{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:06:45Z","timestamp":1781968005479,"version":"3.54.5"},"reference-count":33,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:00:00Z","timestamp":1719360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In the context of Industry 4.0, bearings, as critical components of machinery, play a vital role in ensuring operational reliability. The detection of their health status is thus of paramount importance. Existing predictive models often focus on point predictions of bearing lifespan, lacking the ability to quantify uncertainty and having room for improvement in accuracy. To accurately predict the long-term remaining useful life (RUL) of bearings, a novel time convolutional network model with an attention mechanism-based soft thresholding decision residual structure for quantifying the lifespan interval of bearings, namely TCN-AM-GPR, is proposed. Firstly, a spatio-temporal graph is constructed from the bearing sensor signals as the input to the prediction model. Secondly, a residual structure based on a soft threshold decision with a self-attention mechanism is established to further suppress noise in the collected bearing lifespan signals. Thirdly, the extracted features pass through an interval quantization layer to obtain the RUL and its confidence interval of the bearings. The proposed methodology has been verified using the PHM2012 bearing dataset, and the comparison of simulation experiment results shows that TCN-AM-GPR achieved the best point prediction evaluation index, with a 2.17% improvement in R2 compared to the second-best performance from TCN-GPR. At the same time, it also has the best interval prediction comprehensive evaluation index, with a relative decrease of 16.73% in MWP compared to the second-best performance from TCN-GPR. The research results indicate that TCN-AM-GPR can ensure the accuracy of point estimates, while having superior advantages and practical significance in describing prediction uncertainty.<\/jats:p>","DOI":"10.3390\/s24134132","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T09:29:33Z","timestamp":1719394173000},"page":"4132","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Application of Residual Structure Time Convolutional Network Based on Attention Mechanism in Remaining Useful Life Interval Prediction of Bearings"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6642-8996","authenticated-orcid":false,"given":"Chunsheng","family":"Zhang","sequence":"first","affiliation":[{"name":"SCNU Environmental Research Institute, Guangdong Provincial Key Laboratory of Chemical Pollution and Environmental Safety & MOE Key Laboratory of Theoretical Chemistry of Environment, School of Environment, South China Normal University, Guangzhou 510006, China"},{"name":"Shantou Yerei Technology Co., Ltd., Shantou 515000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengxin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Shanwei Institute of Technology, Shanwei 516600, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjin","family":"Fan","sequence":"additional","affiliation":[{"name":"Research Institute of History for Science and Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7371-7924","authenticated-orcid":false,"given":"Xiaoyong","family":"Li","sequence":"additional","affiliation":[{"name":"SCNU Environmental Research Institute, Guangdong Provincial Key Laboratory of Chemical Pollution and Environmental Safety & MOE Key Laboratory of Theoretical Chemistry of Environment, School of Environment, South China Normal University, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106272","DOI":"10.1016\/j.ymssp.2019.106272","article-title":"Mechanical fault diagnosis using convolutional neural networks and extreme learning machine","volume":"133","author":"Chen","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1016\/j.isatra.2021.10.023","article-title":"Parallel multi-fusion convolutional neural networks based fault diagnosis of rotating machinery under noisy environments","volume":"128","author":"Li","year":"2022","journal-title":"ISA Trans."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1687814019897212","DOI":"10.1177\/1687814019897212","article-title":"Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions","volume":"11","author":"Che","year":"2019","journal-title":"Adv. Mech. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"123768","DOI":"10.1016\/j.eswa.2024.123768","article-title":"A Lightweight Channel and Time Attention Enhanced 1D CNN Model for Environmental Sound Classification","volume":"249","author":"Xu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3495","DOI":"10.1007\/s10845-022-02015-x","article-title":"A novel feature-fusion-based end-to-end approach for remaining useful life prediction","volume":"34","author":"Zhu","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.isatra.2019.08.058","article-title":"Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model","volume":"98","author":"Yan","year":"2020","journal-title":"ISA Trans."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"8514","DOI":"10.1109\/JSEN.2023.3246595","article-title":"Dual Channel Feature-Attention-based Approach for RUL Prediction Considering the Spatiotemporal Difference of Multisensor Data","volume":"23","author":"Gao","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108528","DOI":"10.1016\/j.ress.2022.108528","article-title":"Bearing remaining useful life prediction with convolutional long short-term memory fusion networks","volume":"224","author":"Wan","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110888","DOI":"10.1016\/j.ymssp.2023.110888","article-title":"Multi-scale time series analysis using TT-ConvLSTM technique for bearing remaining useful life prediction","volume":"206","author":"Niazi","year":"2024","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_10","first-page":"333","article-title":"A two-stage Gaussian process regression model for remaining useful prediction of bearings","volume":"238","author":"Cui","year":"2024","journal-title":"Proc. Inst. Mech. Eng. Part O J. Risk Reliab."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Tian, Q., and Wang, H. (2021). Predicting remaining useful life of rolling bearings based on reliable degradation indicator and temporal convolution network with the quantile regression. Appl. Sci., 11.","DOI":"10.3390\/app11114773"},{"key":"ref_12","unstructured":"Shi, H., Kang, H., Zhang, Z., Sun, X., and Gu, F. (2020). Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width. International Conference on Maintenance Engineering, Springer International Publishing."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1089\/big.2020.0159","article-title":"Deep learning for time series forecasting: A survey","volume":"9","author":"Torres","year":"2021","journal-title":"Big Data"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1007\/s40430-022-03856-6","article-title":"Remaining useful life prediction of bearings based on temporal convolutional networks with residual separable blocks","volume":"44","author":"Zhang","year":"2022","journal-title":"J. Braz. Soc. Mech. Sci. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"045107","DOI":"10.1088\/1361-6501\/acb0e9","article-title":"Remaining useful life prediction of bearings based on self-attention mechanism, multi-scale dilated causal convolution, and temporal convolution network","volume":"34","author":"Wei","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_16","unstructured":"Ayoub, I. (2019). Multimodal Affective Computing Using Temporal Convolutional Neural Network and Deep Convolutional Neural Networks. [Doctoral Dissertation, Universit\u00e9 d\u2019Ottawa\/University of Ottawa]."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"111043","DOI":"10.1016\/j.petrol.2022.111043","article-title":"Temporal convolution network based on attention mechanism for well production prediction","volume":"218","author":"Zhen","year":"2022","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_18","unstructured":"Hasan, U., Hossain, E., and Gani, M.O. (2023). A Survey on Causal Discovery Methods for I.I.D. and Time Series Data. Trans. Mach. Learn. Res., 2835\u20138856."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"31078","DOI":"10.1109\/ACCESS.2021.3059761","article-title":"Rolling bearing fault diagnosis based on one-dimensional dilated convolution network with residual connection","volume":"9","author":"Liang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107813","DOI":"10.1016\/j.ress.2021.107813","article-title":"A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings","volume":"215","author":"Cao","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.neucom.2021.06.009","article-title":"Context-aware self-attention networks for natural language processing","volume":"458","author":"Yang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"126343","DOI":"10.1016\/j.jclepro.2021.126343","article-title":"Application of novel hybrid deep leaning model for cleaner production in a paper industrial wastewater treatment system","volume":"294","author":"Li","year":"2021","journal-title":"J. Clean. Prod."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"104902","DOI":"10.1016\/j.jwpe.2024.104902","article-title":"Application of deep learning model based on transfer learning in activated sludge process for wastewater purification","volume":"59","author":"Li","year":"2024","journal-title":"J. Water Process Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"095116","DOI":"10.1063\/5.0171091","article-title":"IRMSwin-T: A lightweight shifted windows transformer based on inverted residual structure and residual multi-layer perceptron for rolling bearing fault diagnosis","volume":"94","author":"Ding","year":"2023","journal-title":"Rev. Sci. Instrum."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102558","DOI":"10.1016\/j.aei.2024.102558","article-title":"The LPST-Net: A new deep interval health monitoring and prediction framework for bearing-rotor systems under complex operating conditions","volume":"62","author":"Yang","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"112942","DOI":"10.1016\/j.envres.2022.112942","article-title":"Water quality prediction model using Gaussian process regression based on deep learning for carbon neutrality in papermaking wastewater treatment system","volume":"211","author":"Wan","year":"2022","journal-title":"Environ. Res."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jia, X., Huang, B., Feng, J., Cai, H., and Lee, J. (2018, January 24\u201327). A review of PHM Data Competitions from 2008 to 2017: Methodologies and Analytics. Proceedings of the Annual Conference of the Prognostics and Health Management Society, Philadelphia, PA, USA.","DOI":"10.36001\/phmconf.2018.v10i1.462"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1016\/j.jmsy.2021.03.012","article-title":"A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing","volume":"61","author":"Huang","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.apenergy.2019.04.047","article-title":"Wind speed prediction method using shared weight long short-term memory network and Gaussian process regression","volume":"247","author":"Zhang","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2831","DOI":"10.1007\/s11063-022-10742-8","article-title":"CNN-based hidden-layer topological structure design and optimization methods for image classification","volume":"54","author":"Liu","year":"2022","journal-title":"Neural Process. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.neucom.2019.11.054","article-title":"BiLSTM with multi-polarity orthogonal attention for implicit sentiment analysis","volume":"383","author":"Wei","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ogundokun, R.O., Maskeliunas, R., Misra, S., and Dama\u0161evi\u010dius, R. (2022, January 4\u20137). Improved CNN based on batch normalization and adam optimizer. Proceedings of the International Conference on Computational Science and Its Applications, Malaga, Spain.","DOI":"10.1007\/978-3-031-10548-7_43"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"135285","DOI":"10.1109\/ACCESS.2021.3117002","article-title":"Prediction of bearings remaining useful life across working conditions based on transfer learning and time series clustering","volume":"9","author":"Mao","year":"2021","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4132\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:04:27Z","timestamp":1760108667000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,26]]},"references-count":33,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24134132"],"URL":"https:\/\/doi.org\/10.3390\/s24134132","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,26]]}}}