To Study Induction Motor External Faults Detection and Classification using ANN and Fuzzy Soft Computing Techniques

Abstract

Induction motors are widely used electrical load and appears to various faults during their operation. Accurate fault identification is the prime industrial need. Overload, overvoltage, undervoltage, single phasing and voltage unbalance are most probable external faults. In conventional protection, relays applied for one hazard may operate for others. The recent trends for the multiple fault diagnosis in induction machines is using soft computing techniques mainly ANN and fuzzy logic. ANN and clustering based fuzzy logic are suitable and well proven for complex and linearly non separable fault identification task. This work used and demonstrated neural networks and clustering based fuzzy inference systems for accurate and generalized identification of external faults. Performance of neural network and clustering based fuzzy classifiers is done alongwith conventional LDA and NBC using statistical parameters classification accuracy, sensitivity, specificity, precision and F-measure. Clustering based fuzzy systems have advantage of obtaining rules besides good statistical parameter results. MLPNN outperforms for all statistical measures.