Induction Motor Fault Classification using Pattern Recognition Neural Network
Shaina Grover1, Amandeep Sharma2, Lini Mathew3, Shantanu Chatterji4

1Shaina Grover, Department of Electrical Engineering, NITTTR Chandigarh, Chandigarh, India.
2Amandeep Sharma, Department of Electrical Engineering, NITTTR Chandigarh, Chandigarh, India.
3Lini Mathew, Department of Electrical Engineering, NITTTR Chandigarh, Chandigarh, India.
4Shantnu Chaterji, Department of Electrical Engineering, NITTTR Chandigarh, Chandigarh, India.

Manuscript received on 04 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 July 2019 | PP: 3340-3345 | Volume-8 Issue-9, July 2019 | Retrieval Number: I7591078919/19©BEIESP | DOI: 10.35940/ijitee.I7591.078919

Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The industrial growth has escalated the use of induction motors as prime movers in modern industry. This is due to its low cost, simple construction and ruggedness. Although rugged, these may fail earlier than expected life due to, excessive mechanical, electrical and environmental stresses. Automatic Artificial Intelligence (AI)-based systems are nowadays widely employed in the domain of induction motor fault identification with high success rate. Artificial neural network are utilized extensively for the detection and diagnosis of various induction motor faults. These systems generally use supervised learning, where the models are pre-trained such that these are skilled enough to classify the absence or presence of faults in motor under investigation. In this paper, a highly effective approach for detection of different motor fault conditions, based on pattern recognition technique is presented. In the proposed method the statistical time domain features are computed from three phase motor current and used as inputs of ANN. Seven different classes of motor conditions: healthy, broken rotor bar, broken rotor bar with stator winding short circuit and inner and outer race bearing defects were considered. The results indicates that the proposed methodology is highly effective for diagnosis of various induction motor faults with high success rate.
Keywords: Artificial Neural Networks (ANN), Condition Monitoring, Fault Diagnosis, Induction Motor. About four Key Words or Phrases in Alphabetical Order, Separated by Commas.

Scope of the Article: Classification