CN111898206A - Parameter optimization method based on improved genetic algorithm, computer equipment and storage medium - Google Patents
Parameter optimization method based on improved genetic algorithm, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111898206A CN111898206A CN202010752793.8A CN202010752793A CN111898206A CN 111898206 A CN111898206 A CN 111898206A CN 202010752793 A CN202010752793 A CN 202010752793A CN 111898206 A CN111898206 A CN 111898206A
- Authority
- CN
- China
- Prior art keywords
- chromosome
- control system
- population
- electric vehicle
- vehicle control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 68
- 238000005457 optimization Methods 0.000 title claims abstract description 50
- 230000002068 genetic effect Effects 0.000 title claims abstract description 32
- 210000000349 chromosome Anatomy 0.000 claims abstract description 81
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000009827 uniform distribution Methods 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000001174 ascending effect Effects 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 4
- YTAHJIFKAKIKAV-XNMGPUDCSA-N [(1R)-3-morpholin-4-yl-1-phenylpropyl] N-[(3S)-2-oxo-5-phenyl-1,3-dihydro-1,4-benzodiazepin-3-yl]carbamate Chemical compound O=C1[C@H](N=C(C2=C(N1)C=CC=C2)C1=CC=CC=C1)NC(O[C@H](CCN1CCOCC1)C1=CC=CC=C1)=O YTAHJIFKAKIKAV-XNMGPUDCSA-N 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 2
- 230000035772 mutation Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Genetics & Genomics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physiology (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a parameter optimization method based on an improved genetic algorithm, computer equipment and a storage medium, and belongs to the field of parameter optimization. The optimization method comprises the following steps: 1) defining an initial chromosome population; 2) constructing a dynamic evaluation index function of the electric automobile control system, and optimizing to obtain chromosome fitness; 3) selecting by using a championship selection algorithm to serve as a parent population; utilizing a self-adaptive crossover and variation algorithm to operate to generate a progeny population; adjusting an optimization area of the nth chromosome by adopting a self-adaptive search strategy in the jth step, after the search is finished, checking whether j reaches the maximum allowable optimization step number, and if not, returning to 2); otherwise, go to 4); 4) and finding out the chromosome individual with the minimum fitness in the current population, wherein the value corresponding to each dimension of the chromosome is the parameter value of the electric automobile control system. The method solves the problems of complex modeling and large calculation amount in the parameter optimization process of the electric automobile control system.
Description
Technical Field
The invention belongs to the field of parameter optimization of automobile control systems, and particularly relates to a parameter optimization method based on an improved genetic algorithm, computer equipment and a storage medium.
Background
The electric automobile control system is a multi-input multi-output nonlinear system with complex dynamic coupling characteristics, and can be used for ensuring the stability and the maneuverability of a vehicle, improving the task completion capability and the smoothness of the vehicle, enhancing the safety of the vehicle and reducing the burden of a driver. The design of control parameters of an electric vehicle control system becomes the most direct and important key link for ensuring the driving safety of the electric vehicle. Many engineers are faced with the parameter design and adjustment problem of complex system with internal implicit relationship in the actual design process of electric vehicle control system. Although the design of the control system can be performed by means of small-disturbance linearized equations, strong coupling often exists between the input quantities of the linearized equations, and no obvious mapping relation exists between the desired performance index and the controller parameters, which brings great difficulty to the selection of the controller parameters.
Under the general condition, when the traditional classical optimization method is applied to carry out parameter optimization on the electric automobile control system, the comprehensive consideration of the system pre-constraint is difficult to achieve. In the existing methods applying linear programming and quadratic programming, when system parameter optimization is performed by the methods, clear mathematical definition and structured design are required for an electric vehicle control system, however, final optimization results may be deteriorated due to uncertainty of a model in an actual operation process. In addition, methods using integer programming and hybrid programming need to consider the internal relation and possible coupling relation among parameters of the electric vehicle control system, so that a lot of time is consumed to take account of and balance the influence of each adjusted parameter on the multi-aspect performance of the system, and the process is time-consuming and labor-consuming. How to realize the rapid and accurate design of the parameters of the control system of the electric automobile according to the preset requirements under the condition of saving manpower and physical force as much as possible is a problem to be solved urgently at present.
Genetic algorithm is a heuristic algorithm by simulating the evolution behavior of a natural organism. Compared with the traditional optimization method, a more convenient way is provided for solving the target problem. The genetic algorithm has global searching capability, flexibility in searching, robustness and self-adaption characteristics, so that the genetic algorithm has excellent characteristics in processing complex problems. The genetic algorithm carries out generation-by-generation updating through operations such as variation, intersection, selection and the like among individuals, and finally, the high-degree evolution function of the whole population is realized. In genetic algorithms, each individual represents a possible feasible solution, and the information exchange between different individuals and other individuals is carried out to realize the transition of the whole population to a better solution set. In recent years, genetic algorithms have been increasingly applied to the solution and computation of complex engineering problems. Because the method hardly needs prior knowledge on the processed problems and hardly provides preset conditions, the genetic algorithm has good effect on processing a large class of black box problems, and is widely applied to the field of parameter optimization of a large class of control systems. However, in the process of performing parameter optimization on the electric vehicle control system by using the genetic algorithm at present, the algorithm may fall into local optimization due to insufficient search of a target problem solution space, so that a global optimal solution cannot be finally obtained, and also may have a problem of slow later convergence speed due to an excessively large search range of the target problem solution space, which affect the effect of applying the genetic algorithm to perform parameter optimization on the electric vehicle control system to a certain extent, thereby affecting the performance of the system.
Disclosure of Invention
The invention aims to overcome the defects that the parameter optimization of an electric vehicle control system by using a genetic algorithm is easy to fall into local optimization or the convergence speed is low, and provides a parameter optimization method based on an improved genetic algorithm, computer equipment and a storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
an electric vehicle control system parameter optimization method based on an improved genetic algorithm comprises the following steps:
1) defining an initial chromosome population based on a parameter to be optimized of the electric vehicle control system, and constructing a dynamic evaluation index function of the electric vehicle control system;
2) optimizing the parameters of the electric vehicle control system by using the chromosome population, and calculating by using a dynamic evaluation index function to obtain the corresponding fitness of each chromosome;
3) arranging chromosome individuals in the chromosome population in an ascending order according to fitness, and selecting the chromosome individuals by using a championship selection algorithm to generate chromosomes to be crossed and mutated to serve as a parent population;
operating the parent population by using a self-adaptive intersection and variation algorithm to generate a child population;
after each step of searching is completed, each chromosome in the offspring population is adjusted in the optimizing area by adopting a self-adaptive searching strategy, whether the maximum allowable optimizing step number is reached is judged, and if the maximum allowable optimizing step number is not reached, the step 2 is returned;
otherwise, go to step 4);
4) and finding out chromosome individuals with the minimum fitness in the current population, wherein the value corresponding to each dimension of the chromosome individuals is the parameter value of the electric vehicle control system obtained through final optimization.
Further, the defining of the initial chromosome population in step 1) is specifically performed by:
defining the dimension of the initial chromosome population as NxD dimension, wherein N represents the total number of chromosomes, D represents the total number of parameters to be optimized of the electric vehicle control system stored in each chromosome individual, and the D (D-1, 2, …, D) dimension element C of the nth (N-1, 2, …, N) chromosomen,dComprises the following steps:
wherein mod (X, 2)n) Denotes dividing X by 2nMod (Y, 2)d) Denotes dividing Y by 2dThe remainder of (1); x satisfies the condition: x>2NY satisfies the condition: 2Y>D；
A binary bitwise XOR operator; cn,dIndicating the d-th requirement of the nth chromosome on the control system of the electric vehicleA predicted value of the optimized parameter.
Further, the step 1) of constructing a dynamic evaluation index function of the electric vehicle control system specifically comprises:
J＝ω1∫dt+ω2σ+ω3γ+ω4κ
wherein, four evaluation indexes of the performance of the sigma, gamma and kappa electric automobile control system are respectively tracking error, overshoot percentage, rise time and establishment time; omega1、ω2、ω3、ω4The weight coefficients are respectively corresponding to the four evaluation indexes; and t is the test time of the system.
Further, the optimizing process in the step 2) is as follows:
when the parameters of the electric automobile control system are optimized, presetting an initial value of a weight coefficient:
in the process of algorithm optimization, a first weight coefficient omega is given first1Assigning values such that:
ω2＝ω3＝ω4＝0；
giving a second weight factor ω when the desired condition is satisfied2Assigning values such that:
ω3＝ω4＝0；
giving a third weight coefficient ω when the sum σ satisfies a desired condition3Assigning values such that:
ω 40; when, σ and γ satisfy the expected conditions, a fourth weighting factor ω is given4Assigning values such that:
then for each chromosome CnAnd calculating the corresponding J value, namely the fitness of the system.
Further, in step 3), the parent population is operated by using a self-adaptive crossover and mutation algorithm to generate a child population, and the specific process is as follows:
the generation of the offspring population by using the adaptive crossover algorithm is as follows:
wherein the content of the first and second substances,
performing variation algorithm operation on the filial generation population generated based on the self-adaptive cross algorithm to generate the filial generation population as follows:
wherein the content of the first and second substances,
wherein the content of the first and second substances,
and
respectively representing the nth and mth chromosomes selected from the parent using the tournament selection algorithm,
and
represents the corresponding child generated therefrom; r isi(i ═ 1,2,3,4) to U (0,1) denote a uniform distribution of all random variables (0, 1); etacAnd ηmIs a distribution coefficient used to determine cross and variance distribution functions; mpIs the variation probability; l isuAnd LlRespectively an upper boundary and a lower boundary of the search domain; beta is used for controlling the information quantity inherited by the child population from the parent population; χ is used to control the degree of variation in the progeny population.
Further, in step 3), an adaptive search strategy is adopted to adjust the optimization area, and for the nth chromosome in the jth step, the method specifically comprises the following steps:
wherein L isu(j) And Ll(j) Respectively represent CnUpper and lower bounds, [ alpha ] of the search at step j1,α2,…,αD]And [ beta ]1,β2,…,βD]Respectively represent the constituent vectors LuAnd LlD elements of (a), thetadFor the angle of rotation of the d-th position, r5U (0,1) is a random variable with a uniform distribution;
representing the bitwise multiplication operator.
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 the steps of the method for optimizing parameters of an electric vehicle control system based on an improved genetic algorithm when executing the computer program.
A computer-readable storage medium, which stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for optimizing parameters of an electric vehicle control system based on an improved genetic algorithm.
Compared with the prior art, the invention has the following beneficial effects:
the parameter optimization method of the electric vehicle control system based on the improved genetic algorithm adopts the chromosome population with uniform distribution to carry out self-adaptive search on the solution space, dynamically adjusts the optimizing area of each chromosome in the searching process, and gives consideration to the global and local optimizing capabilities of the algorithm, so that the algorithm can avoid falling into local optimization in the searching process, can ensure the convergence speed of the algorithm, and can more quickly approach the global optimal solution; the method solves the problems of complex modeling and large calculation amount in the parameter optimization process of the electric vehicle control system, and can quickly and accurately optimize the parameters of the electric vehicle control system; compared with the traditional linear programming method, the optimized electric vehicle control system has better stability and quickly reduced lateral offset error when the double-shift-line task is completed.
Furthermore, the initial chromosome population definition mode of the invention ensures that the generated chromosome sequences are uniformly distributed, and the generated chromosome population can be uniformly distributed in the solution space as far as possible.
Furthermore, the self-adaptive crossover and variation algorithm of the invention keeps the diversity of the offspring population and improves the overall optimizing capability of the population.
The invention provides computer equipment and a storage medium of an electric vehicle control system parameter optimization method based on an improved genetic algorithm, which are used for realizing the specific steps of the optimization method.
Drawings
FIG. 1 is a block diagram of an electric vehicle control system;
FIG. 2 is a flow chart of parameter optimization based on an improved genetic algorithm;
FIG. 3 is a diagram illustrating the yaw angle of an electric vehicle control system optimized by applying the linear programming method and the method of the present invention in a double-shift line condition;
FIG. 4 is a diagram illustrating the yaw rate of an electric vehicle control system optimized by the linear programming method and the method of the present invention in a double-traverse mode;
FIG. 5 is a diagram illustrating the centroid slip angle of the electric vehicle control system optimized by the linear programming method and the method of the present invention under the double-shift working condition;
FIG. 6 is a side overload of an electric vehicle control system optimized by applying the linear programming method and the method of the present invention in a double-shift line condition;
FIG. 7 is a diagram illustrating lateral offset errors of an electric vehicle control system optimized by applying a linear programming method and the method of the present invention in a double-shift line condition;
FIG. 8 is a schematic diagram of a computer device in an embodiment of the invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, 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 in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the accompanying drawings:
referring to fig. 1, fig. 1 is a schematic structural diagram of a control system of an electric vehicle, which passes 5 state parameters (yaw angle phi, lateral overload n) during the running process of the vehicleyLateral offset y, centroid lateral offset angle β, and yaw rate r) to generate a desired yaw moment input and a steering wheel angle input; phi is acAnd ycCommand signals for yaw angle and lateral offset, respectively; controlling gain parameter k in each feedback channel1～k8I.e. the parameters that need to be optimized for the target system.
