Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning

The intelligent gear recognition method based on convolutional neural network can effectively identify the gear fault, but the convolutional neural network needs a lot of labeled training data, which limits the application of convolutional neural network in gear fault diagnosis. To solve this proble...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenguo Jie, Xiyang Wang, Tingkai Gong
Format: Article
Language:zho
Published: Editorial Office of Journal of Mechanical Transmission 2022-05-01
Series:Jixie chuandong
Subjects:
Online Access:http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2022.05.024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841548811566055424
author Zhenguo Jie
Xiyang Wang
Tingkai Gong
author_facet Zhenguo Jie
Xiyang Wang
Tingkai Gong
author_sort Zhenguo Jie
collection DOAJ
description The intelligent gear recognition method based on convolutional neural network can effectively identify the gear fault, but the convolutional neural network needs a lot of labeled training data, which limits the application of convolutional neural network in gear fault diagnosis. To solve this problem, a gear fault diagnosis method based on distribution adaptation layer and soft label learning is proposed. The convolutional neural network is used to extract features and soft labels. The distribution discrepancy is extracted by the distribution adaptation layer, and the soft label loss is generated by the soft label learning. The joint loss of distribution discrepancy, soft label loss and classification loss are used as the objective function, and the model is trained to diagnose the faults of target domain. The proposed method is verified by gear vibration signals. The results show that the proposed method can classify gear fault data accurately and effectively.
format Article
id doaj-art-209fed3e3ea240dca495ffca91c6870e
institution Kabale University
issn 1004-2539
language zho
publishDate 2022-05-01
publisher Editorial Office of Journal of Mechanical Transmission
record_format Article
series Jixie chuandong
spelling doaj-art-209fed3e3ea240dca495ffca91c6870e2025-01-10T13:58:14ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392022-05-014616016630480523Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label LearningZhenguo JieXiyang WangTingkai GongThe intelligent gear recognition method based on convolutional neural network can effectively identify the gear fault, but the convolutional neural network needs a lot of labeled training data, which limits the application of convolutional neural network in gear fault diagnosis. To solve this problem, a gear fault diagnosis method based on distribution adaptation layer and soft label learning is proposed. The convolutional neural network is used to extract features and soft labels. The distribution discrepancy is extracted by the distribution adaptation layer, and the soft label loss is generated by the soft label learning. The joint loss of distribution discrepancy, soft label loss and classification loss are used as the objective function, and the model is trained to diagnose the faults of target domain. The proposed method is verified by gear vibration signals. The results show that the proposed method can classify gear fault data accurately and effectively.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2022.05.024Gear fault diagnosisConvolutional neural networkDeep transfer learningDistribution adaptation layerSoft label learning
spellingShingle Zhenguo Jie
Xiyang Wang
Tingkai Gong
Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning
Jixie chuandong
Gear fault diagnosis
Convolutional neural network
Deep transfer learning
Distribution adaptation layer
Soft label learning
title Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning
title_full Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning
title_fullStr Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning
title_full_unstemmed Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning
title_short Gear Fault Diagnosis based on Distribution Adaptation Layer and Soft Label Learning
title_sort gear fault diagnosis based on distribution adaptation layer and soft label learning
topic Gear fault diagnosis
Convolutional neural network
Deep transfer learning
Distribution adaptation layer
Soft label learning
url http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2022.05.024
work_keys_str_mv AT zhenguojie gearfaultdiagnosisbasedondistributionadaptationlayerandsoftlabellearning
AT xiyangwang gearfaultdiagnosisbasedondistributionadaptationlayerandsoftlabellearning
AT tingkaigong gearfaultdiagnosisbasedondistributionadaptationlayerandsoftlabellearning