CN110807290A - Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution - Google Patents

Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution Download PDF

Info

Publication number
CN110807290A
CN110807290A CN201910849428.6A CN201910849428A CN110807290A CN 110807290 A CN110807290 A CN 110807290A CN 201910849428 A CN201910849428 A CN 201910849428A CN 110807290 A CN110807290 A CN 110807290A
Authority
CN
China
Prior art keywords
individuals
evolution
condition
markov chain
adaptive
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
Application number
CN201910849428.6A
Other languages
Chinese (zh)
Other versions
CN110807290B (en
Inventor
张曼
施树明
沈云波
程文冬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Technological University
Original Assignee
Xian Technological University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian Technological University filed Critical Xian Technological University
Priority to CN201910849428.6A priority Critical patent/CN110807290B/en
Publication of CN110807290A publication Critical patent/CN110807290A/en
Application granted granted Critical
Publication of CN110807290B publication Critical patent/CN110807290B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Genetics & Genomics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Physiology (AREA)
  • Feedback Control In General (AREA)

Abstract

The invention discloses a road slope-containing automobile operation condition design method based on self-adaptive Markov chain evolution, which integrates self-adaptive characteristics into a Markov chain evolution method, combines the evolution strategy in the Markov chain evolution method to meet the specificity of Markov performance of the working condition, defines a strategy function boundary variable, classifies the evolution strategy into two strategies with general global and local search functions, and adjusts the probability of the evolution strategy by using a self-adaptive formula, so that the evolution strategy not only meets the Markov performance of the working condition, but also has self-adaptability. Compared with the operation condition design method based on Markov chain evolution, the method can obtain the representative operation condition of the multi-parameter highway, and meanwhile, the operation efficiency is obviously improved under the set condition. The design method can be used for designing the operation conditions with different parameters, the application range is expanded, and the applicability is strong.

