基于无监督深度模型迁移的滚动轴承寿命预测方法
针对实际中某种工况滚动轴承带标签振动数据获取困难,健康指标难以构建及寿命预测误差大的问题,提出一种基于无监督深度模型迁移的滚动轴承剩余使用寿命(Remaining useful life,RUL)预测方法.该方法首先对滚动轴承全寿命周期振动数据提取均方根(Root mean square,RMS)特征,并引入新的自下而上(Bottom-up,BUP)时间序列分割算法将特征序列分割为正常期、退化期和衰退期3种状态;对振动信号经快速傅里叶(Fast Fourier transform,FFT)变换后的幅值序列进行状态信息标记,并将其输入到新增卷积层的全卷积神经网络(Full convolution...
Saved in:
| Published in | 自动化学报 Vol. 49; no. 12; pp. 2627 - 2638 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
哈尔滨理工大学测控技术与通信工程学院 哈尔滨 150000 中国%海南师范大学物理与电子工程学院 海口 571158 中国%白俄罗斯国立大学 明斯克 220030 白俄罗斯
01.12.2023
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0254-4156 |
| DOI | 10.16383/j.aas.c200890 |
Cover
| Abstract | 针对实际中某种工况滚动轴承带标签振动数据获取困难,健康指标难以构建及寿命预测误差大的问题,提出一种基于无监督深度模型迁移的滚动轴承剩余使用寿命(Remaining useful life,RUL)预测方法.该方法首先对滚动轴承全寿命周期振动数据提取均方根(Root mean square,RMS)特征,并引入新的自下而上(Bottom-up,BUP)时间序列分割算法将特征序列分割为正常期、退化期和衰退期3种状态;对振动信号经快速傅里叶(Fast Fourier transform,FFT)变换后的幅值序列进行状态信息标记,并将其输入到新增卷积层的全卷积神经网络(Full convolutional neural network,FCN)中,提取深层特征,得到预训练模型;提出将预训练模型的梯度作为一种"特征"与传统预训练模型特征一起参与目标域网络训练过程,从而得到状态识别模型;利用状态概率估计法结合状态识别模型建立滚动轴承寿命预测模型.实验验证所提方法无需构建健康指标,可实现无监督条件下不同工况滚动轴承剩余寿命预测,并获得较好的效果. |
|---|---|
| AbstractList | 针对实际中某种工况滚动轴承带标签振动数据获取困难,健康指标难以构建及寿命预测误差大的问题,提出一种基于无监督深度模型迁移的滚动轴承剩余使用寿命(Remaining useful life,RUL)预测方法.该方法首先对滚动轴承全寿命周期振动数据提取均方根(Root mean square,RMS)特征,并引入新的自下而上(Bottom-up,BUP)时间序列分割算法将特征序列分割为正常期、退化期和衰退期3种状态;对振动信号经快速傅里叶(Fast Fourier transform,FFT)变换后的幅值序列进行状态信息标记,并将其输入到新增卷积层的全卷积神经网络(Full convolutional neural network,FCN)中,提取深层特征,得到预训练模型;提出将预训练模型的梯度作为一种"特征"与传统预训练模型特征一起参与目标域网络训练过程,从而得到状态识别模型;利用状态概率估计法结合状态识别模型建立滚动轴承寿命预测模型.实验验证所提方法无需构建健康指标,可实现无监督条件下不同工况滚动轴承剩余寿命预测,并获得较好的效果. |
| Abstract_FL | In order to solve the problems such as difficulty in acquiring labeled vibration data of rolling bearings under certain working condition in practice,difficulty in constructing health indicators and large error in life predic-tion of rolling bearings,a method of remaining useful life(RUL)prediction of rolling bearings is proposed based on unsupervised deep model transfer.Firstly,the root mean square(RMS)features of the vibration data of the full life cycle of the rolling bearings are extracted,and a new bottom-up(BUP)time series segmentation algorithm is intro-duced to divide the feature sequence into three states:Normal period,degradation period and recession period.Mark the state information of the amplitude sequence of the vibration signal after the fast Fourier transform(FFT),and input it into the fully convolutional neural network(FCN)of the newly added convolutional layer to extract deep features,and the pre-trained model can be obtained.The gradient of the pre-trained model is proposed and used as a"feature"to participate in the target domain network training process together with the traditional pre-trained model features,and the state identification model is obtained.Using state probability estimation method combined with state identification model,life prediction model of rolling bearing can be established.Experiments verify that,without establishing health indicators,the proposed method can realize remaining useful life prediction of rolling bearings for different working conditions under unsupervised conditions,and achieve better results. |
