Multi-objective optimization method for general operation power platform of hill and mountain machinery based on regression model

Abstract

The invention discloses a multi-objective optimization method for a general operation power platform of hill and mountain machinery based on a regression model, and relates to the technical field of data optimization. Comprising the following steps: determining performance parameters and design parameters of the general operation power platform for the hill and mountain machinery, establishing a finite element model of the power platform, and representing the performance parameters of the general operation power platform for the hill and mountain machinery through the finite element model; establishing a regression model between the performance parameters of the power platform and each design parameter, determining a regression coefficient through a Bayesian regression algorithm, and generating a linear regression model; constructing a fitness function based on each performance parameter of the linear regression model, and determining a target chromosome through a genetic algorithm; environmental parameters of the power platform working hilly and mountainous regions are obtained, gene parameters in the target chromosomes are corrected based on the obtained environmental parameters, and optimal design parameters of the power platform for general operation of the hilly and mountainous region machinery are obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of data optimization, and in particular to a multi-objective optimization method for a universal operating power platform of hilly and mountainous machinery based on a regression model. Background Art

[0002] In today's rapidly developing agricultural and engineering machinery fields, the operating environment in hilly and mountainous areas places higher demands on the performance of mechanical equipment. Hilly areas often face problems such as complex terrain, steep slopes, and variable soil conditions, all of which directly affect the operating efficiency and stability of mechanical equipment. Traditional mechanical design methods often focus on the optimization of a single performance indicator and lack comprehensive consideration of multiple performance parameters, making it difficult to meet diverse operating needs in specific applications.

[0003] In addition, with the rapid development of intelligent and automated technologies, the design of mechanical equipment also needs to keep pace with the times and adopt more advanced design methods to improve performance. Multi-objective optimization technology based on regression models, especially in complex environments, is becoming an important trend in the design of a new generation of machinery. The relationship between design parameters and performance parameters is quantitatively analyzed to achieve the optimal combination of various performance indicators. Existing design methods often lack real-time feedback and adaptability to environmental factors, resulting in the final design often not being consistent with the actual operating conditions, affecting the operating efficiency of machinery in hilly areas.

[0004] At the same time, environmental parameters in hilly areas, such as slope and soil moisture, directly affect the operating performance of machinery, but these factors are often not fully considered in the design stage. This may cause problems such as insufficient power, poor stability, and low operating efficiency in actual operation, which in turn affects the overall production efficiency and economic benefits. Therefore, how to effectively integrate environmental parameters and mechanical performance in the design process and improve the operating capacity of hilly and mountainous machinery through scientific optimization methods has become a technical problem that needs to be solved urgently.

[0005] In the prior art, the publication number CN117725764B discloses a multi-objective optimization method, device and medium for a vehicle chassis based on a regression model. By determining each prediction parameter and each design factor, a linear regression model is determined based on a corresponding sample set for each prediction parameter in a linear list, and a threshold threshold corresponding to each design factor is determined for each prediction parameter in a nonlinear list, and then a corresponding threshold regression model is constructed. The model coefficient is determined through the sample set, and a threshold effect and a threshold value significance test is performed on each threshold regression model. The threshold regression model that fails the test is eliminated, and a linear regression model is determined. Finally, each objective function is optimized in turn according to a preset optimization order. However, this method can only optimize each objective function in turn according to a preset optimization order, and the global optimization capability is weak. At the same time, the influence of environmental conditions on each design factor is not considered, so that the actual performance of the optimization result is poor, which cannot meet the expected requirements, and also reduces the accuracy and effectiveness of the system.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a multi-objective optimization method for a universal working power platform of hilly and mountainous machinery based on a regression model to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A multi-objective optimization method for a universal working power platform of hilly and mountainous machinery based on a regression model, the specific steps include:

[0010] Determine the performance parameters and design parameters of the universal operating power platform for hilly and mountainous machinery, establish a finite element model of the universal operating power platform for hilly and mountainous machinery based on the design parameters, and characterize the performance parameters of the universal operating power platform for hilly and mountainous machinery through finite element models with different design parameters;

[0011] Based on the performance parameters and design parameters determined by the finite element model, a regression model between the power platform performance parameters and the design parameters is established. At the same time, the regression coefficient is determined by the Bayesian regression algorithm, and a complete linear regression model is generated based on the determined regression coefficient.

[0012] Each design parameter based on the linear regression model constitutes a gene, and the combination of all different types of genes constitutes an individual chromosome. A fitness function is constructed based on each performance parameter of the linear regression model, and an individual chromosome with the highest fitness is determined by a genetic algorithm and recorded as a target chromosome, wherein the design parameters include the design parameters of the power platform, and the performance parameters include the performance parameters of the power platform;

[0013] The environmental parameters of the hilly and mountainous areas where the power platform works are obtained, and the gene parameters in the target chromosome are modified based on the obtained environmental parameters to obtain the optimal design parameters of the universal power platform for hilly and mountainous areas machinery, wherein the environmental parameters of the hilly and mountainous areas include the average slope and the average soil moisture.

[0014] Furthermore, the performance parameters and design parameters of the universal operating power platform for hilly and mountainous machinery are determined, wherein the performance parameters of the universal operating power platform for hilly and mountainous machinery include: maximum passing height, suspension travel, ground contact pressure, turning radius, load capacity and energy consumption; the design parameters of the universal operating power platform for hilly and mountainous machinery include: engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight; the value range of each design parameter is obtained according to existing public information, and based on the determined value range of each design parameter of the universal operating power platform for hilly and mountainous machinery, a group of design parameter values ​​are randomly selected and input into the established finite element model, and the performance parameters corresponding to the group of design parameters are obtained by performing simulation tests on the finite element model, and no less than m groups of test data are recorded as a sample set.

[0015] Furthermore, based on the performance parameters and design parameters determined by the finite element model, the specific steps of establishing the regression model between the performance parameters of the power platform and the design parameters include: calibrating the performance parameters of the power platform, calibrating the maximum passing height as C 1 , the suspension travel is calibrated as C 2 , ground pressure, turning radius, load capacity and energy consumption are calibrated as C 3 , C 4 , C 5 and C 6 ;

[0016] The design parameters of the power platform are calibrated, and the engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight are calibrated as X 1 , X 2 , X 3 , X 4 , X 5 , X 6 and X 7 ;

[0017] A regression model expression between the power platform performance parameters and various design parameters is established, where the specific regression model expression is:

[0018] C i =β i，0 +β i，1 *X 1 +β i，2 *X 1 +…+β i，7 *X 7 +∈ i

[0019] In the formula, C i represents the i-th performance parameter, β i，1 To β i，7 represents the regression coefficient of each design parameter in the i-th performance parameter regression model expression, β i，0 Represents the intercept term in the regression model expression of the i-th performance parameter, ∈ i represents the error term in the regression model expression of the i-th performance parameter, where i is the index of the performance parameter, i=1, 2, ..., 6;

[0020] The regression coefficients are determined by the Bayesian regression algorithm, and a complete linear regression model is generated based on the determined regression coefficients.

[0021] Furthermore, the specific steps of determining the regression coefficient by using the Bayesian regression algorithm include:

[0022] First, a prior distribution is defined for each regression coefficient; a likelihood function is established based on the collected performance parameter and design parameter data; according to Bayes' theorem, the posterior distribution is calculated through the prior distribution and the likelihood function; the estimated value of the regression coefficient is extracted from the posterior distribution, and the extracted regression coefficient value is substituted into the regression model expression to obtain a complete linear regression model.

[0023] Furthermore, each design parameter based on the linear regression model constitutes a gene, which is specifically expressed as: T is labeled to represent all optional sets of all design parameters, where T = {P 1 , P 2 ,…,P u ,…,P n}, where P u ={X u1 , X u2 , …, X u7}, P u represents the design parameter set of the uth group, n represents the number of parameter combinations, and the parameters in the optimized parameter combination are encoded one by one as a gene. The genes generated by the same type of data are alleles to each other, that is, X 1 1, X21 , …, X n1 are alleles of each other;

[0024] According to the obtained genes, individual chromosomes are formed, and the individual chromosomes are composed of 7 genes. Each individual chromosome S has 7 gene positions, and each gene position corresponds to a gene, that is, X 1 1, X 21 , …, X n1 They are all optional values ​​of the gene position No. 1 of the individual chromosome. The seven gene positions correspond to a gene for the parameters of engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight.

[0025] Furthermore, a fitness function is constructed based on each performance parameter of the linear regression model, where the expression of the fitness function is:

[0026]

[0027] Where f(S) represents the fitness function, ω 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 and ω 6 , are the weight coefficients of maximum clearance height, suspension travel, ground contact pressure, turning radius, load capacity and energy consumption, respectively. 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 and ω 6 All greater than 0:

[0028] The genetic algorithm is used to determine an individual chromosome with the highest fitness, wherein the specific steps of the genetic algorithm include: constructing an initial population based on individual chromosomes; performing selection, crossover and mutation operations on individual chromosomes in the initial population; performing iterative operations, while setting mutation probabilities and iteration termination conditions. When the iterative operation is terminated, the individual chromosome with the highest fitness in the current population is recorded as the target chromosome.

[0029] Furthermore, the logic for modifying the genetic parameters in the target chromosome based on the acquired environmental parameters is: modifying the genetic parameters of engine power, torque and suspension stiffness in the target chromosome, and the specific formulas for the modification are:

[0030] X″ 1 =X′ 1 +(1+X′ 7 *g*sinθ)

[0031] X″ 1=X′ 2 +(1+X′ 7 *g*r*sinθ)

[0032] X″ 3 =X′ 3 *(1+α*sinθ+δ*H)

[0033] In the formula, X″ 1 , X″ 2 and X″ 3 represent the corrected engine power, torque and suspension stiffness respectively, X′ 1 , X′ 2 and X′ 3 Respectively represent the values ​​of engine power, torque and suspension stiffness in the target chromosome, X′ 7 represents the total weight data of the platform in the target chromosome, g is the gravitational acceleration, θ represents the average slope, r is the wheel radius of the power platform, α and δ are the slope influence coefficient and soil moisture influence coefficient respectively, where α>δ, and α and δ are both greater than 0, and H is the average soil moisture;

[0034] The corrected engine power, torque and suspension stiffness parameters are replaced with the engine power, torque and suspension stiffness data in the target chromosome, and finally the optimal design parameters of the universal operating power platform for hilly and mountainous machinery are obtained, that is, the data contained in the replaced target chromosome.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] By establishing a finite element model, the relationship between the various performance parameters and design parameters of the power platform can be fully characterized, providing data support for the optimization design. Secondly, the regression model and Bayesian regression algorithm are used to determine the regression coefficient, which can improve the accuracy of the model and ensure that accurate performance predictions can be provided under different design parameters. In addition, combined with the genetic algorithm for optimization, the optimal solution can be quickly found in the multidimensional parameter space, which significantly improves the design efficiency and achieves comprehensive optimization. After obtaining the environmental parameters, the target chromosome is corrected so that the final design parameters not only meet the performance requirements, but also can adapt to the actual working environment. This optimization design method that comprehensively considers the design parameters and environmental factors ensures the stability and efficiency of hilly mountain machinery in complex environments, greatly improves the operating capacity and economy of the machinery, and thus provides more reliable technical guarantees for agricultural and engineering operations in hilly areas. Through this innovative design optimization method, the mechanical failure rate can be effectively reduced and work efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0039] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0040] Example:

[0041] See also Figure 1 , the present invention provides a technical solution:

[0042] A multi-objective optimization method for a universal working power platform of hilly and mountainous machinery based on a regression model, the specific steps include:

[0043] Step 1: Determine the performance parameters and design parameters of the universal operating power platform for hilly and mountainous machinery, establish a finite element model of the universal operating power platform for hilly and mountainous machinery based on the design parameters, and characterize the performance parameters of the universal operating power platform for hilly and mountainous machinery through finite element models with different design parameters;

[0044] Determine the performance parameters and design parameters of the universal operating power platform for hilly and mountainous machinery, wherein the performance parameters of the universal operating power platform for hilly and mountainous machinery include: maximum passing height, suspension travel, ground contact pressure, turning radius, load capacity and energy consumption; the design parameters of the universal operating power platform for hilly and mountainous machinery include: engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight; obtain the value range of each design parameter according to existing public information, and based on the determined value range of each design parameter of the universal operating power platform for hilly and mountainous machinery, randomly select a group of design parameter values ​​and input them into the established finite element model, obtain the performance parameters corresponding to the group of design parameters by performing simulation tests on the finite element model, and record no less than m groups of test data as a sample set.