Description

Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution
Technical Field
The invention relates to a method for designing an automobile running condition, in particular to a method for designing a road gradient-containing automobile running condition based on self-adaptive Markov chain evolution.
Background
The fuel consumption rate and pollutant discharge amount of the automobile are obviously increased along with the increase of the gradient, and the fuel consumption and pollutant discharge amount of the automobile are obviously influenced by the gradient of the road. In addition, heavy-duty vehicle energy consumption assessment and hybrid vehicle powertrain size selection also exhibit strong sensitivity to road grade. The method of condition design requires consideration of road grade parameters that would otherwise result in impractical or limited designs for automotive applications. The current working condition design method containing the road gradient mainly comprises a traditional Markov chain-based working condition design method and an intelligent method derived based on the Markov chain. The Markov chain method based on the multi-factor influence has the problem of low design efficiency during the design of the operation working condition, and the reason is that the working condition is randomly generated by the method essentially, and the target working condition cannot be approached due to the lack of directivity in the process. Compared with the Markov chain method, the method enables the working condition design process to have directionality, and can improve the operation efficiency of the design working condition. However, both methods lack the property of adaptability to the design environment, i.e., adaptability, in other words, the method with adaptability can more fully exploit the space for improving the design efficiency. There is therefore a continuing need for improvements to existing markov chain evolution methods.
Disclosure of Invention
The invention aims to solve the technical problem of providing a road slope-containing automobile operating condition design method based on self-adaptive Markov chain evolution, which can greatly optimize a Markov chain evolution method and further improve the subsequent operating condition design efficiency containing parameters such as gears, rotating speed, torque or power.
The technical scheme adopted by the invention for solving the technical problems is to provide a method for designing the running condition of an automobile with a road gradient based on self-adaptive Markov chain evolution, which comprises the following steps: s1) setting speed, acceleration and road gradient steps Δ v, Δ a and Δ g and minimum speed v, respectively, based on test data of the vehicle actually including the road gradientminMaximum velocity vmaxMinimum acceleration aminMaximum acceleration amaxMinimum slope gminAnd maximum slope gmaxCarrying out state coding, counting a state transition probability matrix P with three parameters according to the time length L of the operation condition and the size N of the populationPGenerating a state sequence by using a Markov chain random simulation method to form an initial population; s2) setting the relative deviation absolute value of the operation condition and the evaluation index of the original acquisition database to be kept at the threshold value TrIn the range, designing a target function, decoding the population individuals into a sequence, and sequentially calculating adaptive values of the population individuals; s3) according to the set elite probability psSelecting and reserving NP×psRandomly pairing the residual individuals of the population by using a fitness scale transformation function; s4) selecting the operator operation to be executed, and calculating the cross probability pcGenerating pseudo-random numbers r, when r > pcWhen the method is used, self-adaptive Markov variation operation is carried out on the individual to generate a variation individual; when r is less than or equal to pcSelecting the category of the crossover operator to be executed, and performing crossover operation on the individuals to generate crossover individuals; s5) forming a new population by the elite individuals, the crossed individuals and the variant individuals, outputting an optimal sequence chain if a termination condition is met, and decoding to obtain a three-parameter working condition time sequence; otherwise, the process returns to step S2.
Further, in the step S1, L takes 1800S, NPIs 24, Δ v is 0.5m/s, Δ a is 0.1m/s2The value of Δ g is 1%.
Further, T in the step S2rThe value of (a) is 10%; p in said step S13sIs 1/12.
Further, the step S4 calculates the cross probability p according to the formula (1)c；
In the formula: p is a radical ofcTo cross probability, pc_maxTo maximum cross probability, pc_minTo minimum cross probability, itmax is the maximum algebra, iter is the current algebra, favgFor population average fitness value, f' is the greater fitness value among the two individuals to be crossed.
Further, p isc_max，pc_minAnd itmax are 0.7,0.1 and 400, respectively.
Further, the variant object generation process in step S4 is as follows: two working condition sequence chains X (in random pairing mode)1) And X: (2)
Figure BDA0002196400190000031
Figure BDA0002196400190000032
Wherein i, j belongs to [1, 2.,. L ], and x is a working condition state gene code;
when the constraint (2) is satisfied, the variant individual X is generated by exchanging the gene fragment lc1And Xc2
Figure BDA0002196400190000033
Figure BDA0002196400190000034
Figure BDA0002196400190000035
In the formula IbVariables are demarcated for operator functions.
Further, the lbIs Lx0.05.
Further, the cross individual generation process in step S4 is as follows: setting a Selective Cross Category probability pcmGenerating a pseudo-random number r1 when r1 > pcmThen, step 6.1 is executed, and the situation-crossing operation is carried out on the individuals to generate crossed individuals; otherwise, executing step 6.2, and performing situation two-way crossing operation on the individuals to generate crossed individuals;
step 6.1: when r1 > pcmTwo working condition sequence chains X matched randomly(1)And X(2)When constraint (3) is satisfied, crossover individuals X are generated by exchanging gene segments lc1And Xc2
Figure BDA0002196400190000041
Step 6.2: when r1 is not more than pcmTwo working condition sequence chains X matched randomly(1)And X(2)By the condition (4), the crossover individual X is generatedc1And Xc2，
In the formula: pop is the population of the current iteration number.
Further, said pcmIs 0.1.
Compared with the prior art, the invention has the following beneficial effects: the invention integrates the self-adaptive characteristic into the Markov chain evolution method, combines the evolution strategy in the Markov chain evolution method to meet the specificity of the Markov property of the working condition, defines the strategy function boundary variable, classifies the evolution strategy into two strategies with general global and local search functions, and adjusts the probability of the evolution strategy by using the self-adaptive formula, so that the evolution strategy not only meets the Markov property of the working condition, but also has the self-adaptive property. Compared with the operation condition design method based on Markov chain evolution, the method can obtain the representative operation condition of the multi-parameter highway, and meanwhile, the operation efficiency is obviously improved under the set condition. The design method can be used for designing the operation conditions with different parameters, the application range is expanded, and the applicability is strong.
Drawings
FIG. 1 is a flow chart of the adaptive Markov chain evolution method of the present invention.
Fig. 2 is a graph showing the variation of the minimum objective function value with the number of iterations of the design result of the present invention.
FIG. 3 is a graph of velocity versus time for the results of the inventive design.
FIG. 4 is a graph of acceleration versus time for the results of the inventive design.
Fig. 5 is a graph of slope versus time for the design results of the present invention.
Detailed Description
The invention is further described below with reference to the figures and examples.
FIG. 1 is a flow chart of the adaptive Markov chain evolution method of the present invention.
Referring to fig. 1, the method for designing the operating condition of the vehicle with the road gradient based on the adaptive mahalanobis chain evolution provided by the invention comprises the following steps:
step S1: based on the test data of the actual road gradient of the vehicle, the speed, the acceleration, the road gradient step length delta v, delta a and delta g and the minimum speed v are respectively setminMaximum velocity vmaxMinimum acceleration aminMaximum acceleration amaxMinimum slope gminAnd maximum slope gmaxCarrying out state coding, counting a three-parameter state transition probability matrix P according to a formula (5), and carrying out state coding according to the time length L of the operation condition and the size N of the populationPGenerating a state sequence by using a Markov chain random simulation method to form an initial population; the parameters are respectively that Deltav is 0.5m/s and Deltaa is 0.1m/s2，Δg＝1％，vmin＝0m/s，vmax＝35m/s，amin＝-2m/s2，amax＝2m/s2，gmin-10% and g max10%, L1800 s and NP＝24；
Figure BDA0002196400190000061
In the formula:
Figure BDA0002196400190000062
k is the number of one-dimensional space states, NijIs a one-dimensional space state siTo a one-dimensional space state sjNumber of transfers of，NiIs a one-dimensional space state siThe sum of the number of transitions to other states, pijIs a one-dimensional space state siTo a one-dimensional space state sjS is a space state set;
state s at time ttCalculated according to equation (6)
st＝mt+(nt-1)×M+(ht-1)×M×N (6)
In the formula: m istIs the speed state at time t, ntAcceleration state at time t, htAnd M is the number of speed states and N is the number of acceleration states for the gradient state at the time t, and the calculation modes are respectively shown in the formula (7) to the formula (11).
Figure BDA0002196400190000063
Figure BDA0002196400190000064
Figure BDA0002196400190000065
Figure BDA0002196400190000066
Figure BDA0002196400190000067
Step S2: the relative deviation absolute values of the set operation condition and the evaluation index of the original acquisition database are all kept at a threshold value TrIn the range, designing a target function, decoding the population individuals into a sequence, and sequentially calculating adaptive values of the population individuals; t isrIs 10%;
the design of the objective function is specifically as follows: the absolute value of the relative deviation of the operating condition from the selected evaluation index of the original collected database can be expressed as formula (12)
|Ij(X)-Idj|≤δj,j＝1,2,...,w (12)
In the formula: x is an operating condition under the current iteration number, IdThe method comprises the following steps of taking an evaluation index vector of an original acquisition database, wherein I is the evaluation index vector of the operation working condition, delta is an evaluation index deviation value vector, and w is the number of selected evaluation indexes, wherein the selected evaluation indexes comprise: the system comprises an idle speed time proportion, an acceleration time proportion, a uniform speed time proportion, a deceleration time proportion, an average speed, an average running speed, a running speed standard deviation, and probability distribution correlation coefficients of positive acceleration kinetic energy, an average climbing slope, an average descending slope, speed and acceleration in unit distance;
normalizing the formula (12) to make the absolute value of the relative deviation of each index on the left side of the normalization equal to fj(X) as in formula (13), the absolute value of the tolerance deviation of each index on the right side of the normalization is
Figure BDA0002196400190000071
As shown in formula (14);
fj(X)＝|1-Ij(X)/Idj| (13)
Figure BDA0002196400190000072
construction auxiliary variable Hi(X), see formula (15)
Figure BDA0002196400190000073
Design objective function F, see formula (16)
In the formula: x is the state of the operating condition, S is the state space of the operating condition, according to the design objective
Figure BDA0002196400190000075
Therefore, T is not more than min (F)r；
Step S3: according to a set elite probability psSelecting and reserving NP×psRandomly pairing the residual individuals of the population by using a fitness scale transformation function; p is a radical ofsIs 1/12;
step S4: selecting the operator operation to be performed, i.e. calculating the crossover probability p according to equation (17)cGenerating pseudo-random numbers r, when r > pcThen, step 5.1 is executed, and the individual carries out self-adaptive Markov variation operation to generate a variation individual; otherwise, executing step 5.2, and selecting the category for executing the crossover operator;
Figure BDA0002196400190000081
in the formula: p is a radical ofcTo cross probability, pc_maxTo maximum cross probability, pc_minIs the minimum cross probability, itmax is the maximum algebra, iter is the current algebra, favgF' is the larger fitness value of the two selected individuals; p is a radical ofc_max，pc_minAnd itmax are preferably 0.7,0.1 and 400, respectively;
step S5.1: when r > pcTwo working condition sequence chains X matched randomly(1)And X(2)；
Figure BDA0002196400190000082
Figure BDA0002196400190000083
Wherein i, j belongs to [1, 2.,. L ], and x is a working condition state gene code;
when the constraint (18) is satisfied, the variant individual X is generated by exchanging the gene fragment lc1And Xc2
Figure BDA0002196400190000084
Figure BDA0002196400190000085
Figure BDA0002196400190000086
In the formula IbDemarcating variables for operator functions,/bIs lx0.05;
step S5.2: when r is less than or equal to pcWhen selecting a class for which a crossover operator is to be performed, i.e. setting a probability p for selecting a crossover classcmGenerating a pseudo-random number r1 when r1 > pcmThen, step 6.1 is executed, and the individuals carry out situation-crossing operation to generate crossing individuals; otherwise, executing step 6.2, carrying out situation two-way crossing operation by the individuals to generate crossed individuals; p is a radical ofcmIs 0.1;
step 6.1: when r1 > pcmTwo working condition sequence chains X matched randomly(1)And X(2)
Crossing over gene segments l to generate crossover individuals X when the constraint (19) is satisfiedc1And Xc2
Figure BDA0002196400190000091
Step 6.2: when r1 is not more than pcmTwo working condition sequence chains X matched randomly(1)And X(2)Generating the crossover individual X by the condition (20)c1And Xc2，
Figure BDA0002196400190000092
In the formula: pop is the population of the current iteration times;
and 7: forming a new population by the elite individuals, the crossed individuals and the variant individuals;
and 8: judging whether a termination condition is met, namely when iter is less than itmax, returning to the step 2, otherwise, executing the step 9;
and step 9: and outputting the optimal sequence chain and the change curve of the minimum function value, as shown in figure 2 in the figure, and decoding to obtain the three-parameter working condition time sequence, as shown in figure 3, figure 4 and figure 5 in the figure.
Fig. 2 to 5 show the results obtained from a certain test, and from the change of the minimum function value, the adjustment of the adaptive cross probability allows the individual proportion of the population where the cross and variation occur to change adaptively, and the optimum function value can approach the optimum solution more quickly at different stages; the parameter time series curve shows the characteristic that the vehicle runs at a high speed on the road gradient, and in addition, through statistics, compared with a working condition design method based on Markov chain evolution, the working efficiency is improved by 43.08%.
Although the present invention has been described with respect to the preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (9)

