{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T09:40:13Z","timestamp":1774863613342,"version":"3.50.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003329","name":"MICINN","doi-asserted-by":"publisher","award":["PID2023-148396NB-I00"],"award-info":[{"award-number":["PID2023-148396NB-I00"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011011","name":"Junta de Andaluc\u00eda","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011011","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008679","name":"Universidad de C\u00f3rdoba","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008679","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.neucom.2025.132506","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T15:50:53Z","timestamp":1767109853000},"page":"132506","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["A two-stage framework for early failure detection in predictive maintenance: A case study on metro trains"],"prefix":"10.1016","volume":"670","author":[{"given":"Luis","family":"Toribio","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7980-0972","authenticated-orcid":false,"given":"Bruno","family":"Veloso","sequence":"additional","affiliation":[]},{"given":"Jo\u00e3o","family":"Gama","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3868-6143","authenticated-orcid":false,"given":"Amelia","family":"Zafra","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2025.132506_bib0005","article-title":"Paradigm shift for predictive maintenance and condition monitoring from industry 4.0 to industry 5.0: a systematic review, challenges and case study","author":"Murtaza","year":"2024","journal-title":"Results Eng."},{"issue":"5","key":"10.1016\/j.neucom.2025.132506_bib0010","article-title":"Data mining in predictive maintenance systems: a taxonomy and systematic review","volume":"12","author":"Esteban","year":"2022","journal-title":"Wiley Interdiscip. Rev.: Data Min. Knowl. Discov."},{"issue":"17","key":"10.1016\/j.neucom.2025.132506_bib0015","doi-asserted-by":"crossref","first-page":"5739","DOI":"10.3390\/s21175739","article-title":"A survey on data-driven predictive maintenance for the railway industry","volume":"21","author":"Davari","year":"2021","journal-title":"Sensors"},{"issue":"2","key":"10.1016\/j.neucom.2025.132506_bib0020","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1002\/sys.21651","article-title":"Predictive maintenance analytics and implementation for aircraft: challenges and opportunities","volume":"26","author":"Stanton","year":"2023","journal-title":"Syst. Eng."},{"key":"10.1016\/j.neucom.2025.132506_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102506","article-title":"Predictive maintenance system for high-end equipment in nuclear power plant under limited degradation knowledge","volume":"61","author":"Liu","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.neucom.2025.132506_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106715","article-title":"Integrated failure analysis using machine learning predictive system for smart management of medical equipment maintenance","volume":"125","author":"Zamzam","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"2","key":"10.1016\/j.neucom.2025.132506_bib0035","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1108\/JQME-10-2020-0107","article-title":"Review of fault detection techniques for predictive maintenance","volume":"29","author":"Divya","year":"2023","journal-title":"J. Qual. Maint. Eng."},{"issue":"2","key":"10.1016\/j.neucom.2025.132506_bib0040","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1007\/s10462-022-10199-0","article-title":"Hybridization of hybrid structures for time series forecasting: a review","volume":"56","author":"Hajirahimi","year":"2023","journal-title":"Artif. Intell. Rev."},{"issue":"3","key":"10.1016\/j.neucom.2025.132506_bib0045","first-page":"829","article-title":"A comprehensive survey of anomaly detection algorithms","volume":"10","author":"Samariya","year":"2023","journal-title":"Ann. Data Sci."},{"key":"10.1016\/j.neucom.2025.132506_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107339","article-title":"Cost aware LSTM model for predicting hard disk drive failures based on extremely imbalanced smart sensors data","volume":"127","author":"Ahmed","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2025.132506_bib0055","first-page":"61","article-title":"Failure detection of an AIR production unit in operational context","author":"Barros","year":"2020"},{"key":"10.1016\/j.neucom.2025.132506_bib0060","series-title":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","first-page":"1","article-title":"Predictive maintenance based on anomaly detection using deep learning for AIR production unit in the railway industry","author":"Davari","year":"2021"},{"key":"10.1016\/j.neucom.2025.132506_bib0065","series-title":"Available at SSRN 4403258","article-title":"Predictive maintenance of urban Metro vehicles: classification of AIR production unit failures using machine learning","author":"Najjar","year":"2023"},{"key":"10.1016\/j.neucom.2025.132506_bib0070","doi-asserted-by":"crossref","first-page":"57574","DOI":"10.1109\/ACCESS.2024.3391130","article-title":"Explainable predictive maintenance: a survey of current methods, challenges and opportunities","volume":"12","author":"Cummins","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2025.132506_bib0075","doi-asserted-by":"crossref","first-page":"3487","DOI":"10.1007\/s00170-016-9307-8","article-title":"Fault diagnostics of spur gear using decision tree and fuzzy classifier","volume":"89","author":"Krishnakumari","year":"2017","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"6","key":"10.1016\/j.neucom.2025.132506_bib0080","doi-asserted-by":"crossref","first-page":"895","DOI":"10.3390\/s16060895","article-title":"Fault diagnosis for rotating machinery using vibration measurement deep statistical feature learning","volume":"16","author":"Li","year":"2016","journal-title":"Sensors"},{"key":"10.1016\/j.neucom.2025.132506_bib0085","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.patrec.2020.06.008","article-title":"Using an autoencoder in the design of an anomaly detector for smart manufacturing","volume":"136","author":"Alfeo","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2025.132506_bib0090","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1409","article-title":"A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data","volume":"vol. 33","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neucom.2025.132506_bib0095","series-title":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","first-page":"188","article-title":"Verifying autoencoders for anomaly detection in predictive maintenance","author":"Guidotti","year":"2024"},{"issue":"1","key":"10.1016\/j.neucom.2025.132506_bib0100","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00170-023-11497-9","article-title":"Development and implementation of real-time anomaly detection on tool wear based on stacked LSTM encoder-decoder model","volume":"127","author":"Oshida","year":"2023","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"1","key":"10.1016\/j.neucom.2025.132506_bib0105","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1002\/qre.3668","article-title":"Condition assessment and predictive maintenance for contact probe using health index and encoder-decoder LSTM model","volume":"41","author":"Luk","year":"2025","journal-title":"Qual. Reliab. Eng. Int."},{"key":"10.1016\/j.neucom.2025.132506_bib0110","series-title":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","first-page":"78","article-title":"Advanced correlation-based anomaly detection method for predictive maintenance","author":"Zhao","year":"2017"},{"issue":"11","key":"10.1016\/j.neucom.2025.132506_bib0115","doi-asserted-by":"crossref","first-page":"7718","DOI":"10.1109\/TII.2022.3144177","article-title":"Multiple instance learning with random forest for event logs analysis and predictive maintenance in ship electric propulsion system","volume":"18","author":"Bakdi","year":"2022","journal-title":"IEEE Trans. Ind. Inf."},{"issue":"1","key":"10.1016\/j.neucom.2025.132506_bib0120","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s42979-024-03599-2","article-title":"The impact of predictive maintenance on the performance of industrial enterprises","volume":"6","author":"Er-Ratby","year":"2025","journal-title":"SN Comput. Sci."},{"key":"10.1016\/j.neucom.2025.132506_bib0125","series-title":"NeurIPS","article-title":"Copod: copula-based outlier detection","author":"Zhao","year":"2020"},{"key":"10.1016\/j.neucom.2025.132506_bib0130","series-title":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","first-page":"1","article-title":"A semi-supervised railway foreign object detection method based on GAN","author":"Chen","year":"2021"},{"issue":"8","key":"10.1016\/j.neucom.2025.132506_bib0135","doi-asserted-by":"crossref","first-page":"2679","DOI":"10.1109\/TIM.2018.2868490","article-title":"Deep architecture for high-speed railway insulator surface defect detection: denoising autoencoder with multitask learning","volume":"68","author":"Kang","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"19","key":"10.1016\/j.neucom.2025.132506_bib0140","doi-asserted-by":"crossref","first-page":"9290","DOI":"10.3390\/app11199290","article-title":"Anomaly detection of the brake operating unit on Metro vehicles using a one-class LSTM autoencoder","volume":"11","author":"Kang","year":"2021","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2025.132506_bib0145","series-title":"2018 International Conference on Control, Automation and Diagnosis (ICCAD)","first-page":"1","article-title":"Detection of anomaly in train speed for intelligent railway systems","author":"Kang","year":"2018"},{"key":"10.1016\/j.neucom.2025.132506_bib0150","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.eswa.2017.05.079","article-title":"Fault detection and explanation through big data analysis on sensor streams","volume":"87","author":"Manco","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2025.132506_bib0155","series-title":"2020 16th International Conference on Distributed Computing in Sensor Systems (DCOSS)","first-page":"236","article-title":"An agnostic data-driven approach to predict stoppages of industrial packing machine in near future","author":"Filios","year":"2020"},{"key":"10.1016\/j.neucom.2025.132506_bib0160","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cie.2017.10.033","article-title":"Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling","volume":"115","author":"Baptista","year":"2018","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.neucom.2025.132506_bib0165","series-title":"2021 IEEE 37th International Conference on Data Engineering (ICDE)","first-page":"2744","article-title":"Graph based approach to real-time Metro passenger flow anomaly detection","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2025.132506_bib0170","series-title":"2019 Chinese Control and Decision Conference (CCDC)","first-page":"1954","article-title":"An unsupervised anomaly detection method based on density peak clustering for rail vehicle door system","author":"Shi","year":"2019"},{"key":"10.1016\/j.neucom.2025.132506_bib0175","series-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","first-page":"387","article-title":"Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding","author":"Hundman","year":"2018"},{"key":"10.1016\/j.neucom.2025.132506_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119978","article-title":"A time series anomaly detection method based on series-parallel transformers with spatial and temporal association discrepancies","volume":"657","author":"Fu","year":"2024","journal-title":"Inf. Sci."