CIPSO算法在城市有轨电车控制策略中的应用研究
|
摘要
在保证电车安全的前提下,轨道交通中的城市有轨电车控制策略优化问题实质上是多目标优化问题,主要是针对节能、正点、停靠准确和乘客舒适度优化等方面的复杂问题,以电车运动学方程为基础,针对粒子群优化算法在离散优化问题中处理不佳,容易陷入局部最优的问题,采用混沌Tent映射初始化粒子群,建立其多目标优化模型。而后采用免疫接种和免疫选择的方法提高PSO优化算法的优化能力,对模型进行求解。以广州市海珠区环岛新型有轨电车试验段数据为对象进行实例仿真,结果表明,混沌免疫微粒群优化算法较传统微粒群优化算法可获得更好的控制策略,能更有效的解决电车运行多目标优化问题。
Under the premise that the safety of train is guaranteed,the optimization of city tram control strategy is actually a multi-objective optimization issue,and it is mainly aimed at the complex problems about energy saving,punctuality,stopping accuracy and the improvement on passenger comfort and etc.Particle swarm optimization algorithm does not perform well in discrete optimization,because it is likely to result in local optimum. Therefore,chaos Tent mapping is adopted to initialize particle swarm and to establish its multi-objective optimization model on the basis of the train kinematic equation. Then immune vaccination and immune selection are used to improve the optimization ability of PSO optimization algorithm and to solve the model. Simulation is conducted on the data from the test section of the new city tram around Haizhu district of Guangzhou. The results show that the chaotic immune particle swarm optimization algorithm can obtain better control strategy than the traditional particle swarm optimization algorithm,and it is more effective in solving the multi target optimization problem in train operation.
Under the premise that the safety of train is guaranteed,the optimization of city tram control strategy is actually a multi-objective optimization issue,and it is mainly aimed at the complex problems about energy saving,punctuality,stopping accuracy and the improvement on passenger comfort and etc.Particle swarm optimization algorithm does not perform well in discrete optimization,because it is likely to result in local optimum. Therefore,chaos Tent mapping is adopted to initialize particle swarm and to establish its multi-objective optimization model on the basis of the train kinematic equation. Then immune vaccination and immune selection are used to improve the optimization ability of PSO optimization algorithm and to solve the model. Simulation is conducted on the data from the test section of the new city tram around Haizhu district of Guangzhou. The results show that the chaotic immune particle swarm optimization algorithm can obtain better control strategy than the traditional particle swarm optimization algorithm,and it is more effective in solving the multi target optimization problem in train operation.
引文
[1] Yu Jin,Qian quan,He Zhengyou. Genetic Algorithms with Application to Optimize High Speed Train ATO[C]∥Proceedings of the First International Conference on Transportation Engineering. Chengdu,China:American Society of Civil Engineers,2007:2512-2517.
[2]余进,何正友,钱清泉.基于混合微粒群优化的多目标列车控制研究[J].铁道学报,2010,32(1):38-42.
[3]沙泉,仓小娣.基于速度变异粒子群算法的电车运行策略优化[J].微电子学与计算机,2014,31(3):130-133.
[4]李忠继,林红松,颜华,等.空轨电车系统横向运行稳定性研究[J].铁道科学与工程学报,2016,13(3):564-569.
[5]王龙生,徐洪泽,张梦楠,等.基于混合系统模型预测控制的电车自动驾驶策略[J].铁道学报,2015,37(12):53-60.
[6]李诚,王小敏.基于粒子群优化的多ATO控制策略[J].铁道学报,2017,39(3):53-58.
[7] PHIL Howlett. The Optimal Control of a Train. Annals of Operations Research 98[M]. Netherlands:Kluwer Aca-demic Publishers,2000.
[8]朱晓敏,徐振华.基于单质点模型的城市轨道交通电车动力学仿真[J].铁道学报,2011,33(6):16-19.
[9] Yan X,Cai B,Ning B,et al. Moving Horizon Optimization of Dynamic Trajectory Planning for High-speed Train Operation[J]. IEEE Transactions on Intelligent Transportation Systems, 2016,17(5):1258-1270.
[10]严细辉,蔡伯根,宁滨,等.基于差分进化的高速电车运行操纵的多目标优化研究[J].铁道学报,2013,35(9):65-71.
[11] Yan X,Cai B,Ning B,et al. Online Distributed Cooperative Model Predictive Control of Energy-Saving Trajectory Planning for Multiple High-speed Train Movements[J]. Transportation Research Part C:Emerging Technologies,2016,69:60-78.
[12]唐海川,朱金陵,王青元,等.一种可在线调整的电车正点运行节能操纵控制算法[J].中国铁道科学,2013,34(4):89-93.
[13]庄河,何世伟,戴杨铖.高速铁路电车运调整的模型及其策略优化方法[J].中国铁道科学,2017,38(2):118-126.
[14]孙飞,桂行东,李婷,等.基于Pareto多目标遗传算法的高峰时段多地铁电车节能优化[J].铁道标准设计,2017,61(12):114-119.
[15]陈志杰,毛保华,柏!,等.城市轨道交通追踪电车定时节能操纵优化[J].铁道学报,2017,39(8):10-17.
[16]饶忠.电车牵引计算[M]. 2版.北京:中国铁道出版社,2002.
[17]刘朝华,张英杰,章兢,等.基于免疫双态微粒群的混沌系统自抗扰控制[J].物理学报,2011,60(1):791-799.
[18]和贵,陆小军,张祥德,等.基于二维Logistic映射和二次剩余的图像加密算法[J].东北大学学报(自然科学版),2014,35(1):20-23.
[19]郑晓明,吕士颖,王晓东.免疫接种粒子群的聚类算法[J].电子科技大学学报,2007,36(6):1264-1267.
[20]杜振鑫,王兆青.一种个性化变异的免疫粒子群算法[J].计算机工程及应用,2011,47(27):44-48.
[2]余进,何正友,钱清泉.基于混合微粒群优化的多目标列车控制研究[J].铁道学报,2010,32(1):38-42.
[3]沙泉,仓小娣.基于速度变异粒子群算法的电车运行策略优化[J].微电子学与计算机,2014,31(3):130-133.
[4]李忠继,林红松,颜华,等.空轨电车系统横向运行稳定性研究[J].铁道科学与工程学报,2016,13(3):564-569.
[5]王龙生,徐洪泽,张梦楠,等.基于混合系统模型预测控制的电车自动驾驶策略[J].铁道学报,2015,37(12):53-60.
[6]李诚,王小敏.基于粒子群优化的多ATO控制策略[J].铁道学报,2017,39(3):53-58.
[7] PHIL Howlett. The Optimal Control of a Train. Annals of Operations Research 98[M]. Netherlands:Kluwer Aca-demic Publishers,2000.
[8]朱晓敏,徐振华.基于单质点模型的城市轨道交通电车动力学仿真[J].铁道学报,2011,33(6):16-19.
[9] Yan X,Cai B,Ning B,et al. Moving Horizon Optimization of Dynamic Trajectory Planning for High-speed Train Operation[J]. IEEE Transactions on Intelligent Transportation Systems, 2016,17(5):1258-1270.
[10]严细辉,蔡伯根,宁滨,等.基于差分进化的高速电车运行操纵的多目标优化研究[J].铁道学报,2013,35(9):65-71.
[11] Yan X,Cai B,Ning B,et al. Online Distributed Cooperative Model Predictive Control of Energy-Saving Trajectory Planning for Multiple High-speed Train Movements[J]. Transportation Research Part C:Emerging Technologies,2016,69:60-78.
[12]唐海川,朱金陵,王青元,等.一种可在线调整的电车正点运行节能操纵控制算法[J].中国铁道科学,2013,34(4):89-93.
[13]庄河,何世伟,戴杨铖.高速铁路电车运调整的模型及其策略优化方法[J].中国铁道科学,2017,38(2):118-126.
[14]孙飞,桂行东,李婷,等.基于Pareto多目标遗传算法的高峰时段多地铁电车节能优化[J].铁道标准设计,2017,61(12):114-119.
[15]陈志杰,毛保华,柏!,等.城市轨道交通追踪电车定时节能操纵优化[J].铁道学报,2017,39(8):10-17.
[16]饶忠.电车牵引计算[M]. 2版.北京:中国铁道出版社,2002.
[17]刘朝华,张英杰,章兢,等.基于免疫双态微粒群的混沌系统自抗扰控制[J].物理学报,2011,60(1):791-799.
[18]和贵,陆小军,张祥德,等.基于二维Logistic映射和二次剩余的图像加密算法[J].东北大学学报(自然科学版),2014,35(1):20-23.
[19]郑晓明,吕士颖,王晓东.免疫接种粒子群的聚类算法[J].电子科技大学学报,2007,36(6):1264-1267.
[20]杜振鑫,王兆青.一种个性化变异的免疫粒子群算法[J].计算机工程及应用,2011,47(27):44-48.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |