计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (24): 212-220.DOI: 10.3778/j.issn.1002-8331.1808-0241

• 工程与应用 • 上一篇    下一篇

R-dPSO算法及其在ATO控制策略中的应用

胡  震,邹德旋,张  旭   

  1. 江苏师范大学 电气工程及自动化学院,江苏 徐州 221116
  • 出版日期:2018-12-15 发布日期:2018-12-14

R-dPSO algorithm and its application in ATO control strategy

HU Zhen, ZOU Dexuan, ZHANG Xu   

  1. School of Electrical Engineering and Automation, Jiangsu Normal University, Xuzhou, Jiangsu 221116, China
  • Online:2018-12-15 Published:2018-12-14

摘要: 城市轨道交通列车自动运行中,通过调整列车的5种工况序列解决含有安全、准点、准时、舒适度和能耗等指标的多目标优化问题。根据轨道交通列车自动运行过程中涉及的动力学公式建立ATO目标速度曲线的数学模型。提出一种随机驱动的全局粒子群优化算法(R-dPSO),用12个基准函数测试了R-dPSO算法的有效性。进而,利用SPSO算法、XEPSO算法和R-dPSO算法解决上述多目标优化问题。实验表明,只有R-dPSO算法的优化结果满足ATO控制策略的各个指标要求。

关键词: 工况序列, 速度曲线, 粒子群优化算法, 随机驱动

Abstract: In the automatic operation of urban rail transit trains, multi-objective optimization problems including safety, punctuality, punctuality, comfort and energy consumption are solved by adjusting the sequence of five working conditions of the train. The mathematical model of the ATO target speed curve is established according to the dynamic formula involved in the automatic operation of the rail transit train. A Randomness-driven global Particle Swarm Optimization algorithm(R-dPSO) is proposed. The effectiveness of the R-dPSO algorithm is tested with 12 benchmark functions. Furthermore, the SPSO algorithm, XEPSO algorithm and R-dPSO algorithm are used to solve the above multi-objective optimization problem. Experiments show that only the optimization results of the R-dPSO algorithm meet the requirements of the various indicators of the ATO control strategy.

Key words: working sequence, speed curve, particle swarm optimization, randomness-driven