1. A road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution is characterized by comprising the following steps:
s1) setting speed, acceleration and road gradient steps Δ v, Δ a and Δ g and minimum speed v, respectively, based on test data of the vehicle actually including the road gradientminMaximum velocity vmaxMinimum acceleration aminMaximum acceleration amaxMinimum slope gminAnd maximum slope gmaxCarrying out state coding, counting a state transition probability matrix P with three parameters according to the time length L of the operation condition and the size N of the populationPGenerating a state sequence by using a Markov chain random simulation method to form an initial population;
s2) setting the relative deviation absolute value of the operation condition and the evaluation index of the original acquisition database to be kept at the threshold value TrIn the range, designing a target function, decoding the population individuals into a sequence, and sequentially calculating adaptive values of the population individuals;
s3) according to the set elite probability psSelecting and reserving NP×psRandomly pairing the residual individuals of the population by using a fitness scale transformation function;
s4) selecting the operator operation to be executed, and calculating the cross probability pcGenerating pseudo-random numbers r, when r > pcWhen the method is used, self-adaptive Markov variation operation is carried out on the individual to generate a variation individual; when r is less than or equal to pcSelecting the category of the crossover operator to be executed, and performing crossover operation on the individuals to generate crossover individuals;
s5) forming a new population by the elite individuals, the crossed individuals and the variant individuals, outputting an optimal sequence chain if a termination condition is met, and decoding to obtain a three-parameter working condition time sequence; otherwise, the process returns to step S2.
2. The method for designing the operating condition of the road-grade-containing automobile based on the adaptive Markov chain evolution of claim 1, wherein the value of L in the step S1 is 1800S, and the value of N is 1800SPIs 24, Δ v is 0.5m/s, Δ a is 0.1m/s2The value of Δ g is 1%.
3. The method for designing the operating condition of the automobile with the road gradient based on the adaptive Markov chain evolution as claimed in claim 1, wherein T in the step S2rThe value of (a) is 10%; p in said step S13sIs 1/12.
4. The method for designing road gradient-containing automobile operating condition based on adaptive Markov chain evolution as claimed in claim 1, wherein said step S4 is implemented by calculating cross probability p according to formula (1)c；
Figure FDA0002196400180000021
In the formula: p is a radical ofcTo cross probability, pc_maxTo maximum cross probability, pc_minIs the minimum cross probability, itmax is the maximum algebra, iter is the current algebra, favgIs a value of the population-average fitness value,f' is the larger fitness value in the two individuals to be crossed.
5. The method for designing road gradient-containing automobile operating condition based on adaptive Markov chain evolution as claimed in claim 4, wherein p isc_max，pc_minAnd itmax are 0.7,0.1 and 400, respectively.
6. The method for designing the running condition of the automobile with the road gradient based on the adaptive Markov chain evolution as claimed in claim 4, wherein the generation process of the variant in the step S4 is as follows:
two working condition sequence chains X matched randomly(1)And X(2)
Figure FDA0002196400180000022
Figure FDA0002196400180000023
Wherein i, j belongs to [1, 2.,. L ], and x is a working condition state gene code;
when the constraint (2) is satisfied, the variant individual X is generated by exchanging the gene fragment lc1And Xc2
Figure FDA0002196400180000024
Figure FDA0002196400180000025
Figure FDA0002196400180000031
In the formula IbVariables are demarcated for operator functions.
7. The adaptive mahalanobis chain based evolution of claim 6The method for designing the running condition of the automobile with the road gradient is characterized in thatbIs Lx0.05.
8. The method for designing the operating condition of the automobile with the road gradient based on the adaptive Markov chain evolution as claimed in claim 4, wherein the generation process of the crossed individuals in the step S4 is as follows:
setting a Selective Cross Category probability pcmGenerating a pseudo-random number r1 when r1 > pcmThen, step 6.1 is executed, and the situation-crossing operation is carried out on the individuals to generate crossed individuals; otherwise, executing step 6.2, and performing situation two-way crossing operation on the individuals to generate crossed individuals;
step 6.1: when r1 > pcmTwo working condition sequence chains X matched randomly(1)And X(2)When constraint (3) is satisfied, crossover individuals X are generated by exchanging gene segments lc1And Xc2
Figure FDA0002196400180000041
Step 6.2: when r1 is not more than pcmTwo working condition sequence chains X matched randomly(1)And X(2)By the condition (4), the crossover individual X is generatedc1And Xc2，
Figure FDA0002196400180000042
In the formula: pop is the population of the current iteration number.
9. The method for designing road gradient-containing automobile operating condition based on adaptive Markov chain evolution as claimed in claim 8, wherein p iscmIs 0.1.
CN201910849428.6A 2019-09-09 2019-09-09 Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution Active CN110807290B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910849428.6A CN110807290B (en) 2019-09-09 2019-09-09 Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910849428.6A CN110807290B (en) 2019-09-09 2019-09-09 Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution

Publications (2)

Publication Number Publication Date
CN110807290A true CN110807290A (en) 2020-02-18
CN110807290B CN110807290B (en) 2020-08-28

Family

ID=69487442

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910849428.6A Active CN110807290B (en) 2019-09-09 2019-09-09 Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution

Country Status (1)

Country Link
CN (1) CN110807290B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102044011A (en) * 2009-10-20 2011-05-04 北京交通大学 Method and system for scheduling police force resource
CN103246943A (en) * 2013-05-31 2013-08-14 吉林大学 Vehicle operating condition multi-scale predicting method based on Markov chain
US8612107B2 (en) * 2008-06-10 2013-12-17 The Regents Of The University Of Michigan Method, control apparatus and powertrain system controller for real-time, self-learning control based on individual operating style
CN105043786A (en) * 2015-07-13 2015-11-11 吉林大学 Road grade-containing vehicle driving cycle Markov chain design method
US20170048266A1 (en) * 2015-08-13 2017-02-16 Accenture Global Services Limited Computer asset vulnerabilities
CN106934459A (en) * 2017-02-03 2017-07-07 西北工业大学 A kind of self-adapted genetic algorithm based on Evolution of Population process
CN107122573A (en) * 2017-06-26 2017-09-01 吉林大学 The vehicle operational mode design method evolved based on Markov Chain
CN107908853A (en) * 2017-11-10 2018-04-13 吉林大学 Vehicle operational mode design method based on prior information and big data
CN108897928A (en) * 2018-06-13 2018-11-27 吉林大学 A kind of intelligent vehicle slope road energy conservation speed optimization method based on the search of nested Monte Carlo tree

