Condition Based Monitoring of Rolling Bearing by Naive Bayes Classifier

Sujit Kumar, Alka Kumari, Durgesh Nandani, Manish Kumar

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

Abstract

Rolling bearings are the main components of rotating machines which are mostly damaged. Therefore, correct and quick fault diagnosis of rolling bearings is very necessary for maintenance. Nowadays, machine learning has emerged as a very effective artificial intelligence technique for fault diagnosis. The Naive Bayes classifier is one of the machine learning techniques that effectively classifies faults. In this work, intelligent fault classification of bearing faults based on Naive Bayes is proposed. The proposed model correctly classifies the different types of fault conditions of rolling bearings. The proposed model has achieved the best results and has been compared with existing methods.

Original languageEnglish
Title of host publicationInnovations in Electrical and Electronics Engineering - Proceedings of ICEEE 2024
EditorsAkhtar Kalam, Saad Mekhilef, Sheldon S. Williamson
PublisherSpringer Science and Business Media Deutschland GmbH
Pages589-599
Number of pages11
ISBN (Print)9789819791118
DOIs
StatePublished - 1 Jan 2025
Externally publishedYes
Event5th International Conference on Electrical and Electronics Engineering, ICEEE 2024 - Melbourne, Australia
Duration: 11 Sep 202412 Sep 2024

Publication series

NameLecture Notes in Electrical Engineering
Volume1295 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference5th International Conference on Electrical and Electronics Engineering, ICEEE 2024
Country/TerritoryAustralia
CityMelbourne
Period11/09/2412/09/24

Keywords

  • Fault diagnosis
  • Machine learning
  • Multiclassification
  • Naive Bayes

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Condition Based Monitoring of Rolling Bearing by Naive Bayes Classifier'. Together they form a unique fingerprint.

Cite this