[0045] The steps of establishing the finite element model include: selecting appropriate finite element analysis (FEA) software (such as ANSYS, Abaqus, SolidWorks, etc.), using modeling software (such as AutoCAD, SolidWorks, etc.) to design a 3D model of the mechanical structure; generating different models based on various design parameters, and characterizing the corresponding performance parameters through simulation tests;

[0046] The specific method for obtaining the value range of each design parameter based on existing public information is: through the existing publicly available design parameter values ​​in related fields, the obtained design parameter values ​​are appropriately enlarged or reduced to form a design parameter value range, wherein the enlargement and reduction ratios are based on what is actually achievable.

[0047] Step 2: Based on the performance parameters and design parameters determined by the finite element model, a regression model between the power platform performance parameters and the design parameters is established. At the same time, the regression coefficient is determined by the Bayesian regression algorithm, and a complete linear regression model is generated based on the determined regression coefficient;

[0048] Based on the performance parameters and design parameters determined by the finite element model, the specific steps of establishing the regression model between the performance parameters of the power platform and the design parameters include: calibrating the performance parameters of the power platform, calibrating the maximum passing height as C 1 , the suspension travel is calibrated as C 2 , ground pressure, turning radius, load capacity and energy consumption are calibrated as C 3 , C 4 , C 5 and C 6 ;

[0049] The design parameters of the power platform are calibrated, and the engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight are calibrated as X 1 , X 2 , X 3 , X 4 , X 5 , X 6 and X 7 ;

[0050] A regression model expression between the power platform performance parameters and various design parameters is established, where the specific regression model expression is:

[0051] C i =β i，0 +β i，1 *X 1 +β i，2 *X 1 +…+β i，7 *X7 +∈ i

[0052] In the formula, C i represents the i-th performance parameter, β i，1 To β i，7 represents the regression coefficient of each design parameter in the i-th performance parameter regression model expression, β i，0 Represents the intercept term in the regression model expression of the i-th performance parameter, ∈ i represents the error term in the regression model expression of the i-th performance parameter, where i is the index of the performance parameter, i=1, 2, ..., 6;

[0053] The regression coefficients are determined by the Bayesian regression algorithm, and a complete linear regression model is generated based on the determined regression coefficients.

[0054] The specific steps of determining the regression coefficient by the Bayesian regression algorithm include:

[0055] First, define a prior distribution for each regression coefficient. The prior distribution can be set based on domain knowledge, expert opinions or historical data. The commonly used distribution is the normal distribution, which is suitable for most regression coefficients. According to the collected performance parameters and design parameter data, a likelihood function is established. According to Bayes' theorem, the posterior distribution is calculated by the prior distribution and the likelihood function, and numerical methods such as Markov Chain Monte Carlo (MCMC) are used to approximate the posterior distribution. The MCMC method can generate a series of samples to estimate the posterior distribution of the regression coefficient. The estimated value of the regression coefficient can be extracted from the posterior distribution by calculating the posterior mean or median. The posterior mean is usually used: Substitute the extracted regression coefficient value into the regression model expression to obtain a complete linear regression model.

[0056] Step 3: Each design parameter of the linear regression model constitutes a gene, and the combination of all different types of genes constitutes an individual chromosome. A fitness function is constructed based on each performance parameter of the linear regression model. The individual chromosome with the highest fitness is determined by a genetic algorithm and recorded as the target chromosome.

[0057] Each design parameter based on the linear regression model constitutes a gene, which is specifically expressed as follows: T is labeled to represent all optional sets of all design parameters, where T = {P 1 , P 1 ,…,P u ,…,P n}, where P u ={X u1 , X u2 , …, X u7}, P urepresents the design parameter set of the uth group, n represents the number of parameter combinations, and the parameters in the optimized parameter combination are encoded one by one as a gene. The genes generated by the same type of data are alleles to each other, that is, X 1 1, X 21 , …, X n1 are alleles of each other;

[0058] According to the obtained genes, individual chromosomes are formed, and the individual chromosomes are composed of 7 genes. Each individual chromosome S has 7 gene positions, and each gene position corresponds to a gene, that is, X 1 1, X 21 , …, X n1 They are all optional values ​​of the gene position No. 1 of the individual chromosome. The seven gene positions correspond to a gene for the parameters of engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight.

[0059] A fitness function is constructed based on each performance parameter of the linear regression model, where the expression of the fitness function is:

[0060]

[0061] Where f(S) represents the fitness function, ω 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 and ω 6 , are the weight coefficients of maximum clearance height, suspension travel, ground contact pressure, turning radius, load capacity and energy consumption, respectively. 1 ,ω 2 ,ω 3 ,ω 4 ,ω 5 and ω 6 are all greater than 0; since the influence of ground contact pressure on the performance of the universal operating power platform of hilly and mountainous machinery is greater than other parameters, followed by suspension travel and steering radius, the influence of load capacity, energy consumption and maximum passing height on the performance of the universal operating power platform of hilly and mountainous machinery is weaker than other parameters, so ω is set 3 >ω 2 ≥ω 4 >ω 5 ≥ω 6 ≥ω 1 .

[0062] The individual chromosome with the highest fitness is determined by a genetic algorithm, wherein the specific steps of the genetic algorithm include: constructing an initial population based on individual chromosomes; performing selection, crossover and mutation operations on individual chromosomes in the initial population; performing iterative operations, while setting mutation probabilities and iteration termination conditions, and after the iterative operation is terminated, the individual chromosome with the highest fitness in the current population is recorded as the target chromosome.

[0063] The selection operation uses the roulette method to select individuals. The system randomly generates a random number in the interval [0, 1]. According to the generated probability of being selected, the random number is distributed in the selection interval of the individual chromosome to determine which individual chromosome to select in this round. The process of selecting individuals is based on the fitness of the individual. The greater the fitness of the individual, the greater the possibility of being selected, and vice versa. The possibility of being selected is smaller, and an individual may be selected multiple times;

[0064] At the same time, the mutation probability is set to 0.5. The iteration termination condition can be set by setting the maximum number of iterations. When the number of iterations reaches the set maximum number of iterations, the iteration operation is stopped, and the individual chromosome with the highest fitness in the current population is selected as the target chromosome; the fitness threshold can also be set. When an individual chromosome with a fitness greater than the fitness threshold appears during the iteration process, the iteration operation is stopped, and the individual chromosome with a fitness greater than the fitness threshold is selected as the target chromosome. If there are multiple individual chromosomes with a fitness greater than the fitness threshold in the current population, the individual chromosome with the largest fitness is selected as the target chromosome;

[0065] The genetic algorithm is a publicly available and mature algorithm for finding the optimal solution, and other detailed steps are not described here.

[0066] Step 4: Obtain the environmental parameters of the hilly and mountainous areas where the power platform works, and modify the gene parameters in the target chromosome based on the obtained environmental parameters to obtain the optimal design parameters of the universal power platform for hilly and mountainous machinery, wherein the environmental parameters of the hilly and mountainous areas include the average slope and the average soil moisture.

[0067] The logic for modifying the genetic parameters in the target chromosome based on the acquired environmental parameters is: modifying the genetic parameters of engine power, torque and suspension stiffness in the target chromosome, and the specific formulas for the modification are:

[0068] X″ 1 =X′ 1 +(1+X′ 7 *g*sinθ)

[0069] X″ 1 =X′ 2 +(1+X′ 7*g*r*sinθ)

[0070] X″ 3 =X′ 3 *(1+α*sinθ+δ*H)

