A Novel Wavelet-based-CMAC Neural Network Controller for Nonlinear Systems

This paper proposes a wavelet-based cerebellar model arithmetic controller neural network (CMAC NN) and develops a hybrid control scheme, combining supervisory controller, filter, and CMAC, for nonlinear systems. The Gaussian functions of traditional CMAC are replaced by wavelet functions. In addition, properties and advantages of fuzzy TSK-model are used to modify the activation functions of CMAC for obtaining high approximation accuracy and convergent rate. A PD type wavelet-based CMAC controller with pre-filter is constructed for nonlinear affine systems. The corresponding supervisory controller is used to compensate the wavelet-based CMAC controller for better performance. Several simulation results are shown to demonstrate the effectiveness of our approach.