A vehicle body frame parameter optimization method, electronic device, storage medium and program

Abstract

The embodiment of the application discloses a kind of vehicle body framework parameter optimization method, electronic equipment, storage medium and program, comprising: using random chaos mapping mode according to the design variable initialization generation of each rod piece of vehicle body framework Myxomycete population;The fitness of each Myxomycete individual of Myxomycete population is calculated and sorted, and Myxomycete individual of target fitness is screened;According to enhanced nonlinear convergence factor, self-adapting adjustment feedback factor and Myxomycete individual of target fitness, Myxomycete updating method using elite guide strategy is used to update Myxomycete population;Using weight coefficient self-adapting adjustment Cauchy disturbance and Gaussian disturbance to disturb the Myxomycete population updated;If the current iteration number does not reach preset iteration number, return to execute the operation of calculating the fitness of each Myxomycete individual of Myxomycete population;The target design variable of each rod piece of vehicle body framework is determined according to the value of Myxomycete population at iteration end.The embodiment of the application can improve the optimization precision and efficiency of vehicle body framework parameter.

Description

Technical Field

[0001] The embodiments of the present invention relate to the fields of vehicle frame structure optimization and swarm intelligence optimization technology, and particularly to a method, device, electronic device, storage medium and program for optimizing vehicle frame parameters. Background Technology

[0002] As a crucial component bearing the weight of the entire vehicle and transmitting ground loads, the vehicle's chassis frame directly impacts its stiffness, NVH (Noise, Vibration, and Harshness) performance, and strength. Optimizing the structural dimensions of the chassis frame requires comprehensive consideration of multiple performance indicators, including NVH, stiffness, and strength, making it an expensive, multidisciplinary optimization problem.

[0003] Due to the large number of design variables, complex constraints, and strong nonlinearity, multidisciplinary optimization problems are typically solved using metaheuristic algorithms with strong global search capabilities. Swarm intelligence optimization algorithms such as particle swarm optimization, gray wolf optimization, and genetic algorithms have been widely applied in vehicle body structure optimization. However, in the optimization process of traditional swarm intelligence optimization algorithms, it is often impossible to balance the constraints between local exploitation and global search, leading to premature convergence or getting trapped in local optima. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, storage medium, and program for optimizing vehicle body frame parameters, which can improve the accuracy and efficiency of vehicle body frame parameter optimization.

[0005] According to one aspect of the present invention, a method for optimizing vehicle body frame parameters is provided, comprising:

[0006] A stochastic chaotic mapping method was used to initialize and generate slime mold populations based on the design variables of each component of the vehicle body frame.

[0007] The fitness of each slime mold individual in the slime mold population is calculated, and the slime mold population is sorted according to the fitness. Slime mold individuals with the target fitness are then selected based on the sorting results.

[0008] Based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and target fitness of slime mold individuals adapted to the slime mold population, the slime mold population is updated using an elite-guided slime mold update method to obtain an updated slime mold population.

[0009] The local slime mold population of the updated slime mold population is perturbed by Cauchy perturbation and Gaussian perturbation with adaptive weight coefficient adjustment;

[0010] If it is determined that the current iteration number has not reached the preset iteration number, return to perform the operation of calculating the fitness of each slime mold individual in the slime mold population until it is determined that the current iteration number has reached the preset iteration number;

[0011] The target design variables for each component of the vehicle body frame are determined based on the value of the slime mold population at the end of the iteration.

[0012] According to another aspect of the present invention, a vehicle body frame parameter optimization device is provided, comprising:

[0013] The slime mold population initialization module is used to initialize and generate a slime mold population based on the design variables of each component of the vehicle body frame using a random chaotic mapping method.

[0014] The slime mold individual screening module is used to calculate the fitness of each slime mold individual in the slime mold population, sort the slime mold population according to the fitness, and screen slime mold individuals with the target fitness according to the sorting results.

[0015] The slime mold population update module is used to update the slime mold population using an elite-guided slime mold update method based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor and slime mold individuals with the target fitness adapted to the slime mold population, thereby obtaining an updated slime mold population.

[0016] The slime mold population perturbation module is used to perturb the local slime mold population of the updated slime mold population using Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients;

[0017] The loop iteration module is used to return to the operation of calculating the fitness of each slime mold individual in the slime mold population if it is determined that the current iteration number has not reached the preset iteration number, until it is determined that the current iteration number has reached the preset iteration number;

[0018] The target design variable determination module is used to determine the target design variables of each member of the vehicle body frame based on the value of the slime mold population at the end of the iteration.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and a memory communicatively connected to said at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle frame parameter optimization method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle frame parameter optimization method according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the vehicle body frame parameter optimization method according to any embodiment of the present invention.

