STUDY OF ADAPTIVE SELF-CONSTRUCTING FUZZY NEURAL NETWORK FOR UNCERTAIN NONLINEAR SYSTEMS

• Main Authors: Chih-Chia Chao, 趙志家
• Other Authors: Hung-Ching Lu
• Format: Others
• Language: en_US
• Published: 2009
• Online Access: http://ndltd.ncl.edu.tw/handle/29594622319465428138

碩士 === 大同大學 === 電機工程學系(所) === 97 === The adaptive self-constructing fuzzy neural network (ASCFNN) controller is proposed for the uncertain nonlinear systems in this thesis. The ASCFNN control system is composed of an ASCFNN identifier, a computation controller and a robust controller. The ASCFNN identifier is used to estimate parameters of the uncertain nonlinear system. The computation controller is designed to sum up the output of the ASCFNN identifier. The robust controller is designed to compensate the uncertainties of the system parameters and uncertain external disturbance, and achieve robust stability of the system. The structure and parameter learnings are adopted in the ASCFNN identifier to achieve favorable approximation performance. The Mahalanobis distance (M-distance) method in the structure learning is employed to determine if the fuzzy rules are generated/ eliminated or not. Concurrently, the adaptive laws are derived based on the sense of Lyapunov so that the stability of the system can be guaranteed. Finally, the simulation results and the experiment which integrates the linear induction motor (LIM) and an inverted pendulum (IP) are implemented to verify the effectiveness of the proposed ASCFNN controller.