Adaptive neural network fault-tolerant control for a class of nonlinear systems

In this paper, a direct adaptive neural network sliding-mode fault-tolerance control architecture is proposed for a class of SISO nonlinear systems. The architecture employs neural network to approximate the optimal controller which is designed on the assumption that all the dynamics in the system are known. With the sliding-mode controller technique, the influence of the uncertainty on the systems was considerably reduced. Furthermore, Global asymptotic stability is established in the Lyapunov sense, with the tracking errors converging to a neighborhood of zero. The example shows that the proposed control architecture is effective for a class of SISO nonlinear system.