| Author | 王庆岩 王玉静 邢颖怡 MIKULOVICH Vladimir Ivanovich 康守强 谢金宝 |
| AuthorAffiliation | 哈尔滨理工大学测控技术与通信工程学院 哈尔滨 150000 中国%海南师范大学物理与电子工程学院 海口 571158 中国%白俄罗斯国立大学 明斯克 220030 白俄罗斯 |
| AuthorAffiliation_xml | – name: 哈尔滨理工大学测控技术与通信工程学院 哈尔滨 150000 中国%海南师范大学物理与电子工程学院 海口 571158 中国%白俄罗斯国立大学 明斯克 220030 白俄罗斯 |
| Author_FL | KANG Shou-Qiang XING Ying-Yi WANG Yu-Jing XIE Jin-Bao MIKULOVICH Vladimir Ivanovich WANG Qing-Yan |
| Author_FL_xml | – sequence: 1 fullname: KANG Shou-Qiang – sequence: 2 fullname: XING Ying-Yi – sequence: 3 fullname: WANG Yu-Jing – sequence: 4 fullname: WANG Qing-Yan – sequence: 5 fullname: XIE Jin-Bao – sequence: 6 fullname: MIKULOVICH Vladimir Ivanovich |
| Author_xml | – sequence: 1 fullname: 康守强 – sequence: 2 fullname: 邢颖怡 – sequence: 3 fullname: 王玉静 – sequence: 4 fullname: 王庆岩 – sequence: 5 fullname: 谢金宝 – sequence: 6 fullname: MIKULOVICH Vladimir Ivanovich |
| BookMark | eNotzT1Lw0AYwPEbKlhrVz-CW-Jzz-Uul1GLb1Bw0blccolaJAWDKG5CFy0IHapQ8R20m4iKmFLyZcylfgsLOv23_2-GlOJWHBIyR8Gmgkm20LSVSuwAAaQHJVIG5I7lUC6mSTVJdn0ASgE9SstkKb9Nv9Nzc3lXXHWL60fz-ZqnT2Zwn990xtlJ8Tws-m0z7Odng_Ho3Zxm-UuWd0c_D23z0TEXX-atN0umIrWXhNX_VsjWyvJmbc2qb6yu1xbrVkKBCosLqQPqhIorVzPlBlwi9xkGKmICOdUggUlfRU4gtQ8eIDJPeNwVIWoHJauQ-b_voYojFW83mq2D_XgiNo71zpGPgIziRGK_jM5kmw |
| 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 | 10.16383/j.aas.c200890 |
| 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 | Rolling Bearing Life Prediction Based on Unsupervised Deep Model Transfer |
| EndPage | 2638 |
| ExternalDocumentID | zdhxb202312016 |
| GroupedDBID | --K -0Y .~1 0R~ 1B1 1~. 1~5 2B. 4.4 457 4A8 4G. 5GY 5VS 5XA 5XJ 7-5 71M 8P~ 92H 92I 93N AAIKJ AALRI AAQFI AAXUO ABJNI ABWVN ACGFS ACRPL ADEZE ADNMO ADTZH AECPX AEKER AFTJW AGHFR AGYEJ AITUG ALMA_UNASSIGNED_HOLDINGS BLXMC CCEZO CS3 CUBFJ CW9 EBS EJD EO8 EO9 EP2 EP3 FDB FEDTE FNPLU GBLVA HVGLF HZ~ IHE J1W JJJVA M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PSX Q38 ROL RPZ SDF SDG SES TCJ TGT U1G U5S |
| ID | FETCH-LOGICAL-s1016-568dc14ea5a7d3a7c5825b32caf36251d08038baf4c8db090223969576e2d4283 |
| ISSN | 0254-4156 |
| IngestDate | Thu May 29 04:10:31 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Keywords | state identification 滚动轴承 model transfer different working conditions remaining useful life(RUL) 剩余使用寿命 模型迁移 不同工况 状态识别 Rolling bearing |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1016-568dc14ea5a7d3a7c5825b32caf36251d08038baf4c8db090223969576e2d4283 |
| PageCount | 12 |
| ParticipantIDs | wanfang_journals_zdhxb202312016 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-12-01 |
| PublicationDateYYYYMMDD | 2023-12-01 |
| PublicationDate_xml | – month: 12 year: 2023 text: 2023-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 自动化学报 |
| PublicationTitle_FL | Acta Automatica Sinica |
| PublicationYear | 2023 |
| Publisher | 哈尔滨理工大学测控技术与通信工程学院 哈尔滨 150000 中国%海南师范大学物理与电子工程学院 海口 571158 中国%白俄罗斯国立大学 明斯克 220030 白俄罗斯 |
