Multi-objective Optimization Improved GA Algorithm and Fuzzy PID Control of ATO System for Train Operation

Abstract

In order to solve the problem that automatic train operation control system considering the single factor and control is not easy to be accurate, a multi-objective optimization (MO) based on improved genetic algorithm (GA) and fuzzy PID control method is proposed in this paper. Firstly, based on train operation characteristics, a multi-objective model of train operation process is established. Secondly, in order to improve the performance of the algorithm, the train operation process is optimized by using linear weight method and multi-objective genetic algorithm. Third, in order to suppress the local convergence of GA, a dual population genetic mechanism is adopted in the iterative process. Finally, a fuzzy PID controller is embedded into the control designer after target curve and control train operation in real time according to the real time running state. The results show that the proposed algorithm can get a reasonable MO result and accurate real-time control.