Energy-efficient operation trajectory optimization of heavy-haul trains based on hybrid biological intelligent heuristic strategy

The operation trajectory optimization of heavy-haul trains has potential to diminish transportation energy consumption. This can lead to significant economic benefits. However, in the domain of heavy-haul train trajectory optimization, existing swarm intelligence algorithms are prone to falling into local optima. To address this issue, a novel heavy-haul train trajectory optimization method based on hybrid biological intelligent heuristic strategy is proposed. The method expands the trajectory search space of heavy-haul trains and further reduces transportation energy consumption. This is achieved by utilizing sparrow colony predation behavior and ant colony probabilistic path construction. Through the implementation of iteration reset, the optimization process for the trajectory of heavy-haul trains mitigates the risk of being trapped in local optima. The proposed method is compared with mainstream swarm intelligence algorithms. Simulation experiments are conducted under normal operating condition, section speed restrictions, and temporary speed restrictions. The results of the comparative experiments indicate that the proposed method generates an optimal trajectory. The energy consumption of this trajectory is lower compared to other methods. This approach offers a more effective improvement in the freight efficiency of heavy-haul trains and provides a valuable contribution to intelligent scheduling in railway operations. • A hybrid biological intelligent heuristic algorithm is proposed, utilizing sparrow predation behavior and ant colony probabilistic path construction to further mitigate the issue of swarm intelligence algorithms falling into local optima. • A hybrid biological intelligent heuristic is proposed for energy-efficient trajectory optimization of heavy-haul trains, integrating strategies from two colonies with inter-colony information exchange to generate low-energy trajectories that satisfy operational constraints. • The energy-saving effect of the proposed method is experimentally validated, and results demonstrate that its optimal trajectory achieves the lowest energy consumption compared with mainstream swarm intelligence methods.