Referring to fig. 2, fig. 2 is a flowchart of a method for optimizing parameters of an electric vehicle control system based on an improved genetic algorithm, and is directed to 8 parameters k to be optimized of the electric vehicle control system in fig. 11～k8Defining the dimension of the initial chromosome population as NxD dimension, wherein N-100 represents the total number of chromosomes, D-8 represents the total number of parameters to be optimized of the electric vehicle control system stored in each chromosome individual, and the maximum allowable optimization step number of the algorithm is 500 steps;
in order to make the generated chromosome population distributed in the solution space as uniform as possible, a chromosome sequence having a uniform distribution is generated by a method in which the D (D ═ 1,2, …, D) dimensional element C of the nth (N ═ 1,2, …, N) chromosome is generatedn,dCan be composed ofThe following formula gives:
wherein mod (X, 2)n) Denotes dividing X by 2nMod (Y, 2)d) Denotes dividing Y by 2dThe remainder of (1); wherein the selection of X needs to meet the conditions: x>2NAnd Y needs to be selected to meet the conditions: 2Y>D；
A binary bitwise XOR operator; cn,dRepresenting the estimated value of the nth chromosome to the d parameter to be optimized of the electric vehicle control system;
step 2: constructing a dynamic evaluation index function J of the electric vehicle control system as follows:
J＝ω1∫dt+ω2σ+ω3γ+ω4κ
wherein, sigma, gamma and kappa are four evaluation indexes of the performance of the control system of the electric automobile, and respectively track error, overshoot percentage, rise time and establishing time; omega1、ω2、ω3、ω4The weight coefficients are respectively corresponding to the four evaluation indexes; t is the test time of the system; when the parameters of the electric automobile control system are optimized, presetting an initial value of a weight coefficient:
in the process of algorithm optimization, a first weight coefficient omega is given first1Assigning values such that:
ω2＝ω3＝ω 40; giving a second weight factor ω when the desired condition is satisfied2Assigning values such that:
ω3＝ω 40; when andwhen sigma meets the expected condition, giving a third weight coefficient omega3Assigning values such that:
ω 40; when, σ and γ satisfy the expected conditions, a fourth weighting factor ω is given4Assigning values such that:
then for each chromosome CnCalculating the corresponding J value, namely the fitness;
and step 3: arranging chromosome individuals of the whole population in an ascending order according to the corresponding J values, and then carrying out preferential selection on the chromosome individuals by applying a championship selection algorithm to generate chromosomes which are required to be crossed and mutated;
in order to maintain the diversity of the filial population and improve the overall optimizing capability of the population, the parent population is operated according to the following self-adaptive crossover and variation algorithm to generate the filial population:
wherein the content of the first and second substances,
representing the nth chromosome selected from the parent using the tournament selection algorithm,
representing the mth chromosome selected from the parent using the tournament selection algorithm,
is represented by
The generation of the offspring is carried out,
is represented by
The corresponding child generated; r isi(i ═ 1,2,3,4) to U (0,1) denote a uniform distribution of all random variables (0, 1); etacAnd ηmAre distribution coefficients used to determine the cross and variance distribution functions. MpIs the variation probability; l isuTo search the upper bound of the domain, LlIs the lower bound of the search domain; in the optimization process of the algorithm, beta is used for controlling the information bearing amount of the offspring population from the parent population; χ is used to control the magnitude of the degree of variation that the progeny population undergoes.
And 4, step 4: to enable the algorithm to approach the optimal solution more quickly, the nth chromosome Cn(N-1, …, N) at step j, the following adaptive search strategy will be used to dynamically adjust its seek area:
wherein L isu(j) Is represented by CnUpper bound of search at step j, Ll(j) Is represented by CnLower bound, [ alpha ] of search at step j1,α2,…,αD]Represents a composition vector LuD elements of (b), [ beta ]1,β2,…,βD]Represents a composition vector LlD elements of (a), thetadFor the angle of rotation of the d-th position, r5U (0,1) is a random variable with a uniform distribution;
representing a bitwise multiplication operator;
and 5: after the search in the jth step is finished, checking whether j reaches the maximum allowable optimization step number, and if not, returning to the step 2) to continue the optimization;
otherwise, stopping calculation, and finding out the chromosome individual C with the minimum J value in the current populationminThe value (C) corresponding to each dimension of the chromosomemin,1,Cmin,2,…,Cmin,D) Namely, the parameter values of the electric vehicle control system obtained by final optimization.
And testing and verifying the new method by using data obtained in a Simulink simulation environment:
examples
8 final optimization parameters k of the electric vehicle control system obtained by applying the method of the invention1～k8＝[3.59880.0168 -0.0574 -50.6347 -95.8745 -2.6417 48.1147 -0.2087]And carrying out double-wire-shifting working condition test.
