BP neural network and PID combined control applied to vehicle active suspension system

Abstract

In order to adjust the suspension performance to improve the ride comfort of the vehicle, a PID controller based on BP neural network is proposed to optimize the performance of the active suspension system in real time. First, the simplified model of a quarter-vehicle active suspension system is built. Then, the vehicle active suspension system equipped with the proposed BP neural network-based PID controller (BP-PID controller) is simulated in MATLAB/Simulink software under bump road surface and random road surface. Finally, the response curves and the root mean square values of the vehicle body acceleration, suspension dynamic deflection and dynamic tire load of the active suspension and passive suspension are compared and analysed. The simulation results show that the BP-PID controller can improve the suspension performance and inhibit the vehicle body acceleration, suspension dynamic deflection and dynamic tire load of the vehicle.