[0024] This invention employs a random chaotic mapping method to initialize and generate a slime mold population based on the design variables of each component of the vehicle body frame. The fitness of each individual slime mold in the population is calculated, and the population is sorted according to fitness. Individuals with the target fitness are then selected based on the sorting results. Further, an elite-guided slime mold update method is used to update the population based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and slime mold individuals with the target fitness. The updated slime mold population is then perturbed using Cauchy and Gaussian perturbations with adaptively adjusted weight coefficients, and it is determined whether the current iteration count has reached the preset iteration count. If the current iteration count has not reached the preset iteration count, the operation of calculating the fitness of each individual slime mold in the population can be repeated until the current iteration count is determined to have reached the preset iteration count. Finally, the target design variables of each component of the vehicle body frame can be determined based on the values ​​of the slime mold population at the end of the iteration. The above technical solution improves the traditional slime mold algorithm to optimize the vehicle body frame parameters, solving the problems of low convergence efficiency and easy getting trapped in local optima in the traditional slime mold algorithm, and can improve the optimization accuracy and efficiency of vehicle body frame parameters.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a method for optimizing vehicle body frame parameters provided in an embodiment of the present invention;

[0028] Figure 2This is a schematic diagram illustrating the three-dimensional structure of a vehicle frame and the corresponding positions of design variables provided in an embodiment of the present invention.

[0029] Figure 3 This is a schematic diagram comparing the convergence effects of an enhanced nonlinear convergence factor and a traditional nonlinear convergence factor provided in an embodiment of the present invention;

[0030] Figure 4 This is a schematic diagram of the convergence curve of an improved slime mold algorithm provided in an embodiment of the present invention;

[0031] Figure 5 This is a schematic diagram of a vehicle body frame parameter optimization device provided in an embodiment of the present invention;

[0032] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0035] Figure 1 This is a flowchart of a vehicle body frame parameter optimization method provided by an embodiment of the present invention. This embodiment is applicable to situations where a modified slime mold algorithm is used to optimize vehicle body frame parameters. This method can be executed by a vehicle body frame parameter optimization device, which can be implemented in software and / or hardware, and is generally integrated into an electronic device. This electronic device can be a terminal device or a server device, as long as it can execute the vehicle body frame parameter optimization method. This embodiment of the present invention does not limit the specific type of electronic device. Correspondingly, as... Figure 1 As shown, the method includes the following operations:

[0036] S110. The slime mold population is generated by initializing the design variables of each member of the vehicle body frame using a random chaotic mapping method.

[0037] The vehicle body frame can be the frame structure of any type of vehicle, including but not limited to unmanned inspection vehicles, cars, buses, and trucks, as well as the frame structure of subway or high-speed rail carriages. This embodiment of the invention does not limit the vehicle type to which the vehicle body frame belongs. Optionally, the design variables for each member of the vehicle body frame can be the member thickness parameters at corresponding positions.

[0038] Figure 2 This is a schematic diagram illustrating the three-dimensional structure of a vehicle body frame and the corresponding positions of design variables according to an embodiment of the present invention. In a specific example, such as... Figure 2 As shown, before optimizing the vehicle body frame, manufacturing constraints can be fully considered, and the members of the frame can be subjected to symmetrical constraints, ensuring that the dimensions of the members on both sides of the vehicle body remain consistent. For example, the initial design values ​​for each member of the vehicle body frame can be 3mm, the initial bending stiffness can be 25000N / mm, the initial torsional stiffness can be 20286.2N·m / deg, the initial first-order torsional modal frequency can be 95.09Hz, the initial first-order bending modal frequency can be 215.88Hz, and the initial mass can be 518kg. These initial parameter values ​​for the vehicle body frame can be used as reference comparison values ​​to determine the optimization effect of the improved slime mold algorithm on the vehicle body frame parameters.

[0039] In this embodiment of the invention, a single-objective, multi-constraint optimization mathematical model for the vehicle body frame can be constructed with the goal of minimizing the vehicle body mass and the various performance indicators of the vehicle body as constraints. The vehicle body frame optimization mathematical model is as follows:

[0040]

[0041] Y=min( )

[0042]

[0043] Where X represents the design variables of each member of the vehicle body frame, and Find X represents the set of design variables of each member of the vehicle body frame. For example... Figure 2 As shown, if 16 positional parameters are selected for each member of the vehicle body frame, then lb represents the lower limit of the design variable's value, and ub represents the upper limit of the design variable's value. Let Y represent the total vehicle mass. Y represents the objective function for constructing the vehicle body frame, and min() represents finding the minimum value. This is the design value for the bending stiffness of the vehicle body frame. This represents the target value for the bending stiffness of the vehicle body frame. This is the design value for the torsional stiffness of the vehicle body frame. This represents the target value for the torsional stiffness of the vehicle body frame. The design value for the first-order bending mode frequency of the vehicle body frame. The target value is the first-order bending mode frequency of the vehicle body frame. The design value for the first-order torsional modal frequency of the vehicle body frame. The target value is the first-order torsional modal frequency of the vehicle body frame. This is the i-th constraint condition, i.e., the i-th constraint function. Optional, the lower bound of the design variable values. Upper limit of the design variable value The target values ​​for all performance indicators of the vehicle body frame can be the performance values ​​at the initial design stage. For example, the target value for the bending stiffness of the vehicle body frame can be... The target value for the torsional stiffness of the car body frame can be The target value for the first-order bending mode frequency of the vehicle body frame is 20286.2 N·m / deg. The target value of the first-order torsional modal frequency of the vehicle body frame can be .

[0044] After constructing the mathematical model of the vehicle body frame, the improved slime mold algorithm can be used to optimize the parameters of the vehicle body frame.

[0045] Currently, traditional slime mold algorithms typically employ the Tent chaotic map method to initialize the slime mold population. The Tent chaotic map in slime mold algorithms is a simple piecewise linear function used to generate chaotic sequences, often employed to improve the algorithm's population initialization or perturbation mechanisms. However, because the Tent chaotic map method uses a linear mapping, it struggles to effectively cover all possible design variable values, potentially leading the slime mold algorithm to get trapped in local optima.

[0046] To address this technical problem, this invention replaces the Tent chaotic mapping method with a random chaotic mapping method. The random chaotic mapping method initializes and generates a slime mold population based on the design variables of each component of the vehicle body frame. Specifically, the random chaotic mapping method can generate the values ​​of the design variables randomly within a defined parameter range, thereby maximizing the range of design variable values ​​within the constraints. This results in high-quality initial population individual positions, ensuring the diversity of slime mold individuals and significantly improving the global search performance, convergence speed, and accuracy of the slime mold algorithm.

[0047] In an optional embodiment of the present invention, the initialization of the slime mold population based on the design variables of each member of the vehicle body frame using a random chaotic mapping method may include: determining the target members of the vehicle body frame; determining the parameter variable vector of each slime mold individual in the slime mold population based on the number of the target members of the vehicle body frame; and generating initial values ​​for each parameter variable of the parameter variable vector of each slime mold individual in the slime mold population using a random chaotic mapping method to obtain the initialized slime mold population.

[0048] The target member can be a member type for which relevant parameters need to be calculated.

[0049] For example, such as Figure 2 As shown, x1-x 16 The identified rods are designated as target rods. Accordingly, based on the number of target rods in the vehicle frame (16), the parameter variable vector for each slime mold individual in the slime mold population can be determined as follows: Furthermore, a random chaotic mapping method is used to map the parameter variables of each slime mold individual in the slime mold population to each parameter variable vector. By randomly generating initial values, the initial slime mold population can be obtained.

[0050] In an optional embodiment of the present invention, the step of generating initial values ​​for each parameter variable of the parameter variable vector of each slime mold individual in the slime mold population using a random chaotic mapping method may include: generating initial values ​​for each parameter variable of the parameter variable vector of each slime mold individual in the slime mold population based on the following formula:

[0051]

[0052] In the formula, The value of the parameter variable generated in the nth generation. The value of the parameter variable generated in the (n+1)th iteration. This is a control constant, which is optional. The value can be 0.499.

[0053] Specifically, the parameter variable vector of each slime mold individual in the slime mold population. The first batch of reference values ​​can be randomly generated by the system, with the random number ranging from [0,1]. Further, by substituting the first batch of reference values ​​for the parameter variable vectors of each slime mold individual in the slime mold population into the aforementioned formula for random chaotic mapping, and performing a nonlinear random mapping process on the first batch of reference values ​​using the formula, the initial values ​​of the parameter variable vectors of each slime mold individual in the slime mold population can be obtained. For example, x1 is randomly generated by the system, and... The first reference value is used as Substituting into the above formula for calculating random chaotic mappings, the calculated... The value can be used as The initial values ​​are then used. The above formula for calculating random chaotic mapping allows setting the initial values ​​of the parameter variable vectors for each slime mold individual in the slime mold population within the range of 2-5 mm.

[0054] S120. Calculate the fitness of each slime mold individual in the slime mold population, sort the slime mold population according to the fitness, and select slime mold individuals with the target fitness based on the sorting results.

[0055] The target fitness can be a fitness value that is relatively high in the slime mold population, such as the fitness value that ranks in the top half of the slime mold population.

[0056] Fitness refers to the evaluation value of each slime mold individual to the objective function, used to guide the search direction. When the slime mold algorithm iteratively updates the population, it calculates the fitness of each slime mold individual based on the objective function, then sorts them according to their fitness, and selects slime mold individuals with higher fitness based on the fitness ranking. For example, it can select slime mold individuals from the top half or top third of the population based on their fitness.

