Wavelet neural network based-identification and control for a class of nonlinear-systems: Application to two-mass motor drive system

In the framework of nonlinear process modeling, we propose a scheme of identification and control of a class of nonlinear systems based on the wavelet neural networks technique. The rules to update the system parameters are managed by gradient-based techniques. Initialization procedure of wavelet parameters is established by the heuristic method. The structure of the proposed approach is tested for the identification and the control of a class of nonlinear systems based type motor drive system and dynamic plants commonly used in the literature.