Unsupervised Gear Fault Diagnosis Using Raw Vibration Signal Based on Deep Learning

Xueyi Li, Zhendong Liu, Yongzhi Qu, David He

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Gears are the most common parts of a mechanical transmission system. Gear wearing faults could cause the transmission system to crash and give rise to the economic loss. It is always a challenging problem to diagnose the gear wearing condition directly through the raw signal of vibration. In this paper, a novel method named augmented deep sparse autoencoder (ADSAE) is proposed. The method can be used to diagnose the gear wearing fault with relatively few raw vibration signal data. This method is mainly based on the theory of wearing fault diagnosis, through creatively combining with both data augmentation ideology and the deep sparse autoencoder algorithm for the fault diagnosis of gear wear. The effectiveness of the proposed method is verified by experiments of six types of gear wearing conditions. The results show that the ADSAE method can effectively increase the network generalization ability and robustness with very high accuracy. This method can effectively diagnose different gear wearing conditions and show the obvious trend according to the severity of gear wear faults. This paper provides an important insight into the field of gear fault diagnosis based on deep learning and has a potential practical application value.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
EditorsPing Ding, Chuan Li, Shuai Yang, Ping Ding, Rene-Vinicio Sanchez
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1025-1030
Number of pages6
ISBN (Electronic)9781538653791
DOIs
StatePublished - Jan 4 2019
Externally publishedYes
Event2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018 - Chongqing, China
Duration: Oct 26 2018Oct 28 2018

Publication series

NameProceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018

Conference

Conference2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
CountryChina
CityChongqing
Period10/26/1810/28/18

    Fingerprint

Keywords

  • Augmentation
  • Autoencoder
  • Gear fault diagnosis
  • Raw vibration signal
  • Unsupervised learning

Cite this

Li, X., Liu, Z., Qu, Y., & He, D. (2019). Unsupervised Gear Fault Diagnosis Using Raw Vibration Signal Based on Deep Learning. In P. Ding, C. Li, S. Yang, P. Ding, & R-V. Sanchez (Eds.), Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018 (pp. 1025-1030). [8603490] (Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PHM-Chongqing.2018.00182