[0071] In the formula, X″ 1 , X″ 2 and X″ 3 represent the corrected engine power, torque and suspension stiffness respectively, X′ 1 , X′ 2 and X′ 3 Respectively represent the values ​​of engine power, torque and suspension stiffness in the target chromosome, X 7 ′ represents the total weight data of the platform in the target chromosome, g is the acceleration of gravity, θ represents the average slope, r is the wheel radius of the power platform, α and δ are the slope influence coefficient and soil moisture influence coefficient respectively. Since the slope has a greater impact on the performance of the power platform than the soil moisture, α>δ is set, and α and δ are both greater than 0, and H is the average soil moisture;

[0072] On steeper slopes, the power and torque requirements of the power system will increase to overcome the effects of gravity. The increase in slope may cause changes in the force state of the suspension, affecting the stiffness of the suspension. Soil with different moisture levels may have different effects on the response of the suspension. For example, a larger suspension travel may be required on slippery roads to improve stability.

[0073] The corrected engine power, torque and suspension stiffness parameters are replaced with the engine power, torque and suspension stiffness data in the target chromosome, and finally the optimal design parameters of the universal operating power platform for hilly and mountainous machinery are obtained, that is, the data contained in the replaced target chromosome.

[0074] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0075] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0076] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A multi-objective optimization method for a universal working power platform for hilly and mountainous machinery based on a regression model, characterized in that: The specific steps include: Determine the performance parameters and design parameters of the universal operating power platform for hilly and mountainous machinery, establish a finite element model of the universal operating power platform for hilly and mountainous machinery based on the design parameters, and characterize the performance parameters of the universal operating power platform for hilly and mountainous machinery through finite element models with different design parameters; Based on the performance parameters and design parameters determined by the finite element model, a regression model between the power platform performance parameters and the design parameters is established. At the same time, the regression coefficient is determined by the Bayesian regression algorithm, and a complete linear regression model is generated based on the determined regression coefficient. Each design parameter based on the linear regression model constitutes a gene, and the combination of all different types of genes constitutes an individual chromosome. A fitness function is constructed based on each performance parameter of the linear regression model. The individual chromosome with the highest fitness is determined by the genetic algorithm and recorded as the target chromosome. The environmental parameters of the hilly and mountainous areas where the power platform works are obtained, and the gene parameters in the target chromosome are modified based on the obtained environmental parameters to obtain the optimal design parameters of the universal power platform for hilly and mountainous areas machinery, wherein the environmental parameters of the hilly and mountainous areas include the average slope and the average soil moisture.

2. The multi-objective optimization method for a universal working power platform of hilly and mountainous machinery based on a regression model according to claim 1 is characterized by: Determine the performance parameters and design parameters of the universal operating power platform for hilly and mountainous machinery, wherein the performance parameters of the universal operating power platform for hilly and mountainous machinery include: maximum passing height, suspension travel, ground contact pressure, turning radius, load capacity and energy consumption; the design parameters of the universal operating power platform for hilly and mountainous machinery include: engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight; obtain the value range of each design parameter according to existing public information, and based on the determined value range of each design parameter of the universal operating power platform for hilly and mountainous machinery, randomly select a group of design parameter values ​​and input them into the established finite element model, obtain the performance parameters corresponding to the group of design parameters by performing simulation tests on the finite element model, and record no less than m groups of test data as a sample set.

3. The multi-objective optimization method of a universal working power platform for hilly and mountainous machinery based on a regression model according to claim 2 is characterized by: Based on the performance parameters and design parameters determined by the finite element model, the specific steps of establishing the regression model between the performance parameters of the power platform and the design parameters include: calibrating the performance parameters of the power platform, calibrating the maximum passing height as C1, calibrating the suspension travel as C2, and calibrating the ground contact pressure, turning radius, load capacity and energy consumption as C3, C4, C5 and C6 respectively; The design parameters of the power platform are calibrated, and the engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight are calibrated as X1, X2, X3, X4, X5, X6 and X7 in sequence; A regression model expression between the power platform performance parameters and various design parameters is established, where the specific regression model expression is: C i =b i，0 +b i，1 *X1+β i，2 *X1+…+b i，7 *X7+∈ i In the formula, C i represents the i-th performance parameter, β i，1 To β i，7 represents the regression coefficient of each design parameter in the i-th performance parameter regression model expression, β i，0 Represents the intercept term in the regression model expression of the i-th performance parameter, ∈ i represents the error term in the regression model expression of the i-th performance parameter, where i is the index of the performance parameter, i=1, 2, ..., 6; The regression coefficients are determined by the Bayesian regression algorithm, and a complete linear regression model is generated based on the determined regression coefficients.

