Title :
A Design of Improved FCMAC Neural Network
Author :
Liu Li-ye ; Ma Cui-hong
Author_Institution :
Coll. of Comput. & Autom. Control, Hebei Polytech. Univ., Tangshan, China
Abstract :
Aiming at the parameters of fuzzy controller and CMAC neural network are difficult to tune,GA is introduced to the control system to optimize the parameters of fuzzy CMAC neural network. The strong points of fuzzy control, CMAC, genetic algorithms and improved structure are together. A FCMAC control system is designed based on modified GA. Both the overall architecture of the system and the design of every part are proposed here. The results of simulation show that the proposed control system has better performance in the learning ability and approximation accuracy.
Keywords :
approximation theory; cerebellar model arithmetic computers; control system synthesis; fuzzy control; genetic algorithms; learning systems; neurocontrollers; CMAC; approximation accuracy; fuzzy cerebellar model articulation controller neural network design; genetic algorithms; learning ability; Approximation methods; Control systems; Fuzzy control; Fuzzy logic; Genetic algorithms; MATLAB; Mathematical model;
Conference_Titel :
Control, Automation and Systems Engineering (CASE), 2011 International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4577-0859-6
DOI :
10.1109/ICCASE.2011.5997558
