基于小生境粒子群算法的ATO运行过程优化研究  

Optimization research on ATO operation process based on niche particle swarm algorithm

作　　者：朱爱红[1] 卢稳[1] 宋丽梅[1] ZHU Aihong;LU Wen;SONG Limei(School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China)

机构地区：[1]兰州交通大学自动化与电气工程学院,兰州730070

出　　处：《铁道科学与工程学报》2017年第9期1998-2004,共7页Journal of Railway Science and Engineering

摘　　要：针对自动驾驶(ATO)列车的低能耗、高准时和高舒适度问题,以列车运行过程中的安全性及其列车动力学模型为约束条件,建立列车运行过程的多目标优化模型,提出粒子群算法与小生境技术相结合的求解算法。该求解算法首先计算随机生成的粒子间欧式距离的平均值,确定小生境半径,划分小生境种群;采用共享机制对更新后的小生境群体进行调节,提高粒子的适应度值;最后通过迭代求出最优解。通过对选取线路的仿真模拟,验证该算法在降低ATO列车的运行能耗、提高列车运行过程的准时性与舒适性方面的有效性。Aiming at the train effective driving problem that equipped with the automatic train operation(ATO)system which needs to realize low energy consumption,high punctuality and high comfort in the operationprocess of the train.A multi-objective optimization model was built based on the safety operation and the vehicledynamic model of the train.The method,including niche technology and particle swarm optimization algorithm,was put forward to solve the optimization problem.This method calculates the average value of the Euclideandistance of the particles which was randomly generated firstly,and determines the niche radius and divides nichepopulations.Then a sharing mechanism was used to regulate the niche populations,which in order to increase thefitness value of the particles.Finally,we can receive the optimal solution by iteration.Through simulation of theselected line,that the algorithm in reducing energy consumption of ATO trains,improving train punctuality duringoperation and comfort as a very good effectiveness.

关 键 词：列车自动驾驶 运行过程 多目标优化 小生境 粒子群算法 

分 类 号：U268.6[机械工程—车辆工程]