基于混合微粒群优化的多目标列车控制研究

列车控制策略包括输入控制序列和每一控制序列作用距离两方面,本文建立列车运行过程多目标优化模型,以二进制和实数域的混合微粒群优化方法对该问题进行了研究,二进制微粒群算法优化列车输入控制序列,实数域微粒群算法对列车运行距离进行优化,以此得到列车最佳控制策略;针对实际的问题,提出了微粒群算法中pBest更新和gBest选择策略;并与传统的单个目标的列车运行过程优化模型进行了对比研究,仿真研究结果表明混合微粒群优化算法用于列车运行过程优化控制,可以获得满意的效果。

Study on Multi-objecive Train Control Based on Hybrid Particle Swarm Optimization

Train control involves input control sequences and the operating distance of each control sequence. The multi-objective model is established to optimize the train running process. The hybrid particle swarm optimization(HPSO) alrgorithm is employed, i.e., the binary particle swarm optimization(BPSO) algorithm is employed to optimize the input control sequences and the real particle swarm optimization(RPSO) algorithm is used to optimize train running distances. As a result, the optimal train control strategy is obtained. To deal with practical train control problems, the pBest updating strategies and gBest selection strategies of PSO are proposed . Stimulation results reveal that the HPSO algorithm can be used to achieve satisfactory optimized train running process control.