Vehicle parameter processing method, computer equipment, storage medium and program product

Abstract

The embodiment of the invention provides a vehicle parameter processing method, computer equipment, a storage medium and a program product, and is applied to the technical field of vehicles and the field of artificial intelligence. The method comprises the steps of generating an initial population based on constraint conditions of vehicle parameters; performing evolution processing on the initial population by adopting a genetic algorithm to obtain a first candidate population; under the condition that the first candidate population meets the interval frequency condition, constructing a multi-objective function based on candidate individuals in the first candidate population meeting the interval frequency condition, and performing local optimization on the candidate individuals by taking solving the minimum value of the multi-objective function as a target through a sequence optimization algorithm to obtain a second candidate population; and under the condition that the second candidate population meets the condition of the number of iterations, determining a target parameter value of the vehicle parameter based on the second candidate population meeting the condition of the number of iterations. The method is used for achieving the effect of improving the accuracy of the determined target parameter.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a vehicle parameter processing method, computer equipment, storage medium and program product. Background Art

[0002] Industrial production in many fields involves parameter optimization design. In the field of vehicle production, since the vehicle is a complex system, there are a large number of parameters to be optimized. These parameters need to meet multiple optimization objectives. There is usually a competition mechanism between these optimization objectives, that is, the improvement of one optimization objective leads to the decrease of another optimization objective.

[0003] In the related art, a multi-objective optimization function is established, and based on the optimization function, the parameter space is globally optimized through a genetic algorithm. This method is difficult to obtain a global optimal solution, resulting in low accuracy in determining the target parameters. Summary of the invention

[0004] The embodiments of the present application provide a vehicle parameter processing method, a computer device, a storage medium, and a program product to achieve the effect of improving the accuracy of the determined target parameters.

[0005] In a first aspect, an embodiment of the present application provides a method for processing vehicle parameters, including: generating an initial population based on constraint conditions of vehicle parameters; evolving the initial population using a genetic algorithm to obtain a first candidate population; when the first candidate population does not meet the interval number condition, replacing the initial population with the first candidate population, and continuing to perform the step of evolving the initial population using a genetic algorithm; when the first candidate population meets the interval number condition, constructing a multi-objective function based on candidate individuals in the first candidate population that meet the interval number condition, and locally optimizing the candidate individuals through a sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function to obtain a second candidate population; when the second candidate population does not meet the iteration number condition, replacing the initial population with the second candidate population, and continuing to perform the step of evolving the initial population using a genetic algorithm; when the second candidate population meets the iteration number condition, determining the target parameter value of the vehicle parameter based on the second candidate population that meets the iteration number condition.

[0006] In a second aspect, an embodiment of the present application provides a vehicle parameter processing device, including:

[0007] A generation module, used to generate an initial population based on constraints of vehicle parameters;

[0008] An evolution processing module, used for performing evolution processing on the initial population using a genetic algorithm to obtain a first candidate population;

[0009] A first iteration module is used to replace the initial population with the first candidate population when the first candidate population does not meet the interval number condition, and continue to perform the step of using the genetic algorithm to evolve the initial population;

[0010] A local optimization module is used to construct a multi-objective function based on candidate individuals in the first candidate population that meet the interval number condition when the first candidate population meets the interval number condition, and to locally optimize the candidate individuals with the goal of solving the minimum value of the multi-objective function through a sequence optimization algorithm to obtain a second candidate population;

[0011] A second iteration module is used to replace the initial population with the second candidate population when the second candidate population does not meet the iteration number condition, and continue to perform the step of using the genetic algorithm to evolve the initial population;

[0012] The target parameter value determination module is used to determine the target parameter value of the vehicle parameter based on the second candidate population that meets the iteration number condition when the second candidate population meets the iteration number condition.

[0013] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory, a processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the processor executes the first aspect above and / or various possible implementations of the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0016] The vehicle parameter processing method, computer device, storage medium and program product provided in the embodiments of the present application generate an initial population based on the constraints of the vehicle parameters, and perform evolution processing on the initial population through a genetic algorithm to globally optimize the design space of the vehicle parameters to obtain a first candidate population. When the first candidate population meets the interval number condition, the first candidate population is locally optimized through a sequence optimization algorithm to obtain a second candidate population. When the second candidate population does not meet the iteration number condition, the second candidate population is continuously globally optimized through a genetic algorithm. In this way, the genetic algorithm and the sequence optimization algorithm are alternately used to perform multi-objective optimization on the vehicle parameters, so that the multi-objective optimization can have both global search capabilities and local search capabilities. The sequence optimization algorithm improves the convergence speed of the multi-objective optimization, and the genetic algorithm avoids falling into the local optimal solution. That is, while ensuring the optimization efficiency, the reliability of the multi-objective optimization is improved, thereby improving the accuracy of the determined target parameter values. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] Figure 1 A schematic diagram of a scenario of a method for processing vehicle parameters provided in this application;

[0019] Figure 2 Schematic diagram of the process of processing vehicle parameters provided in this application Figure 1 ;

[0020] Figure 3 A reference schematic diagram of selected representative individuals provided for this application;

[0021] Figure 4 A reference schematic diagram for determining weight coefficients provided in this application;

[0022] Figure 5 Schematic diagram of the process of processing vehicle parameters provided in this application Figure 2 ;

[0023] Figure 6 Schematic diagram of the process of processing vehicle parameters provided in this application Figure 3 ;

[0024] Figure 7 A schematic diagram of the structure of a vehicle parameter processing device provided in this application;

[0025] Figure 8 A schematic diagram of the structure of the computer device provided for this application.

[0026] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The vehicle parameter processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0029] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0030] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0031] Figure 2 Schematic diagram of the process of processing vehicle parameters provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0032] S201. Generate an initial population based on the constraints of vehicle parameters.

[0033] Among them, vehicle parameters are parameters of the vehicle to be designed; the number of vehicle parameters can be multiple; vehicle parameters will affect the performance of the vehicle system, and there may be interference between multiple vehicle parameters. There is often a competition mechanism between multiple optimized design objectives, that is, the improvement of one design indicator may lead to the decrease of another design indicator.

[0034] For example, taking the three-point suspension decoupling optimization of the powertrain system in automotive engineering as an example, the powertrain system is mounted on the subframe through three bushings. exist The stiffness on , and , ; Through 9 stiffness values, the suspension energy decoupling rate of the powertrain system in 6 degrees of freedom (3 translational degrees of freedom and 3 rotational degrees of freedom) maximum, ; That is, the vehicle parameters can include the stiffness of the three bushings in three directions; the suspension energy decoupling rate of the powertrain system in the six degrees of freedom directions Maximum is the optimization target of vehicle parameters.

[0035] Specifically, for each vehicle parameter, the computer device obtains the constraint conditions of the vehicle parameter, which can be used to constrain the maximum and minimum values ​​of the vehicle parameters; based on the maximum and minimum values ​​of the vehicle parameters, the initial individuals of the vehicle parameters are randomly generated, and the initial population is determined based on the multiple initial individuals.

[0036] S202: Using a genetic algorithm to perform evolution processing on the initial population to obtain a first candidate population.

[0037] The first candidate population is obtained by evolving the initial population. A genetic algorithm is an optimization algorithm based on the principle of evolution. The genetic algorithm starts searching from the population rather than from the individual, which is conducive to global optimization and reduces the risk of falling into a local optimal solution. The genetic algorithm in this embodiment can be a non-dominated sorting genetic algorithm II (NSGA-II) with an elite strategy.

[0038] Specifically, the initial population is subjected to crossover and mutation processing to obtain an offspring population; the initial population and the offspring population are merged to obtain a merged population; a multi-level Pareto solution set is determined based on the merged population; a critical Pareto solution set is determined in the multi-level Pareto solution set; individuals in the critical Pareto solution set are sorted by crowding degree, and critical individuals are selected from the results of the crowding degree sorting, and a first candidate population is determined based on the Pareto solution set and critical individuals of the preceding level of the critical Pareto solution set, and the iteration count and interval count corresponding to the first candidate population are determined.

[0039] Exemplarily, the vehicle parameters include bushing exist Stiffness in three directions, initial population: ; in, is the number of initial individuals in the initial population; after generating the initial population, the iteration count and interval counting All are set to 0.

[0040] For the initial population Apply crossover and mutation operators to generate offspring populations , merge the initial population and the offspring population to get the merged population ; For the combined population Perform non-dominated sorting to obtain Pareto solution sets of multiple levels: ;in, Represents the Pareto solution set of the first level; determines the critical Pareto solution set among the Pareto solution sets of multiple levels , satisfy:

[0041] ;

[0042] in, represents the number of elements in the calculation set, that is, the critical Pareto solution set The previous Pareto solution sets of multiple levels (including ) includes the number of individuals, and The previous Pareto solution sets of multiple levels (including ) is equal to the number of initial individuals in the initial population.

[0043] Critical Pareto solution set The individuals in the cluster are sorted by their crowding degree, and the ones ranked first are selected. The critical individual , , …, is the critical Pareto solution set The Pareto solution set of the previous level; the first candidate population is composed of the critical individuals and the Pareto solution set of the previous level , iteration count and interval counting All are accumulated by 1, that is, the iteration count , interval count .

[0044] S203: When the first candidate population does not meet the interval number condition, the first candidate population is used to replace the initial population, and the step of using the genetic algorithm to perform evolution processing on the initial population is continued.

[0045] The fact that the first candidate population does not meet the interval number condition means that the interval count corresponding to the first candidate population does not reach the interval threshold; the specific value of the interval threshold can be determined according to actual conditions.

[0046] Specifically, when the interval count corresponding to the first candidate population does not reach the interval threshold, the computer device replaces the initial population with the first candidate population, and uses a genetic algorithm to perform evolution processing on the replaced initial population.

[0047] S204. When the first candidate population satisfies the interval number condition, a multi-objective function is constructed based on the candidate individuals in the first candidate population that satisfy the interval number condition, and the candidate individuals are locally optimized by a sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function to obtain a second candidate population.

[0048] The first candidate population satisfies the interval number condition, which means that the interval count corresponding to the first candidate population reaches the interval threshold.

[0049] Among them, a multi-objective function is constructed based on the candidate individuals in the first candidate population that meet the interval number conditions. Through the sequence optimization algorithm, the candidate individuals are locally optimized with the goal of solving the minimum value of the multi-objective function to obtain the second candidate population. This is the process of locally optimizing the individuals in the first candidate population.

[0050] The sequence optimization algorithm is to analyze a given sequence and adjust the elements in the sequence to solve the multi-objective function. The sequence optimization algorithm in this embodiment can be a Sequential Least Squares Programming (SLSQP) algorithm.

[0051] The multi-objective function may include multiple sub-objective functions, which correspond to multiple design objectives to be optimized. For example, the suspension energy decoupling rate of the powertrain system in the six degrees of freedom directions needs to be met. The maximum number of sub-objective functions may be a function for calculating the suspension energy decoupling rate in the directions of the six degrees of freedom.

