一种车辆路径规划的改进混合算法

摘要

Aiming to the requirements to find the shortest path among distribution nodes in logistics activities to guide logis-tics vehicle scheduling, this paper provides a new method which combines genetic algorithm and BP algorithm for vehicle path planning to achieve the goal of saving transporting cost. In this paper, the genetic algorithm is improved, and the shortcomings of the genetic algorithm, such as poor local search capability, easy to be early-maturing and not good enough global feasible solution, are covered. This hybrid algorithm covers the shortage of genetic algorithm efficiently, and adopts the optimal preservation strategy in the genetic optimize operation and tournament selection method in the selec-tion operation, which improves the efficiency and function of the algorithm highly. Through the simulation to the perfor-mance of this improved hybrid algorithm of vehicle path planning based on genetic algorithm, and compared with adap-tive genetic algorithm and immune genetic algorithm, and analyzing the results, the advantages and effectiveness of the hybrid algorithm are proved.%针对物流活动中需要找出各个配货节点之间的最短路径，用以指导物流车辆调度的问题，提出一种将遗传算法与BP神经网络相结合的新方法，规划车辆的路径，达到节约运送成本的目标。对遗传算法进行了改进，克服了遗传算法局部搜索能力差、易早熟和总体可行解质量不高的缺点。该混合算法有效弥补了遗传算法的不足，同时在遗传优化操作中引入最优保存策略，并在选择操作中采用锦标赛选择法，使算法的效率和功能得到了很大提高。通过对基于遗传算法的改进混合算法求解车辆路径优化问题的性能进行仿真，并与自适应遗传算法和免疫遗传算法进行对比分析，验证了改进混合算法的优点和有效性。