Research on energy-saving operation optimization of urban rail trains based on genetic particle swarm hybrid algorithm

Abstract

In order to effectively reduce the energy consumption of urban rail trains during station-to-station operation, an energy-saving optimisation method for train operating curves is proposed by introducing a genetic algorithm (GA) into a particle swarm algorithm (PSO).Firstly, under the premise of considering the train characteristic parameters and the speed limit conditions of the line, the energy consumption model is established with the constraints such as speed limit, running time and running distance; secondly, the particle swarm algorithm is improved by using inertia weights and learning factor, and the cross-variance operator of genetic algorithm is introduced to verify that the improved algorithm improves convergence speed, global optimization ability and local search ability. The speed-distance operation curve that uses the least amount of energy between stations is then derived by solving the energy-saving operation energy consumption model of the train using the GAPSO algorithm. According to the simulation results, the approach can successfully cut operational energy consumption by 11.46% while still ensuring punctual arrival and exact stopping, which offers a workable solution for the best-case scenario design of energy-saving train operation curves.