In this paper, the authors present a new self-learning fuzzy neural network controller based on reference model. Based on the difference between the output of the reference model and that of the real control process, a gradient descent learning algorithm completes the real-time online modification of the parameters of the fuzzy-neural network hybrid system. The simulation experiments based on the inverted pendulum proved the effectiveness and performance of this new scheme
Published in:
Neural Networks, 1999. IJCNN '99. International Joint Conference on
(Volume:6
)
Date of Conference: Jul 1999