CN111898726A - Parameter optimization method for electric vehicle control system, computer equipment and storage medium - Google Patents

Abstract

The invention discloses a parameter optimization method of an electric vehicle control system, a computer device and a storage medium. The invention includes: 1) defining an initial bee colony, and constructing a dynamic evaluation index function of an electric vehicle control system; 2) performing optimization to obtain the fitness of the bees; 3) arranging the bees in ascending order of fitness, and setting the first several bees to be Investigate bees, and the rest are follower bees; 4) Update the positions of the two; in the process of position update, the adaptive search strategy is used to dynamically adjust the optimization area of the bees, and check whether the maximum allowable number of search steps is reached, if not, Then return to 2); otherwise, go to 5); 5) Find the bee with the smallest fitness in the current population, and the value corresponding to each dimension of the bee is the parameter value of the optimized electric vehicle control system. The invention solves the problems of complex parameter optimization modeling and large calculation amount of the electric vehicle control system.

Description

A kind of electric vehicle control system parameter optimization method, computer equipment and storage medium

technical field

The invention belongs to the field of vehicle control system parameter optimization, in particular to an electric vehicle control system parameter optimization method, computer equipment and storage medium.

Background technique

The electric vehicle control system is a complex multi-input and multi-output time-varying nonlinear system, which can be used to ensure the stability and maneuverability of electric vehicles, improve the ability to complete tasks and vehicle ride comfort, and enhance vehicle safety and mitigation. Driver burden. The design of the control parameters of the electric vehicle control system has become the most direct and important key link to ensure the safety of electric vehicles. In the process of actually designing electric vehicle control systems, many engineers have to face the problem of parameter design and adjustment of complex systems with internal implicit relationships. Although the control system can be designed with the help of small disturbance linearization equations, there is often a strong coupling between the various inputs of these linearization equations, and there is no obvious mapping relationship between the desired performance index and the controller parameters. All these bring great difficulty to the selection of controller parameters.

Under normal circumstances, when applying traditional classical optimization methods to optimize parameters of electric vehicle control systems, it is difficult to fully consider the pre-constraints of the system. Existing methods of applying linear programming and quadratic programming require a clear mathematical definition and structured design for the electric vehicle control system when optimizing system parameters. lead to poor final optimization results. There are also methods of applying integer programming and hybrid programming. This type of method needs to consider the internal relationship and possible coupling relationship between the parameters of the electric vehicle control system, which will consume a lot of time to take into account and balance the adjusted parameters. Performance impact, the process is often time-consuming and labor-intensive. How to realize the fast and accurate design of the parameters of the electric vehicle control system according to the predetermined requirements under the condition of saving manpower and material resources as much as possible is an urgent problem to be solved at present.

The bee colony algorithm is an optimization method proposed by imitating the foraging behavior of bees. It is a specific application of the swarm intelligence idea. Multiple design objectives such as overshoot, steady-state error, and adjustment time are transformed into a single optimization objective through weighted algebraic summation. Faster convergence rate. Each bee updates its own position in the iterative calculation process of each step, and searches for the possible optimal solution on the path during the moving process. Each iteration is not only an update of the individual's own state, but also a process of information interaction between the entire population and a gradual convergence to the global optimum. Because it requires little prior knowledge of the problems it deals with, and hardly mentions preset conditions, the bee colony algorithm has been widely used in the field of parameter optimization of a large class of control systems. However, in the current process of applying the bee colony algorithm to optimize the parameters of the electric vehicle control system, the algorithm may fall into the local optimum due to insufficient search for the solution space of the target problem, resulting in the final failure to obtain the global optimal solution. The spatial search range is too large, which leads to the problem of slow convergence in the later stage. These problems affect the effect of applying the bee colony algorithm to the parameter optimization of the electric vehicle control system to a certain extent, and then affect the performance of the system.

