Support Vector Classifier-Based Broken Rotor Bar Detection in Squirrel Cage Induction Motor

Prashant Kumar, Ananda Shankar Hati

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Condition monitoring based on machine learning techniques for preventive maintenance of squirrel cage induction motors (SCIM) is the need of modern industries. Early detection of broken rotor bar (BRB) fault can reduce the unwanted production loss and minimizes downtime. With the advancement in high computational machines, machine learning techniques like logistic regression, artificial neural network, random forest technique, etc. can be efficiently implemented in BRB detection in SCIM. This paper deals with broken rotor bar detection in SCIM under different loading condition based on support vector machine (SVM)-based technique with the help of current spectrum analysis. Different kernel functions like linear, quadratic, cubic and Gaussian functions are analysed for finding the best kernel functions for achieving the good accuracy of the system.

Original languageEnglish
Title of host publicationMachines, Mechanism and Robotics - Proceedings of iNaCoMM 2019
EditorsRajeev Kumar, Vishal S. Chauhan, Mohammad Talha, Himanshu Pathak
PublisherSpringer Science and Business Media Deutschland GmbH
Pages429-438
Number of pages10
ISBN (Print)9789811605499
DOIs
StatePublished - 2022
Event4th International and 19th National Conference on Machines and Mechanism, iNaCoMM 2019 - Mandi, India
Duration: 5 Dec 20197 Dec 2019

Publication series

NameLecture Notes in Mechanical Engineering
ISSN (Print)2195-4356
ISSN (Electronic)2195-4364

Conference

Conference4th International and 19th National Conference on Machines and Mechanism, iNaCoMM 2019
Country/TerritoryIndia
CityMandi
Period5/12/197/12/19

Keywords

  • Kernel functions
  • SCIM
  • Support vector machines

Fingerprint

Dive into the research topics of 'Support Vector Classifier-Based Broken Rotor Bar Detection in Squirrel Cage Induction Motor'. Together they form a unique fingerprint.

Cite this