{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:31:09Z","timestamp":1786696269777,"version":"build-2736575974"},"reference-count":20,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shanghai Science and Technology Commission \u201cBelt and Road\u201d China-Laos Railway Project International Joint Laboratory","award":["21210750300"],"award-info":[{"award-number":["21210750300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The accuracy of axle-box bearing temperature prediction is important for monitoring the operating condition of high-speed electric multiple units. However, temperature data collected in service often contain missing values, abnormal fluctuations, and noise, which can affect the reliability of the prediction results. To address this problem, this paper proposes an Attention-BP-LSTM framework that combines data preprocessing with temperature prediction. First, missing data are completed by linear interpolation. The dynamically augmented temperature sequence is then processed using time-delay low-rank sparse decomposition to separate the normal temperature variation trend, sparse anomalies, and measurement noise, based on which the abnormal data are reconstructed. After Z-score normalization, the processed time series is converted into supervised learning samples using a sliding window. The prediction model consists of LSTM, an attention mechanism, Dropout, and a BP network. LSTM is used to extract the temporal dependencies in the temperature sequence, the attention mechanism assigns corresponding weights to different historical features, Dropout alleviates model overfitting, and the BP network completes the nonlinear mapping from temporal features to the predicted temperature. Experimental results based on axle-box bearing temperature data show that, compared with BP, LSTM, and BP-LSTM, the proposed model achieves lower MAE and RMSE and a higher R2. This indicates that improving data quality before prediction, together with attention-based temporal feature extraction, helps improve the reliability of short-term axle-box bearing temperature prediction.<\/jats:p>","DOI":"10.3390\/s26165137","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:08:29Z","timestamp":1786694909000},"page":"5137","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Time-Delay Low-Rank Reconstruction and Attention-BP-LSTM Framework for Axle-Box Bearing Temperature Prediction in Railway Vehicles"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9963-5035","authenticated-orcid":false,"given":"Yufei","family":"Xie","sequence":"first","affiliation":[{"name":"School of Intellectual Technology, Shanghai Institute of Technology, Shanghai 201418, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4273-9669","authenticated-orcid":false,"given":"Kun","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Intellectual Technology, Shanghai Institute of Technology, Shanghai 201418, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbai","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Intellectual Technology, Shanghai Institute of Technology, Shanghai 201418, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanyi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Intellectual Technology, Shanghai Institute of Technology, Shanghai 201418, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0322-7693","authenticated-orcid":false,"given":"Yushuo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Intellectual Technology, Shanghai Institute of Technology, Shanghai 201418, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"22680","DOI":"10.1038\/s41598-023-50177-2","article-title":"Dynamic response of axle box bearing for high-speed train considering wheelset flexibility and polygonal wear","volume":"13","author":"Guan","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"112119","DOI":"10.1016\/j.ymssp.2024.112119","article-title":"Dynamic response analysis of high-speed train axle box bearing by considering time-varying dynamic parameters","volume":"224","author":"Zheng","year":"2025","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Bai, Y., Xue, H., and Chen, J. (2023). Train Axlebox Bearing Fault Diagnosis Based on MSC-SGMD. Sensors, 24.","DOI":"10.3390\/s24010254"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"118510","DOI":"10.1016\/j.measurement.2025.118510","article-title":"Towards railways safety: A systematic review on predictive diagnostics for axle bearings","volume":"257","author":"Konecny","year":"2026","journal-title":"Measurement"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1186\/s10033-022-00789-y","article-title":"Analysis of the Temperature Characteristics of High-speed Train Bearings Based on a Dynamics Model and Thermal Network Method","volume":"35","author":"Wang","year":"2022","journal-title":"Chin. J. Mech. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mosleh, A., Mohammadi, M., Silva, R., Magalh\u00e3es, J., Jorge, T., Vale, C., Ribeiro, D., and Zhai, W. (2026). Recent advances in wayside condition monitoring for railways: A comprehensive review. Railw. Eng. Sci.","DOI":"10.1007\/s40534-025-00423-2"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"117098","DOI":"10.1016\/j.measurement.2025.117098","article-title":"Axle bearing fault diagnosis for high-speed trains: A comprehensive review of methodologies, technologies, challenges and emerging trends","volume":"251","author":"Abtane","year":"2025","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.apacoust.2014.04.005","article-title":"A new synthetic detection technique for trackside acoustic identification of railroad roller bearing defects","volume":"85","author":"Wang","year":"2014","journal-title":"Appl. Acoust."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"109325","DOI":"10.1016\/j.ymssp.2022.109325","article-title":"High-speed train wheel set bearing fault diagnosis and prognostics: Research on acoustic emission detection mechanism","volume":"179","author":"Hou","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1177\/09544097261417814","article-title":"Advances in railway condition monitoring and fault diagnosis: Transition from industry 4.0 automation to industry 5.0 human-centric maintenance","volume":"240","author":"Bhadouria","year":"2026","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2450","DOI":"10.1080\/00423114.2023.2292647","article-title":"Research on temperature of high-speed train axle box bearing considering lubrication state evolution and vehicle dynamics response","volume":"62","author":"Zheng","year":"2023","journal-title":"Veh. Syst. Dyn."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"111037","DOI":"10.1016\/j.ymssp.2023.111037","article-title":"Fault detection of high-speed train axle bearings based on a hybridized physical and data-driven temperature model","volume":"208","author":"Yang","year":"2024","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, W., Xie, K., Zou, J., Huang, K., Mu, F., and Chen, L. (2024). Transformer-Based High-Speed Train Axle Temperature Monitoring and Alarm System for Enhanced Safety and Performance. Appl. Sci., 14.","DOI":"10.3390\/app14198643"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.3390\/modelling5030054","article-title":"A Spatiotemporal Locomotive Axle Temperature Prediction Approach Based on Ensemble Graph Convolutional Recurrent Unit Networks","volume":"5","author":"Li","year":"2024","journal-title":"Modelling"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, F., Wang, Z., Yang, C., Zhang, W., and Gu, F. (2025). Temperature Characteristics of Axle-Box Bearings Under Wheel Flat Excitation. Lubricants, 13.","DOI":"10.3390\/lubricants13010019"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, L., Song, D., Geng, Z., and Zheng, Z. (2020). A Real-Time Fault Early Warning Method for a High-Speed EMU Axle Box Bearing. Sensors, 20.","DOI":"10.3390\/s20030823"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.psep.2023.07.094","article-title":"Robust fault detection for chemical processes based on dynamic low-rank matrix and optimized LSTM","volume":"178","author":"Cen","year":"2023","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"026204","DOI":"10.1088\/1361-6501\/ae2f80","article-title":"Prediction of high-speed train bearing temperature based on a hybrid physics-informed and data-driven model","volume":"37","author":"Zhang","year":"2025","journal-title":"Meas. Sci. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Krichen, M., and Mihoub, A. (2025). Long Short-Term Memory Networks: A Comprehensive Survey. AI, 6.","DOI":"10.3390\/ai6090215"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Salehin, I., and Kang, D.-K. (2023). A Review on Dropout Regularization Approaches for Deep Neural Networks within the Scholarly Domain. Electronics, 12.","DOI":"10.3390\/electronics12143106"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5137\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:11:47Z","timestamp":1786695107000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":20,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165137"],"URL":"https:\/\/doi.org\/10.3390\/s26165137","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}