SUMMARY OF THE INVENTION

The purpose of the present invention is to overcome the shortcoming that the bee colony algorithm is easy to fall into the local optimum or the convergence speed is slow in the process of parameter optimization of the electric vehicle control system, and to provide a parameter optimization method, computer equipment and storage medium of the electric vehicle control system.

To achieve the above object, the present invention adopts the following technical solutions to realize:

A method for optimizing parameters of an electric vehicle control system based on an improved bee colony algorithm, comprising the following steps:

1) Define the initial bee colony and construct the dynamic evaluation index function of the electric vehicle control system;

2) Use the bee colony to optimize the parameters of the electric vehicle control system, and use the dynamic evaluation index function to calculate the fitness corresponding to each individual bee in the bee colony;

3) The bee colony individuals are arranged in ascending order according to their fitness, and the first several bees in the arrangement are set as scout bees, and the remaining bees are follower bees;

4) Update the position of the scout bee and the position of the follower bee;

In the process of location update, adopt the adaptive search strategy to adjust the optimal search area for the individual bees that have completed the search in each step, and determine whether the maximum allowable number of optimal search steps is reached, if not, return to step 2);

Otherwise, go to step 5);

5) Find the bee individual with the smallest fitness in the current population, and the value corresponding to each dimension of the bee individual is the parameter value of the electric vehicle control system obtained by the final optimization.

Further, the specific process of step 1) is:

The dimension of the initial bee colony is defined as N×D dimension, where N represents the total number of bee colonies, and D represents the total number of parameters to be optimized for the electric vehicle control system stored by the individual bees, then the nth (n=1,2,…, The d (d=1,2,...,D)-dimensional element B _n,d of N) bees is given by the following formula:

B _n,d =<x ₁ ,x ₂ ,…,x _n >⊕<y ₁ ,y ₂ ,…,y _d >

Among them, <x ₁ ,x ₂ ,…,x _n >represents a binary number composed of x ₁ ,x ₂ ,…,x _n ; <y ₁ ,y ₂ ,…,y _d >represents a binary number composed of y ₁ ,y ₂ ,...,y _d ; x _i (i=1,...,n) is the ith bit in the binary representation of a positive integer X, X satisfies the condition: 2 ^X >N; y _i (i= 1,...,d) is the ith bit in the binary expression of another positive integer Y that is relatively prime to X, and Y satisfies: 2 ^Y >_D; ⊕ is the XOR operator; The estimated value of the nth bee for the dth parameter that needs to be optimized in the electric vehicle control system.

Further, step 1) constructing the dynamic evaluation index function of the electric vehicle control system is specifically:

J=ω ₁ ∫εdt+ω ₂ σ+ω ₃ γ+ω ₄ κ

Among them, ε, σ, γ and κ are the four evaluation indicators of the performance of the electric vehicle control system, which are tracking error, overshoot percentage, rise time and settling time, respectively; ω ₁ , ω ₂ , ω ₃ , and ω ₄ are four is the weight coefficient corresponding to the evaluation index; t is the test time of the system.

Further, the optimization process in step 2) is:

When starting the optimization, preset the initial value of the weight coefficient:

ω₂＝ω₃＝ω₄＝0；In the optimization process, the first weight coefficient ω ₁ is first assigned, so that:

ω ₂ =ω ₃ =ω ₄ =0;

ω₃＝ω₄＝0；When ε meets the preset conditions, assign a value to the second weight coefficient ω ₂ so that:

ω ₃ =ω ₄ =0;

ω₄＝0；When ε and σ satisfy the preset conditions, the third weight coefficient ω ₃ is assigned a value such that:

ω ₄ =0;

When ε, σ and γ satisfy the preset conditions, the fourth weight coefficient ω ₄ is assigned a value such that:

Then, for each bee B, the corresponding J value is obtained, which is its fitness.

