{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:35:42Z","timestamp":1777696542580,"version":"3.51.4"},"reference-count":33,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2024,2,3]]},"abstract":"<jats:p>Nowadays, the massive industrial data has effectively improved the performance of the data-driven deep learning Remaining Useful Life (RUL) prediction method. However, there are still problems of assigning fixed weights to features and only coarse-grained consideration at the sequence level. This paper proposes a Transformer-based end-to-end feature-level mask self-supervised learning method for RUL prediction. First, by proposing a fine-grained feature-level mask self-supervised learning method, the data at different time points under all features in a time window is sent to two parallel learning streams with and without random masks. The model can learn more fine-grained degradation information by comparing the information extracted by the two parallel streams. Instead of assigning fixed weights to different features, the abstract information extracted through the above process is invariable correlations between features, which has a good generalization to various situations under different working conditions. Then, the extracted information is encoded and decoded again using an asymmetric structure, and a fully connected network is used to build a mapping between the extracted information and the RUL. We conduct experiments on the public C-MAPSS datasets and show that the proposed method outperforms the other methods, and its advantages are more obvious in complex multi-working conditions.<\/jats:p>","DOI":"10.3233\/ida-227099","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T11:31:00Z","timestamp":1702380660000},"page":"217-237","source":"Crossref","is-referenced-by-count":2,"title":["A feature-level mask self-supervised assisted learning approach based on transformer for remaining useful life prediction"],"prefix":"10.1177","volume":"28","author":[{"given":"Bing","family":"Xue","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Production Department, Langfang Oil and Gas Transportation Branch of National Petroleum Network Group North Pipeline Co., Ltd, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Production and Operation Department, National Petroleum Network Group North Pipeline Co., Ltd, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyuan","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-227099_ref1","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.neucom.2017.05.063","article-title":"Remaining useful life estimation of engineered systems using vanilla LSTM neural networks","volume":"275","author":"Wu","year":"2018","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-227099_ref2","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.neucom.2021.09.022","article-title":"Attention-based sequence to sequence model for machine remaining useful life prediction","volume":"466","author":"Ragab","year":"2021","journal-title":"Neurocomputing"},{"issue":"2","key":"10.3233\/IDA-227099_ref3","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1109\/TII.2020.2983760","article-title":"Remaining useful life prediction using a novel feature-attention-based end-to-end approach","volume":"17","author":"Liu","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.3233\/IDA-227099_ref4","doi-asserted-by":"publisher","first-page":"101396","DOI":"10.1016\/j.aei.2021.101396","article-title":"A multi-head neural network with unsymmetrical constraints for remaining useful life prediction","volume":"50","author":"Liu","year":"2021","journal-title":"Advanced Engineering Informatics"},{"issue":"4","key":"10.3233\/IDA-227099_ref5","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1109\/TR.2016.2590997","article-title":"Model-based fault diagnosis of a planetary gear: A novel approach using transmission error","volume":"65","author":"Park","year":"2016","journal-title":"IEEE Transactions on Reliability"},{"issue":"7","key":"10.3233\/IDA-227099_ref6","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1007\/s10845-021-01750-x","article-title":"Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit","volume":"32","author":"Mo","year":"2021","journal-title":"Journal of Intelligent Manufacturing"},{"key":"10.3233\/IDA-227099_ref7","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2018.04.043","article-title":"A method for remaining useful life prediction of crystal oscillators using the Bayesian approach and extreme learning machine under uncertainty","volume":"305","author":"Liu","year":"2018","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-227099_ref8","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.ymssp.2014.10.014","article-title":"Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network","volume":"56","author":"Ali","year":"2015","journal-title":"Mechanical Systems and Signal Processing"},{"issue":"1","key":"10.3233\/IDA-227099_ref9","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/TII.2017.2723943","article-title":"Online tool wear monitoring via hidden semi-markov model with dependent durations","volume":"14","author":"Zhu","year":"2018","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"4","key":"10.3233\/IDA-227099_ref10","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1109\/TR.2013.2285318","article-title":"Remaining useful life estimation in rolling bearings utilizing data-driven probabilistic e-support vectors regression","volume":"62","author":"Loutas","year":"2013","journal-title":"IEEE