Artificial Neural Network Based Fault Classifier For Three Phase Induction Motor

Induction machines play a pivotal role in industry and there is a strong demand for their reliable and safe operation. They are generally reliable but eventually do wear out. Faults and failures of induction machines can lead to excessive downtimes and generate large losses in terms of maintenance and lost revenues, and this motivates on line fault detection and diagnosis of induction motor. This paper proposed the support vector machine based classifier to detect the faults in the induction motor. This research is based on real word data which collected from the experimentation on custom designed 2 Hp, 440 V, three phase induction motor. Statistical parameters extracted from the stator current are used as input. Principal Component Analysis is used for feature selection. Proposed fault detection scheme gives about 100% classification accuracy, hence it can be used in industrial applications and hardware implementation is possible.