{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:34:33Z","timestamp":1777696473374,"version":"3.51.4"},"reference-count":38,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2023,7,20]]},"abstract":"<jats:p>The emergence of the Industry 4.0 trend brings automation and data exchange to industrial manufacturing. Using computational systems and IoT devices allows businesses to collect and deal with vast volumes of sensorial and business process data. The growing and proliferation of big data and machine learning technologies enable strategic decisions based on the analyzed data. This study suggests a data-driven predictive maintenance framework for the air production unit (APU) system of a train of Metro do Porto. The proposed method assists in detecting failures and errors in machinery before they reach critical stages. We present an anomaly detection model following an unsupervised approach, combining the Half-Space-trees method with One Class K Nearest Neighbor, adapted to deal with data streams. We evaluate and compare our approach with the Half-Space-Trees method applied without the One Class K Nearest Neighbor combination. Our model produced few type-I errors, significantly increasing the value of precision when compared to the Half-Space-Trees model. Our proposal achieved high anomaly detection performance, predicting most of the catastrophic failures of the APU train system.<\/jats:p>","DOI":"10.3233\/ida-226811","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T10:14:30Z","timestamp":1686305670000},"page":"1087-1102","source":"Crossref","is-referenced-by-count":4,"title":["Data-driven predictive maintenance framework for railway systems"],"prefix":"10.1177","volume":"27","author":[{"given":"Jorge","family":"Meira","sequence":"first","affiliation":[{"name":"GECAD, Polytechnic Institute of Porto (ISEP\/IPP), Porto, Portugal"}]},{"given":"Bruno","family":"Veloso","sequence":"additional","affiliation":[{"name":"LIAAD, INESC TEC, Porto, Portugal"}]},{"given":"Ver\u00f3nica","family":"Bol\u00f3n-Canedo","sequence":"additional","affiliation":[{"name":"LIDIA \u2013 CITIC, University of Coru\u00f1a, Coru\u00f1a, Spain"}]},{"given":"Goreti","family":"Marreiros","sequence":"additional","affiliation":[{"name":"GECAD, Polytechnic Institute of Porto (ISEP\/IPP), Porto, Portugal"}]},{"given":"Amparo","family":"Alonso-Betanzos","sequence":"additional","affiliation":[{"name":"LIDIA \u2013 CITIC, University of Coru\u00f1a, Coru\u00f1a, Spain"}]},{"given":"Jo\u00e3o","family":"Gama","sequence":"additional","affiliation":[{"name":"LIAAD, INESC TEC, Porto, Portugal"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-226811_ref1","doi-asserted-by":"crossref","first-page":"23484","DOI":"10.1109\/ACCESS.2017.2765544","article-title":"Industrial big data in an industry 4.0 environment: Challenges, schemes, and applications for predictive maintenance","volume":"5","author":"Yan","year":"2017","journal-title":"IEEE Access"},{"key":"10.3233\/IDA-226811_ref2","doi-asserted-by":"crossref","unstructured":"P. Kamat and R. Sugandhi, Anomaly detection for predictive maintenance in industry 4.0-A survey, in: E3S Web of Conferences, Vol. 170, EDP Sciences, 2020, p. 02007.","DOI":"10.1051\/e3sconf\/202017002007"},{"key":"10.3233\/IDA-226811_ref3","unstructured":"S.C. Tan, K.M. Ting and T.F. Liu, Fast anomaly detection for streaming data, in: Twenty-Second International Joint Conference on Artificial Intelligence, 2011."},{"issue":"6","key":"10.3233\/IDA-226811_ref7","doi-asserted-by":"publisher","first-page":"7003","DOI":"10.1016\/j.eswa.2010.12.014","article-title":"Anomaly detection in monitoring sensor data for preventive maintenance","volume":"38","author":"Rabatel","year":"2011","journal-title":"Expert Syst. Appl."},{"key":"10.3233\/IDA-226811_ref8","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.trc.2014.04.013","article-title":"Improving rail network velocity: A machine learning approach to predictive maintenance","volume":"45","author":"Li","year":"2014","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.3233\/IDA-226811_ref9","first-page":"264","article-title":"Failure prediction \u2013 an application in the railway industry","volume":"8777","author":"Pereira","year":"2014","journal-title":"Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)"},{"issue":"1","key":"10.3233\/IDA-226811_ref10","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s10994-016-5584-6","article-title":"Sequential anomalies: A study in the Railway Industry","volume":"105","author":"Ribeiro","year":"2016","journal-title":"Machine Learning"},{"key":"10.3233\/IDA-226811_ref11","doi-asserted-by":"publisher","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":"10.3233\/IDA-226811_ref12","unstructured":"W.-j. Lee, Anomaly detection and severity prediction of air leakage in train braking pipes, International Journal of Prognostics and Health Management 21 (2017)."},{"key":"10.3233\/IDA-226811_ref13","doi-asserted-by":"crossref","unstructured":"S. Kang, S. Sristi, J. Karachiwala and Y. Hu, Detection of anomaly in train speed for intelligent railway systems, in: 2018 Int. Conf. Control. Autom. Diagnosis, ICCAD 2018, 2018.","DOI":"10.1109\/CADIAG.2018.8751374"},{"key":"10.3233\/IDA-226811_ref14","doi-asserted-by":"crossref","unstructured":"K. Chen, S. Pashami, Y. Fan and S. Nowaczyk, Predicting air compressor failures using long short term memory networks, in: EPIA Conference on Artificial Intelligence, Springer, 2019, pp.\u00a0596\u2013609.","DOI":"10.1007\/978-3-030-30241-2_50"},{"key":"10.3233\/IDA-226811_ref15","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.trc.2019.02.001","article-title":"Predictive maintenance using tree-based classification techniques: A case of railway switches","volume":"101","author":"Bukhsh","year":"2019","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.3233\/IDA-226811_ref16","unstructured":"M. Barros, B. Veloso, P.M. Pereira, R.P. Ribeiro and J. Gama, Failure Detection of an Air Production Unit in Operational Context, in: IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning, J. Gama, S. Pashami, A. Bifet, M. Sayed-Mouchawe, H. Fr\u00f6ning, F. Pernkopf, G. Schiele and M. Blott, eds, Springer International Publishing, Cham, 2020, pp.\u00a061\u201374. ISBN 978-3-030-66770-2."},{"key":"10.3233\/IDA-226811_ref17","doi-asserted-by":"crossref","unstructured":"G. Salierno, S. Morvillo, L. Leonardi and G. Cabri, An architecture for predictive maintenance of railway points based on big data analytics, in: International Conference on Advanced Information Systems Engineering, Springer, 2020, pp.\u00a029\u201340.","DOI":"10.1007\/978-3-030-49165-9_3"},{"issue":"1","key":"10.3233\/IDA-226811_ref18","doi-asserted-by":"crossref","first-page":"5","DOI":"10.3390\/designs5010005","article-title":"Predictive maintenance using machine learning and data mining: A pioneer method implemented to greek railways","volume":"5","author":"Kalathas","year":"2021","journal-title":"Designs"},{"issue":"17","key":"10.3233\/IDA-226811_ref19","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":"1","key":"10.3233\/IDA-226811_ref20","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.cie.2012.10.013","article-title":"Automatic bearing fault diagnosis based on one-class \u03bd-SVM","volume":"64","author":"Fern\u00e1ndez-Francos","year":"2013","journal-title":"Computers & Industrial Engineering"},{"key":"10.3233\/IDA-226811_ref21","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.patrec.2016.07.019","article-title":"Fault detection via recurrence time statistics and one-class classification","volume":"84","author":"Mart\u00ednez-Rego","year":"2016","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/IDA-226811_ref22","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.procs.2015.07.321","article-title":"Condition based maintenance in railway transportation systems based on big data streaming analysis","volume":"53","author":"Fumeo","year":"2015","journal-title":"Procedia Computer Science"},{"key":"10.3233\/IDA-226811_ref23","doi-asserted-by":"crossref","unstructured":"N. Davari, B. Veloso, R.P. Ribeiro, P.M. Pereira and J. Gama, Predictive maintenance based on anomaly detection using deep learning for air production unit in the railway industry, in: 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA), IEEE, 2021, pp.\u00a01\u201310.","DOI":"10.1109\/DSAA53316.2021.9564181"},{"issue":"1","key":"10.3233\/IDA-226811_ref24","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/BF00337288","article-title":"Self-organized formation of topologically correct feature maps","volume":"43","author":"Kohonen","year":"1982","journal-title":"Biological Cybernetics"},{"key":"10.3233\/IDA-226811_ref25","doi-asserted-by":"crossref","unstructured":"R. Wetzig, A. Gulenko and F. Schmidt, Unsupervised Anomaly Alerting for IoT-Gateway Monitoring using Adaptive Thresholds and Half-Space Trees, in: 2019 Sixth International Conference on Internet of Things: Systems, Management and Security (IOTSMS), IEEE, 2019, pp.\u00a0161\u2013168.","DOI":"10.1109\/IOTSMS48152.2019.8939201"},{"issue":"1","key":"10.3233\/IDA-226811_ref26","first-page":"2915","article-title":"Scikit-multiflow: A multi-output streaming framework","volume":"19","author":"Montiel","year":"2018","journal-title":"The Journal of Machine Learning Research"},{"key":"10.3233\/IDA-226811_ref27","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"The Journal of machine Learning Research"},{"key":"10.3233\/IDA-226811_ref28","doi-asserted-by":"crossref","unstructured":"E. Manzoor, H. Lamba and L. Akoglu, xstream: Outlier detection in feature-evolving data streams, in: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, pp.