Transactions on Reliability"},{"key":"10.3233\/IDA-227099_ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2022.108610"},{"key":"10.3233\/IDA-227099_ref12","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.isatra.2018.04.005","article-title":"Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders","volume":"77","author":"Liu","year":"2018","journal-title":"ISA Transactions"},{"key":"10.3233\/IDA-227099_ref13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3055788","article-title":"Degradation-aware remaining useful life prediction with LSTM autoencoder","volume":"70","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"3","key":"10.3233\/IDA-227099_ref14","doi-asserted-by":"publisher","first-page":"2521","DOI":"10.1109\/TIE.2020.2972443","article-title":"Machine remaining useful life prediction via an attention-based deep learning approach","volume":"68","author":"Chen","year":"2021","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"9","key":"10.3233\/IDA-227099_ref15","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.1109\/TII.2019.2900295","article-title":"Joint learning of degradation assessment and RUL prediction for aeroengines via dual-task deep LSTM networks","volume":"15","author":"Miao","year":"2019","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.3233\/IDA-227099_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRMS.2018.00067"},{"key":"10.3233\/IDA-227099_ref17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2022.3160561","article-title":"Dual-aspect self-attention based on transformer for remaining useful life prediction","volume":"71","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.3233\/IDA-227099_ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.06377"},{"key":"10.3233\/IDA-227099_ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"10.3233\/IDA-227099_ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762"},{"key":"10.3233\/IDA-227099_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3136768"},{"key":"10.3233\/IDA-227099_ref22","doi-asserted-by":"publisher","first-page":"108330","DOI":"10.1016\/j.ress.2022.108330","article-title":"Aircraft engine remaining useful life estimation via a double attention-based data-driven architecture","volume":"221","author":"Liu","year":"2022","journal-title":"Reliability Engineering & System Safety"},{"key":"10.3233\/IDA-227099_ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.10916"},{"key":"10.3233\/IDA-227099_ref24","doi-asserted-by":"publisher","DOI":"10.1109\/PHM-Chongqing.2018.00184"},{"key":"10.3233\/IDA-227099_ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ress.2017.11.021","article-title":"Remaining useful life estimation in prognostics using deep convolution neural networks","volume":"172","author":"Li","year":"2018","journal-title":"Reliability Engineering & System Safety"},{"issue":"19","key":"10.3233\/IDA-227099_ref26","doi-asserted-by":"publisher","first-page":"4156","DOI":"10.3390\/app9194156","article-title":"Convolution and long short-term memory hybrid deep neural networks for remaining useful life prognostics","volume":"9","author":"Kong","year":"2019","journal-title":"Applied Sciences"},{"issue":"12","key":"10.3233\/IDA-227099_ref27","doi-asserted-by":"publisher","first-page":"9594","DOI":"10.1109\/JIOT.2020.3004452","article-title":"Distributed attention-based temporal convolutional network for remaining useful life prediction","volume":"8","author":"Song","year":"2020","journal-title":"IEEE Internet of Things Journal"},{"key":"10.3233\/IDA-227099_ref28","doi-asserted-by":"publisher","first-page":"109642","DOI":"10.1016\/j.measurement.2021.109642","article-title":"A deep attention residual neural network-based remaining useful life prediction of machinery","volume":"181","author":"Zeng","year":"2021","journal-title":"Measurement"},{"key":"10.3233\/IDA-227099_ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PHM.2008.4711414"},{"key":"10.3233\/IDA-227099_ref30","doi-asserted-by":"publisher","first-page":"106113","DOI":"10.1016\/j.asoc.2020.106113","article-title":"Remaining useful life prediction using multi-scale deep convolutional neural network","volume":"89","author":"Li","year":"2020","journal-title":"Applied Soft Computing"},{"issue":"11","key":"10.3233\/IDA-227099_ref31","doi-asserted-by":"publisher","first-page":"8792","DOI":"10.1109\/TIE.2019.2891463","article-title":"A bidirectional LSTM prognostics method under multiple operational conditions","volume":"66","author":"Huang","year":"2019","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"10.3233\/IDA-227099_ref32","doi-asserted-by":"crossref","unstructured":"G. Sateesh Babu, P. Zhao and X.-L. Li, Deep convolutional neural network based regression approach for estimation of remaining useful life, in: Database Systems for Advanced Applications: 21st International Conference, DASFAA 2016, Dallas, TX, USA, April 16\u201319, 2016, Proceedings, Part I 21, Springer, 2016, pp.\u00a0214\u2013228.","DOI":"10.1007\/978-3-319-32025-0_14"},{"key":"10.3233\/IDA-227099_ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/324"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-227099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:20:19Z","timestamp":1777454419000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-227099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,3]]},"references-count":33,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ida-227099","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,3]]}}}