Neural network predictive control of vehicle suspension

Smooth traveling and comfort ride are the basic evaluation criterions for a ground vehicle. This paper attempts to establish the vibration control technology based on neural network predictive control, use these predicted values to determine control input to optimize the future performance of the vehicle and improve the smooth and comfort ride of vehicle. The dynamic model of vehicle suspension system is discussed, and the linear passive suspension model and nonlinear spring suspension model of the vertical acceleration are compared. Because of the great advantages of the neural network in dealing with the nonlinear property of the spring suspension system, a BP neural network predictive controller is designed and implemented to predict the vertical acceleration of the vehicle suspension system. Simulations demonstrate the effectiveness of the neural network predictive controller with application to vehicle system.