[0052] Specifically, when the interval count corresponding to the first candidate population reaches the interval threshold, the weights of multiple sub-objective functions are determined according to the candidate individuals in the first candidate population, and a multi-objective function is constructed according to the weights of the multiple sub-objective functions and the multiple sub-objective functions; the first candidate population is taken as the iterative starting point, and the candidate individuals are locally optimized through the sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function until convergence to obtain the second candidate population.

[0053] In an optional manner, when the interval count corresponding to the first candidate population reaches the interval threshold, a representative individual is selected from the candidate individuals of the first candidate population, and the weights of multiple sub-objective functions are determined according to the representative individual.

[0054] It should be noted that before the first candidate population is locally optimized by the SLSQP algorithm, the interval count is set to 0 to facilitate counting when the NSGA-II algorithm is executed next time; after the first candidate population is locally optimized based on the SLSQP algorithm to obtain the second candidate population, the iteration count corresponding to the first candidate population is used as the iteration count of the second candidate population.

[0055] S205: When the second candidate population does not satisfy the iteration number condition, the second candidate population is used to replace the initial population, and the step of using the genetic algorithm to perform evolution processing on the initial population is continued.

[0056] The second candidate population does not meet the iteration number condition, which means that the iteration count corresponding to the second candidate population does not reach the iteration threshold; the specific value of the iteration threshold can be determined according to actual conditions.

[0057] Specifically, when the iteration count corresponding to the second candidate population does not reach the iteration threshold, the computer device uses the second candidate population to replace the initial population, and uses the genetic algorithm to perform evolution processing on the replaced initial population.

[0058] S206. When the second candidate population satisfies the iteration number condition, determine a target parameter value of the vehicle parameter based on the second candidate population that satisfies the iteration number condition.

[0059] The second candidate population satisfies the iteration number condition, which means that the iteration count corresponding to the second candidate population reaches the iteration threshold.

[0060] Specifically, the computer device determines the target parameter value of the vehicle parameter according to the second candidate population when the iteration count corresponding to the second candidate population reaches the iteration threshold.

[0061] In an optional manner, when the first candidate population does not meet the interval number condition, it is determined whether the first candidate population meets the iteration number condition; if the first candidate population does not meet the iteration number condition, the first candidate population is used to replace the initial population, and the step of using a genetic algorithm to evolve the initial population is continued; if the first candidate population meets the iteration number condition, the target parameter value of the vehicle parameter is determined based on the first candidate population that meets the iteration number condition.

[0062] It should be noted that the above is to perform multi-objective optimization of vehicle parameters by alternating between genetic algorithms and sequence optimization algorithms, wherein there are multiple iterative processes. During the optimization process, if the iteration count corresponding to the first candidate population or the second candidate population meets the iteration number condition, then the target parameter value of the vehicle parameter can be determined based on the first candidate population or the second candidate population that meets the iteration number condition.

[0063] The above-mentioned vehicle parameter processing method generates an initial population based on the constraint conditions of the vehicle parameters, and evolves the initial population through a genetic algorithm to globally optimize the design space of the vehicle parameters to obtain a first candidate population. When the first candidate population meets the interval number condition, the first candidate population is locally optimized through a sequence optimization algorithm to obtain a second candidate population. When the second candidate population does not meet the iteration number condition, the second candidate population is continuously globally optimized through a genetic algorithm. In this way, the genetic algorithm and the sequence optimization algorithm are alternately used to perform multi-objective optimization on the vehicle parameters, so that the multi-objective optimization can have both global search capabilities and local search capabilities. The sequence optimization algorithm improves the convergence speed of the multi-objective optimization, and the genetic algorithm avoids falling into the local optimal solution. That is, while ensuring the optimization efficiency, the reliability of the multi-objective optimization is improved, thereby improving the accuracy of the determined target parameter values.

[0064] In some embodiments, a multi-objective function is constructed based on candidate individuals in the first candidate population that meet the interval number condition, including: screening multiple representative individuals among the candidate individuals included in the first candidate population that meet the interval number condition; determining weight coefficients of the multiple sub-objective functions under each representative individual based on the optimization target values ​​of each representative individual under multiple sub-objective functions; and constructing a multi-objective function corresponding to each representative individual based on the weight coefficients of the multiple sub-objective functions under each representative individual.

[0065] Among them, the representative individuals are some individuals in the first candidate population; the optimization target value is the value obtained by substituting the representative individuals into the sub-objective function; the weight coefficient is used to reflect the importance of the sub-objective function.

[0066] Specifically, for the candidate individuals in the first candidate population, multiple representative individuals are screened from the candidate individuals based on the non-dominance of the candidate individuals; for each representative individual, the representative individual is brought into multiple sub-objective functions to obtain the optimization target value of the representative individual, and the weight coefficients of the multiple sub-objective functions are determined according to the optimization target value of the representative individual; according to the weight coefficients of the multiple sub-objective functions under each representative individual, a multi-objective function corresponding to each representative individual is constructed.

[0067] It should be noted that the weight coefficients of multiple sub-objective functions are determined according to the performance of representative individuals on multiple sub-objective functions, so that the weight coefficients are adaptively determined based on the representative individuals and are not fixed weight coefficients.

[0068] In the above embodiment, multiple representative individuals are screened from the candidate individuals. The multiple representative individuals can reflect multiple angles of the vehicle parameter design space. The diversity of the population can be improved through the multiple representative individuals. The weight coefficients are adaptively determined through the performance of the representative individuals in multiple sub-objective functions, so that the multi-objective function constructed based on the adaptive weight coefficients can be iteratively optimized towards the dominated aspects of the representative individuals, thereby improving the local search capability while improving the diversity.