[0057] In an optional embodiment of the present invention, calculating the fitness of each slime mold individual in the slime mold population may include: calculating the fitness of each slime mold individual in the slime mold population based on the following formula, wherein the fitness of the slime mold individual can be divided into two parts: namely, target distance and adaptive penalty term:

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064]

[0065] in, For the j-th slime mold individual, Let be the fitness of the j-th slime mold individual. Let j be the target distance for the j-th slime mold individual. For the j-th slime mold individual, there is an adaptive penalty term; The constraint deviation for the j-th slime mold individual; Let j be the normalized target value for the j-th slime mold individual. For the determination parameters, N is the total number of slime mold individuals in the slime mold population, and m is the number of feasible solutions in the slime mold population. A feasible solution can be a solution that satisfies all constraints. For the target value of the j-th slime mold individual, To minimize the target value, This represents the maximum target value. For example, based on finite element calculations, when the thickness of all members of the vehicle body frame is... At that time, the mass of the car body frame ,Right now When the thickness of all members of the car body frame is At that time, the mass of the car body frame ,Right now . Let q be the violation severity value of the k-th constraint, and q be the number of constraints. To find the minimum degree of constraint violation for the k-th constraint among all slime mold individuals in the current iteration. To find the maximum degree of constraint violation for the k-th constraint among all slime mold individuals in the current iteration. It is a constant. The value can be 0.000001. For the k-th constraint, The configuration of constraints can be referenced from the above-mentioned mathematical model for vehicle body frame optimization.

[0066] The aforementioned method for calculating the fitness of slime mold individuals incorporates an adaptive penalty function based on vehicle body performance constraints. This function penalizes infeasible solutions in the slime mold algorithm, guiding it to explore and optimize within the feasible region, thus reducing computational cost. During the iterative optimization process, the penalty function can continuously adjust its weights to obtain the optimal solution that satisfies all constraints. This method requires no parameter tuning, is simple to operate, and has good operability.

[0067] S130. Based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and slime mold individuals with the target fitness adapted to the slime mold population, the slime mold population is updated using an elite-guided slime mold update method to obtain an updated slime mold population.

[0068] Among them, the enhanced nonlinear convergence factor is a nonlinear convergence factor that can reduce the convergence speed in the early stages of the slime mold algorithm iteration. The adaptive adjustment feedback factor can be used to improve the convergence speed of slime mold individuals. The updated slime mold population can be a new slime mold population obtained by updating the existing slime mold population.

[0069] Traditional slime mold algorithms employ linear or nonlinear convergence factors in their iterative processes. These factors tend to decrease convergence rapidly in the early stages of iteration, hindering global optimization and leading to premature convergence. To address this issue, enhanced nonlinear convergence factors can replace traditional ones. This reduces the initial convergence speed and gradually converges with each iteration, achieving a slow, nonlinear convergence. Correspondingly, when iteratively updating the slime mold population, an enhanced nonlinear convergence factor, an adaptively adjusting feedback factor, and slime mold individuals with target fitness can be used. An elite-guided update strategy is employed to update the population, resulting in an updated slime mold population. The elite-guided strategy uses slime mold individuals with optimal fitness to guide the overall update of the population, allowing the algorithm to fully utilize information from superior individuals and improve convergence accuracy.

[0070] In an optional embodiment of the present invention, the slime mold population update method using an elite-guided strategy, which updates the slime mold population based on the enhanced nonlinear convergence factor, the adaptive adjustment feedback factor, and the target fitness of the slime mold individuals adapted to the slime mold population, may include updating the slime mold population based on the following formula:

[0071]

[0072]

[0073]

[0074]

[0075] in, For the first Location information of slime molds, Here, represents the location information of the t-th generation slime mold, rand represents a random number, UB is the upper limit of the search range, and LB is the lower limit of the search range. This is the location of the slime mold individual with the best current fitness. To take values ​​in A random number between the given values, where a is the enhanced nonlinear convergence factor; The location information of a randomly selected slime mold individual among the slime mold individuals with the target fitness can be, for example, the location information of a randomly selected slime mold individual among the slime mold individuals ranked in the top 1 / 2 of fitness. As the oscillation factor, The value is in Random numbers between [a certain range], optional. , The preset iteration number is t, the current iteration number is t, and r is the value of t. A random number within a certain range; W is the weighting coefficient, D is the adaptive adjustment feedback factor, and z is a constant, which can take the value of 0.03; Let be the fitness value of the i-th slime mold individual. The hyperbolic tangent function is represented by bF, which is the first reference fitness in the calculation iteration process, such as the optimal fitness in the calculation iteration process; sort() represents the sorting function, condition is the slime mold individuals with the target fitness, such as slime mold individuals with the top 1 / 2 fitness in the population; others are slime mold individuals with non-target fitness, such as slime mold individuals with the bottom 1 / 2 fitness in the population; wF is the second reference fitness in the calculation iteration process, such as the worst fitness in the calculation iteration process; A random number in the range [0,1]. The position index of slime mold individuals after fitness sorting.

[0076] In an optional embodiment of the present invention, the enhanced nonlinear convergence factor adapted to the slime mold population can be: Where a represents the enhanced nonlinear convergence factor, and t represents the current iteration number. The preset iteration number is represented by C, which is a constant; the adaptive adjustment feedback factor can be: Where D represents the adaptive adjustment feedback factor, and g is a constant greater than 1. For example, the value of g can be 6.

