Title :
A methodology for characterizing fault tolerant switched reluctance motors using neurogenetically derived models
Author :
Belfore, Lee A., II ; Arkadan, A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
fDate :
9/1/2002 12:00:00 AM
Abstract :
This paper examines the feasibility of using artificial neural networks (ANNs) and genetic algorithms (GAs) to develop discrete time dynamic models for fault free and faulted switched-reluctance-motor (SRM) drive systems. The results of using the ANN-GA-based (neurogenetic) model to predict the performance characteristics of a prototype SRM drive motor under normal and abnormal operating conditions are presented and verified by comparison to test data.
Keywords :
electric machine analysis computing; electrical faults; fault diagnosis; fault tolerance; finite element analysis; genetic algorithms; neural nets; reluctance motor drives; artificial neural networks; discrete time dynamic models; fault tolerant SRM characterisation; fault-free SRM drives; faulted SRM drives; genetic algorithms; neurogenetically derived models; switched reluctance motors; Artificial neural networks; Circuit faults; Coupling circuits; DC motors; Fault tolerance; Genetic algorithms; Magnetic circuits; Reluctance machines; Reluctance motors; Synchronous motors;
Journal_Title :
Energy Conversion, IEEE Transactions on
DOI :
10.1109/TEC.2002.801999
