Optimization of Train ATO System Based on RBF Neural Network PID Control

In the process of high-speed train operation, due to the complex and changeable operation environment, the traditional controller can't carry out real-time and effective control. Therefore, in order to improve the adaptability of the system, a PID control algorithm based on RBF neural network is proposed. Firstly, the multi-objective operation model of high-speed train is established with comfort, accurate parking, punctuality and so on as indicators, and the target curve of train operation is generated by using genetic algorithm. Then the RBF neural network PID controller is established by combining the traditional PID control and RBF neural network. The RBF neural network is used to adjust the PID control parameters automatically, so as to make up for the shortcomings of the traditional controller. The simulation results show that the RBF neural network PID control algorithm has better adaptability and smaller error of tracking target curve compared with the traditional algorithm.