| In response to the issue that the optimization algorithm for the target speed curve of high-speed trains in ordinary environments is not suitable for crosswind environments,the paper proposes a rolling GAPSO(Genetic Particle Swarm Optimization)algorithm,which improves the dynamic model of the train by considering the effect of crosswind wind speed resistance.A rolling optimization framework is introduced to adjust the target speed curve in real-time,and the GAPSO algorithm optimizes the target speed curve.A train optimization operation plan has been established,in which the GAPSO algorithm is used to optimize the cruise speed and generate an optimized target speed curve during the initial stage.The train operates in the crosswind speed limit area according to the improved fast running strategy,and the GAPSO algorithm is used to optimize the coasting point and generate the target speed curve before the train enters the station.The simulation results show that GAPSO algorithm has the advantages of strong search ability and fast convergence speed compared to GA algorithm and PSO algorithm;The rolling GAPSO algorithm can generate optimized target speed curves in real-time under different crosswind environments,and has better energy-saving,punctuality,and comfort compared to the improved fast travel strategy and RH-PSO algorithm.The optimization of train target speed curve based on rolling GAPSO algorithm in crosswind environment can provide guidance for energy-saving and punctual operation of trains in crosswind environment.The main research work is as follows:Firstly,analyze the impact of crosswind environment on the safe operation of trains,and calculate the safe operation limit values of trains corresponding to different crosswind wind speeds.Establish a dynamic model of high-speed trains under crosswind conditions by analyzing the forces acting on trains,taking into account the effect of crosswind resistance and constraints.Secondly,improve the GAPSO algorithm,introduce a rolling optimization framework,and propose a rolling GAPSO algorithm for optimizing the target speed curve of trains in crosswind.The improvement points include the crossover of GA algorithm,the selection of genetic probability values,the selection of inertia weight values for PSO algorithm,simulation verification of the advantages of random inertia weight,and the advantages of improving GAPSO algorithm in optimization speed and convergence accuracy.Develop operational strategies for trains in crosswind environments to ensure punctuality,energy efficiency,and comfort,providing a theoretical basis for simulating train speed curves in different crosswind environments.Finally,analyze the impact of rolling time window length on the computational performance of rolling optimization algorithms,and select the optimal time window length value.Based on the 363 km line of the Beijing Shenyang Passenger Dedicated Line and the CRH380 A train data,the rolling GAPSO algorithm is simulated and validated.Simulate the dynamic adjustment of the ATO target speed curve of trains when the crosswind wind speed is less than 12.5m/s,15m/s,20m/s,25m/s,and>30m/s.Simulation verification: The rolling GAPSO algorithm can generate optimized target speed curves in real-time under different crosswind environments,and has better energy-saving,punctuality,and comfort compared to the fast moving strategy and RH-PSO algorithm.The optimization of train target speed curve based on rolling GAPSO algorithm in crosswind environment can provide a feasible solution for energy-saving,punctual,and comfortable operation of trains in crosswind environment. |