[0069] In some embodiments, a plurality of representative individuals are screened from the candidate individuals included in the first candidate population that meets the interval number condition, including: determining a grid in the parameter space based on the resolution of the vehicle parameters, and obtaining a candidate grid in which the candidate individuals exist in the grid; performing non-dominated sorting on the candidate individuals in the candidate grid to obtain a first Pareto solution set of the first level; and screening representative individuals from the first Pareto solution set.

[0070] Among them, the resolution of vehicle parameters can reflect the accuracy of vehicle parameters; the resolution of vehicle parameters can be set according to needs; non-dominated sorting is a method used to evaluate the pros and cons of individuals in multi-objective optimization problems. The first Pareto solution set of the first level includes individuals that are not dominated by other representative individuals.

[0071] Specifically, a computer device obtains a resolution of vehicle parameters, divides the parameter space according to the resolution of the vehicle parameters, and obtains a plurality of grids; among the plurality of grids, there are some grids that include candidate individuals, and there are some grids that do not include candidate individuals; among the plurality of grids, candidate grids that fall into the candidate individuals are obtained, and the candidate individuals in the candidate grids are non-dominatedly sorted to obtain a multi-level Pareto solution set, and a first Pareto solution set of the first level is obtained in the multi-level Pareto solution set.

[0072] Screening representative individuals in the first Pareto solution set includes: determining the centroid of the candidate grid based on the candidate individuals in the candidate grid; determining the distance between the candidate individuals included in the first Pareto solution set and the centroid; and screening representative individuals from the candidate individuals included in the first Pareto solution set based on the distance.

[0073] For example, Figure 3 As shown in FIG. 1 , taking the design space of two vehicle parameters (X1 and X2) as an example, the parameter space is divided by the resolution of the vehicle parameters to obtain multiple grids. For each candidate grid containing candidate individuals, all individuals in the candidate grid are non-dominated and sorted, and the first Pareto solution set of the first level is obtained. The centroid points of all individuals in the first Pareto solution set are calculated, as shown in formula (1).

[0074] (1)

[0075] in, Represents the candidate grid The center of gravity, Represents the candidate grid The candidate individuals in Represents the candidate grid The number of candidate individuals in .

[0076] Calculate the distance between each candidate individual and the centroid in the first Pareto solution set, as shown in formula (2).

[0077] (2)

[0078] in, is a candidate individual in the first Pareto solution set With center of gravity The distance between Is a candidate The component on the vehicle parameter X1, is the normalization coefficient of vehicle parameter X1, It is the center of gravity The component on the vehicle parameter X1, Is a candidate The component on the vehicle parameter X2, is the normalization coefficient of vehicle parameter X2, It is the center of gravity Component on vehicle parameter X2.

[0079] The candidate individual with the closest distance to the center of gravity in the first Pareto solution set is taken as the representative individual; Figure 3 In the first Pareto solution set corresponding to the candidate grid, the candidate individuals include: , , and ,Sure , , and The centroid of the candidate individual is selected according to the distance between the candidate individual and the centroid. As a representative individual of the candidate grid.

[0080] In the above embodiment, a plurality of representative individuals are screened from the candidate individuals. The plurality of representative individuals can reflect various angles of the vehicle parameter design space, and the diversity of the population can be improved through the plurality of representative individuals.

[0081] In some embodiments, based on the optimization objective value of each representative individual under the multiple sub-objective functions, weight coefficients of the multiple sub-objective functions under each representative individual are determined, including:

[0082] For each sub-objective function, the minimum optimization objective value corresponding to the sub-objective function is selected based on the optimization objective values ​​of multiple representative individuals under the sub-objective function; for each representative individual, the weight coefficient of the sub-objective function corresponding to the representative individual is determined based on the optimization objective value of the representative individual under the sub-objective function and the minimum optimization objective value corresponding to the sub-objective function.

[0083] Specifically, for each sub-objective function, the optimization objective value of each representative individual under the sub-objective function is calculated, and the minimum optimization objective value is determined among multiple optimization objective values, that is, the minimum optimization objective value corresponding to the sub-objective function.

[0084] For each representative individual, obtain the optimization target value of the representative individual under the sub-objective function, calculate the difference between the optimization target value and the minimum optimization target value, calculate the product of the difference and the normalization coefficient of the sub-objective function, and use the inverse of the product as the weight coefficient of the sub-objective function corresponding to the representative individual.

[0085] Exemplarily, the number of sub-objective functions is two (there are two optimization objectives); for each sub-objective function, based on the optimization objective values ​​of multiple representative individuals under the sub-objective function, the minimum optimization objective value corresponding to the sub-objective function is selected, that is:

[0086] ;

[0087] in, is the optimization target value of multiple representative individuals under the first sub-objective function, is the population to which multiple representative individuals belong, is the minimum optimization target value corresponding to the first sub-objective function; are multiple representative individuals in the second sub-objective function The optimization target value under It is the minimum optimization target value corresponding to the second sub-objective function.

[0088] For each representative individual, the weight coefficient of the representative individual is determined according to the optimization target value of the representative individual under the first sub-objective function and the minimum optimization target value corresponding to the first sub-objective function, as shown in formula (3).