[0077] Figure 3 This is a schematic diagram comparing the convergence performance of an enhanced nonlinear convergence factor and a traditional nonlinear convergence factor according to an embodiment of the present invention. In a specific example, assuming the constant C in the enhanced nonlinear convergence factor is 4, such as... Figure 3 As shown, the enhanced nonlinear factor has a larger value in the early stages of iteration, which can ensure the diversity of slime mold individuals to a certain extent and improve the global search performance of the algorithm. As the iteration progresses, the decay rate of the enhanced nonlinear factor undergoes a process of first increasing and then decreasing, with its value decreasing from 4 to 0. This enhanced nonlinear convergence factor can actively balance the local and global search capabilities of the algorithm based on the number of iterations. Introducing an adaptive feedback factor into the biological oscillation process of the slime mold algorithm can improve the slow convergence speed of the slime mold population, thereby improving the overall stability, convergence rate, and global search capability of the slime mold algorithm.

[0078] S140. The local slime mold population of the updated slime mold population is perturbed by Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients.

[0079] In this context, a local slime mold population can refer to a subset of slime mold individuals within a larger slime mold population. Cauchy perturbation and Gaussian perturbation are two probability distribution-based perturbation strategies used in intelligent optimization algorithms or stochastic search to introduce random mutations. Their core difference lies in the tail characteristics of the distribution used: Gaussian perturbation (normal distribution) excels at local fine-grained search, while Cauchy perturbation (heavy-tailed distribution) is better suited for escaping local optima and enhancing global exploration.

[0080] In an optional embodiment of the present invention, the perturbation of the local slime mold population of the updated slime mold population may include: perturbing the local slime mold population of the updated slime mold population using Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients based on the following formula:

[0081]

[0082] in, This provides the location information for the (t+1)th generation slime mold. For the first Location information of slime molds, The preset number of iterations is t, where t is the current iteration number. It is Cauchy distribution. It follows a Gaussian distribution.

[0083] In this embodiment of the invention, to improve the perturbation effect, dynamically changing weighting coefficients are added to the Cauchy distribution. At the same time, dynamically changing weighting coefficients were added to the Gaussian distribution. When solving high-dimensional problems, mutation perturbation of the top half of slime mold individuals in terms of fitness allows the slime mold population to better traverse the entire search domain, helping it escape the control of local optima to some extent and improving the convergence accuracy of the algorithm. Commonly used mutation perturbations include Cauchy perturbation and Gaussian perturbation. Compared to Gaussian perturbation, Cauchy perturbation has a flatter probability distribution function and stronger perturbation capability. In the early stages of iteration, the weight coefficients of the Cauchy distribution can bring about larger mutation perturbations, thereby expanding the search range of slime mold individuals and strengthening the global search capability; while in the later stages of iteration, the weight coefficients of the Cauchy distribution can bring about smaller deformation perturbations, thereby allowing for deeper development of slime mold individuals with better fitness and improving the quality of the solution. As the value of t increases, the value of Cauchy perturbation decreases, while Gaussian perturbation increases. Thus, in the early stages of iteration, the larger Cauchy perturbation strengthens the global search capability of the entire algorithm; in the later stages of iteration, the smaller Cauchy perturbation and the larger Gaussian perturbation strengthen the local search and lead to faster convergence.

[0084] S150. Determine whether the current iteration count has reached the preset iteration count. If yes, execute S160; otherwise, return to execute S120.

[0085] The preset number of iterations can be configured according to actual needs, such as 300 times. This embodiment of the invention does not limit the specific value of the preset number of iterations.

[0086] S160. Determine the target design variables for each member of the vehicle frame based on the value of the slime mold population at the end of the iteration.

[0087] The target design variable can be the optimized design value of each member of the vehicle body frame.

[0088] The improved slime mold algorithm described above is used to continuously update the slime mold population iteratively. After the algorithm iteration ends, the final values ​​of each parameter variable vector of each slime mold individual in the slime mold population can be obtained at the end of the iteration. These values ​​are used as target design variables at the corresponding positions of each member of the vehicle body frame, thereby realizing the optimization process of the parameters of each member of the vehicle body frame.

[0089] Table 1. Design variable values ​​for each member of the vehicle body frame after algorithm optimization.

[0090]

[0091] Table 2 Improvement in overall vehicle performance after optimization

[0092]

[0093] In a specific example, the initial population size for the slime mold algorithm is configured to be 20. Each slime mold individual can include 16 design variables, each representing the thickness of a member at a certain location on the vehicle's frame. A maximum number of iterations is also set. 300. The convergence curve of the optimal fitness F(x) of the slime mold population during the algorithm iteration process is attached. Figure 4 As shown. Figure 4 As shown, the slime mold algorithm converges to the optimal solution as the iteration progresses. Table 1 shows the design variable values ​​of each member of the vehicle frame after optimization using the slime mold algorithm, and Table 2 shows the improvement data of the overall vehicle performance after optimization. Referring to Table 2, compared to the initial design value of 3mm for each member of the vehicle frame, the optimized vehicle frame's bending stiffness increased from 25000 N / mm to 26007.8 N / mm, an increase of 4.03%; torsional stiffness increased from 20286.2 N·m / deg to 20511.9 N·m / deg, an increase of 1.11%; the first-order torsional modal frequency increased from 95.1 Hz to 95.1 Hz, an increase of 4.31%; the first-order bending modal frequency increased from 215.9 Hz to 219.3 Hz, an increase of 1.57%; and the overall vehicle weight decreased from 518 kg to 451.2 kg, a reduction of 12.72%.

