Minimal learning parameters-based adaptive neural control for vehicle active suspensions with input saturation

In this paper, a neural network (NN) control method is developed for nonlinear quarter vehicle active suspension systems (VASSs) which have the features of parameter uncertainties, input saturation and road disturbance, whose aim is to ensure safe driving and improve the ride comfort. The NNs are employed to approximate unkown nonlinear functions that the forming reason is uncertainties by caused varied sprung mass. When the output of actuator goes beyond its maximums, an NN control scheme combined with anti-saturation is proposed to handle this problem. Furthermore, an NN controller with the minimal learning parameters is constructed to ensure that the number of adaptive learning parameters and the burden computation are largely reduced for VASSs. Meanwhile, the control objectives of VASSs are proved based on the stability analysis. Finally, the effectiveness of designed scheme is demonstrated by an example.