[0089] (3)

[0090] in, is the normalized coefficient of the first sub-objective function, is the minimum optimization target value corresponding to the first sub-objective function, A representative individual The optimization target value under the first sub-objective function, is the weight coefficient of the first sub-objective function corresponding to the representative individual; is the normalized coefficient of the second sub-objective function, is the minimum optimization target value corresponding to the second sub-objective function, A representative individual The optimization target value under the second sub-objective function, It is the weight coefficient of the second sub-objective function corresponding to the representative individual.

[0091] It should be noted that there are two optimization objectives for explanation, such as Figure 4 As shown, for the representative individual p, according to the position of the representative individual p, the optimization target space can be divided into three categories: the dominant area, the non-dominated area and the dominated area; if the representative individual p moves to the dominant area, it means that the performance of the representative individual p on the two optimization targets is getting worse, if the representative individual p moves to the non-dominated area, it means that the representative individual p gets better on one optimization target and gets worse on the other optimization target; if the representative individual p moves to the dominated area, it means that the performance of the representative individual on the two optimization targets is getting better, and the diversity of the population can be maintained; by calculating the weight coefficient of the sub-objective function through the above embodiment, the representative individual can be iteratively optimized towards the dominated area, thereby ensuring the diversity of the population and increasing the local optimization capability.

[0092] In some embodiments, a sequence optimization algorithm is used to locally optimize candidate individuals with the goal of solving a minimum value of a multi-objective function to obtain a second candidate population, including: for each representative individual corresponding to the multi-objective function, a sequence optimization algorithm is used to optimize the representative individual with the goal of solving a minimum value of the multi-objective function to obtain an optimized individual; when the optimized individual does not meet the termination condition, the optimized individual is used to replace the representative individual, and the step of optimizing the representative individual with the goal of solving a minimum value of the multi-objective function through the sequence optimization algorithm is continued until the optimized individual meets the termination condition; the second candidate population includes the optimized individuals that meet the termination condition.

[0093] Among them, the optimized individual meets the termination condition, which can be that the optimization iteration count corresponding to the optimized individual reaches the optimization threshold, or that the optimized individual converges; in practical applications, the convergence of the optimized individual can be that the difference between the current optimized individual and the previous optimized individual is less than the preset convergence accuracy.

[0094] Specifically, after constructing the multi-objective function corresponding to each representative individual based on the weight coefficients of multiple sub-objective functions under each representative individual, the multi-objective function corresponding to each representative individual is determined by a sequence optimization algorithm, and the gradient descent direction at the representative individual is determined based on the gradient descent direction to determine the moving step size with the goal of solving the minimum value of the multi-objective function. The representative individual is optimized according to the gradient and the moving step size to obtain the optimized individual.

[0095] For example, the stiffness of the three bushings is solved by the multi-objective function, so that the suspension energy decoupling rate of the powertrain system in the six degrees of freedom directions is

[0096] Maximum, in this case, the multi-objective function corresponding to the representative individual is expressed as formula (4).

[0097] (4)

[0098] in, , is the vehicle parameter space; It is sub-objective function, It is The weight coefficient of each sub-objective function, It is The normalized coefficient of the sub-objective function.

[0099] The optimization iteration count corresponding to the representative individual is recorded as 0, and the gradient descent direction is calculated by solving the non-negative least squares problem , using one-dimensional linear search to calculate the moving step , so that the multi-objective function is minimized and the gradient descent direction is adopted and moving step length Optimizing representative individuals , and get the optimized individual , and update the Hessian matrix of the representative individual to obtain the Hessian matrix of the optimized individual; the Hessian matrix is ​​used to describe the curvature information. In the iterative optimization process of the sequence optimization algorithm, the Hessian matrix can be used to determine the direction of gradient descent and improve accuracy.

[0100] When the representative individual is optimized to obtain the optimized individual, the optimization iteration count is increased by 1 to obtain the optimization iteration count corresponding to the optimized individual; if the optimization iteration count corresponding to the optimized individual does not reach the optimization threshold, and the difference between the optimized individual and the previous optimized individual (representative individual) is greater than the preset convergence accuracy, the next optimization is performed based on the optimized individual until the optimization iteration count corresponding to the optimized individual reaches the optimization threshold, or the difference between the optimized individual and the previous optimized individual is greater than the preset convergence accuracy, and the optimized individual that meets the end condition is obtained.

[0101] Since there are multiple representative individuals, according to the above process, a sequence optimization algorithm is used to perform local optimization on each representative individual, and multiple optimized individuals that meet the end condition can be obtained. The second candidate population includes multiple optimized individuals that meet the end condition.

[0102] It should be noted that the second candidate population includes multiple optimized individuals that meet the termination conditions, which correspond to multiple representative individuals respectively. That is to say, it is necessary to complete the optimization of each representative individual, and after obtaining the optimized individual corresponding to each representative individual, the complete second candidate population is obtained, and then the genetic algorithm is executed alternately.

[0103] In the above embodiment, a sequence optimization algorithm is used to optimize representative individuals with the goal of solving the minimum value of the multi-objective function, thereby improving the local search capability and further improving the reliability of the multi-objective optimization.

[0104] In some embodiments, based on the optimization target values ​​of each representative individual under multiple sub-objective functions, weight coefficients of multiple sub-objective functions under each representative individual are determined, including: through multiple processes, in parallel, based on the optimization target values ​​of each representative individual under multiple sub-objective functions, weight coefficients of multiple sub-objective functions under each representative individual are determined; for the multi-objective function corresponding to each representative individual, through a sequential optimization algorithm, with the goal of solving the minimum value of the multi-objective function, the representative individual is optimized to obtain an optimized individual, including: through multiple processes, in parallel, for each representative individual, through a sequential optimization algorithm, with the goal of solving the minimum value of the multi-objective function, the representative individual is optimized to obtain an optimized individual.

[0105] Specifically, after obtaining multiple representative individuals, for each representative individual, a multi-objective function corresponding to the representative individual is constructed, and a sequence optimization algorithm is used to solve the minimum value of the multi-objective function corresponding to the representative individual. The process of optimizing the representative individual to obtain the optimized individual can be executed independently of each other. In order to improve the efficiency of the sequence optimization algorithm, multiple processes can be used to determine the weight coefficients corresponding to the representative individuals in parallel, construct the multi-objective functions corresponding to the weight coefficients in parallel, and optimize the representative individuals through the sequence optimization algorithm in parallel.

[0106] In the above embodiment, multiple representative individuals are optimized in parallel through multiple processes and a sequential optimization algorithm, which improves the efficiency of optimizing the representative individuals and further improves the efficiency of multi-objective optimization.

[0107] In some embodiments, Figure 5 As shown, the method for processing vehicle parameters includes:

[0108] S501, generating an initial population based on the constraints of vehicle parameters;

[0109] S502, using a genetic algorithm to perform evolution processing on the initial population to obtain a first candidate population;

[0110] S503: when the first candidate population does not meet the interval number condition, the first candidate population is used to replace the initial population, and the step of using the genetic algorithm to perform evolution processing on the initial population is continued;

[0111] S504, when the first candidate population meets the interval number condition, determine the grid in the parameter space based on the resolution of the vehicle parameters, and obtain the candidate grid where the candidate individuals exist in the grid; perform non-dominated sorting on the candidate individuals in the candidate grid to obtain the first Pareto solution set of the first level; and select representative individuals in the first Pareto solution set;

[0112] S505. For each sub-objective function, based on the optimization objective values ​​of multiple representative individuals under the sub-objective function, select the minimum optimization objective value corresponding to the sub-objective function; for each representative individual, based on the optimization objective value of the representative individual under the sub-objective function and the minimum optimization objective value corresponding to the sub-objective function, determine the weight coefficient of the sub-objective function corresponding to the representative individual;

[0113] S506, constructing a multi-objective function corresponding to each representative individual based on the weight coefficients of the multiple sub-objective functions under each representative individual;

[0114] S507, for each representative individual corresponding to the multi-objective function, by using a sequence optimization algorithm, with the goal of finding the minimum value of the multi-objective function, optimizing the representative individual to obtain an optimized individual;

[0115] S508, when the optimized individual does not meet the termination condition, the optimized individual is used to replace the representative individual, and the steps of optimizing the representative individual by the sequence optimization algorithm are continued to be executed with the goal of solving the minimum value of the multi-objective function until the optimized individual meets the termination condition; the second candidate population includes the optimized individual that meets the termination condition;

[0116] S509, when the second candidate population does not meet the iteration number condition, the second candidate population is used to replace the initial population, and the step of using the genetic algorithm to perform evolution processing on the initial population is continued;

[0117] S510: When the second candidate population satisfies the iteration number condition, determine a target parameter value of the vehicle parameter based on the second candidate population that satisfies the iteration number condition.

[0118] In some embodiments, the genetic algorithm is a non-dominated sorting genetic algorithm with an elite strategy (NSGA-II), and the sequence optimization algorithm is a sequential least squares programming algorithm (SLSQP) as an example, refer to Figure 6 , the method of processing vehicle parameters is explained.

[0119] Execute the NSGA-II algorithm: Generate the initial population based on the constraints of vehicle parameters , get the iteration threshold V1 and interval threshold V2, and record the current iteration count =0, interval count =0.

[0120] For the initial population Perform crossover and mutation processing to generate offspring populations , the offspring population and the initial population Merge to get the merged population ; For the combined population Perform non-dominated sorting to obtain Pareto solution sets at multiple levels: ; Determine the critical Pareto solution set among multiple levels of Pareto solution sets ; For the critical Pareto solution set Sort the crowding degree and select individuals from them to get the first candidate population , update the iteration count: , update interval count: , at this time the first candidate population is recorded as ; Determine the interval count Whether the interval threshold V2 is reached, if not, determine the iteration count Whether the iteration threshold V1 is reached. If the iteration count does not reach the iteration threshold V1, the first candidate population is used. Replace the initial population , continue to execute the initial population The process of crossover and mutation processing; if the iteration count reaches the iteration threshold V1, according to the first candidate population Determine the target parameter value of the vehicle parameter; if the interval count When the interval threshold V2 is reached, the SLSQP algorithm is executed.

[0121] In the SLSQP algorithm, the interval count is set to 0, that is, =0, get the preset convergence accuracy and optimize the threshold V3; in the first candidate population Select multiple representative individuals from the ,set up , is the number of representative individuals that complete the local area; , as the starting point for iteration , according to the optimization target values ​​of multiple representative individuals under the sub-objective function, determine the representative individual The weight coefficient of the corresponding sub-objective function is based on the representative individual The weight coefficients of the corresponding sub-objective functions construct a multi-objective function, and the gradient descent direction is calculated by solving the non-negative least squares problem , using one-dimensional linear search to calculate the moving step , so that the multi-objective function is minimized; using the gradient descent direction and moving step length optimization , and get the optimized individual , update the corresponding Hessian matrix, set ,judge Is it less than the preset convergence accuracy? ,or Is it greater than the optimization threshold V3? Not less than ,and If it is not greater than the optimization threshold V3, then continue to execute the step of calculating the gradient descent direction by solving the non-negative least squares problem, and optimize the individual Continue to optimize until Less than the preset convergence accuracy ,or Greater than the optimization threshold V3, complete the representative individual The local optimization of ,set up ;judge Is it equal to , to determine the completion of the specific optimization of all representative individuals, if , indicating that there are other representative individuals that have not completed local optimization, then continue to wait for other representative individuals to perform local optimization until ,according to Optimized individuals that meet the termination conditions Identify the second candidate population , jump out of the SLSQP algorithm and continue to execute the NSGA-II algorithm.