[0094] This invention employs a random chaotic mapping method to initialize and generate a slime mold population based on the design variables of each component of the vehicle body frame. The fitness of each individual slime mold in the population is calculated, and the population is sorted according to fitness. Individuals with the target fitness are then selected based on the sorting results. Further, an elite-guided slime mold update method is used to update the population based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and slime mold individuals with the target fitness. The updated slime mold population is then perturbed using Cauchy and Gaussian perturbations with adaptively adjusted weight coefficients, and it is determined whether the current iteration count has reached the preset iteration count. If the current iteration count has not reached the preset iteration count, the operation of calculating the fitness of each individual slime mold in the population can be repeated until the current iteration count is determined to have reached the preset iteration count. Finally, the target design variables of each component of the vehicle body frame can be determined based on the values ​​of the slime mold population at the end of the iteration. The above technical solution improves the traditional slime mold algorithm to optimize the vehicle body frame parameters, solving the problems of low convergence efficiency and easy getting trapped in local optima in the traditional slime mold algorithm, and can improve the optimization accuracy and efficiency of vehicle body frame parameters.

[0095] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, and do not violate public order and good morals.

[0096] It should be noted that any arrangement or combination of the technical features in the above embodiments also falls within the protection scope of this invention.

[0097] Figure 5 This is a schematic diagram of a vehicle body frame parameter optimization device provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes: a slime mold population initialization module 510, a slime mold individual screening module 520, a slime mold population update module 530, a slime mold population perturbation module 540, a loop iteration module 550, and a target design variable determination module 560, wherein:

[0098] The slime mold population initialization module 510 is used to initialize and generate a slime mold population based on the design variables of each member of the vehicle frame using a random chaotic mapping method.

[0099] The slime mold individual screening module 520 is used to calculate the fitness of each slime mold individual in the slime mold population, sort the slime mold population according to the fitness, and screen slime mold individuals with the target fitness according to the sorting results.

[0100] The slime mold population update module 530 is used to update the slime mold population using an elite-guided slime mold update method based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor and slime mold individuals with the target fitness adapted to the slime mold population, so as to obtain an updated slime mold population.

[0101] The slime mold population perturbation module 540 is used to perturb the local slime mold population of the updated slime mold population using Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients;

[0102] The loop iteration module 550 is used to return to the operation of calculating the fitness of each slime mold individual in the slime mold population if it is determined that the current iteration number has not reached the preset iteration number, until it is determined that the current iteration number has reached the preset iteration number;

[0103] The target design variable determination module 560 is used to determine the target design variables of each member of the vehicle body frame based on the value of the slime mold population at the end of the iteration.

[0104] This invention employs a random chaotic mapping method to initialize and generate a slime mold population based on the design variables of each component of the vehicle body frame. The fitness of each individual slime mold in the population is calculated, and the population is sorted according to fitness. Individuals with the target fitness are then selected based on the sorting results. Further, an elite-guided slime mold update method is used to update the population based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and slime mold individuals with the target fitness. The updated slime mold population is then perturbed using Cauchy and Gaussian perturbations with adaptively adjusted weight coefficients, and it is determined whether the current iteration count has reached the preset iteration count. If the current iteration count has not reached the preset iteration count, the operation of calculating the fitness of each individual slime mold in the population can be repeated until the current iteration count is determined to have reached the preset iteration count. Finally, the target design variables of each component of the vehicle body frame can be determined based on the values ​​of the slime mold population at the end of the iteration. The above technical solution improves the traditional slime mold algorithm to optimize the vehicle body frame parameters, solving the problems of low convergence efficiency and easy getting trapped in local optima in the traditional slime mold algorithm, and can improve the optimization accuracy and efficiency of vehicle body frame parameters.

[0105] Optionally, the slime mold population initialization module 510 is further configured to: determine the target rods of the vehicle body frame; determine the parameter variable vector of each slime mold individual in the slime mold population according to the number of target rods of the vehicle body frame; and generate initial values ​​for each parameter variable of the parameter variable vector of each slime mold individual in the slime mold population using a random chaotic mapping method to obtain the initialized slime mold population.

[0106] Optionally, the slime mold population initialization module 510 is further configured to: generate initial values ​​for each parameter variable of the parameter variable vector of each slime mold individual in the slime mold population based on the following formula:

[0107] ;

[0108] In the formula, The value of the parameter variable generated in the nth generation. The value of the parameter variable generated in the (n+1)th iteration. This is the control constant.

