Robust adaptive control via neural linearization and four types of compensation

— In this paper, we propose a new type of neural adaptive control via dynamic neural networks. For a class of unknown nonlinear systems, a neural identifierFbased feedback linearization controller is first used. DeadFzone and projection techniques are applied to assure the stability of neural idenF tification. Then four types of compensator are addressed. The stability of closedFloop system is also proven.

• Type: Conference
• Year: 2008
• Where: IJCNN
• Authors: Wen Yu, Xiaoou Li
• Keywords: Artificial Intelligence, Dynamic Neural Networks, IJCNN 2008, Neural, Neural Adaptive Control