Adaptive sliding mode control using RBF neural network for nonlinear system

A novel adaptive sliding mode controller based on radial basis function neural network (RBFNN) is proposed in this paper for the nonlinear systems with uncertainties using feedback linearization method. An adaptive rule is utilized to on-line adjusting the weights of RBFNN, which is used to compute the equivalent control. Adaptive training algorithm was derived in the sense of Lyapunov stability analysis, so that the stability of the closed-loop system can be guaranteed even in the case of uncertainty. Using the RBFNN, instead of multilayer feed forward network trained with back propagation, works out shorter reaching time. Chattering problem of SMC is substantially derived in the proposed controller. Simulation results show that the position tracking responses closely follow the desired trajectory occurrence of the disturbances. Also, simulation results demonstrate that the proposed controller is a stable control scheme for the inverted pendulum trajectory tracking applications and has strong robustness.