Title :
Modelling of switched reluctance motor based on variable structure fuzzy-neural networks
Author :
Hongtao, Zheng ; Bin, Qiao ; Zhijiang, Guo ; Jingping, Jiang
Author_Institution :
Dept. of Electron. Eng., Zhe Jiang Univ., Hangzhou, China
Abstract :
Switched reluctance motors (SRM) are almost always operated within the saturation region for a very large operation region. This yields very strong nonlinearities, which makes it very difficult to derive a comprehensive mathematical model for the behavior of the machine. This paper presents the variable structure fuzzy-neural networks model of SRM. Based on the Takagi-Sugeno fuzzy-neural networks, a variable structure and step learning arithmetic was presented. Then the fuzzy-simulation results show that this method is more precise and less time-consuming for convergence than BP neural networks model
Keywords :
electric machine analysis computing; fuzzy neural nets; learning (artificial intelligence); machine theory; reluctance motors; BP neural networks model; Takagi-Sugeno fuzzy-neural networks; convergence; fuzzy simulation; mathematical model; nonlinearities; step learning arithmetic; switched reluctance motor; variable structure; variable structure fuzzy-neural networks; Arithmetic; Convergence; Couplings; Fuzzy neural networks; Magnetic analysis; Magnetic flux; Neural networks; Reluctance machines; Reluctance motors; Saturation magnetization;
Conference_Titel :
Electrical Machines and Systems, 2001. ICEMS 2001. Proceedings of the Fifth International Conference on
Conference_Location :
Shenyang
Print_ISBN :
7-5062-5115-9
DOI :
10.1109/ICEMS.2001.971908
