Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining

Roller bearings are one of the most commonly used components in rotational machines. The fault diagnosis of roller bearings thus plays an important role in ensuring the safe functioning of the mechanical systems. However, in most cases of bearing fault diagnosis, there are limited number of labeled...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei-Li Qin, Wen-Jin Zhang, Zhen-Ya Wang
Format: Article
Language:English
Published: Wiley 2016-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2016/1646898
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850174489597313024
author Wei-Li Qin
Wen-Jin Zhang
Zhen-Ya Wang
author_facet Wei-Li Qin
Wen-Jin Zhang
Zhen-Ya Wang
author_sort Wei-Li Qin
collection DOAJ
description Roller bearings are one of the most commonly used components in rotational machines. The fault diagnosis of roller bearings thus plays an important role in ensuring the safe functioning of the mechanical systems. However, in most cases of bearing fault diagnosis, there are limited number of labeled data to achieve a proper fault diagnosis. Therefore, exploiting unlabeled data plus few labeled data, this paper proposed a roller bearing fault diagnosis method based on tritraining to improve roller bearing diagnosis performance. To overcome the noise brought by wrong labeling into the classifiers training process, the cut edge weight confidence is introduced into the diagnosis framework. Besides a small trick called suspect principle is adopted to avoid overfitting problem. The proposed method is validated in two independent roller bearing fault experiment vibrational signals that both include three types of faults: inner-ring fault, outer-ring fault, and rolling element fault. The results demonstrate the desirable diagnostic performance improvement by the proposed method in the extreme situation where there is only limited number of labeled data.
format Article
id doaj-art-d5d7a1b4ebb34dbf9c23924ae31882d4
institution OA Journals
issn 1070-9622
1875-9203
language English
publishDate 2016-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-d5d7a1b4ebb34dbf9c23924ae31882d42025-08-20T02:19:38ZengWileyShock and Vibration1070-96221875-92032016-01-01201610.1155/2016/16468981646898Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based TritrainingWei-Li Qin0Wen-Jin Zhang1Zhen-Ya Wang2School of Reliability and System Engineering, Beihang University, Beijing, ChinaSchool of Reliability and System Engineering, Beihang University, Beijing, ChinaSchool of Reliability and System Engineering, Beihang University, Beijing, ChinaRoller bearings are one of the most commonly used components in rotational machines. The fault diagnosis of roller bearings thus plays an important role in ensuring the safe functioning of the mechanical systems. However, in most cases of bearing fault diagnosis, there are limited number of labeled data to achieve a proper fault diagnosis. Therefore, exploiting unlabeled data plus few labeled data, this paper proposed a roller bearing fault diagnosis method based on tritraining to improve roller bearing diagnosis performance. To overcome the noise brought by wrong labeling into the classifiers training process, the cut edge weight confidence is introduced into the diagnosis framework. Besides a small trick called suspect principle is adopted to avoid overfitting problem. The proposed method is validated in two independent roller bearing fault experiment vibrational signals that both include three types of faults: inner-ring fault, outer-ring fault, and rolling element fault. The results demonstrate the desirable diagnostic performance improvement by the proposed method in the extreme situation where there is only limited number of labeled data.http://dx.doi.org/10.1155/2016/1646898
spellingShingle Wei-Li Qin
Wen-Jin Zhang
Zhen-Ya Wang
Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining
Shock and Vibration
title Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining
title_full Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining
title_fullStr Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining
title_full_unstemmed Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining
title_short Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining
title_sort improvement of roller bearing diagnosis with unlabeled data using cut edge weight confidence based tritraining
url http://dx.doi.org/10.1155/2016/1646898
work_keys_str_mv AT weiliqin improvementofrollerbearingdiagnosiswithunlabeleddatausingcutedgeweightconfidencebasedtritraining
AT wenjinzhang improvementofrollerbearingdiagnosiswithunlabeleddatausingcutedgeweightconfidencebasedtritraining
AT zhenyawang improvementofrollerbearingdiagnosiswithunlabeleddatausingcutedgeweightconfidencebasedtritraining