Multi-objective route optimization for electric vehicle hazardous materials transportation in uncertain environments

This paper focuses on the application of electric vehicles in the transportation of Category 9 hazardous materials. Given the high requirements for safety and timeliness in hazardous materials transportation, this study first comprehensively considers the impacts of population density uncertainty and cargo volume changes on transportation risks and power consumption. Furthermore, a multi-objective path optimization model is developed. The model aims to minimize transportation risks, reduce costs, and maximize customer satisfaction. It includes constraints on accident probability, cargo volume, and time windows. To solve this model, an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II), named H-NSGA-II, is designed. It is based on the fusion characteristics of the greedy algorithm and the traditional NSGA-II algorithm. Through case validation, it is found that the algorithm can efficiently obtain high-quality Pareto solutions. Compared with the original NSGA-II algorithm, the optimal transportation risk, transportation cost, and average customer satisfaction are improved by 14.40%, 12.81%, and 13.53%, respectively. The research results can provide decision-making support for the safe, economical, and green distribution of urban Category 9 hazardous materials.