Computational Technology Resources - CCC

A. Sansiñena^1,2, B. Rodríguez-Arana^1,2 and S. Arrizabalaga^1,2,3

¹, Ceit-Basque Research and Technology Alliance (BRTA), Donostia – San Sebastián, Spain
²Tecnun, Universidad de Navarra, Donostia – San Sebastián, Spain
³Institute of Data Science and Artificial Intelligence (DATAI), Universidad de Navarra, Pamplona, Spain

doi:10.4203/ccc.15.8.2

A. Sansiñena, B. Rodríguez-Arana, S. Arrizabalaga, "Transfer Learning in Railway Health Monitoring: Taxonomy, Applications and Future Directions", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 8.2, 2026, doi:10.4203/ccc.15.8.2

Keywords: transfer learning, railway infrastructure, faults assessment, machine learning, data scarcity, unsupervised domain adaptation.

Abstract

The deployment of Machine Learning (ML) and Deep Learning (DL) approaches for railway health monitoring is frequently hindered by the scarcity of labelled data and the inherent domain shift between controlled laboratory conditions and diverse operational environments. In recent years, Transfer Learning (TL) has emerged as a critical paradigm to enable the application of ML and DL models in real scenarios, ensuring the strict safety and precision conditions required in the railway industry. In this paper, a comprehensive survey on the recent advancements in TL with regard to the assessment of railway assets is provided. A taxonomy is established based on the availability of data in the target domain to serve as a brief guide for new researchers interested in TL. To highlight the potential of these techniques, the latest applications on different railway assets, including faults in tracks, brake pads and bearings, are evaluated. Finally, trends and gaps for the future research are identified.

download the full-text of this paper (PDF, 11 pages, 809 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 15 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 8.2 Transfer Learning in Railway Health Monitoring: Taxonomy, Applications and Future Directions A. Sansiñena^1,2, B. Rodríguez-Arana^1,2 and S. Arrizabalaga^1,2,3 ¹, Ceit-Basque Research and Technology Alliance (BRTA), Donostia – San Sebastián, Spain ²Tecnun, Universidad de Navarra, Donostia – San Sebastián, Spain ³Institute of Data Science and Artificial Intelligence (DATAI), Universidad de Navarra, Pamplona, Spain doi:10.4203/ccc.15.8.2 Full Bibliographic Reference for this paper A. Sansiñena, B. Rodríguez-Arana, S. Arrizabalaga, "Transfer Learning in Railway Health Monitoring: Taxonomy, Applications and Future Directions", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 8.2, 2026, doi:10.4203/ccc.15.8.2 Keywords: transfer learning, railway infrastructure, faults assessment, machine learning, data scarcity, unsupervised domain adaptation. Abstract The deployment of Machine Learning (ML) and Deep Learning (DL) approaches for railway health monitoring is frequently hindered by the scarcity of labelled data and the inherent domain shift between controlled laboratory conditions and diverse operational environments. In recent years, Transfer Learning (TL) has emerged as a critical paradigm to enable the application of ML and DL models in real scenarios, ensuring the strict safety and precision conditions required in the railway industry. In this paper, a comprehensive survey on the recent advancements in TL with regard to the assessment of railway assets is provided. A taxonomy is established based on the availability of data in the target domain to serve as a brief guide for new researchers interested in TL. To highlight the potential of these techniques, the latest applications on different railway assets, including faults in tracks, brake pads and bearings, are evaluated. Finally, trends and gaps for the future research are identified. download the full-text of this paper (PDF, 11 pages, 809 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions