameter d' 2 , output shaft diameter d' 3 , z 1 and z 3 is an integer, m n1 and m n2 is a discrete variable.

[0073] The technical problem to be solved by the present invention can also be further achieved by the following technical solution, wherein the update formula in step 5 is:

[0074] NewXl i =N D (Xl i ,σ 2 )

[0075]

[0076] In the formula, NewXl i is the offspring generated after the position of the ith individual in the first group is updated, Xl i,j is the jth component of the ith individual, N D (Xl i ,σ 2 ) is Xl i is the mean, σ 2 is a D-dimensional random row vector with a normal distribution.

[0077] The technical problem to be solved by the present invention can be further achieved by the following technical solution. The random individuals in the first group of step 6 are moved to a new position after Cauchy mutation, which is represented as follows:

[0078] NewXl rand =Xl rand +δ×s Cauchy

[0079] After Lévy mutation, the movement to the new position is expressed as:

[0080] NewXl rand =Xl rand +δ×s Lévy

[0081] Where Xl rand are individuals randomly selected from the first group except the best individual, and δ is the adjustment parameter and takes 1.

[0082] The technical problem to be solved by the present invention can be further achieved by the following technical solution. The elite guidance strategy in step seven includes the following steps: first, the individuals in the first group and the second group are evenly divided into two parts, that is, the individuals in the first group are divided into [1, 2, ..., 0.5N 1 ] and [0.5N 1 +1,0.5N 1 +2,…,N 1 ], the individuals in the second group are divided into [1,2,…,0.5N 2 ] and [0.5N 2 +1,0.5N 2 +2,…,N 2 ]; Then, when [1,2,…,0.5N in the second group 2 ]When an individual updates its position, it starts from the first group [1,2,…,0.5N 1 ] to randomly select an elite individual to guide the second group [1,2,…,0.5N 2 ]An individual updates its position, and the position update formula of the second individual is:

[0083]

[0084] The updated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

[0085] Embodiment 1: In order to give the optimal structural parameters of the reducer, the structural parameter optimization of a certain type of reducer is taken as an example; first, a mathematical model of the reducer structural parameter optimization problem is established; secondly, the proposed frog leaping algorithm (ISFLA) is used to solve the mathematical model of the reducer structural parameter optimization problem, and the optimal structural parameters of the reducer that minimizes the reducer volume are obtained;

[0086] The objective function of the reducer structural parameter optimization problem is:

[0087]

[0088] Assume that the maximum running time of the frog leaping algorithm (ISFLA) solution MaxTime = 20s, and the penalty factor M = 10 8 , population size N = 100, p m =0.8, the corresponding relationship between the standard modulus and the mapping value is shown in the following table:

[0089]

[0090] The mathematical model of the reducer structure optimization problem is solved by using the frog leaping algorithm (ISFLA). The optimal structural parameters are: the transmission ratio of the first gear set i 1 Equal to 3.3, the number of teeth of the first-stage pinion is z 1 Equal to 17, the number of teeth of the secondary pinion is z 3 Equal to 17, the module of the first gear set is m n1 Equal to 2mm, secondary gear set module m n2 Equal to 2mm, the helix angle of the first gear set is β 1 Equal to 8°, the helix angle of the secondary gear set is β 2 Equal to 8°, first gear set tooth width coefficient Equal to 0.6, secondary gear set tooth width coefficient Equal to 0.6, input shaft diameter d' 1 Equal to 20mm, intermediate shaft diameter d' 2 Equal to 25mm, output shaft diameter d' 3 Equal to 23.3mm, the volume of the reducer after optimization is 529011.373mm 3 , and the actual volume of the reducer before optimization is 717646.8mm 3The optimized reducer has a significantly smaller volume, which can save raw material consumption and reduce costs. In addition, the reduced volume can reduce the weight of the reducer, thereby reducing the weight of the vehicle and helping to reduce fuel consumption.

Claims

1. A method for optimizing reducer structural parameters based on frog leaping algorithm. Its characteristics are: The steps include: Step 1: The chromosome is encoded in segmented form, and the chromosome is divided into three parts. The first part is a continuous real number variable, the second part is an integer variable, and the third part is a discrete variable. Step 2: Population initialization. The variables include continuous real variables, integer variables, and discrete variables. They need to be initialized separately. For the i-th individual X in the population i Its initialization method is as follows: The continuous real number variable initialization method is random generation, that is, X i1 =Lb i +(Ub i -Lb i )×rand(1,DN iv -N dv ), Lb i and Ub i are the lower and upper limit vectors of the value of the ith variable, N iv is the number of integer variables, N dv is the number of discrete variables, rand is a randomly generated random number uniformly distributed between [0,1]; The initialization method of the integer variable is random generation, that is, X i2 =Lb i +randperm(Ub i -Lb i ,N iv ), randperm(Ub i -Lb i ,N iv ) is randomly generated [1,Ub i -Lb i ]N without repetition iv integers; The initialization method of the discrete variables is as follows: First, the i-th discrete variable X i3 The value set of S i ={s 1 ,s 2 ,…,s Qi }, S i Each number in is mapped to a continuous integer interval Z i , Z i ∈[1,2,…,Q i ],i=1,2,…,N dv ; Then, in set Z i A random integer is generated in the system, and the randomly generated integer is set to k. Then the discrete variable takes S i The kth value s in k ; The i-th individual X in the population generated by the above method i =[X i1 ,X i2 ,X i3 ], repeat the above steps N times to generate an initial population containing N individuals; Step 3: Construct the objective function of reducer optimization, and establish the objective function according to the sum of the volumes of the shaft system components. The objective function is to find the minimum value; Use penalty function method to deal with constraints; Step 4: Calculate the individual fitness values ​​and arrange them in descending order according to the fitness values. Group the individuals in the population according to the improved grouping method, and divide the individuals into two groups, the first N / 2 individuals into one group, and the last N / 2 individuals into another group; The improved grouping method is to sort by fitness and divide them into two groups according to the predation method. The individuals with better fitness are in the first group, which prey by searching in situ to simulate local development; the individuals with poorer fitness are in the second group, which jump and move towards places with more food to simulate global exploration. Step 5: Update the positions of the individuals in the first group and adopt the elite retention evolutionary strategy; Step 6: Perform a combined mutation operation on the individuals in the first group, including the following steps: Step 1: Set the mutation probability p m =0.8, randomly select individuals from the first group except the best individual, and randomly generate a random number r between [0,1] 1 , when r 1 ≤p m When , mutation operation is performed on the selected individuals; Step 2: Set the dynamic adaptive adjustment conversion probability p, p(t) = p max -(p max -p min )×Rt(t) / MaxRt, let p max =1, p min =0, Rt(t) is the running time from the beginning to the tth iteration, and MaxRt is the maximum running time; Step 3: Randomly generate a random number r between [0, 1] 2 , when r 2 < p, perform Cauchy mutation; otherwise, perform Lévy mutation; Step 7: Update the individuals in the second group. First, set the step adjustment coefficient c i , Then, the elite guidance strategy is executed to update the positions of individuals in the second group; Step 8: Combine the individuals in the first group and the second group as a new population, sort and record the optimal solution and optimal value; determine whether the iteration termination condition is met, stop the iteration if it is met, and output the optimal solution and optimal value; if not, repeat steps 4 to 8 until the iteration termination condition is met.

2. According to claim 1, the method for optimizing reducer structural parameters based on frog leaping algorithm, Features: The position update formula of the individuals in the first group in step 5 is: NewXl i =N D (Xl i ,σ 2 ) In the formula, NewXl i is the offspring generated after the position of the i-th frog in the first group is updated, Xl i,j is the jth component of the ith frog, N D (Xl i ,σ 2 ) is Xl i is the mean, σ 2 is the variance, a D-dimensional random row vector that follows a normal distribution; The updated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

3. According to claim 1, the method for optimizing reducer structural parameters based on frog leaping algorithm, Features: In step 6, the individuals in the first group move to a new position after Cauchy mutation, which is expressed as: NewXl rand =Xl rand +δ×s Cauchy After Lévy mutation, the movement to the new position is expressed as: NewXl rand =Xl rand +δ×s Lévy Where Xl rand is the individual other than the best individual randomly selected from the first group, δ is the adjustment parameter and takes 1; The mutated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

4. According to claim 1, the method for optimizing reducer structural parameters based on frog leaping algorithm, Features: The elite guidance strategy in step 7 includes the following steps: first, the individuals in the first group and the second group are evenly divided into two parts, that is, the individuals in the first group are divided into [1, 2, ..., 0.5N 1 ] and [0.5N 1 +1,0.5N 1 +2,…,N 1 ], the individuals in the second group are divided into [1,2,…,0.5N 2 ] and [0.5N 2 +1,0.5N 2 +2,…,N 2 ]; Then, when [1,2,…,0.5N in the second group 2 ]When an individual updates its position, it starts from the first group [1,2,…,0.5N 1 ] to randomly select an elite individual to guide the second group [1,2,…,0.5N 2 ]An individual updates its position, and the position update formula of the second individual is: The updated integer variables and discrete variables are rounded to the nearest integer. The processed integers need to be verified to see if they are within the solution space. If they are outside the solution space, a new integer value needs to be randomly generated within the solution space.

Citation Information

Patent Citations

  • Method for improving standard shuffled frog leaping algorithm

    CN105786759A

  • Power big data oriented microgrid short-period load prediction method

    CN106570250A

  • Intelligent radar offshore target detection system and method based on adaptive Shuffled Frog Leaping Algorithm (SFLA)

    CN107918117A

  • Cylindrical gear reducer structure optimization method based on sine and cosine algorithms

    CN118246159A

  • Scheduling method and system based on improved variable neighborhood search and differential evolution algorithm

    US20190080244A1