Further, in step 4), the process of updating the position of the scout bee is:

The j-th movement of the n-th scout bee B _n is carried out as follows:

_Bn (j)= _Bn (j-1)+ _λn (j) _Δn (j)

为第(j-1)步时所有侦查蜂群的几何中心，μ₁～U(0,1)和

为具有均匀分布的随机变量。Among them, λ _n is the movement step length of B _n , Δ _n is the movement direction of B _n , ω ₀ is the inertia weight used to set the contribution of the movement distance of the first two steps to the next step,

is the geometric center of all reconnaissance bee colonies at step (j-1), μ ₁ ~ U(0,1) and

is a random variable with a uniform distribution.

Further, in step 4), the process of following the bee position update is:

The j-th movement of the m-th follower bee B _m proceeds as follows:

B _m (j)=B _m (j-1)+λ _m (j)Δ _m (j)

为具有均匀分布的随机变量。Among them, λ _m is the motion step length of B _m , Δ _m is the motion direction of B _m , ω ₀ is the inertia weight used to set the contribution of the motion distance of the first two steps to the next step, and B _nm is the nth nearest to B _m . scout bees, μ ₃ ～U(0,1) and

is a random variable with a uniform distribution.

Further, in step 4), adopting the adaptive search strategy to dynamically adjust the optimal search area of the bees is specifically:

For the n-th bee B _n (n=1,...,N) after the j-th search is completed, the following adaptive search strategy is used to dynamically adjust its optimal area:

和

分别表示B_n在第j步搜索的上界和下界，

为第j-1步时整个蜂群的几何中心，|| ||表示求取欧式距离，μ₅～U(0,1)为具有均匀分布的随机变量。in,

and

respectively represent the upper and lower bounds of B _n searched in the jth step,

is the geometric center of the entire bee colony in the j-1th step, || || represents the Euclidean distance, μ ₅ ～U(0,1) is a random variable with uniform distribution.

A computer device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, when the processor executes the computer program, the above-mentioned improved bee colony-based Algorithmic steps of an electric vehicle control system parameter optimization method.

A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the steps of the above-mentioned method for optimizing parameters of an electric vehicle control system based on an improved bee colony algorithm are implemented .

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

A method for parameter optimization of electric vehicle control system based on improved bee colony algorithm, which uses bee populations with low degree of variance to adaptively search the solution space, and dynamically adjusts the optimization area of each bee during the search process, taking into account the The global and local optimization capabilities of the algorithm enable the algorithm to avoid falling into the local optimum during the search process, and at the same time to ensure its convergence speed, and to approach the global optimal solution more quickly; the invention solves the problem of the electric vehicle control system. In the process of parameter optimization, the modeling is complex and the amount of calculation is large, and the parameters of the electric vehicle control system can be optimized quickly and accurately; it has been verified that compared with the traditional linear programming method, the electric vehicle optimized by the optimization method of the present invention can be optimized. The control system can make the system have better stability and quickly reduce the lateral offset error when completing the double line shifting task.

Further, the definition of the bee colony of the present invention makes the generated bee colony as evenly distributed in the solution space as possible, and the generated bee sequence has a low degree of difference.

The present invention provides a computer device and a storage medium for a method for optimizing parameters of an electric vehicle control system based on an improved bee colony algorithm, which are used to implement the specific steps of the above-mentioned optimization method.

Description of drawings

Fig. 1 is the structural schematic diagram of electric vehicle control system;

Fig. 2 is the flow chart of parameter optimization based on improved bee colony algorithm of the present invention;

Fig. 3 is the yaw angle of the electric vehicle control system optimized by applying the linear programming method and the method of the present invention under the double-lane shifting condition;

Fig. 4 is the yaw rate of the electric vehicle control system optimized by applying the linear programming method and the method of the present invention under the double-lane shift condition;

Fig. 5 is the center-of-mass slip angle of the electric vehicle control system optimized by applying the linear programming method and the method of the present invention under the double-line shifting condition;

Fig. 6 is the lateral overload of the electric vehicle control system optimized by applying the linear programming method and the method of the present invention under double line shifting conditions;

Fig. 7 is the lateral offset error of the electric vehicle control system optimized by applying the linear programming method and the method of the present invention under double line shifting conditions;

FIG. 8 is a schematic diagram of a computer device in an embodiment of the present invention.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Embodiments are part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

Below in conjunction with accompanying drawing, the present invention is described in further detail:

Referring to Fig. 1, Fig. 1 is a schematic diagram of the structure of the electric vehicle control system. The control system passes the five state parameters during the operation of the vehicle - the yaw angle φ, the lateral overload _ny , the lateral offset y, the center of mass slip angle β and yaw rate r are fed back to generate the required yaw moment input and steering wheel angle input, φ _c and y _c are the yaw angle and lateral offset command signals, respectively. The control gains k ₁ to k ₈ in each feedback channel are parameters that need to be optimized for the target system.

The flow chart of the parameter optimization method of the electric vehicle control system based on the improved bee colony algorithm is shown in Figure 2. For the eight parameters k ₁ ~ k ₈ to be optimized in the electric vehicle control system in Figure 1, the dimension of the initial bee colony is defined as N ×D dimension, where N=100 represents the total number of bee colonies, D=8 represents the total number of parameters to be optimized in the electric vehicle control system stored by each bee individual, and the maximum allowable number of optimization steps in the algorithm is 500 steps;

In order to make the generated bee colonies as evenly distributed as possible in the solution space, the following method is used to generate a bee sequence with low degree of difference, where the dth of the nth (n=1,2,...,N) bee (d=1,2,...,D) dimensional element B _n,d is given by the following formula:

B _n,d =<x ₁ ,x ₂ ,…,x _n >⊕<y ₁ ,y ₂ ,…,y _d >

Among them, <x ₁ ,x ₂ ,…,x _n >represents a binary number composed of x ₁ ,x ₂ ,…,x _n , and <y ₁ ,y ₂ ,…,y _d >represents a binary number composed of y ₁ ,y ₂ ,...,y _d is composed of binary numbers, x _i (i=1,...,n) is the ith bit in the binary representation of the positive integer X, where the selection of X needs to satisfy the conditions: 2 ^X >N, y _i (i=1,...,d) is the ith bit in the binary expression of another positive integer Y that is relatively prime to X, and the selection of Y needs to satisfy the conditions: 2 ^Y >D; ⊕ is the exclusive OR Operation operator; B _n,d represents the estimated value of the nth bee to the dth parameter that needs to be optimized in the electric vehicle control system;

Step 2: Construct the dynamic evaluation index function J of the electric vehicle control system as follows:

J=ω ₁ ∫εdt+ω ₂ σ+ω ₃ γ+ω ₄ κ

Among them, ε, σ, γ and κ are the four evaluation indicators of the electric vehicle control system performance: tracking error, overshoot percentage, rise time and settling time; ω ₁ , ω ₂ , ω ₃ , and ω ₄ are four items respectively The weight coefficient corresponding to the evaluation index; t is the test time of the system;

在算法寻优的过程中，首先给第一个权重系数ω₁赋值，使得：

ω₂＝ω₃＝ω₄＝0；当ε满足预设条件时，给第二个权重系数ω₂赋值，使得：

ω₃＝ω₄＝0；当ε和σ满足预设条件时，给第三个权重系数ω₃赋值，使得：

ω₄＝0；当ε、σ和γ满足预设条件时，给第四个权重系数ω₄赋值，使得：

然后对每个蜜蜂B，求取其所对应的J值，即为其适应度；When optimizing the parameters of the electric vehicle control system, the initial value of the weight coefficient is preset:

In the process of algorithm optimization, the first weight coefficient ω ₁ is first assigned, so that:

ω ₂ =ω ₃ =ω ₄ =0; when ε meets the preset condition, assign a value to the second weight coefficient ω ₂ , so that:

ω ₃ =ω ₄ =0; when ε and σ meet the preset conditions, assign a value to the third weight coefficient ω ₃ , so that:

ω ₄ =0; when ε, σ and γ satisfy the preset conditions, assign a value to the fourth weight coefficient ω ₄ so that:

Then, for each bee B, the corresponding J value is obtained, which is its fitness;

的第j步运动按照如下方式进行：Step 3: Arrange the individuals of the entire population in ascending order according to their corresponding J values, and set the top 10% of the bees as scout bees, and the last 90% of the bees as follower bees; during the search process, the nth scout bee

The j-th motion of is performed as follows:

_Bn (j)= _Bn (j-1)+ _λn (j) _Δn (j)

为第j-1步时所有侦查蜂群的几何中心，μ₁～U(0,1)和

为具有均匀分布的随机变量；Among them, λ _n is the movement step length of B _n , Δ _n is the movement direction of B _n , ω ₀ is the inertia weight used to set the contribution of the movement distance of the first two steps to the next step,

is the geometric center of all reconnaissance bee colonies in step j-1, μ ₁ ~ U(0,1) and

is a random variable with uniform distribution;

的第j步运动按照如下方式进行：m-th follower bee

The j-th motion of is performed as follows:

B _m (j)=B _m (j-1)+λ _m (j)Δ _m (j)

为具有均匀分布的随机变量；Among them, λ _m is the motion step length of B _m , Δ _m is the motion direction of B _m , ω ₀ is the inertia weight used to set the contribution of the motion distance of the first two steps to the next step, and B _nm is the nth nearest to B _m . scout bees, μ ₃ ～U(0,1) and

is a random variable with uniform distribution;

Step 4: In order to take into account the global and local optimization capabilities of the algorithm, the nth bee B _n (n=1,...,N) will use the following adaptive search strategy in the jth step to dynamically adjust its optimization area:

和

分别表示B_n在第j步搜索的上界和下界，

为第j-1步时整个蜂群的几何中心，|| ||表示求取欧式距离，μ₅～U(0,1)为具有均匀分布的随机变量；in,

and

respectively represent the upper and lower bounds of B _n searched in the jth step,

is the geometric center of the entire bee colony at the j-1th step, || || represents the Euclidean distance, μ ₅ ～U(0,1) is a random variable with uniform distribution;

Step 5: When the search of the jth step is completed, check whether j reaches the maximum allowable number of optimization steps. If not, return to step 2 to continue the optimization, otherwise, stop the calculation and find the bee with the smallest J value in the current population. Individual B _min , the values corresponding to each dimension of the individual bee (B _min,1 ,B _min,2 ,…,B _min,D ) are the parameter values of the electric vehicle control system obtained by the final optimization.

Test and verify using data obtained in the Simulink simulation environment:

Example

The 8 final optimized parameters k ₁ to k ₈ =[2.43780.0080-0.0377-45.6130-83.0195-3.511751.5439-0.1968] of the electric vehicle control system obtained by the method of the present invention are used to perform a double-line-shifting working condition test.

The parameters of the electric vehicle control system are optimized by using the traditional linear programming method and the improved bee colony algorithm proposed by the present invention, and then the optimized system is tested under double line shifting conditions, and the test time is 10 seconds. Compare the five state parameters of the system optimized by the two methods - yaw angle, yaw angle rate, center of mass slip angle, lateral overload and lateral offset error, see Figure 3-Figure 7, from Figure 3-Figure 6 It can be seen that, compared with the traditional linear programming method, the control system optimized by the method of the present invention can make the electric vehicle have smaller yaw angle, yaw angle rate, and side-slip angle of the center of mass under the double-line shifting condition. It can be seen from FIG. 7 that the application of the method of the present invention can make the lateral offset error of the electric vehicle reduce to zero more quickly during the driving process, which improves the stability of the system. The speed with which the vehicle can track commands. Therefore, it can be seen from the working state under the condition of double line shifting: compared with the traditional linear programming method, the electric vehicle control system optimized by the method of the present invention can make the system have better stability when completing the task of double line shifting and a rapidly decreasing lateral offset error.

In one embodiment, a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 8 . The computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. When the computer program is executed by the processor, the method for optimizing the parameters of the electric vehicle control system based on the improved bee colony algorithm is realized.

In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: 1) Define an initial bee colony , construct the dynamic evaluation index function of electric vehicle control system;

2) Use the bee colony to optimize the parameters of the electric vehicle control system, and use the dynamic evaluation index function to calculate the fitness corresponding to each individual bee in the bee colony;

3) The bee colony individuals are arranged in ascending order according to their fitness, and the first several bees in the arrangement are set as scout bees, and the remaining bees are follower bees;

4) Update the position of the scout bee and the position of the follower bee;

In the process of location update, adopt the adaptive search strategy to adjust the optimal search area for the individual bees that have completed the search in each step, and determine whether the maximum allowable number of optimal search steps is reached, if not, return to step 2);

Otherwise, go to step 5);

5) Find the bee individual with the smallest fitness in the current population, and the value corresponding to each dimension of the bee individual is the parameter value of the electric vehicle control system obtained by the final optimization.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: 1) Define an initial bee colony, and construct a dynamic evaluation index of an electric vehicle control system function;

2) Use the bee colony to optimize the parameters of the electric vehicle control system, and use the dynamic evaluation index function to calculate the fitness corresponding to each individual bee in the bee colony;

3) The bee colony individuals are arranged in ascending order according to their fitness, and the first several bees in the arrangement are set as scout bees, and the remaining bees are follower bees;

4) Update the position of the scout bee and the position of the follower bee;

In the process of location update, adopt the adaptive search strategy to adjust the optimal search area for the individual bees that have completed the search in each step, and determine whether the maximum allowable number of optimal search steps is reached, if not, return to step 2);

Otherwise, go to step 5);

5) Find the bee individual with the smallest fitness in the current population, and the value corresponding to each dimension of the bee individual is the parameter value of the electric vehicle control system obtained by the final optimization.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided by the present invention may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The above content is only to illustrate the technical idea of the present invention, and cannot limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention all fall within the scope of the claims of the present invention. within the scope of protection.

Claims (9)

1. an electric vehicle control system parameter optimization method based on improved bee colony algorithm, is characterized in that, comprises the following steps: 1) Define the initial bee colony and construct the dynamic evaluation index function of the electric vehicle control system; 2) Use the bee colony to optimize the parameters of the electric vehicle control system, and use the dynamic evaluation index function to calculate the fitness corresponding to each individual bee in the bee colony; 3) The bee colony individuals are arranged in ascending order according to their fitness, and the first several bees in the arrangement are set as scout bees, and the remaining bees are follower bees; 4) Update the position of the scout bee and the position of the follower bee; In the process of location update, adopt the adaptive search strategy to adjust the optimal search area for the individual bees that have completed the search in each step, and determine whether the maximum allowable number of optimal search steps is reached, if not, return to step 2); Otherwise, go to step 5); 5) Find the bee individual with the smallest fitness in the current population, and the value corresponding to each dimension of the bee individual is the parameter value of the electric vehicle control system obtained by the final optimization. 2. the electric vehicle control system parameter optimization method based on improved bee colony algorithm according to claim 1, is characterized in that, the concrete process of step 1) is: The dimension of the initial bee colony is defined as N×D dimension, where N represents the total number of bee colonies, and D represents the total number of parameters to be optimized for the electric vehicle control system stored by the individual bees, then the nth (n=1,2,…, The d (d=1,2,...,D)-dimensional element B _n,d of N) bees is given by the following formula:

Among them, <x ₁ ,x ₂ ,…,x _n >represents a binary number composed of x ₁ ,x ₂ ,…,x _n ; <y ₁ ,y ₂ ,…,y _d >represents a binary number composed of y ₁ ,y ₂ ,...,y _d ; x _i (i=1,...,n) is the ith bit in the binary representation of a positive integer X, X satisfies the condition: 2 ^X >N; y _i (i= 1,...,d) is the ith bit in the binary expression of another positive integer Y that is relatively prime to X, and Y satisfies: 2 ^Y >D;

is the XOR operator; B _n,d represents the estimated value of the nth bee to the dth parameter that needs to be optimized in the electric vehicle control system. 3. the electric vehicle control system parameter optimization method based on improved bee colony algorithm according to claim 2, is characterized in that, the dynamic evaluation index function that step 1) constructs electric vehicle control system is specially: J=ω ₁ ∫εdt+ω ₂ σ+ω ₃ γ+ω ₄ κ Among them, ε, σ, γ and κ are the four evaluation indicators of the performance of the electric vehicle control system, which are tracking error, overshoot percentage, rise time and settling time, respectively; ω ₁ , ω ₂ , ω ₃ , and ω ₄ are four is the weight coefficient corresponding to the evaluation index; t is the test time of the system. 4. the electric vehicle control system parameter optimization method based on improved bee colony algorithm according to claim 3, is characterized in that, the optimization process in step 2) is: When starting the optimization, preset the initial value of the weight coefficient:

In the optimization process, the first weight coefficient ω ₁ is first assigned, so that:

ω ₂ =ω ₃ =ω ₄ =0; When ε meets the preset conditions, assign a value to the second weight coefficient ω ₂ so that:

ω ₃ =ω ₄ =0; When ε and σ satisfy the preset conditions, the third weight coefficient ω ₃ is assigned a value such that:

ω ₄ =0; When ε, σ and γ satisfy the preset conditions, the fourth weight coefficient ω ₄ is assigned a value such that:

Then, for each bee B, the corresponding J value is obtained, which is its fitness. 5. the electric vehicle control system parameter optimization method based on improved bee colony algorithm according to claim 4, is characterized in that, the process that carries out reconnaissance bee position update in step 4) is: The j-th movement of the n-th scout bee B _n is carried out as follows: _Bn (j)= _Bn (j-1)+ _λn (j) _Δn (j)

Among them, λ _n is the movement step length of B _n , Δ _n is the movement direction of B _n , ω ₀ is the inertia weight used to set the contribution of the movement distance of the first two steps to the next step,

is the geometric center of all reconnaissance bee colonies at step (j-1), μ ₁ ~ U(0,1) and

is a random variable with a uniform distribution. 6. the electric vehicle control system parameter optimization method based on improved bee colony algorithm according to claim 5, is characterized in that, in step 4), the process that carries out following bee position update is: The j-th movement of the m-th follower bee B _m proceeds as follows: B _m (j)=B _m (j-1)+λ _m (j)Δ _m (j)

Among them, λ _m is the motion step length of B _m , Δ _m is the motion direction of B _m , ω ₀ is the inertia weight used to set the contribution of the motion distance of the first two steps to the next step, and B _nm is the nth nearest to B _m scout bees, μ ₃ ～U(0,1) and

is a random variable with a uniform distribution. 7. the electric vehicle control system parameter optimization method based on improved bee colony algorithm according to claim 4, is characterized in that, in step 4), adopt the adaptive search strategy dynamic adjustment honeybee's search area to be specially: For the n-th bee B _n (n=1,...,N) after the j-th search is completed, the following adaptive search strategy is used to dynamically adjust its optimal area:

in,

and

respectively represent the upper and lower bounds of B _n searched in the jth step,

is the geometric center of the entire bee colony in the j-1th step, || || represents the Euclidean distance, μ ₅ ～U(0,1) is a random variable with uniform distribution. 8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements claim 1 when executing the computer program -7 The steps of any one of the steps of the method for optimizing parameters of an electric vehicle control system based on an improved bee colony algorithm. 9. A computer-readable storage medium, wherein the computer-readable storage medium is stored with a computer program, characterized in that, when the computer program is executed by the processor, the improved bee Steps of a swarm algorithm for electric vehicle control system parameter optimization method.

Images