A fuzzy neural network approximator with fast terminal sliding mode and its applications

This paper presents a novel training method for fuzzy neural network (FNN) systems to approximate unknown nonlinear continuous functions. The training algorithm uses the principle of the fast terminal sliding mode (TSM) into the conventional gradient descent (GD) learning algorithm. It guarantees th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:ICONIP '02 : proceedings of the 9th International Conference on Neural Information Processing : computational intelligence for the E-age : November 18-22, 2002, Singapore Ročník 3; s. 1257 - 1261 vol.3
Hlavní autoři: Shuanghe Yu, Xinghuo Yu, Zhihong Man
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 2002
Témata:
Application software
Artificial neural networks
Australia
Computer networks
Convergence
Fuzzy control
Fuzzy neural networks
Fuzzy systems
Informatics
Nonlinear control systems
ISBN:9810475241, 9789810475246
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper presents a novel training method for fuzzy neural network (FNN) systems to approximate unknown nonlinear continuous functions. The training algorithm uses the principle of the fast terminal sliding mode (TSM) into the conventional gradient descent (GD) learning algorithm. It guarantees that the approximation is stable and converges to the optimal approximation function with improved speed. The proposed FNN approximator is then applied in the control of an unstable nonlinear system and the Duffing system. The simulation results demonstrate the effectiveness of the proposed method.
ISBN:9810475241
9789810475246
DOI:10.1109/ICONIP.2002.1202822