Induction Motor Fault Monitoring and Fault Classification Using Deep Learning Probablistic Neural Network

Hadi Salih, Idris and Babu Loganathan, Ganesh (2020) Induction Motor Fault Monitoring and Fault Classification Using Deep Learning Probablistic Neural Network. Solid State Technology, 63 (6). pp. 2196-2213. ISSN 0038111X

[img] Text (Research Article)
INDUCTIONMOTORFAULTMONITORINGANDFAULTCLASSIFICATIONUSINGDEEPLEARNINGPROBABLISTICNEURALNETWORK.pdf - Published Version

Download (911kB)
Official URL: http://solidstatetechnology.us/index.php/JSST/

Abstract

Asynchronous motor plays a major part in all kind of industries. Even though, Induction motors are robust and reliable, they are liable to various faults. Faults in induction motor may leads to terrible events such as, operating personal injuries, disturbance in production and loss of raw material. Therefore identification of fault became more important in Induction motor maintenance. Among the various defects occurring in the motor, bearing failure is a major fault, which leads to disastrous harm to machine if it is left unobserved at early stage of fault. So the condition of bearing in induction machines has to be monitored continuously. In this work, a novel approach is proposed employing Discrete Cosine transform (DCT) for analyzing speed and Probabilistic Neural Network (PNN) is utilized to identify the bearing failures. The induction motor stator currents are analyzed and classified when the motor is operated at various loading conditions with healthy and faulty bearings. The proposed PNN classifier has the ability to classify the types of fault in bearing and the experimental result supports the worth of the developed method. The PNN based motor bearing fault detection and diagnosis provides better performance compared with conventional SVM and ANN classifiers.

Item Type: Article
Uncontrolled Keywords: Induction Motor, Bearing Defects, Probabilistic Neural Network, Discrete cosine Transform, Fault Identification.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TJ Mechanical engineering and machinery
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Depositing User: ePrints deposit
Date Deposited: 01 Feb 2021 06:27
Last Modified: 01 Feb 2021 06:27
URI: http://eprints.tiu.edu.iq/id/eprint/339

Actions (login required)

View Item View Item