Research on Train Energy Saving Optimization Problem Based on Multi-Objective Genetic Algorithm

With the gradual development of urban rail transit, the passenger flow of public transportation facilities increases, resulting in the rapid growth of energy consumption, which brings a significant burden to the sustainable development of the city. This paper explores the marching strategy to reduce the energy consumption of train operation through the study of a single train running between two stations, so as to further explore the potential of energy-saving and carbon-reducing of the train. A single-train multi-objective energy-saving optimization model is established, and a multi-objective genetic algorithm is used to solve for the lowest energy consumption and shortest running time of the train under the consideration of complex road conditions and the influence of complex dynamic processes of the motor. The BP neural network optimized by Gray Wolf algorithm is used to verify the solutions, and the minimum energy consumption is 2.0166e+12J and the shortest running time is 211.6529s.