4. The multi-objective optimization method of a universal working power platform for hilly and mountainous machinery based on a regression model according to claim 3 is characterized by: The specific steps of determining the regression coefficient by the Bayesian regression algorithm include: First, a prior distribution is defined for each regression coefficient; a likelihood function is established based on the collected performance parameter and design parameter data; according to Bayes' theorem, the posterior distribution is calculated through the prior distribution and the likelihood function; the estimated value of the regression coefficient is extracted from the posterior distribution, and the extracted regression coefficient value is substituted into the regression model expression to obtain a complete linear regression model.

5. The multi-objective optimization method of a universal working power platform for hilly and mountainous machinery based on a regression model according to claim 3 is characterized by: Each design parameter based on the linear regression model constitutes a gene, which is specifically expressed as follows: T is labeled to represent all optional sets of all design parameters, where T = {P1, P2, ..., P u ,…,P n }, where P u ={X u1 , X u2 , …, X u7 }, P u represents the design parameter set of the uth group, n represents the number of parameter combinations, and the parameters in the optimized parameter combination are encoded one by one as a gene. The genes generated by the same type of data are alleles to each other, that is, X 11 , X 21 , …, X n1 are alleles of each other; According to the obtained genes, individual chromosomes are formed, and the individual chromosomes are composed of 7 genes. Each individual chromosome S has 7 gene positions, and each gene position corresponds to a gene, that is, X 11 , X 21 , …, X n1 They are all optional values ​​of the gene position No. 1 of the individual chromosome. The seven gene positions correspond to a gene for the parameters of engine power, torque, suspension stiffness, platform width, platform height, center of gravity height and total platform weight.

6. The multi-objective optimization method of a universal working power platform for hilly and mountainous machinery based on a regression model according to claim 5 is characterized by: A fitness function is constructed based on each performance parameter of the linear regression model, where the expression of the fitness function is: Where f(S) represents the fitness function, ω1, ω2, ω3, ω4, ω5 and ω6 are the weight coefficients of maximum clearance height, suspension travel, ground contact pressure, steering radius, load capacity and energy consumption, respectively, where ω1, ω2, ω3, ω4, ω5 and ω6 are all greater than 0; The genetic algorithm is used to determine an individual chromosome with the highest fitness, wherein the specific steps of the genetic algorithm include: constructing an initial population based on individual chromosomes; performing selection, crossover and mutation operations on individual chromosomes in the initial population; performing iterative operations, while setting mutation probabilities and iteration termination conditions. When the iterative operation is terminated, the individual chromosome with the highest fitness in the current population is recorded as the target chromosome.

7. The multi-objective optimization method of a universal working power platform for hilly and mountainous machinery based on a regression model according to claim 1 is characterized by: The logic for modifying the genetic parameters in the target chromosome based on the acquired environmental parameters is: modifying the genetic parameters of engine power, torque and suspension stiffness in the target chromosome, and the specific formulas for the modification are: X″1=X′1+(1+X′7*g*sinθ) X″1=X′2+(1+X′7*g*r*sinθ) X″3=X′3*(1+α*sinθ+δ*H) Where X″1, X″2 and X″3 represent the corrected engine power, torque and suspension stiffness respectively, X′1, X′2 and X′3 represent the values ​​of engine power, torque and suspension stiffness in the target chromosome respectively, X′7 represents the total weight data of the platform in the target chromosome, g is the acceleration of gravity, θ represents the average slope, r is the wheel radius of the power platform, α and δ are the slope influence coefficient and soil moisture influence coefficient respectively, where α>δ, and α and δ are both greater than 0, and H is the average soil moisture; The corrected engine power, torque and suspension stiffness parameters are replaced with the engine power, torque and suspension stiffness data in the target chromosome, and finally the optimal design parameters of the universal operating power platform for hilly and mountainous machinery are obtained, that is, the data contained in the replaced target chromosome.

Images