Fault diagnosis algorithm based on artificial immunity system

Abstract

Artificial immunity systems have been emerged as simulation of human immunity. The negative selection algorithm which is most important component of artificial immunity system can determine undesired condition, easily. In this study, motor current signature analysis and negative selection algorithm have been used for broken rotor bar faults. Current signal obtained from motor has been transformed to current spectrum by using motor current signature analysis. The side bands extracted from this spectrum have been taken as input to negative selection algorithm, and broken rotor bar faults have been diagnosed. The application of developed fault diagnosis algorithm has been demonstrated by diagnosing faults in induction motor real time. Furthermore, proposed fault diagnosis approach is adapted for diagnosing other faults.