[0122] In the NSGA-II algorithm, the second candidate population is determined The iteration count of Whether the iteration threshold V1 is reached. If the iteration count does not reach the iteration threshold V1, the second candidate population is used. Replace the initial population , continue to execute the initial population The process of crossover and mutation; if the second candidate population The iteration count of Reaching the iteration threshold V1, according to the second candidate population Target parameter values ​​for vehicle parameters are determined.

[0123] It should be noted that in the SLSQP algorithm, the process of local optimization for a representative individual does not depend on other representative individuals, that is, multiple representative individuals can be locally optimized in parallel until the local optimization of multiple representative individuals is completed. Through parallelism, the optimization efficiency can be improved.

[0124] The above-mentioned vehicle parameter processing method generates an initial population based on the constraint conditions of the vehicle parameters, and evolves the initial population through a genetic algorithm to globally optimize the design space of the vehicle parameters to obtain a first candidate population. When the first candidate population meets the interval number condition, the first candidate population is locally optimized through a sequence optimization algorithm to obtain a second candidate population. When the second candidate population does not meet the iteration number condition, the second candidate population is continuously globally optimized through a genetic algorithm. In this way, the genetic algorithm and the sequence optimization algorithm are alternately used to perform multi-objective optimization on the vehicle parameters, so that the multi-objective optimization can have both global search capabilities and local search capabilities. The sequence optimization algorithm improves the convergence speed of the multi-objective optimization, and the genetic algorithm avoids falling into the local optimal solution. That is, while ensuring the optimization efficiency, the reliability of the multi-objective optimization is improved, thereby improving the accuracy of the determined target parameter values.

[0125] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0126] Figure 7 A schematic diagram of the structure of the vehicle parameter processing device provided in this application, such as Figure 7 As shown, the vehicle parameter processing device provided in this embodiment includes:

[0127] A generation module 701, used to generate an initial population based on the constraints of vehicle parameters;

[0128] An evolution processing module 702 is used to perform evolution processing on the initial population using a genetic algorithm to obtain a first candidate population;

[0129] The first iteration module 703 is used to replace the initial population with the first candidate population when the first candidate population does not meet the interval number condition, and continue to perform the step of using the genetic algorithm to evolve the initial population;

[0130] A local optimization module 704 is used to construct a multi-objective function based on candidate individuals in the first candidate population that meet the interval number condition when the first candidate population meets the interval number condition, and to locally optimize the candidate individuals with the goal of solving the minimum value of the multi-objective function through a sequence optimization algorithm to obtain a second candidate population;

[0131] The second iteration module 705 is used to replace the initial population with the second candidate population when the second candidate population does not meet the iteration number condition, and continue to perform the step of using the genetic algorithm to evolve the initial population;

[0132] The target parameter value determination module 706 is used to determine the target parameter value of the vehicle parameter based on the second candidate population that meets the iteration number condition when the second candidate population meets the iteration number condition.

[0133] In a possible implementation, the local optimization module 704 is also used to screen multiple representative individuals from the candidate individuals included in the first candidate population that meet the interval number condition; determine the weight coefficients of the multiple sub-objective functions under each representative individual based on the optimization target value of each representative individual under multiple sub-objective functions; and construct a multi-objective function corresponding to each representative individual based on the weight coefficients of the multiple sub-objective functions under each representative individual.

[0134] In one possible implementation, the local optimization module 704 is further used to determine a grid in the parameter space based on the resolution of the vehicle parameters, and obtain a candidate grid in which candidate individuals exist in the grid; perform non-dominated sorting on the candidate individuals in the candidate grid to obtain a first Pareto solution set of the first level; and screen representative individuals in the first Pareto solution set.

[0135] In one possible implementation, the local optimization module 704 is also used to select, for each sub-objective function, the minimum optimization target value corresponding to the sub-objective function based on the optimization target values ​​of multiple representative individuals under the sub-objective function; for each representative individual, determine the weight coefficient of the sub-objective function corresponding to the representative individual based on the optimization target value of the representative individual under the sub-objective function and the minimum optimization target value corresponding to the sub-objective function.

[0136] In a possible implementation, the local optimization module 704 is also used to optimize the multi-objective function corresponding to each representative individual through a sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function, and obtain an optimized individual; when the optimized individual does not meet the termination condition, the optimized individual is used to replace the representative individual, and continue to execute the step of optimizing the representative individual through the sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function until the optimized individual meets the termination condition; the second candidate population includes the optimized individuals that meet the termination condition.

[0137] In one possible implementation, the local optimization module 704 is also used to determine, through multiple processes, in parallel, the weight coefficients of multiple sub-objective functions under each representative individual based on the optimization target values ​​of each representative individual under multiple sub-objective functions; through multiple processes, in parallel, for the multi-objective function corresponding to each representative individual, through a sequential optimization algorithm, with the goal of solving the minimum value of the multi-objective function, optimize the representative individual to obtain an optimized individual.

[0138] The vehicle parameter processing device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0139] Figure 8 This is a schematic diagram of the structure of the computer device provided in this application. Figure 8 As shown, the computer device 80 provided in this embodiment includes: at least one processor 801 and a memory 802. Optionally, the device 80 also includes a communication component 803. The processor 801, the memory 802 and the communication component 803 are connected via a bus 804.

