Interval type-2 fuzzy-neural network indirect adaptive sliding mode control for an active suspension system

This paper presents a novel interval type-2 fuzzy-neural network indirect adaptive sliding mode control (SMC) approach (T2FNNAS) for a suspension system including actuator dynamics. It is equipped with a novel moving sliding surface in which the slope and intercept of sliding surface are simultaneity adjusted by adaptive interval T2FNN to improve controller robustness against system uncertainties and unknown disturbances. As a result, the drawbacks of the conventional SMC, such as chattering effect and a required priori knowledge of the bounds of uncertainties, are removed. Based on the Lyapunov synthesis approach, the free parameters of the adaptive FNN are tuned on-line. One advantage of the proposed approach is that, by incorporating the Lyapunov design approach and SMC method into the adaptive fuzzy-neural control scheme to derive the control law, the proposed approach not only assures closed-loop stability but also achieves a good performance for the overall system. Another advantage of the proposed method is that to relax the requirement for the bound of approximation error, and an estimation mechanism is also employed to observe the bound of it real time. Design of the control system consists of two interior loops. The inner loop is a force control of the hydraulic actuator, while the outer loop is position controller that use T2FNNAS. Finally, a comparison between the proposed approach and a robust model reference adaptive control approach is provided. Simulation results confirm that the proposed approach effectively improves both the passenger comfort and the ride quality of the car.