Adaptive Robust Control: Adaptive Neural Sliding Mode Control Technique

Abstract

In this chapter, to attenuate the chattering phenomenon, the discontinuous term of the controllers in Chap. 5 is replaced by single-input single-output (SISO) radial basis function neural networks (RBFNNs), which are non-linear and continuous functions, thus resulting in adaptive neural sliding mode control (ANSMC). And, to relax the demands of knowing the bounds of the uncertainties and disturbances suffered by the system, the output layer weights of the RBFNNs are updated online to compensate for these uncertainties and disturbances as well as to guarantee the stability of the system without any prior knowledge of them and its bounds.