Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors. Zhuang, J., Jia, M., Ding, Y., & Ding, P. Reliability Engineering & System Safety, 216:107946, December, 2021. ![Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Many data-driven models normally assume that the training and test data are independent and identically distributed to predict the remaining useful life (RUL) of industrial machines. However, different failure models caused by variable failure behaviors may lead to a domain shift. Meanwhile, conventional methods lack comprehensive attention to temporal information, resulting in a limitation. To handle the aforementioned challenges, a transferable cross-domain approach for RUL estimation is proposed. The hidden features are extracted adaptively by a temporal convolution network in which residual self-attention is able to fully consider the contextual degradation information. Furthermore, a new cross-domain adaption architecture with the contrastive loss and multi-kernel maximum mean discrepancy is designed to learn the domain invariant features. The effectiveness and superiority of the proposed method are proved by the case study on IEEE PHM challenge 2012 bearing dataset and the comparison with other methods.
@article{zhuang_temporal_2021,
title = {Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors},
volume = {216},
issn = {0951-8320},
url = {https://www.sciencedirect.com/science/article/pii/S0951832021004592},
doi = {10.1016/j.ress.2021.107946},
abstract = {Many data-driven models normally assume that the training and test data are independent and identically distributed to predict the remaining useful life (RUL) of industrial machines. However, different failure models caused by variable failure behaviors may lead to a domain shift. Meanwhile, conventional methods lack comprehensive attention to temporal information, resulting in a limitation. To handle the aforementioned challenges, a transferable cross-domain approach for RUL estimation is proposed. The hidden features are extracted adaptively by a temporal convolution network in which residual self-attention is able to fully consider the contextual degradation information. Furthermore, a new cross-domain adaption architecture with the contrastive loss and multi-kernel maximum mean discrepancy is designed to learn the domain invariant features. The effectiveness and superiority of the proposed method are proved by the case study on IEEE PHM challenge 2012 bearing dataset and the comparison with other methods.},
language = {en},
urldate = {2021-10-02},
journal = {Reliability Engineering \& System Safety},
author = {Zhuang, Jichao and Jia, Minping and Ding, Yifei and Ding, Peng},
month = dec,
year = {2021},
keywords = {Cross-domain adaptation, Remaining useful life estimation, Rolling bearing, Temporal convolutional network, Transfer learning, Variable failure behaviors},
pages = {107946},
}
Downloads: 0
{"_id":"vcXQSWd4BkwsRDupq","bibbaseid":"zhuang-jia-ding-ding-temporalconvolutionbasedtransferablecrossdomainadaptationapproachforremainingusefullifeestimationundervariablefailurebehaviors-2021","author_short":["Zhuang, J.","Jia, M.","Ding, Y.","Ding, P."],"bibdata":{"bibtype":"article","type":"article","title":"Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors","volume":"216","issn":"0951-8320","url":"https://www.sciencedirect.com/science/article/pii/S0951832021004592","doi":"10.1016/j.ress.2021.107946","abstract":"Many data-driven models normally assume that the training and test data are independent and identically distributed to predict the remaining useful life (RUL) of industrial machines. However, different failure models caused by variable failure behaviors may lead to a domain shift. Meanwhile, conventional methods lack comprehensive attention to temporal information, resulting in a limitation. To handle the aforementioned challenges, a transferable cross-domain approach for RUL estimation is proposed. The hidden features are extracted adaptively by a temporal convolution network in which residual self-attention is able to fully consider the contextual degradation information. Furthermore, a new cross-domain adaption architecture with the contrastive loss and multi-kernel maximum mean discrepancy is designed to learn the domain invariant features. The effectiveness and superiority of the proposed method are proved by the case study on IEEE PHM challenge 2012 bearing dataset and the comparison with other methods.","language":"en","urldate":"2021-10-02","journal":"Reliability Engineering & System Safety","author":[{"propositions":[],"lastnames":["Zhuang"],"firstnames":["Jichao"],"suffixes":[]},{"propositions":[],"lastnames":["Jia"],"firstnames":["Minping"],"suffixes":[]},{"propositions":[],"lastnames":["Ding"],"firstnames":["Yifei"],"suffixes":[]},{"propositions":[],"lastnames":["Ding"],"firstnames":["Peng"],"suffixes":[]}],"month":"December","year":"2021","keywords":"Cross-domain adaptation, Remaining useful life estimation, Rolling bearing, Temporal convolutional network, Transfer learning, Variable failure behaviors","pages":"107946","bibtex":"@article{zhuang_temporal_2021,\n\ttitle = {Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors},\n\tvolume = {216},\n\tissn = {0951-8320},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0951832021004592},\n\tdoi = {10.1016/j.ress.2021.107946},\n\tabstract = {Many data-driven models normally assume that the training and test data are independent and identically distributed to predict the remaining useful life (RUL) of industrial machines. However, different failure models caused by variable failure behaviors may lead to a domain shift. Meanwhile, conventional methods lack comprehensive attention to temporal information, resulting in a limitation. To handle the aforementioned challenges, a transferable cross-domain approach for RUL estimation is proposed. The hidden features are extracted adaptively by a temporal convolution network in which residual self-attention is able to fully consider the contextual degradation information. Furthermore, a new cross-domain adaption architecture with the contrastive loss and multi-kernel maximum mean discrepancy is designed to learn the domain invariant features. The effectiveness and superiority of the proposed method are proved by the case study on IEEE PHM challenge 2012 bearing dataset and the comparison with other methods.},\n\tlanguage = {en},\n\turldate = {2021-10-02},\n\tjournal = {Reliability Engineering \\& System Safety},\n\tauthor = {Zhuang, Jichao and Jia, Minping and Ding, Yifei and Ding, Peng},\n\tmonth = dec,\n\tyear = {2021},\n\tkeywords = {Cross-domain adaptation, Remaining useful life estimation, Rolling bearing, Temporal convolutional network, Transfer learning, Variable failure behaviors},\n\tpages = {107946},\n}\n\n","author_short":["Zhuang, J.","Jia, M.","Ding, Y.","Ding, P."],"key":"zhuang_temporal_2021","id":"zhuang_temporal_2021","bibbaseid":"zhuang-jia-ding-ding-temporalconvolutionbasedtransferablecrossdomainadaptationapproachforremainingusefullifeestimationundervariablefailurebehaviors-2021","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0951832021004592"},"keyword":["Cross-domain adaptation","Remaining useful life estimation","Rolling bearing","Temporal convolutional network","Transfer learning","Variable failure behaviors"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["SZvSgtLYdBsPSQ3NM","iwKepCrWBps7ojhDx"],"keywords":["cross-domain adaptation","remaining useful life estimation","rolling bearing","temporal convolutional network","transfer learning","variable failure behaviors"],"search_terms":["temporal","convolution","based","transferable","cross","domain","adaptation","approach","remaining","useful","life","estimation","under","variable","failure","behaviors","zhuang","jia","ding","ding"],"title":"Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors","year":2021}