[0140] In a specific implementation process, at least one processor 801 executes the computer-executable instructions stored in the memory 802, so that at least one processor 801 executes the above method.

[0141] The specific implementation process of the processor 801 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0142] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0143] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0144] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0145] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0146] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0147] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0148] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0149] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0152] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0153] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0154] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for processing vehicle parameters, characterized in that: include: Generate an initial population based on the constraints of vehicle parameters; Using a genetic algorithm to perform evolution processing on the initial population to obtain a first candidate population; In the case where the first candidate population does not meet the interval number condition, the first candidate population is used to replace the initial population, and the step of using the genetic algorithm to perform evolution processing on the initial population is continued; In the case where the first candidate population satisfies the interval number condition, a multi-objective function is constructed based on candidate individuals in the first candidate population that satisfy the interval number condition, and the candidate individuals are locally optimized by a sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function to obtain a second candidate population; In the case where the second candidate population does not meet the iteration number condition, the second candidate population is used to replace the initial population, and the step of using the genetic algorithm to perform evolution processing on the initial population is continued; In a case where the second candidate population satisfies the iteration number condition, a target parameter value of the vehicle parameter is determined based on the second candidate population satisfying the iteration number condition.

2. The method according to claim 1, characterized in that The constructing a multi-objective function based on the candidate individuals in the first candidate population that meet the interval number condition includes: Screening a plurality of representative individuals from the candidate individuals included in the first candidate population that meet the interval number condition; Based on the optimization target value of each representative individual under the multiple sub-objective functions, respectively, determining the weight coefficient of the multiple sub-objective functions under each representative individual; Based on the weight coefficients of the multiple sub-objective functions under each representative individual, a multi-objective function corresponding to each representative individual is constructed.

3. The method according to claim 2, characterized in that The step of screening a plurality of representative individuals from the candidate individuals included in the first candidate population that meet the interval number condition comprises: Determine a grid in a parameter space based on a resolution of the vehicle parameters, and obtain a candidate grid in which the candidate individual exists in the grid; Performing non-dominated sorting on the candidate individuals in the candidate grid to obtain a first Pareto solution set of the first level; Representative individuals are selected from the first Pareto solution set.

4. The method according to claim 2, characterized in that: The step of determining the weight coefficients of the multiple sub-objective functions under each representative individual based on the optimization objective values ​​of each representative individual under the multiple sub-objective functions includes: For each sub-objective function, based on the optimization objective values ​​of multiple representative individuals under the sub-objective function, select the minimum optimization objective value corresponding to the sub-objective function; For each representative individual, the weight coefficient of the sub-objective function corresponding to the representative individual is determined based on the optimization target value of the representative individual under the sub-objective function and the minimum optimization target value corresponding to the sub-objective function.

5. The method according to any one of claims 2 to 4, characterized in that The method of locally optimizing the candidate individuals by a sequence optimization algorithm with the goal of solving the minimum value of the multi-objective function to obtain a second candidate population includes: For each representative individual corresponding to the multi-objective function, a sequence optimization algorithm is used to optimize the representative individual with the goal of finding the minimum value of the multi-objective function to obtain an optimized individual; When the optimized individual does not meet the termination condition, the optimized individual is used to replace the representative individual, and the sequential optimization algorithm is continued to be executed to optimize the steps of the representative individual with the goal of solving the minimum value of the multi-objective function until the optimized individual meets the termination condition; The second candidate population includes the optimized individuals that meet the termination condition.

6. The method according to claim 5, characterized in that The step of determining the weight coefficients of the multiple sub-objective functions under each representative individual based on the optimization objective values ​​of each representative individual under the multiple sub-objective functions includes: Determine, through multiple processes, in parallel, based on the optimization objective value of each representative individual under multiple sub-objective functions, the weight coefficient of the multiple sub-objective functions under each representative individual; The multi-objective function corresponding to each representative individual is optimized by a sequence optimization algorithm with the goal of finding the minimum value of the multi-objective function to obtain the optimized individual, including: Through the multiple processes, the multi-objective functions corresponding to each representative individual are optimized in parallel through a sequence optimization algorithm with the goal of finding the minimum value of the multi-objective function, thereby optimizing the representative individuals and obtaining optimized individuals.

7. A vehicle parameter processing device, characterized in that: The device comprises: A generation module, used to generate an initial population based on constraints of vehicle parameters; An evolution processing module, used for performing evolution processing on the initial population using a genetic algorithm to obtain a first candidate population; A first iteration module is used to replace the initial population with the first candidate population when the first candidate population does not meet the interval number condition, and continue to perform the step of performing evolution processing on the initial population using a genetic algorithm; A local optimization module is used to construct a multi-objective function based on candidate individuals in the first candidate population that meet the interval number condition when the first candidate population meets the interval number condition, and to locally optimize the candidate individuals with the goal of solving the minimum value of the multi-objective function through a sequence optimization algorithm to obtain a second candidate population; A second iteration module is used to replace the initial population with the second candidate population when the second candidate population does not meet the iteration number condition, and continue to perform the step of performing evolution processing on the initial population using a genetic algorithm; The target parameter value determination module is used to determine the target parameter value of the vehicle parameter based on the second candidate population that meets the iteration number condition when the second candidate population meets the iteration number condition.

8. A computer device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The method comprises computer-executable instructions, which implement the method according to any one of claims 1 to 6 when executed by a processor.

Images