Few-shot fault diagnosis of rolling bearing via mutual centralized learning combining simple and parameter-free attention

IF 1.8 4区 工程技术 Q3 ENGINEERING, MECHANICAL
Keheng Zhu, Dexian Tang, Liang Chen, Chaoge Wang, Xueyi Zhang, Xiong Hu
{"title":"Few-shot fault diagnosis of rolling bearing via mutual centralized learning combining simple and parameter-free attention","authors":"Keheng Zhu, Dexian Tang, Liang Chen, Chaoge Wang, Xueyi Zhang, Xiong Hu","doi":"10.1007/s40430-024-05180-7","DOIUrl":null,"url":null,"abstract":"<p>The development of deep learning has led to great success in the bearing fault diagnosis. However, the issue of limited fault samples impedes the extensive application of most fault diagnosis approaches based on deep learning. To address this challenge, a new few-shot fault diagnosis method based on mutual centralized learning (MCL) and simple and parameter-free attention (SimAM) is put forward in this paper. First, MCL is adopted to diagnose the bearing fault with small samples, which employs a bidirectional approach rather than the traditional unidirectional method to better learn mutual affiliations between the fault features, having better few-shot classification ability. Furthermore, a new feature extractor module is constructed through the SimAM to improve the feature extraction capability of the MCL model by providing better feature maps for classification. The effectiveness of the proposed method is tested on CWRU bearing dataset and our own bearing dataset. The experimental results show that the proposed MCL-SimAM model can effectively recognize the bearing fault with few samples. Additionally, the comparison experiments demonstrate that the proposed model is superior to the comparable models [relation network (RN), prototypical network (PN), and matching network (MN), deep subspace networks (DSN), and ridge regression differentiable discriminator (R2D2)], which has a better recognition accuracy in few-shot scenarios.</p>","PeriodicalId":17252,"journal":{"name":"Journal of The Brazilian Society of Mechanical Sciences and Engineering","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of The Brazilian Society of Mechanical Sciences and Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s40430-024-05180-7","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

Abstract

The development of deep learning has led to great success in the bearing fault diagnosis. However, the issue of limited fault samples impedes the extensive application of most fault diagnosis approaches based on deep learning. To address this challenge, a new few-shot fault diagnosis method based on mutual centralized learning (MCL) and simple and parameter-free attention (SimAM) is put forward in this paper. First, MCL is adopted to diagnose the bearing fault with small samples, which employs a bidirectional approach rather than the traditional unidirectional method to better learn mutual affiliations between the fault features, having better few-shot classification ability. Furthermore, a new feature extractor module is constructed through the SimAM to improve the feature extraction capability of the MCL model by providing better feature maps for classification. The effectiveness of the proposed method is tested on CWRU bearing dataset and our own bearing dataset. The experimental results show that the proposed MCL-SimAM model can effectively recognize the bearing fault with few samples. Additionally, the comparison experiments demonstrate that the proposed model is superior to the comparable models [relation network (RN), prototypical network (PN), and matching network (MN), deep subspace networks (DSN), and ridge regression differentiable discriminator (R2D2)], which has a better recognition accuracy in few-shot scenarios.

Abstract Image

通过结合简单注意力和无参数注意力的相互集中学习,对滚动轴承进行少量故障诊断
深度学习的发展为轴承故障诊断带来了巨大成功。然而,故障样本有限的问题阻碍了大多数基于深度学习的故障诊断方法的广泛应用。为解决这一难题,本文提出了一种基于相互集中学习(MCL)和简单无参数注意(SimAM)的新的少量故障诊断方法。首先,采用 MCL 方法对轴承故障进行小样本诊断,该方法采用双向方法而非传统的单向方法,能更好地学习故障特征之间的相互隶属关系,具有更好的少量故障分类能力。此外,还通过 SimAM 构建了一个新的特征提取模块,以提高 MCL 模型的特征提取能力,为分类提供更好的特征图。在 CWRU 轴承数据集和我们自己的轴承数据集上测试了所提方法的有效性。实验结果表明,所提出的 MCL-SimAM 模型只需少量样本就能有效识别轴承故障。此外,对比实验表明,所提出的模型优于同类模型(关系网络(RN)、原型网络(PN)和匹配网络(MN)、深子空间网络(DSN)和脊回归可微分判别器(R2D2)),在少样本场景下具有更高的识别准确率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
3.60
自引率
13.60%
发文量
536
审稿时长
4.8 months
期刊介绍: The Journal of the Brazilian Society of Mechanical Sciences and Engineering publishes manuscripts on research, development and design related to science and technology in Mechanical Engineering. It is an interdisciplinary journal with interfaces to other branches of Engineering, as well as with Physics and Applied Mathematics. The Journal accepts manuscripts in four different formats: Full Length Articles, Review Articles, Book Reviews and Letters to the Editor. Interfaces with other branches of engineering, along with physics, applied mathematics and more Presents manuscripts on research, development and design related to science and technology in mechanical engineering.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信