Active Control of Vertical Vibration for Maglev Train Based on Artificial Intelligence Load Estimation System

Abstract:

An active control strategy of maglev train suspension system based on artificial intelligence load estimation system is proposed in this paper. Firstly, the mathematical model of single-point levitation is given, and the open-loop instability is proven by the Routh-Herwitz criterion. Secondly, considering the load characteristics and the real-time suspension changes, a multi-layer artificial neural network is constructed to control the output of the control variables for the suspension system. Thirdly, the non-dominated sorting genetic algorithm (NSGA) is used to optimize the system parameters. The results show that the proposed control method has better robustness and can still keep relatively small error under large load disturbance.

Key words:maglev train;nonlinear model of levitation system;artificial neural network;load estimation;active control