Nonlinear Control Using Dynamic Structured Learning Recurrent Fuzzy Neural Network and Friction Observer
한성익, 이진우, 이태오, 이권순 · 제어로봇시스템학회 국내학술대회 논문집 · 2009
In this article, we develop a hybrid control scheme of a dynamic structured learning recurrent fuzzy neural network (DRFN) and a dynamic friction observer. The DRFN controller with the adaptive dynamic friction observer based on the LuGre friction is designed to position the servo system and estimate the friction parameters and a directly immeasurable friction state variable. Next, a reconstructed error estimator is also designed to give additional robustness to the control system under the presence of the model uncertainty. A proposed composite control scheme is applied to the position tracking control of the servo system.