KLI

A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network

Metadata Downloads
Alternative Title
A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network
Abstract
Feature extraction from a signal is the most important step in signal-based fault diagnosis. Deep learning or deep neural network (DNN) is an effective method to extract features from signals. In this paper, a novel vibration signal-based bearing fault diagnosis method using DNN is pro-posed. First, the measured vibration signals are transformed into a new data form called multi-ple-domain image-representation. By this transformation, the task of signal-based fault diagno-sis is transferred into the task of image classification. After that, a DNN with a multi-branch structure is proposed to handle the multiple-domain image representation data. The multi-branch structure of the proposed DNN helps to extract features in multiple domains simultane-ously, and to lead to better feature extraction. Better feature extraction leads to a better perfor-mance of fault diagnosis. The effectiveness of the proposed method is verified via the experi-ments conducted with actual bearing fault signals and its comparisons with well-established published methods.
Author(s)
웬 방 꾸옹호앙 주이 땅Xuan-Toa TranMien Van강희준
Issued Date
2021
Type
Article
Keyword
bearing fault diagnosisdeep learningdeep neural network
DOI
10.3390/machines9120345
URI
https://oak.ulsan.ac.kr/handle/2021.oak/9120
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_doaj_primary_oai_doaj_org_article_2f2edb95ebde4cfe8588f0633d5009f6&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,A%20Bearing%20Fault%20Diagnosis%20Method%20Using%20Multi-Branch%20Deep%20%20Neural%20Network&offset=0&pcAvailability=true
Publisher
Machines
Location
스위스
Language
영어
ISSN
2075-1702
Citation Volume
9
Citation Number
12
Citation Start Page
345
Citation End Page
345
Appears in Collections:
Engineering > Aerospace Engineering
Authorize & License
  • Authorize공개
Files in This Item:
  • There are no files associated with this item.

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.