基于自适应变异粒子群算法的铁路空车调配

Railway empty car allocation based on adaptive mutation particle swarm algorithm

提出一种用于求解铁路空车调配的自适应变异粒子群算法.该算法在迭代过程中加入了变异操作,根据群体适应度方差调整变异概率的大小,并通过调整惯性权重因子来增强算法跳出局部最优的能力.将自适应变异粒子群算法用于铁路空车调配,建立以空车总走行距离最小为目标的数学模型,并在此基础上设计相应的算法.算例结果表明,应用自适应变异粒子群算法的最优结果和寻优效率要优于蚁群算法和标准粒子群算法.

An adaptive mutation particle swarm algorithm was proposed for railway empty car allocation.The algorithm added mutation operation into its iteration process and adjusted the inertia weighting factor to enhance its ability to eliminate local optimum,and the mutation probability was adjusted by using the variance of the population fitness.The algorithm of adaptive mutation particle swarm algorithm was used to solve railway empty car allocation problem,the mathematic model which minimized the total traveling distance of the empty car was established and its corresponding procedure of solution was designed on this basis.It was shown by numerical simulation demonstrated that the optimum result and searching performance of adaptive mutation particle swarm optimization were superior to that of ACO and PSO.