},{"issue":"7","key":"10.1016\/j.neucom.2025.132506_bib0185","doi-asserted-by":"crossref","first-page":"4644","DOI":"10.3390\/app13074644","article-title":"Forecasting stock market indices using the recurrent neural network based hybrid models: Cnn-lstm, gru-Cnn, and ensemble models","volume":"13","author":"Song","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2025.132506_bib0190","series-title":"Hybrid Artificial Intelligent Systems - 19th International Conference, HAIS 2024, Salamanca, Spain, October 9\u221211, 2024, Proceedings, Part I","first-page":"339","article-title":"Early failure detection for AIR production unit in Metro trains","volume":"vol. 14857","author":"Zafra","year":"2024"},{"key":"10.1016\/j.neucom.2025.132506_bib0195","first-page":"283","article-title":"Multivariate estimation with high breakdown point","volume":"8","author":"Rousseeuw","year":"1985","journal-title":"Math. Stat. Appl."},{"issue":"3","key":"10.1016\/j.neucom.2025.132506_bib0200","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.neucom.2025.132506_bib0205","author":"Zhao"},{"key":"10.1016\/j.neucom.2025.132506_bib0210","series-title":"Proceedings of the ACM Symposium on Applied Computing","first-page":"237","article-title":"Histogram-based outlier score (Hbos) for fast unsupervised anomaly detection","author":"Goldstein","year":"2012"},{"key":"10.1016\/j.neucom.2025.132506_bib0215","series-title":"Pattern Recognition","first-page":"20","article-title":"Discovering cluster-based local outliers","author":"He","year":"2003"},{"issue":"1","key":"10.1016\/j.neucom.2025.132506_bib0220","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2133360.2133363","article-title":"Isolation-based anomaly detection","volume":"6","author":"Liu","year":"2012","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.neucom.2025.132506_bib0225","author":"Zhao"},{"key":"10.1016\/j.neucom.2025.132506_bib0230","first-page":"378","article-title":"Lscp: locally selective combination in parallel outlier ensembles","author":"Zhao","year":"2019","journal-title":"Proc. of the 2019 SIAM Int. Conf. on Data Min. (SDM)"},{"key":"10.1016\/j.neucom.2025.132506_bib0235","series-title":"Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis","first-page":"4","article-title":"Anomaly detection using autoencoders with nonlinear dimensionality reduction","author":"Sakurada","year":"2014"},{"issue":"1","key":"10.1016\/j.neucom.2025.132506_bib0240","first-page":"1","article-title":"Variational autoencoder based anomaly detection using reconstruction probability","volume":"2","author":"An","year":"2015","journal-title":"Special Lecture on IE"},{"key":"10.1016\/j.neucom.2025.132506_bib0245","author":"Liu"},{"key":"10.1016\/j.neucom.2025.132506_bib0250","unstructured":"N. Davari, B. Veloso, R. Ribeiro, J. Gama, Metropt-3 dataset, UCI Machine Learning Repository, 2023, 10.24432\/C5VW3R"},{"issue":"1","key":"10.1016\/j.neucom.2025.132506_bib0255","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1038\/s41597-022-01877-3","article-title":"The Metropt dataset for predictive maintenance","volume":"9","author":"Veloso","year":"2022","journal-title":"Sci. Data"},{"key":"10.1016\/j.neucom.2025.132506_bib0260","series-title":"Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"issue":"96","key":"10.1016\/j.neucom.2025.132506_bib0265","first-page":"1","article-title":"Pyod: a Python toolbox for scalable outlier detection","volume":"20","author":"Zhao","year":"2019","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"10.1016\/j.neucom.2025.132506_bib0270","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1007\/s10618-023-00988-8","article-title":"Navigating the metric maze: a taxonomy of evaluation metrics for anomaly detection in time series","volume":"38","author":"S\u00f8rb\u00f8","year":"2024","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.neucom.2025.132506_bib0275","first-page":"2677","article-title":"An extension on \u201cstatistical comparisons of classifiers over multiple data sets\u201d for all pairwise comparisons","volume":"9","author":"Garc\u00eda","year":"2009","journal-title":"J. Mach. Learn. Res."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231225031789?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231225031789?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:51:22Z","timestamp":1773967882000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231225031789"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":55,"alternative-id":["S0925231225031789"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2025.132506","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A two-stage framework for early failure detection in predictive maintenance: A case study on metro trains","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2025.132506","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"132506"}}