Modeling and Solving Methods for Eco-Driving of Freight Trains With Traction Chains Temperature Models

Traditional static mechanistic models are hard to accurately capture complex and time-varying dynamics of freight trains, and then the optimized eco-driving strategies might be impractical for real-world operations. To overcome this issue, this paper proposes a hybrid model that combines a “train-track-power grid” mechanistic model with a data-driven model to evaluate both the dynamics and energy consumption of multiple trains. Additionally, a thermal rise model for electrical equipment is developed, and a rapid solution method based on the Laplace transformation is designed to obtain temperature rise. Then, a multi-objective optimization model is formulated to optimize both the energy efficiency of the traction power supply system and the temperature of electrical equipment. To solve the large-scale multi-objective optimization problem encountered in long-distance multi-train operations, a large-scale adaptive multi-strategy multi-objective competitive swarm optimizer (LAMOCSO) is proposed. Experiment results validate the effectiveness of the proposed dynamic modeling approach. Comparisons with four classical algorithms demonstrate that the proposed method can reduce energy consumption by 18.2%, while ensuring that electrical equipment operates within an appropriate temperature range.