The method comprises the steps of optimizing parameters of an electric vehicle control system by respectively utilizing a traditional linear programming method and an improved genetic algorithm of the invention, then carrying out double-shift-line working condition test on the optimized system, wherein the test time is 10 seconds, comparing 5 state parameters of the optimized system of the two methods, namely a yaw angle, a yaw angular rate, a mass center side offset angle, lateral overload and a lateral offset error, and referring to fig. 3-7, as can be seen from fig. 3-6, compared with the traditional linear programming method, the control system optimized by applying the method of the invention can enable the electric vehicle to have smaller variation ranges of the yaw angle, the yaw angular rate, the mass center side offset angle and the lateral overload under the double-shift-line working condition, and improve the system stability; it can be seen from fig. 7 that the method of the present invention can rapidly reduce the lateral offset error to zero in the driving process of the electric vehicle, and improve the rapidity of the vehicle for command tracking. Therefore, the working state in the double-shift line condition can be seen as follows: compared with the traditional linear programming method, the electric vehicle control system optimized by the method has better stability and quickly reduced lateral offset error when the double-shift-line task is completed.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The computer program is executed by a processor to implement a method for optimizing parameters of an electric vehicle control system based on an improved genetic algorithm.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: 1) defining an initial chromosome population based on a parameter to be optimized of the electric vehicle control system, and constructing a dynamic evaluation index function of the electric vehicle control system; 2) optimizing the parameters of the electric vehicle control system by using the chromosome population, and calculating by using a dynamic evaluation index function to obtain the corresponding fitness of each chromosome; 3) arranging chromosome individuals in the chromosome population in an ascending order according to fitness, and selecting the chromosome individuals by using a championship selection algorithm to generate chromosomes to be crossed and mutated to serve as a parent population; operating the parent population by using a self-adaptive intersection and variation algorithm to generate a child population; after each step of searching is completed, each chromosome in the offspring population is adjusted in the optimizing area by adopting a self-adaptive searching strategy, whether the maximum allowable optimizing step number is reached is judged, and if the maximum allowable optimizing step number is not reached, the step 2 is returned; otherwise, go to step 4); 4) and finding out chromosome individuals with the minimum fitness in the current population, wherein the value corresponding to each dimension of the chromosome individuals is the parameter value of the electric vehicle control system obtained through final optimization.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: 1) defining an initial chromosome population based on a parameter to be optimized of the electric vehicle control system, and constructing a dynamic evaluation index function of the electric vehicle control system; 2) optimizing the parameters of the electric vehicle control system by using the chromosome population, and calculating by using a dynamic evaluation index function to obtain the corresponding fitness of each chromosome; 3) arranging chromosome individuals in the chromosome population in an ascending order according to fitness, and selecting the chromosome individuals by using a championship selection algorithm to generate chromosomes to be crossed and mutated to serve as a parent population; operating the parent population by using a self-adaptive intersection and variation algorithm to generate a child population; after each step of searching is completed, each chromosome in the offspring population is adjusted in the optimizing area by adopting a self-adaptive searching strategy, whether the maximum allowable optimizing step number is reached is judged, and if the maximum allowable optimizing step number is not reached, the step 2 is returned; otherwise, go to step 4); 4) and finding out chromosome individuals with the minimum fitness in the current population, wherein the value corresponding to each dimension of the chromosome individuals is the parameter value of the electric vehicle control system obtained through final optimization.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (8)
1. An electric vehicle control system parameter optimization method based on an improved genetic algorithm is characterized by comprising the following steps:
1) defining an initial chromosome population based on a parameter to be optimized of the electric vehicle control system, and constructing a dynamic evaluation index function of the electric vehicle control system;
2) optimizing the parameters of the electric vehicle control system by using the chromosome population, and calculating by using a dynamic evaluation index function to obtain the corresponding fitness of each chromosome;
3) arranging chromosome individuals in the chromosome population in an ascending order according to fitness, and selecting the chromosome individuals by using a championship selection algorithm to generate chromosomes to be crossed and mutated to serve as a parent population;
operating the parent population by using a self-adaptive intersection and variation algorithm to generate a child population;
after each step of searching is completed, each chromosome in the offspring population is adjusted in the optimizing area by adopting a self-adaptive searching strategy, whether the maximum allowable optimizing step number is reached is judged, and if the maximum allowable optimizing step number is not reached, the step 2 is returned;
otherwise, go to step 4);
4) and finding out chromosome individuals with the minimum fitness in the current population, wherein the value corresponding to each dimension of the chromosome individuals is the parameter value of the electric vehicle control system obtained through final optimization.
2. The improved genetic algorithm-based parameter optimization method for the electric vehicle control system according to claim 1, wherein the specific operations of defining the initial chromosome population in the step 1) are as follows:
defining the dimension of the initial chromosome population as NxD dimension, wherein N represents the total number of chromosomes, D represents the total number of parameters to be optimized of the electric vehicle control system stored in each chromosome individual, and the D (D-1, 2, …, D) dimension element C of the nth (N-1, 2, …, N) chromosomen,dComprises the following steps:
wherein mod (X, 2)n) Denotes dividing X by 2nMod (Y, 2)d) Denotes dividing Y by 2dThe remainder of (1); x satisfies the condition: x>2NY satisfies the condition: 2Y>D；
A binary bitwise XOR operator; cn,dAnd representing the estimated value of the nth chromosome to the d parameter needing to be optimized of the electric vehicle control system.