\u00a01963\u20131972.","DOI":"10.1145\/3219819.3220107"},{"issue":"20","key":"10.3233\/IDA-226811_ref29","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3182\/20130902-3-CN-3020.00044","article-title":"An anomaly detection approach based on isolation forest algorithm for streaming data using sliding window","volume":"46","author":"Ding","year":"2013","journal-title":"IFAC Proceedings Volumes"},{"key":"10.3233\/IDA-226811_ref30","doi-asserted-by":"crossref","unstructured":"F. Angiulli and F. Fassetti, Detecting distance-based outliers in streams of data, in: Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, 2007, pp.\u00a0811\u2013820.","DOI":"10.1145\/1321440.1321552"},{"issue":"3","key":"10.3233\/IDA-226811_ref31","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/B978-0-12-398537-8.00004-3","article-title":"Anomaly detection: A survey","volume":"41","author":"Chandola","year":"2009","journal-title":"Conformal Prediction for Reliable Machine Learning: Theory, Adaptations and Applications"},{"issue":"11","key":"10.3233\/IDA-226811_ref32","doi-asserted-by":"crossref","first-page":"4477","DOI":"10.1007\/s12652-019-01417-9","article-title":"Performance evaluation of unsupervised techniques in cyber-attack anomaly detection","volume":"11","author":"Meira","year":"2020","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"issue":"9","key":"10.3233\/IDA-226811_ref33","doi-asserted-by":"crossref","first-page":"1796","DOI":"10.1109\/TKDE.2018.2806975","article-title":"Relationship between variants of one-class nearest neighbors and creating their accurate ensembles","volume":"30","author":"Khan","year":"2018","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/IDA-226811_ref35","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.procs.2015.07.321","article-title":"Condition based maintenance in railway transportation systems based on big data streaming analysis","volume":"53","author":"Fumeo","year":"2015","journal-title":"Procedia Computer Science"},{"issue":"11","key":"10.3233\/IDA-226811_ref36","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/j.ifacol.2018.08.370","article-title":"Structuring data for intelligent predictive maintenance in asset management","volume":"51","author":"Aremu","year":"2018","journal-title":"IFAC-PapersOnLine"},{"issue":"October 2018","key":"10.3233\/IDA-226811_ref37","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.trc.2019.07.020","article-title":"Data-driven predictive maintenance scheduling policies for railways","volume":"107","author":"Lopes Gerum","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"issue":"February","key":"10.3233\/IDA-226811_ref38","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.trc.2019.02.001","article-title":"Predictive maintenance using tree-based classification techniques: A case of railway switches","volume":"101","author":"Allah Bukhsh","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"10.3233\/IDA-226811_ref39","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.neucom.2018.05.017","article-title":"Anomaly detection and predictive maintenance for photovoltaic systems","volume":"310","author":"De Benedetti","year":"2018","journal-title":"Neurocomputing"},{"issue":"10","key":"10.3233\/IDA-226811_ref40","doi-asserted-by":"crossref","first-page":"6509","DOI":"10.1109\/TII.2020.2966033","article-title":"Achieving predictive and proactive maintenance for high-speed railway power equipment with LSTM-RNN","volume":"16","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.3233\/IDA-226811_ref41","unstructured":"D. Morandi and S. J\u00fcngling, Anomaly Detection in Railway Infrastructure, in: AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering, 2021."},{"issue":"1","key":"10.3233\/IDA-226811_ref42","doi-asserted-by":"crossref","first-page":"13","DOI":"10.3390\/app11010013","article-title":"Developing machine learning-based models for railway inspection","volume":"11","author":"Yang","year":"2021","journal-title":"Applied Sciences"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-226811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:20:09Z","timestamp":1777454409000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-226811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,20]]},"references-count":38,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/ida-226811","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,20]]}}}