Hamid Fekri Azgomi - Iran University of Science and Technology (IUST)
Javad Poshtan

The online monitoring of induction motors is becoming increasingly important. The main difficulty in this task is the lack of an accurate analytical model to describe afaulty motor. A fuzzy logic approach may help to diagnose induction motor faults. This work presents a reliable method forthe detection of stator winding faults (which make up 38% ofinduction motor failures) based on monitoring the line/terminal current amplitudes. In this method, fuzzy logic is used to makedecisions about the stator motor condition. In fact, fuzzy logic is reminiscent of human thinking processes and natural languageenabling decisions to be made based on vague information. Therefore, this paper applies fuzzy logic to induction motorsfault detection and diagnosis. The motor condition is described using linguistic variables. Fuzzy subsets and the corresponding membership functions describe stator current amplitudes. A knowledge base, comprising rule and data bases, is built to support the fuzzy inference. The induction motor condition isdiagnosed using a compositional rule of fuzzy inference. Experimental results are presented in terms of accuracy in thedetection motor faults and knowledge extraction feasibility. The preliminary results show that the proposed fuzzy approach canbe used for accurate stator fault diagnosis.

Fault Detection, Induction Motor, Fuzzy Logic, Stator, Dynamic Model