[0109] Optionally, the slime mold individual screening module 520 is further configured to: calculate the fitness of each slime mold individual in the slime mold population based on the following formula:

[0110]

[0111]

[0112]

[0113]

[0114]

[0115]

[0116]

[0117] in, For the j-th slime mold individual, Let be the fitness of the j-th slime mold individual. Let j be the target distance for the j-th slime mold individual. For the j-th slime mold individual, there is an adaptive penalty term; The constraint deviation for the j-th slime mold individual; Let j be the normalized target value for the j-th slime mold individual. For the determination parameters, N is the total number of slime mold individuals in the slime mold population, and m is the number of feasible solutions in the slime mold population. For the target value of the j-th slime mold individual, To minimize the target value, To achieve the maximum target value, Let q be the violation severity value of the k-th constraint, and q be the number of constraints. To find the minimum degree of constraint violation for the k-th constraint among all slime mold individuals in the current iteration. To find the maximum degree of constraint violation for the k-th constraint among all slime mold individuals in the current iteration. It is a constant. This is the k-th constraint.

[0118] Optionally, the slime mold population update module 530 is further configured to: update the slime mold population based on the following formula:

[0119]

[0120]

[0121]

[0122]

[0123] in, For the first Location information of slime molds, Here, represents the location information of the t-th generation slime mold, rand represents a random number, UB is the upper limit of the search range, and LB is the lower limit of the search range. This is the location of the slime mold individual with the best current fitness. To take values ​​in A random number between and , where 'a' is the enhanced nonlinear convergence factor. This refers to the location information of a randomly selected slime mold individual from among the slime mold individuals with the target fitness. As the oscillation factor, The value is in A random number between r and r', where r is a value between r' and r'. A random number within a certain range; W is the weighting coefficient, D is the adaptive adjustment feedback factor, and z is a constant. Let be the fitness value of the i-th slime mold individual, bF be the first reference fitness value during the iteration process, sort() represent the sorting function, condition be slime mold individuals with the target fitness, others be slime mold individuals with non-target fitness, and wF be the second reference fitness value during the iteration process. A random number in the range [0,1]. The position index of slime mold individuals after fitness sorting.

[0124] Optionally, the enhanced nonlinear convergence factor adapted to the slime mold population is: Where a represents the enhanced nonlinear convergence factor, and t represents the current iteration number. This represents the preset number of iterations, where C is a constant;

[0125] The adaptive adjustment feedback factor is: Where D represents the adaptive adjustment feedback factor, and g is a constant greater than 1.

[0126] Optionally, the slime mold population perturbation module 540 is further configured to: perturb the local slime mold population of the updated slime mold population using Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients based on the following formula:

[0127]

[0128] in, This provides the location information for the (t+1)th generation slime mold. For the first Location information of slime molds, The preset number of iterations is t, where t is the current iteration number. It is Cauchy distribution. It follows a Gaussian distribution.

[0129] The aforementioned vehicle body frame parameter optimization device can execute the vehicle body frame parameter optimization method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the vehicle body frame parameter optimization method provided in any embodiment of the present invention.

[0130] Since the vehicle body frame parameter optimization device described above is an apparatus capable of executing the vehicle body frame parameter optimization method in the embodiments of the present invention, those skilled in the art can understand the specific implementation methods and various variations of the vehicle body frame parameter optimization device in this embodiment based on the vehicle body frame parameter optimization method described in the embodiments of the present invention. Therefore, how the vehicle body frame parameter optimization device implements the vehicle body frame parameter optimization method in the embodiments of the present invention will not be described in detail here. Any apparatus used by those skilled in the art to implement the vehicle body frame parameter optimization method in the embodiments of the present invention falls within the scope of protection of this application.

[0131] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0132] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0133] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0134] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the vehicle body frame parameter optimization method.

[0135] Optionally, the vehicle body frame parameter optimization method may include: initializing and generating a slime mold population based on the design variables of each member of the vehicle body frame using a random chaotic mapping method; calculating the fitness of each slime mold individual in the slime mold population, and sorting the slime mold population according to the fitness, and selecting slime mold individuals with target fitness based on the sorting results; updating the slime mold population using an elite-guided slime mold update method based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and slime mold individuals with target fitness adapted to the slime mold population, to obtain an updated slime mold population; perturbing the local slime mold population of the updated slime mold population using Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients; if it is determined that the current iteration number has not reached the preset iteration number, returning to execute the operation of calculating the fitness of each slime mold individual in the slime mold population until it is determined that the current iteration number has reached the preset iteration number; and determining the target design variables of each member of the vehicle body frame based on the value of the slime mold population at the end of the iteration.

[0136] In some embodiments, the vehicle body frame parameter optimization method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle body frame parameter optimization method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle body frame parameter optimization method by any other suitable means (e.g., by means of firmware).

[0137] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0139] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0141] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0142] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0143] This invention also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the vehicle body frame parameter optimization method provided in any embodiment of this invention. This program product shares the same inventive concept as the vehicle body frame parameter optimization methods disclosed in the various embodiments of this invention, and therefore will not be described in detail here.

[0144] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the embodiments of the present invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in the embodiments of the present invention can be achieved, and this is not limited herein.