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8612107B2 (en) * 2008-06-10 2013-12-17 The Regents Of The University Of Michigan Method, control apparatus and powertrain system controller for real-time, self-learning control based on individual operating style
CN102044011A (en) * 2009-10-20 2011-05-04 北京交通大学 Method and system for scheduling police force resource
CN103246943A (en) * 2013-05-31 2013-08-14 吉林大学 Vehicle operating condition multi-scale predicting method based on Markov chain
CN105043786A (en) * 2015-07-13 2015-11-11 吉林大学 Road grade-containing vehicle driving cycle Markov chain design method
US20170048266A1 (en) * 2015-08-13 2017-02-16 Accenture Global Services Limited Computer asset vulnerabilities
CN106934459A (en) * 2017-02-03 2017-07-07 西北工业大学 A kind of self-adapted genetic algorithm based on Evolution of Population process
CN107122573A (en) * 2017-06-26 2017-09-01 吉林大学 The vehicle operational mode design method evolved based on Markov Chain
CN107908853A (en) * 2017-11-10 2018-04-13 吉林大学 Vehicle operational mode design method based on prior information and big data
CN108897928A (en) * 2018-06-13 2018-11-27 吉林大学 A kind of intelligent vehicle slope road energy conservation speed optimization method based on the search of nested Monte Carlo tree

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
MAN ZHANG 等: "High-Efficiency Driving Cycle Generation Using a Markov Chain Evolution Algorithm", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 *
商攀: "动态客流下的城市轨道交通时刻表优化研究", 《中国优秀硕士学位论文全文数据库-工程科技Ⅱ辑》 *
张曼 等: "面向汽车运行工况设计的马氏链非等长交叉进化算法", 《浙江大学学报(工学版)》 *
张曼: "面向浮动车低频数据运行工况设计的经验马尔可夫链进化方法研究", 《中国博士学位论文全文数据库-工程科技Ⅱ辑》 *
沈斌 等: "基于自适应遗传算法的流水车间作业调度", 《计算机工程》 *

Also Published As

Publication number Publication date
CN110807290B (en) 2020-08-28

Similar Documents

Publication Publication Date Title
Wu et al. Multiobjective optimization of HEV fuel economy and emissions using the self-adaptive differential evolution algorithm
CN110149258A (en) A kind of automobile CAN-bus network data method for detecting abnormality based on isolated forest
CN108595853B (en) Parallel hybrid electric vehicle parameter optimization design method based on genetic algorithm
CN106447024A (en) Particle swarm improved algorithm based on chaotic backward learning
CN114495499B (en) Multi-target intelligent internet vehicle cooperative optimization control method
CN101907869B (en) Method for controlling a vehicle
CN109787696B (en) Cognitive radio resource allocation method based on case reasoning and cooperative Q learning
CN107766980A (en) Electric automobile time-sharing charging electricity price optimization method based on user behavior custom
CN107122573B (en) Automobile operation condition design method based on Markov chain evolution
CN111680413B (en) Tramcar timing energy-saving operation optimization method and system based on double-layer algorithm
CN112861362A (en) Power assembly performance parameter optimization method and device based on vehicle oil consumption
CN110807290B (en) Road gradient-containing automobile operation condition design method based on self-adaptive Markov chain evolution
CN113276829B (en) Vehicle running energy-saving optimization weight-changing method based on working condition prediction
CN108615069A (en) A kind of optimized calculation method based on improved adaptable quanta particle swarm optimization
CN113479187B (en) Layered different-step-length energy management method for plug-in hybrid electric vehicle
CN108896330B (en) Fault diagnosis method for hydroelectric generating sets
CN106696952A (en) Energy control method for intelligent network connection hybrid electric vehicle
Zhang et al. Self-adaptive hyper-heuristic Markov chain evolution for generating vehicle multi-parameter driving cycles
CN103209417A (en) Method and device for predicting spectrum occupancy state based on neural network
CN110641470B (en) Pure electric vehicle driving auxiliary system optimization method integrating driver preference
CN110505293A (en) Cooperation caching method based on improved drosophila optimization algorithm in a kind of mist wireless access network
CN113997925B (en) Energy management method for plug-in hybrid power system
CN112373458B (en) Hybrid electric vehicle energy management method based on self-adaptive fuzzy control
CN113537620A (en) Vehicle speed prediction method based on Markov model optimization and working condition recognition
CN104680232A (en) RVM (Relevance Vector Machine)-based engine failure detecting method

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