基于注意力机制多尺度卷积神经网络的轴承故障诊断
TP391; 提出了基于注意力机制的多尺度卷积神经网络(Multi-scale and Attentive Convolutional Neural Network,MACNN)进行轴承故障分类,该模型以一维Resnetl8网络结构为主体,卷积模块采用残差模块和空洞卷积并行方式以达到扩大感受野、避免特征信息丢失的目的,同时利用注意力机制可以自动提取有用特征的能力,将模型提取特征作为输入送入注意力机制模块,进一步提高模型故障分类能力.此外,采用边界平衡生成对抗网络(Boundary Equilibrium Generative Adversarial Networks,BEGAN)模型对故障数据...
Saved in:
| Published in | 华东理工大学学报（自然科学版） Vol. 50; no. 2; pp. 247 - 256 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | Chinese |
| Published |
华东理工大学能源化工过程智能制造教育部重点实验室,上海 200237
01.05.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1006-3080 |
| DOI | 10.14135/j.cnki.1006-3080.20221223001 |
Cover
Loading…
| Abstract | TP391; 提出了基于注意力机制的多尺度卷积神经网络(Multi-scale and Attentive Convolutional Neural Network,MACNN)进行轴承故障分类,该模型以一维Resnetl8网络结构为主体,卷积模块采用残差模块和空洞卷积并行方式以达到扩大感受野、避免特征信息丢失的目的,同时利用注意力机制可以自动提取有用特征的能力,将模型提取特征作为输入送入注意力机制模块,进一步提高模型故障分类能力.此外,采用边界平衡生成对抗网络(Boundary Equilibrium Generative Adversarial Networks,BEGAN)模型对故障数据增强,改变不平衡数据集的比例,增加数据集样本数量,降低MACNN模型的过拟合,提高诊断的准确率.在帕德博恩轴承数据集(Paderborn University Dataset,PU)上验证MACNN模型,实验结果表明,该模型在特征提取和故障分类方面都表现出了良好的性能,优于当前主流模型. |
|---|---|
| AbstractList | TP391; 提出了基于注意力机制的多尺度卷积神经网络(Multi-scale and Attentive Convolutional Neural Network,MACNN)进行轴承故障分类,该模型以一维Resnetl8网络结构为主体,卷积模块采用残差模块和空洞卷积并行方式以达到扩大感受野、避免特征信息丢失的目的,同时利用注意力机制可以自动提取有用特征的能力,将模型提取特征作为输入送入注意力机制模块,进一步提高模型故障分类能力.此外,采用边界平衡生成对抗网络(Boundary Equilibrium Generative Adversarial Networks,BEGAN)模型对故障数据增强,改变不平衡数据集的比例,增加数据集样本数量,降低MACNN模型的过拟合,提高诊断的准确率.在帕德博恩轴承数据集(Paderborn University Dataset,PU)上验证MACNN模型,实验结果表明,该模型在特征提取和故障分类方面都表现出了良好的性能,优于当前主流模型. |
| Abstract_FL | Bearing faults can seriously reduce industrial production efficiency and even endanger the safety of people's lives and property.Monitoring the operating conditions of bearings conducting fault diagnosis are of great significance for ensuring the safe operation of the production process.This paper proposes a Multi-Scale and Attentive Convolutional Neural Network(MACNN)based on attention mechanism for bearing faults classification.Firstly,one-dimensional bearing signals are input into a convolution layer,followed by a maximum pooling layer to suppress noise and reduce information redundancy.Then,four MACNN modules are taken as input,each of which adopts a parallel network structure of ordinary convolution and void convolution.Under the premise without increasing model parameters,the model's receptive field is expanded to extract more fault features for improving the accuracy.In addition,the attention mechanism module is connected at the end of each MACNN model and the feature information is further extracted by using the ability of automatic extraction of important features.The average pooling layer is used in the network