| Publisher_xml | – name: 哈尔滨理工大学测控技术与通信工程学院 哈尔滨 150000 中国%海南师范大学物理与电子工程学院 海口 571158 中国%白俄罗斯国立大学 明斯克 220030 白俄罗斯 |
| SSID | ssib001102911 ssib006576350 ssib051375349 ssib007293330 ssj0059721 ssib007290157 ssib023646446 ssib005904210 |
| Score | 2.4680862 |
| Snippet | 针对实际中某种工况滚动轴承带标签振动数据获取困难,健康指标难以构建及寿命预测误差大的问题,提出一种基于无监督深度模型迁移的滚动轴承剩余使用寿命(Remaining useful life,RUL)预测方法.该方法首先对滚动轴承全寿命周期振动数据提取均方根(Root mean... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 2627 |
| Title | 基于无监督深度模型迁移的滚动轴承寿命预测方法 |
| URI | https://d.wanfangdata.com.cn/periodical/zdhxb202312016 |
| Volume | 49 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Na9RANNT2ogfxE7_twTktsbszmczMMbObtYh6aqW3kq-1pxVsC9Kb0IsWhB5UqPgN2puIithS-mfcbP0XvjeZdNNabfUSJjPv-70kb4bJG8e5whXP4iSOXRGxjusxT7gRy1KXQXIiMqk6HbOYc_OWPz7pXZ_iU0MjY5VdS_Nz8dVkYc__Sv7Hq9AHfsW_ZP_Bs9tEoQPa4F-4gofheiAfk5AT1SY6IKGHVxmS0CdKkKBOQkGUJqphGi0SMBzSgugGYgFw4GNPIElgelRIpCahJLoN2SViBQCsDTpQ9gy6xjYAywAREbhFtBmSChFhKGjbBrCG0VCRgJbo3LAACaGtTA8jxeGXZX6MNCWwrnKBRhNRkHjLio1DvAwWqxAohyCgh0HSTTJYhEA5JEVRCoFUQaUOyg9ABBpQ6rKhEBZMp9QeIIajNEJpoKuqqyeU7dqJYszBSrnqRJXWRPXAvvWSEmjOjRIeWr-q8LbtgD8OGROA_GjNJhodI0CaCFBm90oRE23rXUtZIMdCfEsZNESD1P4iYq2Bx1nUa5YFICKsRu9SbmUrbC9bGHxIQBpKEj0n2V4aCbRvoCrqb8svkLnmFhhGDyZ_VQ5Qm9W4gHmI_JPYAhExQI2VMEAF3iphAzRoD-CRry757lDE8FWyfPJKNIneqlHckol2259X5XtMuefiekc1eSjq7ZYvSVpNBfyi6IVNK6lfVDH6LWWBfmZyliiCdxFuRyrOz91VBn4hnbkfYwQ3IGX3DzkjVAjclzJyTd-4HQxmQDBhUJVPNlfwVa5k-D7HCpSDe4H7KCobH-CescGKAh4v4VdWjHiDCc5wxaZIdjkW_zLL2NY2ti4uKjW2QyXzU2S3E3XvVPL3iWPOUTvxHg2Kt-hxZ2hh5oRzpFKO9aSje6_Wfqw9zp-97j9f7r94l3_71Ft7n6--6b1c2tp80P-w3l9ZzNdXeo9Wtza-5A83ex83e8sbP98u5l-X8qff889PTjmT7XCiOe7aM2bcWVy3dLkv06ThZRGPRMoikXBJecxoEnUgteeNFGbUTMZRx0tkGuMmdsqUr8CKGU2xWOVpZ7h7t5udcUajNBHgk8j3sSAXi-KM0yzKaN2LOwll3lnnsrXAtP2GzE7v9Oq5fSHOO4cHb7ELzvDcvfnsIsyK5uJLNhJ-AUKh-B8 |
| linkProvider | Elsevier |
| 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%97%A0%E7%9B%91%E7%9D%A3%E6%B7%B1%E5%BA%A6%E6%A8%A1%E5%9E%8B%E8%BF%81%E7%A7%BB%E7%9A%84%E6%BB%9A%E5%8A%A8%E8%BD%B4%E6%89%BF%E5%AF%BF%E5%91%BD%E9%A2%84%E6%B5%8B%E6%96%B9%E6%B3%95&rft.jtitle=%E8%87%AA%E5%8A%A8%E5%8C%96%E5%AD%A6%E6%8A%A5&rft.au=%E5%BA%B7%E5%AE%88%E5%BC%BA&rft.au=%E9%82%A2%E9%A2%96%E6%80%A1&rft.au=%E7%8E%8B%E7%8E%89%E9%9D%99&rft.au=%E7%8E%8B%E5%BA%86%E5%B2%A9&rft.date=2023-12-01&rft.pub=%E5%93%88%E5%B0%94%E6%BB%A8%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E6%B5%8B%E6%8E%A7%E6%8A%80%E6%9C%AF%E4%B8%8E%E9%80%9A%E4%BF%A1%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2+%E5%93%88%E5%B0%94%E6%BB%A8+150000+%E4%B8%AD%E5%9B%BD%25%E6%B5%B7%E5%8D%97%E5%B8%88%E8%8C%83%E5%A4%A7%E5%AD%A6%E7%89%A9%E7%90%86%E4%B8%8E%E7%94%B5%E5%AD%90%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2+%E6%B5%B7%E5%8F%A3+571158+%E4%B8%AD%E5%9B%BD%25%E7%99%BD%E4%BF%84%E7%BD%97%E6%96%AF%E5%9B%BD%E7%AB%8B%E5%A4%A7%E5%AD%A6+%E6%98%8E%E6%96%AF%E5%85%8B+220030+%E7%99%BD%E4%BF%84%E7%BD%97%E6%96%AF&rft.issn=0254-4156&rft.volume=49&rft.issue=12&rft.spage=2627&rft.epage=2638&rft_id=info:doi/10.16383%2Fj.aas.c200890&rft.externalDocID=zdhxb202312016 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzdhxb%2Fzdhxb.jpg |