Robust control for nonlinear systems by universal learning network considering fuzzy criterion and second order derivatives
Machiko Ohbayashi, Kotaro Hirasawa, K. Toshimitsu, Junichi Murata, Jinglu Hu · 2002
Control systems using neural networks have been used in many fields, but some problems remain unsolved. One of the problems which should be overcome is to enhance the robustness of the neural network control systems. In the paper, a robust control method is proposed, which is based on the second order derivatives of the universal learning network and fuzzy criterion function.