Vibration control of suspension systems using a proposed neural network

This paper presents a neural scheme for controlling a bus suspension system. The suspension system, designed as quarter bus model, is used to simplify the problem to a one-dimensional spring-damper system. The proposed controller is such that the system is always operating in a closed loop, which should lead to better performance characteristics. For comparison, PID, PI and PD controllers are also utilized to control the bus suspension system. Simulation results give superior performance of the proposed neural control scheme. It was also shown that the designed suspension control system displayed robust performance with system model uncertainties. (C) 2003 Elsevier Ltd. All rights reserved