作者: Ching Hung Lee , Jen Chieh Chien , Ha Han Chang , Hua Hsiang Chang , Che Ting Kuo
DOI:
关键词:
摘要: This paper proposes a direct adaptive backstepping control scheme for class of multi-input-multi- output nonlinear uncertain non-affine systems using recurrent wavelet neural networks (ORWNNs), called DABCORWNN. The proposed ORWNN combines the advantages wavelet-based network, fuzzy network (FNN), and feedback layer. For tracking with non-triangular form, we first transform it into strict-feedback-like form. Subsequently, based controller is developed. ideal virtual controllers actual are approximated by ORWNNs. In addition, robust designed to compensate error Based on Lyapunov approach, laws stability analysis closed-loop system obtained. Finally, simulation results double-pendulums shown demonstrate performance our approaches.