Neural Network-Fuzzy Control Based On Clustering Analyse

With the improvement of science and technology, the objects and processes that the people want to control become more complex, but the aims for control are higher and higher. Intelligent control provides a effective way for solving the problem Fuzzy logic and neural net are the important means of intelligent cybernetics. Fuzzy control does not need to set up the exact math model, have good robustness, but it is difficult to produce and adjust membership function and fuzzy rules. Neural network have the abilities of self-learning, adapt and parallel management, but the structural selection lacks academic bases. Combining the both can learn from other's strong points to offset one's weakness and impel cybernetics to high level.In the paper, we use forward neural network model of five layers to map the fuzzy rules. The neural network-fuzzy controller is more improved than previous controller. But there are some deficiencies, such as confirming number of fuzzy subset, picking up fuzzy rules and confirming the initial value of membership. Aiming at these deficiencies, the thesis brings up the neural network-fuzzy control based on clustering analyse. The number of fuzzy subset can be confirmed by means of confirming number of best clustering in which the valid function of clustering is used. Confirming initial value of membership function and getting rules can be carried through by means of clustering analyse. The neural network-fuzzy controller based on clustering analyse can be gained after training of neural network.Clustering analyse is a method of data disposing and include hard clustering, fuzzy clustering and feasibility clustering. The operation speed of hard clustering is higher, but it dissevers the relations of samples. Fuzzy clustering overcome it, but there is local best The thesis brings up a improved method to overcome it by combining hard clustering and fuzzy clustering.The neural network-fuzzy control based on clustering analyse is applied to the water level control of boiler in power plant .It can be seen from the simulation that the control quality is high and robustness is strongo...