The Process Optimization of Train Operation Based on Multi-objective Memetic Algorithm using Incorporated Preference Information

详细信息    查看官网全文

• 英文论文题名：The Process Optimization of Train Operation Based on Multi-objective Memetic Algorithm using Incorporated Preference Information
• 论文作者：Longda Wang ; Xingcheng Wang ; Dawei Sun ; Weixuan Wang
• 英文论文作者：Longda Wang ; Xingcheng Wang ; Dawei Sun ; Weixuan Wang ; School of Information Science and Technology ; Dalian Maritime University
• 年：2017
• 作者机构：School of Information Science and Technology,Dalian Maritime University;
• 英文论文关键词：train operation process ; multi-objective optimization ; preference information ; fuzzy logic
• 会议召开时间：2017-07-26
• 会议录名称：第36届中国控制会议论文集（B）
• 英文会议录名称：Proceedings of the 36th Chinese Control Conference（B）
• 语种：英文
• 分类号：TP18;U268
• 学会代码：KZLL
• 会议名称：第36届中国控制会议
• 会议地点：中国辽宁大连
• 主办单位：中国自动化学会控制理论专业委员会
• 学会名称：中国自动化学会控制理论专业委员会
• 页数：6
• 文件大小：634k
• 原文格式：D
• 会议级别：全国

摘要

The process optimization of train operation is a sophisticated multi-objective optimization problem. Due to the fact that the multi-objective optimization model of train operation process is difficult to be solved precisely, the process optimization of train operation based on multi-objective memetic algorithm using incorporated preference information and fuzzy logic is proposed in this paper. In order to significantly drive the solution to move to the desired region, a global search algorithm is adopted by genetic particle swarm optimization algorithm using incorporated preference information. Correspondingly, the population diversity can be better maintained, and the global convergence can be improved by using the global search algorithm. To obtain accurately a better solution in the neighborhood of the solution, a local search algorithm is improved by using a simulated annealing algorithm based on the fuzzy logic of driving experience. The advantages of the proposed method are summarized as follows: Firstly, a better convergence effect can be obtained by the global search algorithm. Secondly, by combining the indication algorithm and the heuristic algorithm, the local optimization effect can be improved. Finally, simulation results are provided to show the efficacy of the proposed method.
The process optimization of train operation is a sophisticated multi-objective optimization problem. Due to the fact that the multi-objective optimization model of train operation process is difficult to be solved precisely, the process optimization of train operation based on multi-objective memetic algorithm using incorporated preference information and fuzzy logic is proposed in this paper. In order to significantly drive the solution to move to the desired region, a global search algorithm is adopted by genetic particle swarm optimization algorithm using incorporated preference information. Correspondingly, the population diversity can be better maintained, and the global convergence can be improved by using the global search algorithm. To obtain accurately a better solution in the neighborhood of the solution, a local search algorithm is improved by using a simulated annealing algorithm based on the fuzzy logic of driving experience. The advantages of the proposed method are summarized as follows: Firstly, a better convergence effect can be obtained by the global search algorithm. Secondly, by combining the indication algorithm and the heuristic algorithm, the local optimization effect can be improved. Finally, simulation results are provided to show the efficacy of the proposed method.

引文

[1]YüJin,Qian Qingquan,He Zhengyou.Genetic algorithms with application to optimize high speed train ATO[C].Proceedings of the First International Conference,2007.
    [2]Yang X,Li X,Ning B,et al.A Survey on Energy-Efficient Train Operation for Urban Rail Transit[J].IEEE Transactions on Intelligent Transportation Systems,2015,17(1):1-12.
    [3]Chen D,Ni S,Xu C,et al.A Soft Rough-Fuzzy Preference Set-Based Evaluation Method for High-Speed Train Operation Diagrams[J].Mathematical Problems in Engineering,2016,2016(4):1-8.
    [4]Lin J Y,Chen Y P.Analysis on the Collaboration Between Global Search and Local Search in Memetic Computation[J].Evolutionary Computation IEEE Transactions on,2011,15(5):608-623.
    [5]Bai Y,Ho T K,Mao B,et al.Energy-Efficient Locomotive Operation for Chinese Mainline Railways by Fuzzy Predictive Control[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(3):938-948.
    [6]Gu Q,Tang T,Cao F,et al.Energy-Efficient Train Operation in Urban Rail Transit Using Real-Time Traffic Information[J].Intelligent Transportation Systems IEEE Transactions on,2014,15(3):1216-1233.
    [7]Gu Q,Tang T,Ma F.Energy-Efficient Train Tracking Operation Based on Multiple Optimization Models[J].IEEE Transactions on Intelligent Transportation Systems,2015,17(3):1-11.
    [8]Huang Y,Yang L,Tang T,et al.Saving Energy and Improving Service Quality:Bicriteria Train Scheduling in Urban Rail Transit Systems[J].IEEE Transactions on Intelligent Transportation Systems,2016,17:1-16.
    [9]Rong H,Yu C Z.Multiple Objective of Train Operation Process Based on Modified Particle Swarm Optimization[J].Applied Mechanics&Materials,2014,513-517:2927-2930.
    [10]Dong H Y,Liu Y,Yang L X.Study on multi-objective optimization of high-speed train operation based on clonal selection algorithm[C]//Intelligent Control and Automation.IEEE,2015:2703-2709.
    [11]Huang Y,Ma X,Su S,et al.Optimization of Train Operation in Multiple Interstations with Multi-Population Genetic Algorithm[J].Energies,2015,8(12):14311-14329.
    [12]Hu H,Fu Y P,Hu C.PSO-based optimal operation strategy of energy saving control for train[C].IEEE,International Conference on Industrial Engineering and Engineering Management.IEEE,2010:1560-1563.
    [13]Qiang J W,Yu C G,Deng Y D,et al.Multi-Objective Optimization Design for Cooling Unit of Automotive Exhaust-Based Thermoelectric Generators[J].Journal of Electronic Materials,2016,45(3):1679-1688.