structure to prevent the overfitting and the full connection layer from the output of experimental classification results.Furthermore,the Boundary Equilibrium Generative Adversarial Networks(BEGAN)model is adopted to enhance fault data,change the proportion of unbalanced data sets,increase the number of dataset samples,reduce overfitting of MACNN model,and improve diagnostic accuracy.Finally,the experimental results on the Paderborn University Dataset show that MACNN can achieve better performance in feature extraction and fault classification,outperforming the state-of-the-art methods. |
| Author | 孙俊静 顾幸生 |
| AuthorAffiliation | 华东理工大学能源化工过程智能制造教育部重点实验室,上海 200237 |
| AuthorAffiliation_xml | – name: 华东理工大学能源化工过程智能制造教育部重点实验室,上海 200237 |
| Author_FL | GU Xingsheng SUN Junjing |
| Author_FL_xml | – sequence: 1 fullname: SUN Junjing – sequence: 2 fullname: GU Xingsheng |
| Author_xml | – sequence: 1 fullname: 孙俊静 – sequence: 2 fullname: 顾幸生 |
| BookMark | eNo9j8tKw0AYhWdRwap9DBcuEv9_LulkKaVeoOBG12UyndTWkoJB7ANU0IIWF7qoRTfeNlJBUUgpvoyT1LewoLg6cD44H2eB5KJ2ZAhZRnCRIxOrTVdH-w0XATyHgQSXAqVIKQPAHMn_9_OkEMeNAGZUSPQwT8r2NvlKztPXp7Tbt73rdJjYk3d7N7AviU0e7NlH9jjK7m-ycT-bXGTjYTboTidv6elnenn8PRhOR7306nmJzIWqFZvCXy6S3fXyTmnTqWxvbJXWKk6MwKmjmJRc1zwllR8YNOBTYExqPzTU48Jo0EWuGQ-ZoAi-VkwgCFZUUhg_8BlbJCu_u0cqClVUrzbbhwfRzFjdq7XqtU4nmB3nQAEp-wH1pWqz |
| ClassificationCodes | TP391 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.14135/j.cnki.1006-3080.20221223001 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitle_FL | Bearing Fault Diagnosis Based on Multi-Scale Convolutional Neural Network of Attention Mechanism |
| EndPage | 256 |
| ExternalDocumentID | hdlgdxxb202402012 |
| GrantInformation_xml | – fundername: (国家自然科学基金); (国家自然科学基金) funderid: (国家自然科学基金); (国家自然科学基金) |
| GroupedDBID | -02 2B. 4A8 92I 93N ALMA_UNASSIGNED_HOLDINGS CCEZO CDRFL P2P PSX TCJ U1G U5L UY8 |
| ID | FETCH-LOGICAL-s1042-a3884cd6a8a9be1e0920338c9fe2645ec0c74c34f352109ca3510537a85e9b933 |
| ISSN | 1006-3080 |
| IngestDate | Thu May 29 03:59:03 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | 注意力机制 fault diagnosis 卷积神经网络 BEGAN 故障诊断 attention mechanism convolutional neural network empty convolution 空洞卷积 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1042-a3884cd6a8a9be1e0920338c9fe2645ec0c74c34f352109ca3510537a85e9b933 |
| PageCount | 10 |
| ParticipantIDs | wanfang_journals_hdlgdxxb202402012 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-05-01 |
| PublicationDateYYYYMMDD | 2024-05-01 |
| PublicationDate_xml | – month: 05 year: 2024 text: 2024-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 华东理工大学学报（自然科学版） |
| PublicationTitle_FL | Journal of East China University of Science and Technology(Natural Science Edition) |
