Target speed profile optimization of energy-efficient train operation based on improved heuristic genetic algorithm

For the problems of poor robustness and unsatisfactory optimization effect of many optimization algorithms under extreme line conditions, and low efficiency and easy to fall into local optimum of conventional genetic and particle swarm optimization algorithms, an energy-saving operation optimization strategy of train based on improved genetic algorithm is proposed. According to the second law of Newton mechanics, the basic mathematical model of train operation is established. The algorithm selects the maximum running speed and the position of coast point as optimization variables, uses the maximum traction force to tract the train to the maximum running speed. After that, the train is controlled to run at a constant speed until it reaches the position of coast point, and then the coasting operation is started. If it intersects with the shortest running curve in the middle, it is forced to run along the shortest running curve. Otherwise, it will run according to the original running state until the end point is reached. And the improved genetic algorithm is used in Matlab to optimize the train operation. The simulation results show that the algorithm has the advantages of fast convergence speed, high robustness, and can effectively reduce the energy consumption of train operation. Especially, it overcomes the shortcomings of uncertainties in search results and speed fluctuations of evolutionary algorithm effectively, and has good reference significance and practical value for energy-saving operation and automatic driving of other vehicles in this field.