[0145] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for optimizing vehicle body frame parameters, characterized in that, include: A stochastic chaotic mapping method was used to initialize and generate slime mold populations based on the design variables of each component of the vehicle body frame. The fitness of each slime mold individual in the slime mold population is calculated, and the slime mold population is sorted according to the fitness. Slime mold individuals with the target fitness are then selected based on the sorting results. Based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and target fitness of slime mold individuals adapted to the slime mold population, the slime mold population is updated using an elite-guided slime mold update method to obtain an updated slime mold population. The local slime mold population of the updated slime mold population is perturbed by Cauchy perturbation and Gaussian perturbation with adaptive weight coefficient adjustment; If it is determined that the current iteration number has not reached the preset iteration number, return to perform the operation of calculating the fitness of each slime mold individual in the slime mold population until it is determined that the current iteration number has reached the preset iteration number; The target design variables for each component of the vehicle body frame are determined based on the value of the slime mold population at the end of the iteration. The step of generating initial values ​​for each parameter variable of the parameter variable vector of each slime mold individual in the slime mold population using the random chaotic mapping method includes: Initial values ​​for each parameter variable in the parameter variable vector of each slime mold individual in the slime mold population are generated based on the following formula: ； In the formula, The value of the parameter variable generated in the nth iteration. The value of the parameter variable generated in the (n+1)th iteration. This is the control constant; The step of updating the slime mold population using an elite-guided strategy, based on the enhanced nonlinear convergence factor, adaptive adjustment feedback factor, and slime mold individuals with the target fitness adapted to the slime mold population, includes: The slime mold population is updated based on the following formula: ； ； ； ； in, For the first Location information of slime molds, Here, represents the location information of the t-th generation slime mold, rand represents a random number, UB is the upper limit of the search range, and LB is the lower limit of the search range. This is the location of the slime mold individual with the best current fitness. To take values ​​in A random number between and , where 'a' is the enhanced nonlinear convergence factor. This refers to the location information of a randomly selected slime mold individual from among the slime mold individuals with the target fitness. As the oscillation factor, The value is in A random number between r and r', where r is a value between r' and r'. A random number within a certain range; W is the weighting coefficient, D is the adaptive adjustment feedback factor, and z is a constant. Let be the fitness value of the i-th slime mold individual, bF be the first reference fitness value during the iteration process, sort() represent the sorting function, condition be slime mold individuals with the target fitness, others be slime mold individuals with non-target fitness, and wF be the second reference fitness value during the iteration process. A random number in the range [0,1]. The position index of slime mold individuals after fitness sorting; The enhanced nonlinear convergence factor adapted to the slime mold population is: Where a represents the enhanced nonlinear convergence factor, and t represents the current iteration number. This represents the preset number of iterations, where C is a constant; The adaptive adjustment feedback factor is: Where D represents the adaptive adjustment feedback factor, and g is a constant greater than 1.

2. The method according to claim 1, characterized in that, The method of initializing and generating slime mold populations based on the design variables of each member of the vehicle body frame using a random chaotic mapping approach includes: Identify the target structural members of the vehicle body frame; The parameter variable vector of each slime mold individual in the slime mold population is determined based on the number of target rods in the vehicle body frame. The initial values ​​of each parameter variable in the parameter variable vector of each slime mold individual in the slime mold population are generated using the aforementioned random chaotic mapping method, thereby obtaining an initialized slime mold population.

3. The method according to claim 1, characterized in that, The calculation of fitness for each individual slime mold in the slime mold population includes: The fitness of each slime mold individual in the slime mold population is calculated based on the following formula: ； ； ； ； ； ； ； in, For the j-th slime mold individual, Let be the fitness of the j-th slime mold individual. Let j be the target distance for the j-th slime mold individual. For the j-th slime mold individual, there is an adaptive penalty term; The constraint deviation for the j-th slime mold individual; Let j be the normalized target value for the j-th slime mold individual. For the determination parameters, N is the total number of slime mold individuals in the slime mold population, and m is the number of feasible solutions in the slime mold population. For the target value of the j-th slime mold individual, To minimize the target value, To achieve the maximum target value, Let q be the violation severity value of the k-th constraint, and q be the number of constraints. To find the minimum degree of constraint violation for the k-th constraint among all slime mold individuals in the current iteration. To find the maximum degree of constraint violation for the k-th constraint among all slime mold individuals in the current iteration. It is a constant. This is the k-th constraint.

4. The method according to claim 1, characterized in that, The disturbance of the local slime mold population of the updated slime mold population includes: The local slime mold population of the updated slime mold population is perturbed using Cauchy perturbation and Gaussian perturbation with adaptively adjusted weight coefficients based on the following formula: ； in, This provides the location information for the (t+1)th generation slime mold. For the first Location information of slime molds, The preset number of iterations is t, where t is the current iteration number. It is Cauchy distribution. It follows a Gaussian distribution.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor, such that the at least one processor is able to perform the vehicle frame parameter optimization method according to any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the vehicle body frame parameter optimization method according to any one of claims 1-4.

7. A computer program product, characterized in that, It includes a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the vehicle frame parameter optimization method according to any one of claims 1-4.

Images