Inductance Estimating of Linear Switched Reluctance Motors with the Use of Adaptive Neuro-Fuzzy Inference Systems

Authors : Ferhat DALDABAN, Nurettin USTKOYUNCU

Pages : 89-96

View : 17 | Download : 10

Publication Date : 2010-03-22

Article Type : Other Papers

Abstract :  In this paper, a new method based on adaptive neuro-fuzzy inference system insert ignore into journalissuearticles values(ANFIS); to estimate the phase inductance of linear switched reluctance motors insert ignore into journalissuearticles values(LSRMs); is presented. The ANFIS has the advantages of expert knowledge of fuzzy inference system and learning capability of neural networks. A hybrid learning algorithm, which combines the back-propagation insert ignore into journalissuearticles values(BP); algorithm and the least square method insert ignore into journalissuearticles values(LSM);, is used to identify the parameters of ANFIS. The translator position and the phase current of the three-phase LSRM are used to estimate the phase inductance. The phase inductance results estimated by ANFIS are in very good agreement with the results of finite element analysis insert ignore into journalissuearticles values(FEA);.   Key Words : Linear Switched Reluctance Motor, ANFIS, Inductance .  
Keywords :