http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Vu Thi Yen,Wang Yao Nan,Pham Van Cuong,Nguyen Xuan Quynh,Vu Huu Thich 제어·로봇·시스템학회 2017 International Journal of Control, Automation, and Vol.15 No.6
In this paper, a robust adaptive control method based on Dynamic Structure Fuzzy Wavelet Neural Networks(FWNNs) system is presented for trajectory tracking control of industrial robot manipulators (IRM) withuncertainties and disturbances via adaptive sliding mode control (SMC). Four layer FWNNs in the Dynamic structureFWNNs is constructed on the basis of fuzzy rules which associates with wavelet function in the consequentpart, to compensate for structured and unstructured uncertainties and model complex processes. However, it isdifficult to design a suitable control scheme to achieve the required approximation errors, such as friction forces,external disturbances error and parameter variations. To deal with the mentioned problems, all the parameters of theDynamic structure FWNNs system are tuned on-line by an adaptive learning algorithm, and adaptive robust controllaws are determined by Lyapunov stability theorem. By using Dynamic structure FWNNs, this control systemcould achieve desired tracking performance, the stability and robustness of the closed-loop manipulators system areguaranteed. In addition, the simulations and experimental performed on a three-link IRM are provided in comparisonwith wavelet network control (WNC) and adaptive Fuzzy control (AFC) to demonstrate the effectiveness androbustness of the proposed Dynamic structure FWNNs methodology.