| PublicationYear | 2024 |
| Publisher | 华东理工大学能源化工过程智能制造教育部重点实验室,上海 200237 |
| Publisher_xml | – name: 华东理工大学能源化工过程智能制造教育部重点实验室,上海 200237 |
| SSID | ssib002258161 ssib001104923 ssib057620135 ssib035757162 ssib036434644 ssib006703735 ssib000947709 ssib006595864 ssib051370438 ssib023167207 ssib001050798 ssj0039901 |
| Score | 2.3751698 |
| Snippet | TP391; 提出了基于注意力机制的多尺度卷积神经网络(Multi-scale and Attentive Convolutional Neural... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 247 |
| Title | 基于注意力机制多尺度卷积神经网络的轴承故障诊断 |
| URI | https://d.wanfangdata.com.cn/periodical/hdlgdxxb202402012 |
| Volume | 50 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LaxRBEB5CAqIH8YlvgtjHjTPT8-g-zuzOEsR4MYHcwrw28cEKJoGQcwQNaPCghxj04usiERSFDcE_4-7Gf-FXPb2zEyIShaXp7a6u_qqqd7qrt7vGMK65kltuy3NqZhYnNQyKtIZVglPLzDSXmekjpQvOU7e8yRnnxqw7OzJaq5xaWl5KJtLVP94r-R-rogx2pVuy_2DZkikKkId9kcLCSA9lYxa5TDZZGLDIoVRELPJYyFkgKCOwTmwSjQiYDKlE1hUxSgQLPcoEDpOqJDR1FdJAVYkGC30W-SzAp6ky6C6iTBgqzsg0mLR0CZgjA27oNxJUFToKhmRhU_UOni6LJNEQsSC2wEZVHtOBIe8ORQMAkgiiiQFzkwmFLVRgCvyAR5mGhq0zHnEmGuinTvKiO4FWAfEBQhJfiUb4y1Y-oSXiolW5S6JJpFRwCtSQg0qGJJIFFgsjhU8SaEIM_TarWysYoeVBRvVj-F9JIQ4nJZPFA6InPnXS5LCVUFgLI4K-GANSGbpsXg4GSadeAlNbikQFjc1CW1UVg0oSN6AlRdkkJeGJ1KiQpFsAKEqA1q5riQoTh4SKIljaRfwdPRWa6lRk8Z6twVxZBAnWzwS7OvEVcVP1GsougsUfmJ6xYnLV_Jy2792ZKHuYgPKxhII3rLW_PwL6QnZ_PltZSchE8G7oneJjNrxCzMNjQWPq5u2Kv-D4--IRmnB3KvsJWOs61f0CTGbCqlzspuCa1dcVeJgP_aE_YVPYCHu4X8Lh6wwisKnvWN473nC97Frcp3_ay-9YecDlKv1zTn9Kq-MYWhFHDDZQ0_W_KUndMGy34vZ8ZTE8fcI4rr3Y8aB4JJ00RlYXThnHKrFNTxtR903nZ-dZ78vH3tpGd_1Vb6vTffyt-3az-7nT7bzvPv3e_7Ddf_e6v7PR333e39nqb67t7X7tPfnRe_Ho1-bW3vZ67-WnM8ZMM5quT9b0O1tqixbd9Iu5EE6aebGIZZJbuSltk3ORylYO18vNUzP1nZQ7LTh-linTmJOHx_1YuLlMJOdnjdH2g3Z-zhhP8yyFkWM79hOwTBM7a1m562Y8s4QZp-eNq1oJc_qZvDh3YKhcOAzRRePo8Od_yRhdericX4avsZRc0SPsN9DL2FA |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6%E5%A4%9A%E5%B0%BA%E5%BA%A6%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E8%BD%B4%E6%89%BF%E6%95%85%E9%9A%9C%E8%AF%8A%E6%96%AD&rft.jtitle=%E5%8D%8E%E4%B8%9C%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%87%AA%E7%84%B6%E7%A7%91%E5%AD%A6%E7%89%88%EF%BC%89&rft.au=%E5%AD%99%E4%BF%8A%E9%9D%99&rft.au=%E9%A1%BE%E5%B9%B8%E7%94%9F&rft.date=2024-05-01&rft.pub=%E5%8D%8E%E4%B8%9C%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E8%83%BD%E6%BA%90%E5%8C%96%E5%B7%A5%E8%BF%87%E7%A8%8B%E6%99%BA%E8%83%BD%E5%88%B6%E9%80%A0%E6%95%99%E8%82%B2%E9%83%A8%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E4%B8%8A%E6%B5%B7+200237&rft.issn=1006-3080&rft.volume=50&rft.issue=2&rft.spage=247&rft.epage=256&rft_id=info:doi/10.14135%2Fj.cnki.1006-3080.20221223001&rft.externalDocID=hdlgdxxb202402012 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fhdlgdxxb%2Fhdlgdxxb.jpg |