| Summary: | The automatic driving system serves as the central component for efficiently managing the operation of urban rail trains, enabling train control through algorithmic means. Evolutionary algorithms are commonly employed to optimize control strategies for autonomous driving systems. This paper presents a segmented multi-objective optimization model for the train operation phase and employs a non-dominated sorting genetic algorithm with an elite retention strategy to solve the model. This approach achieves global optimization with respect to the smoothness, accuracy, punctuality, and energy efficiency of urban rail trains. The simulation results demonstrate that traction and braking operations can be optimized for stability and energy conservation, while intermediate operations can be optimized for precision, punctuality, and energy efficiency. This optimization strategy enhances the multi-objective optimization performance of the automatic driving system, accommodating the intricacies of the rail line, and offering valuable insights for enhancing the automatic driving system of urban rail trains. © Beijing Paike Culture Commu. Co., Ltd. 2024.
|
|---|