3. The method for optimizing the parameters of the electric vehicle control system based on the improved genetic algorithm according to claim 1, wherein the dynamic evaluation index function for constructing the electric vehicle control system in the step 1) is specifically as follows:
J＝ω1∫dt+ω2σ+ω3γ+ω4κ
wherein, four evaluation indexes of the performance of the sigma, gamma and kappa electric automobile control system are respectively tracking error, overshoot percentage, rise time and establishment time; omega1、ω2、ω3、ω4The weight coefficients are respectively corresponding to the four evaluation indexes; and t is the test time of the system.
4. The improved genetic algorithm-based parameter optimization method for the electric vehicle control system according to claim 3, wherein the optimization process in the step 2) is as follows:
when the parameters of the electric automobile control system are optimized, presetting an initial value of a weight coefficient:
in the process of algorithm optimization, a first weight coefficient omega is given first1Assigning values such that:
ω2＝ω3＝ω4＝0；
giving a second weight factor ω when the desired condition is satisfied2Assigning values such that:
ω3＝ω4＝0；
giving a third weight when the sum σ satisfies a desired conditionCoefficient omega3Assigning values such that:
ω40; when, σ and γ satisfy the expected conditions, a fourth weighting factor ω is given4Assigning values such that:
then for each chromosome CnAnd calculating the corresponding J value, namely the fitness of the system.
5. The improved genetic algorithm-based parameter optimization method for the electric vehicle control system according to claim 4, wherein in the step 3), the parent population is operated by using a self-adaptive crossover and mutation algorithm to generate the child population, and the specific process is as follows:
the generation of the offspring population by using the adaptive crossover algorithm is as follows:
wherein the content of the first and second substances,
performing variation algorithm operation on the filial generation population generated based on the self-adaptive cross algorithm to generate the filial generation population as follows:
wherein the content of the first and second substances,
wherein the content of the first and second substances,
and
respectively representing the nth and mth chromosomes selected from the parent using the tournament selection algorithm,
and
represents the corresponding child generated therefrom; r isi(i ═ 1,2,3,4) to U (0,1) denote a uniform distribution of all random variables (0, 1); etacAnd ηmIs a distribution coefficient used to determine cross and variance distribution functions; mpIs the variation probability; l isuAnd LlRespectively an upper boundary and a lower boundary of the search domain; beta is used for controlling the information quantity inherited by the child population from the parent population; χ is used to control the degree of variation in the progeny population.
6. The method for optimizing the parameters of the electric vehicle control system based on the improved genetic algorithm as claimed in claim 1, wherein the step 3) adopts an adaptive search strategy to adjust the optimization area, and for the nth chromosome, in the step j, the method specifically comprises the following steps:
wherein L isu(j) And Ll(j) Respectively represent CnUpper and lower bounds, [ alpha ] of the search at step j1,α2,…,αD]And [ beta ]1,β2,…,βD]Respectively represent the constituent vectors LuAnd LlD elements of (a), thetadFor the angle of rotation of the d-th position, r5U (0,1) is a random variable with a uniform distribution;
representing the bitwise multiplication operator.
7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the improved genetic algorithm based parameter optimization method for electric vehicle control systems according to any one of claims 1 to 6.
8. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for optimizing parameters of an electric vehicle control system based on an improved genetic algorithm according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010752793.8A CN111898206B (en) | 2020-07-30 | 2020-07-30 | Parameter optimization method based on improved genetic algorithm, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010752793.8A CN111898206B (en) | 2020-07-30 | 2020-07-30 | Parameter optimization method based on improved genetic algorithm, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111898206A true CN111898206A (en) | 2020-11-06 |
| CN111898206B CN111898206B (en) | 2024-04-12 |
Family
ID=73182606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010752793.8A Active CN111898206B (en) | 2020-07-30 | 2020-07-30 | Parameter optimization method based on improved genetic algorithm, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898206B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380018A (en) * | 2020-11-30 | 2021-02-19 | 海光信息技术股份有限公司 | Method for determining matrix blocking parameters for matrix multiplication based on genetic algorithm |
| CN112463069A (en) * | 2020-12-11 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Method, device and equipment for recovering storage garbage and readable medium |
| CN112784497A (en) * | 2021-02-05 | 2021-05-11 | 中国人民解放军93534部队 | Ground radar networking startup optimization method based on genetic algorithm |
| CN112800547A (en) * | 2021-01-29 | 2021-05-14 | 中国科学院电工研究所 | Layout optimization method and device for motor controller of electric vehicle and storage medium |
| CN112904729A (en) * | 2021-01-21 | 2021-06-04 | 深圳翱诺科技有限公司 | Controller parameter design algorithm for avoiding local optimization |
| CN113159687A (en) * | 2021-04-29 | 2021-07-23 | 长安大学 | Workshop AGV-UAV cooperative material distribution path planning method and system |
| CN113779885A (en) * | 2021-09-16 | 2021-12-10 | 南京航空航天大学 | Tolerance optimization method based on genetic algorithm |
| CN114339564A (en) * | 2021-12-23 | 2022-04-12 | 清华大学深圳国际研究生院 | User self-adaptive hearing aid self-fitting method based on neural network |
| CN116719240A (en) * | 2023-08-02 | 2023-09-08 | 中国一冶集团有限公司 | Dehydration control method and system of mucky soil dehydration device vehicle |
| CN113779885B (en) * | 2021-09-16 | 2024-04-30 | 南京航空航天大学 | Tolerance optimization method based on genetic algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090070281A1 (en) * | 2007-06-01 | 2009-03-12 | Solomon Research Llc | System for hybridized efficient genetic algorithms to solve bi-objective optimization problems with application to network computing |
| CN101504795A (en) * | 2008-11-03 | 2009-08-12 | 天津理工大学 | Working method for DSP control system applied to multi-storied garage parking position scheduling |
| CN102663167A (en) * | 2012-03-20 | 2012-09-12 | 浙江大学 | Optimization design method for electric automobile anti-lock braking system controller based on immune algorithm |
| CN102745192A (en) * | 2012-06-14 | 2012-10-24 | 北京理工大学 | Task allocation system for distributed control system of hybrid vehicle |
| US20180082198A1 (en) * | 2016-09-19 | 2018-03-22 | The Aerospace Corporation | Systems and Methods for Multi-Objective Optimizations with Decision Variable Perturbations |
| CN108399451A (en) * | 2018-02-05 | 2018-08-14 | 西北工业大学 | A kind of Hybrid Particle Swarm Optimization of combination genetic algorithm |
| CN111259506A (en) * | 2018-11-14 | 2020-06-09 | 长春设备工艺研究所 | Improved genetic algorithm-based vehicle engine body machining process path optimization method |
-
2020
- 2020-07-30 CN CN202010752793.8A patent/CN111898206B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090070281A1 (en) * | 2007-06-01 | 2009-03-12 | Solomon Research Llc | System for hybridized efficient genetic algorithms to solve bi-objective optimization problems with application to network computing |
| CN101504795A (en) * | 2008-11-03 | 2009-08-12 | 天津理工大学 | Working method for DSP control system applied to multi-storied garage parking position scheduling |
| CN102663167A (en) * | 2012-03-20 | 2012-09-12 | 浙江大学 | Optimization design method for electric automobile anti-lock braking system controller based on immune algorithm |
| CN102745192A (en) * | 2012-06-14 | 2012-10-24 | 北京理工大学 | Task allocation system for distributed control system of hybrid vehicle |
| US20180082198A1 (en) * | 2016-09-19 | 2018-03-22 | The Aerospace Corporation | Systems and Methods for Multi-Objective Optimizations with Decision Variable Perturbations |
| CN108399451A (en) * | 2018-02-05 | 2018-08-14 | 西北工业大学 | A kind of Hybrid Particle Swarm Optimization of combination genetic algorithm |
| CN111259506A (en) * | 2018-11-14 | 2020-06-09 | 长春设备工艺研究所 | Improved genetic algorithm-based vehicle engine body machining process path optimization method |
Non-Patent Citations (1)
| Title |
|---|
| 林涛;武孟贤;轩倩倩;徐庆国;江冲;: "基于捕食搜索策略混合遗传算法的车辆路径问题研究", 中南民族大学学报(自然科学版), no. 04 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380018A (en) * | 2020-11-30 | 2021-02-19 | 海光信息技术股份有限公司 | Method for determining matrix blocking parameters for matrix multiplication based on genetic algorithm |
