Intelligent optimization method for hazardous materials transportation routing with multi-mode and multi-criterion collaborative constraints
Abstract Hazardous materials transportation route optimization problem is a pressing issue, and multi-dimensional evaluation criteria and diversified transportation modes complicate the problem. In response to this, a method for multi-mode transportation network and multi-criterion route optimizatio...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-92085-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Hazardous materials transportation route optimization problem is a pressing issue, and multi-dimensional evaluation criteria and diversified transportation modes complicate the problem. In response to this, a method for multi-mode transportation network and multi-criterion route optimization is proposed. Initially, A three-objective integer programming model is formulated, and an improved multi-objective genetic algorithm, termed DSNSGA3, is introduced to aid in decision-making. Specifically tailored to the problem’s specifics, a chromosome encoding technique grounded in priority is devised to eliminate infeasible solutions. Subsequently, leveraging non-dominated sorting and crowding distance algorithms to assess the merit of multi-objective solutions, a local search strategy is introduced. This strategy serves dual purposes: it accelerates the algorithm’s convergence rate and effectively minimizes the number of transshipments. Ultimately, an automatic weight-assigning decision-making method based on maximizing deviations is designed, culminating in a definitive decision-making plan. Numerical simulations reveal that the DSNSGA3, as designed in this paper, excels at identifying a diverse and widely distributed Pareto front. Compared to the traditional NSGA3, it demonstrates average improvements of 1.93% in solution accuracy, 1.32% in robustness, and a convergence advancement of 11.33 generations. The proposed decision-making method, based on Pareto solutions, adeptly balances various evaluation criteria, obtains a definitive solution, and provides a basis for multi-criteria intelligent decision-making in complex environments. |
|---|---|
| ISSN: | 2045-2322 |