{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T01:12:52Z","timestamp":1774746772924,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"national natural science foundation of china and civil aviation administration of china joint funded project","award":["U1733108"],"award-info":[{"award-number":["U1733108"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Convolution neural network (CNN) has been widely used in the field of remaining useful life (RUL) prediction. However, the CNN-based RUL prediction methods have some limitations. The receptive field of CNN is limited and easy to happen gradient vanishing problem when the network is too deep. The contribution differences of different channels and different time steps to RUL prediction are not considered, and only use deep learning features or handcrafted statistical features for prediction. These limitations can lead to inaccurate prediction results. To solve these problems, this paper proposes an RUL prediction method based on multi-layer self-attention (MLSA) and temporal convolution network (TCN). The TCN is used to extract deep learning features. Dilated convolution and residual connection are adopted in TCN structure. Dilated convolution is an efficient way to widen receptive field, and the residual structure can avoid the gradient vanishing problem. Besides, we propose a feature fusion method to fuse deep learning features and statistical features. And the MLSA is designed to adaptively assign feature weights. Finally, the turbofan engine dataset is used to verify the proposed method. Experimental results indicate the effectiveness of the proposed method.<\/jats:p>","DOI":"10.1007\/s40747-021-00606-4","type":"journal-article","created":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T15:02:50Z","timestamp":1640012570000},"page":"1409-1424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Machine remaining life prediction based on multi-layer self-attention and temporal convolution network"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7310-0921","authenticated-orcid":false,"given":"Zhiwu","family":"Shang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3368-6112","authenticated-orcid":false,"given":"Baoren","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0804-5791","authenticated-orcid":false,"given":"Wanxiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shiqi","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,20]]},"reference":[{"key":"606_CR1","unstructured":"Babu G, Zhao P, Li X (2016) Deep convolutional neural network based regression approach for estimation of remaining useful life. In: International conference on database systems for advanced applications."},{"key":"606_CR2","unstructured":"Bai S, Kolter J Z, Koltun V (2018) An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv:1803.01271v2"},{"key":"606_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105919","volume":"86","author":"Y Chen","year":"2020","unstructured":"Chen Y, Peng G, Zhu Z, Li S (2020) A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Appl Soft Comput 86:105919. https:\/\/doi.org\/10.1016\/j.asoc.2019.105919","journal-title":"Appl Soft Comput"},{"issue":"3","key":"606_CR4","doi-asserted-by":"publisher","first-page":"2521","DOI":"10.1109\/tie.2020.2972443","volume":"68","author":"Z Chen","year":"2021","unstructured":"Chen Z, Wu M, Zhao R, Guretno F, Yan R, Li X (2021) Machine remaining useful life prediction via an attention-based deep learning approach. IEEE Trans Ind Electron 68(3):2521\u20132531. https:\/\/doi.org\/10.1109\/tie.2020.2972443","journal-title":"IEEE Trans Ind Electron"},{"issue":"3","key":"606_CR5","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/tmech.2020.2971503","volume":"25","author":"C Cheng","year":"2020","unstructured":"Cheng C, Ma G, Zhang Y, Sun M, Teng F, Ding H, Yuan Y (2020) A deep learning-based remaining useful life prediction approach for bearings. IEEE\/ASME Trans Mechatron 25(3):1243\u20131254. https:\/\/doi.org\/10.1109\/tmech.2020.2971503","journal-title":"IEEE\/ASME Trans Mechatron"},{"key":"606_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2020.103298","author":"J Dalzochio","year":"2020","unstructured":"Dalzochio J, Kunst R, Pignaton E, Binotto A, Sanyal S, Favilla J, Barbosa J (2020) Machine learning and reasoning for predictive maintenance in Industry 40: current status and challenges. Comput Ind. https:\/\/doi.org\/10.1016\/j.compind.2020.103298","journal-title":"Comput Ind"},{"issue":"3","key":"606_CR7","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1109\/TIP.2017.2778563","volume":"27","author":"W Du","year":"2018","unstructured":"Du W, Wang Y, Qiao Y (2018) Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans Image Process 27(3):1347\u20131360. https:\/\/doi.org\/10.1109\/TIP.2017.2778563","journal-title":"IEEE Trans Image Process"},{"key":"606_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2021.108114","author":"E Florian","year":"2021","unstructured":"Florian E, Sgarbossa F, Zennaro I (2021) Machine learning-based predictive maintenance: a cost-oriented model for implementation. Int J Prod Econ. https:\/\/doi.org\/10.1016\/j.ijpe.2021.108114","journal-title":"Int J Prod Econ"},{"key":"606_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.107788","author":"M Hou","year":"2020","unstructured":"Hou M, Pi D, Li B (2020) Similarity-based deep learning approach for remaining useful life prediction. Measurement. https:\/\/doi.org\/10.1016\/j.measurement.2020.107788","journal-title":"Measurement"},{"issue":"3","key":"606_CR10","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1109\/tie.2016.2623260","volume":"64","author":"R Khelif","year":"2017","unstructured":"Khelif R, Chebel-Morello B, Malinowski S, Laajili E, Fnaiech F, Zerhouni N (2017) Direct remaining useful life estimation based on support vector regression. IEEE Trans Ind Electron 64(3):2276\u20132285. https:\/\/doi.org\/10.1109\/tie.2016.2623260","journal-title":"IEEE Trans Ind Electron"},{"issue":"7553","key":"606_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444. https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"606_CR12","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1016\/j.ymssp.2017.11.016","volume":"104","author":"Y Lei","year":"2018","unstructured":"Lei Y, Li N, Guo L, Li N, Yan T, Lin J (2018) Machinery health prognostics: a systematic review from data acquisition to RUL prediction. Mech Syst Signal Process 104:799\u2013834. https:\/\/doi.org\/10.1016\/j.ymssp.2017.11.016","journal-title":"Mech Syst Signal Process"},{"key":"606_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106113","volume":"89","author":"H Li","year":"2020","unstructured":"Li H, Zhao W, Zhang Y, Zio E (2020) Remaining useful life prediction using multi-scale deep convolutional neural network. Appl Soft Comput 89:106113. https:\/\/doi.org\/10.1016\/j.asoc.2020.106113","journal-title":"Appl Soft Comput"},{"key":"606_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104279","author":"W Li","year":"2021","unstructured":"Li W, Shang Z, Gao M, Qian S, Zhang B, Zhang J (2021) A novel deep autoencoder and hyperparametric adaptive learning for imbalance intelligent fault diagnosis of rotating machinery. Eng Appl Artif Intell. https:\/\/doi.org\/10.1016\/j.engappai.2021.104279","journal-title":"Eng Appl Artif Intell"},{"key":"606_CR15","doi-asserted-by":"crossref","unstructured":"Li Y, Shan X, Zhao W, Wang G (2019) A LS-SVM based approach for turbine engines prognostics using sensor data. In: 2019 IEEE International Conference on Industrial Technology","DOI":"10.1109\/ICIT.2019.8755209"},{"key":"606_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpowsour.2021.230063","author":"M Lin","year":"2021","unstructured":"Lin M, Zeng X, Wu J (2021) State of health estimation of lithium-ion battery based on an adaptive tunable hybrid radial basis function network. J Power Sources. https:\/\/doi.org\/10.1016\/j.jpowsour.2021.230063","journal-title":"J Power Sources"},{"key":"606_CR17","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","volume":"452","author":"Z Niu","year":"2021","unstructured":"Niu Z, Zhong G, Yu H (2021) A review on the attention mechanism of deep learning. Neurocomputing 452:48\u201362. https:\/\/doi.org\/10.1016\/j.neucom.2021.03.091","journal-title":"Neurocomputing"},{"key":"606_CR18","doi-asserted-by":"publisher","first-page":"13041","DOI":"10.1109\/access.2018.2804930","volume":"6","author":"L Ren","year":"2018","unstructured":"Ren L, Sun Y, Wang H, Zhang L (2018) Prediction of bearing remaining useful life with deep convolution neural network. IEEE Access 6:13041\u201313049. https:\/\/doi.org\/10.1109\/access.2018.2804930","journal-title":"IEEE Access"},{"key":"606_CR19","unstructured":"Saxena A, Goebel K (2008) Turbofan engine degradation simulation data set. NASA Ames Prognostics Data Repository (http:\/\/ti.arc.nasa.gov\/project\/prognostic-data-repository), NASA Ames Research Center, Moffett Field, CA"},{"key":"606_CR20","doi-asserted-by":"crossref","unstructured":"Saxena A, Goebel K, Simon D, Eklund N (2008) Damage propagation modeling for aircraft engine run-to-failure simulation. In: 2008 International Conference on Prognostics and Health Management.","DOI":"10.1109\/PHM.2008.4711414"},{"issue":"11","key":"606_CR21","doi-asserted-by":"publisher","first-page":"5139","DOI":"10.1007\/s12206-018-1012-0","volume":"32","author":"Z Shang","year":"2018","unstructured":"Shang Z, Liao X, Geng R, Gao M, Liu X (2018) Fault diagnosis method of rolling bearing based on deep belief network. J Mech Sci Technol 32(11):5139\u20135145. https:\/\/doi.org\/10.1007\/s12206-018-1012-0","journal-title":"J Mech Sci Technol"},{"key":"606_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s10033-021-00580-5","author":"Z Shang","year":"2021","unstructured":"Shang Z, Li W, Gao M, Liu X, Yu Y (2021) An intelligent fault diagnosis method of multi-scale deep feature fusion based on information entropy. Chin J Mech Eng. https:\/\/doi.org\/10.1186\/s10033-021-00580-5","journal-title":"Chin J Mech Eng"},{"issue":"1","key":"606_CR23","doi-asserted-by":"publisher","first-page":"230","DOI":"10.23940\/ijpe.19.01.p23.230240","volume":"15","author":"Z Shang","year":"2019","unstructured":"Shang Z, Liu X, Liao X, Geng R, Gao M, Yun J (2019) Rolling bearing fault diagnosis method based on EEMD and GBDBN. Int J Perform Eng 15(1):230\u2013240. https:\/\/doi.org\/10.23940\/ijpe.19.01.p23.230240","journal-title":"Int J Perform Eng"},{"issue":"12","key":"606_CR24","doi-asserted-by":"publisher","first-page":"9594","DOI":"10.1109\/jiot.2020.3004452","volume":"8","author":"Y Song","year":"2020","unstructured":"Song Y, Gao S, Li Y, Jia L, Li Q, Pang F (2020) Distributed attention-based temporal convolutional network for remaining useful life prediction. IEEE Internet Things J 8(12):9594\u20139602. https:\/\/doi.org\/10.1109\/jiot.2020.3004452","journal-title":"IEEE Internet Things J"},{"key":"606_CR25","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I (2017) Attention Is all you need. arXiv:1706.03762v5"},{"issue":"3","key":"606_CR26","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1007\/s40747-021-00274-4","volume":"7","author":"H Xia","year":"2021","unstructured":"Xia H, Luo Y, Liu Y (2021) Attention neural collaboration filtering based on GRU for recommender systems. Complex Intell Syst 7(3):1367\u20131379. https:\/\/doi.org\/10.1007\/s40747-021-00274-4","journal-title":"Complex Intell Syst"},{"key":"606_CR27","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.ins.2021.04.053","volume":"571","author":"Z Xiao","year":"2021","unstructured":"Xiao Z, Xu X, Xing H, Luo S, Dai P, Zhan D (2021) RTFN: a robust temporal feature network for time series classification. Inf Sci 571:65\u201386. https:\/\/doi.org\/10.1016\/j.ins.2021.04.053","journal-title":"Inf Sci"},{"issue":"12","key":"606_CR28","doi-asserted-by":"publisher","first-page":"14765","DOI":"10.1109\/tvt.2020.3039553","volume":"69","author":"Q Xue","year":"2020","unstructured":"Xue Q, Shen S, Li G, Zhang Y, Chen Z, Liu Y (2020) Remaining useful life prediction for lithium-ion batteries based on capacity estimation and Box-Cox transformation. IEEE Trans Veh Technol 69(12):14765\u201314779. https:\/\/doi.org\/10.1109\/tvt.2020.3039553","journal-title":"IEEE Trans Veh Technol"},{"key":"606_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2020.107378","volume":"152","author":"B Yan","year":"2021","unstructured":"Yan B, Ma X, Huang G, Zhao Y (2021) Two-stage physics-based Wiener process models for online RUL prediction in field vibration data. Mech Syst Signal Process 152:107378. https:\/\/doi.org\/10.1016\/j.ymssp.2020.107378","journal-title":"Mech Syst Signal Process"},{"key":"606_CR30","doi-asserted-by":"crossref","unstructured":"Yang B, Tu Z, Wong D F, Meng F, Chao L S, Zhang T (2018) Modeling localness for self-attention networks.  arXiv:1810.10182","DOI":"10.18653\/v1\/D18-1475"},{"issue":"9","key":"606_CR31","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/0954406220951209","volume":"235","author":"T Zan","year":"2021","unstructured":"Zan T, Liu Z, Wang H, Wang M, Gao X, Pang Z (2021) Prediction of performance deterioration of rolling bearing based on JADE and PSO-SVM. Proc Inst Mech Eng Part C 235(9):1684\u20131697. https:\/\/doi.org\/10.1177\/0954406220951209","journal-title":"Proc Inst Mech Eng Part C"},{"issue":"1","key":"606_CR32","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/tpami.2018.2876404","volume":"42","author":"B Zhang","year":"2020","unstructured":"Zhang B, Xiong D, Su J (2020) Neural machine translation with deep attention. IEEE Trans Pattern Anal Mach Intell 42(1):154\u2013163. https:\/\/doi.org\/10.1109\/tpami.2018.2876404","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"10","key":"606_CR33","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1109\/TNNLS.2016.2582798","volume":"28","author":"C Zhang","year":"2017","unstructured":"Zhang C, Lim P, Qin AK, Tan K (2017) Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics. IEEE Trans Neural Netw Learn Syst 28(10):2306\u20132318. https:\/\/doi.org\/10.1109\/TNNLS.2016.2582798","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00606-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-021-00606-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00606-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T17:12:41Z","timestamp":1651252361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-021-00606-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,20]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["606"],"URL":"https:\/\/doi.org\/10.1007\/s40747-021-00606-4","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,20]]},"assertion":[{"value":"17 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}