| CN112463069A (en) * | 2020-12-11 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Method, device and equipment for recovering storage garbage and readable medium |
| CN112463069B (en) * | 2020-12-11 | 2023-01-06 | 苏州浪潮智能科技有限公司 | Method, device and equipment for recovering storage garbage and readable medium |
| CN112904729A (en) * | 2021-01-21 | 2021-06-04 | 深圳翱诺科技有限公司 | Controller parameter design algorithm for avoiding local optimization |
| CN112800547B (en) * | 2021-01-29 | 2024-03-08 | 中国科学院电工研究所 | Layout optimization method and device for electric vehicle motor controller and storage medium |
| CN112800547A (en) * | 2021-01-29 | 2021-05-14 | 中国科学院电工研究所 | Layout optimization method and device for motor controller of electric vehicle and storage medium |
| CN112784497B (en) * | 2021-02-05 | 2022-09-27 | 中国人民解放军93534部队 | Ground radar networking startup optimization method based on genetic algorithm |
| CN112784497A (en) * | 2021-02-05 | 2021-05-11 | 中国人民解放军93534部队 | Ground radar networking startup optimization method based on genetic algorithm |
| CN113159687A (en) * | 2021-04-29 | 2021-07-23 | 长安大学 | Workshop AGV-UAV cooperative material distribution path planning method and system |
| CN113159687B (en) * | 2021-04-29 | 2023-08-29 | 长安大学 | Workshop AGV-UAV (automated guided vehicle-unmanned aerial vehicle) coordinated material distribution path planning method and system |
| CN113779885A (en) * | 2021-09-16 | 2021-12-10 | 南京航空航天大学 | Tolerance optimization method based on genetic algorithm |
| CN113779885B (en) * | 2021-09-16 | 2024-04-30 | 南京航空航天大学 | Tolerance optimization method based on genetic algorithm |
| CN114339564A (en) * | 2021-12-23 | 2022-04-12 | 清华大学深圳国际研究生院 | User self-adaptive hearing aid self-fitting method based on neural network |
| CN114339564B (en) * | 2021-12-23 | 2023-06-16 | 清华大学深圳国际研究生院 | Neural network-based self-adaptation method for self-adaptive hearing aid of user |
| CN116719240A (en) * | 2023-08-02 | 2023-09-08 | 中国一冶集团有限公司 | Dehydration control method and system of mucky soil dehydration device vehicle |
| CN116719240B (en) * | 2023-08-02 | 2023-11-24 | 中国一冶集团有限公司 | Dehydration control method and system of mucky soil dehydration device vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111898206B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898206A (en) | Parameter optimization method based on improved genetic algorithm, computer equipment and storage medium | |
| US20220363259A1 (en) | Method for generating lane changing decision-making model, method for lane changing decision-making of unmanned vehicle and electronic device | |
| CN110647042B (en) | Robot robust learning prediction control method based on data driving | |
| CN112101530B (en) | Neural network training method, device, equipment and storage medium | |
| US20220210028A1 (en) | Cloud software service resource allocation method based on qos model self-correctio | |
| CN106383315A (en) | New energy automobile battery state of charge (SOC) prediction method | |
| CN111178487A (en) | Power optimization scheduling method and device, computer equipment and storage medium | |
| CN111103802B (en) | Intelligent autonomous control method and system for impurity removal reactor in liquid zinc purification process | |
| CN114740710A (en) | Random nonlinear multi-agent reinforcement learning optimization formation control method | |
| CN113534669B (en) | Unmanned vehicle control method and device based on data driving and computer equipment | |
| CN113759724B (en) | Robot control method and device based on data driving and computer equipment | |
| Zengin et al. | Blending based multiple-model adaptive control of multivariable systems with application to lateral vehicle motion control | |
| CN115167102A (en) | Reinforced learning self-adaptive PID control method based on parallel dominant motion evaluation | |
| CN112180730B (en) | Hierarchical optimal consistency control method and device for multi-agent system | |
| Fu et al. | Adaptive optimal control of unknown nonlinear systems with different time scales | |
| Picotti et al. | Data-driven Tuning of a NMPC Controller for a Virtual Motorcycle through Genetic Algorithm | |
| CN111898726A (en) | Parameter optimization method for electric vehicle control system, computer equipment and storage medium | |
| Anuradha et al. | Direct inverse neural network control of a continuous stirred tank reactor (CSTR) | |
| Zengin et al. | Blending based multiple-model adaptive control for multivariable systems and application to lateral vehicle dynamics | |
| WO2022117127A2 (en) | Engineering forklift multi-objective performance optimization method based on deep surrogate model | |
| CN111695623A (en) | Large-scale battery energy storage system group modeling method, system and equipment based on fuzzy clustering and readable storage medium | |
| Jiang et al. | Approximated Long Horizon MPC with Hindsight for Autonomous Vehicles Path Tracking | |
| CN112015083B (en) | Parameter self-tuning method of SISO (SISO) compact-format model-free controller based on ensemble learning | |
| CN116819973B (en) | Track tracking control method | |
| CN111103789B (en) | Source network load comprehensive energy scheduling analysis method, system and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |