融入偏好信息的列车运行过程多目标优化算法

列车运行过程优化是一个多目标、大滞后、非线性的极其复杂的优化问题.为了更好地解决上述问题,以列车能耗、舒适性、停靠准确性和运行时间为控制目标,以列车运动动力学方程为约束,建立了列车运行过程的多目标优化模型,提出了一种融入偏好信息的列车运行过程多目标遗传粒子群算法.提出的改进策略具有以下优点,在融入偏好信息的基础上通过控制粒子群中个体在解空间的分布能够更好地保持粒子群多样性,从而在进化过程中具有更明显的全局收敛的指向作用.仿真得到的速度距离曲线表明,在列车及其运行线路相同的情况下,本文所提出的算法性能较佳、寻优结果较好.

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

The optimization of train operation process is a sophisticated problem which is multiple objectives, large delay and nonlinearity. In order to solve the problem, the multi- objective optimization model of train operation process is established, which regards train kinetic equation as constraint, and energy consumption, comfort, precise parking and punctuality as control targets, the optimization of train operation process based on multi-objective genetic particle swarm optimization using incorporated preference information is proposed. The advantage of the proposed method is summarized as follows: the proposed strategy with incorporated preference information can better maintain the diversity of the population by controlling the distribution of individuals of the population in the solution space. Thus, there is a more obvious role of global convergence in the evolution process. The proposed algorithm has better performance and better search results in the same situation of train and line.