Neural Network Based Fault Diagnostics in Multi Phase Induction Machine
Balamurugan Annamalai1, Sivakumaran Thangavel Swaminathan2
1Balamurugan Annamalai*, Research Scholar, Dept. of EEE, Sathyabama Institute of Science and Technology, Tamil Nadu, India.
2Sivakumaran Thangavel Swaminathan, Professor & Principal, Dept. of EEE, Sasurie College of Engineering, Tirupur, Tamil Nadu, India.
Manuscript received on January 17, 2020. | Revised Manuscript received on January 27, 2020. | Manuscript published on February 10, 2020. | PP: 2370-2374 | Volume-9 Issue-4, February 2020. | Retrieval Number: D2057029420/2020©BEIESP | DOI: 10.35940/ijitee.D2057.029420
Open Access | Ethics and Policies | Cite | Mendeley
© 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: This article proposes a new method for solving the diagnosis of faults in a multiphase induction motor using a least-squares filter (LMS) and a neural network. The proposed hybrid fault diagnosis method includes an efficient LMS-based feature extractor and an artificial neural network fault classifier. First, the LMS method is used to obtain efficient functions. The performance and efficiency of the presented neural network hybrid classifier is evaluated by testing a total of 600 samples, which are modeled on a failure model. The average correct classification is 96.17% for different fault signals, respectively. The result obtained from the simulation analysis shows the effectiveness of the proposed neural network for the diagnosis of faults in the multiphase induction motor.
Keywords: Fault Diagnosis, Feature Extraction, Least mean Square, Multi Layer Perceptron Neural Network.
Scope of the Article: Neural Network