Gearbox fault diagnostics using deep learning with simulated data

Ozhan Gecgel, Stephen Ekwaro-Osire, João Paulo Dias, Abdul Serwadda, Fisseha M. Alemayehu, Abraham Nispel

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

4 Scopus citations

Abstract

Transmission components are prone to fatigue damage due to high and intermittent loading cycles, that cause premature failure of gearboxes. Recently, several vibration-based diagnostics approaches using Machine Learning (ML) and Deep Learning (DL) algorithms have been proposed to identify gearboxes faults. However, most of them rely on a large amount of training data collection from physical experiments, which is often associated with high costs. This paper offers an ML and DL classification performance comparison of several algorithms to diagnose faults in a gearbox based on realistic simulated vibration data. A dynamic model of a single-stage gearbox was developed to generate data for different health conditions. Generated datasets were fed to ML and DL algorithms and accuracy results were compared. Results revealed the superiority of Convolutional Neural Network compared to other classifiers. This research contributes to the prevention of catastrophic failures in gearboxes by early crack detection and maintenance schedule optimization.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Prognostics and Health Management, ICPHM 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538683576
DOIs
StatePublished - Jun 2019
Event2019 IEEE International Conference on Prognostics and Health Management, ICPHM 2019 - San Francisco, United States
Duration: Jun 17 2019Jun 20 2019

Publication series

Name2019 IEEE International Conference on Prognostics and Health Management, ICPHM 2019

Conference

Conference2019 IEEE International Conference on Prognostics and Health Management, ICPHM 2019
CountryUnited States
CitySan Francisco
Period06/17/1906/20/19

Keywords

  • Deep learning
  • Dynamic model
  • Image encoding
  • Tooth profile error
  • Vibration-based diagnostics

Fingerprint Dive into the research topics of 'Gearbox fault diagnostics using deep learning with simulated data'. Together they form a unique fingerprint.

Cite this