时变风险下的危险品运输车辆路径优化

Optimization of vehicle routing for hazardous material transportation in time-varying risk environments

针对危险品道路运输车辆路径问题,以运输总风险、运输总成本及车辆运输时间三者最小为优化目标,考虑道路车流速度随时间变化,构建时变风险下的危险品道路运输车辆路径优化模型,并设计了改进强度Pareto进化算法求解模型。该算法引入反向学习策略加强搜索能力,多组仿真试验算例计算表明,改进后的算法比原算法收敛性更好、求解精度更高。在考虑风险时变条件下,运输风险大致随交通量增大而增大,随车辆装载量降低而减小。相比于不考虑时变风险,时变风险模式下的车辆路径优化结果受道路交通状况影响显著,更贴近实际。根据所提出的时变风险下车辆路径优化模型,运输企业可考虑用户的需求量和道路交通状况进行路径规划,从而在保障运输安全的同时缩短车辆行驶里程和减少运输费用。

Addressing routing for vehicles transporting hazardous materials on roads,this study considers variations in traffic flow speed and road population distribution to establish a dynamic model for road transportation risk.The model incorporates time-varying factors such as population exposure and load capacity.By fitting actual road traffic data,this study aims to minimize total transportation risk,costs,and vehicle travel time for optimizing hazardous materials transportation routes.The model integrates various vehicle conditions and time window constraints to achieve an optimized vehicle routing solution under dynamic risk conditions.To determine the optimal route for hazardous materials transportation under time-varying risks,we employed an enhanced Strength Pareto Evolutionary Algorithm(SPEA2)to solve the model.Additionally,we implemented a reverse learning strategy to enhance search capability and improve the algorithm's solution accuracy and convergence performance.We designed multiple test cases based on various risk patterns and departure time periods,conducting numerous simulation experiments to compare the algorithm's performance before and after these enhancements.The results indicate that the total transportation risk varies over time under different risk modes.Specifically,transportation risk in time-varying modes fluctuates due to changes in traffic flow,whereas non-time-varying modes tend to remain constant.The consideration of time-varying risks in hazardous materials transportation holds greater practical significance compared to non-time-varying risks.The load capacity of transportation vehicles decreases gradually over time,with changes in road risk primarily influenced by traffic volume and load capacity.Initially,the total risk increases and then stabilizes.The enhanced algorithm demonstrates enhanced solution capabilities,generating a greater number of Pareto solutions with broader coverage and reduced running time.Therefore,its overall performance surpasses that of the original algorithm.Enterprises should consider road traffic conditions,plan transportation routes sensibly,and ensure transportation safety while reducing vehicle mileage and transportation costs.