Computational Technology Resources - CCC

W. Queiroz¹, P. Pizzigatti Correa¹, R. Motta², P. Pereira², O. Gogliano¹ and L. Bernucci²

¹Department of Computer Engineering, Polytechnic School, University of São Paulo (USP), Brazil
²Department of Civil Engineering, Polytechnic School, University of São Paulo (USP), Brazil

doi:10.4203/ccc.15.17.9

W. Queiroz, P. Pizzigatti Correa, R. Motta, P. Pereira, O. Gogliano, L. Bernucci, "Composite Severity Score for Heavy-Haul Railway Track Assessment Using Dynamic, Geometric, and Contextual Information", 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 17.9, 2026, doi:10.4203/ccc.15.17.9

Keywords: railway infrastructure, condition monitoring, severity classification, serverity classification, composite score, predictive maintenance, railway track geometry, instrumented vehicle, dynamic response.

Abstract

We propose a composite severity score for track condition assessment on heavy-haul railways that combines multisensor dynamic response, structural context, geometric non-compliance, and recurrence in a formulation that remains applicable when some data sources are unavailable. The method is evaluated on approximately 11,000 track segments from August 2020 using instrumented-vehicle measurements, control-car geometry data, and a ground-truth log of confirmed defects and operational restrictions from the Estrada de Ferro Vitoria a Minas (EFVM), a Brazilian heavy-haul railway. Compared with the legacy fixed-threshold method, the proposed score increases recall for expert-confirmed critical segments from 52.3% to 81.6% and reduces the tendency to overclassify isolated signal peaks as high severity. In practical terms, the combined use of dynamic, geometric, and contextual information produces a more stable ranking for maintenance prioritisation.

download the full-text of this paper (PDF, 14 pages, 1340 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 17.9 Composite Severity Score for Heavy-Haul Railway Track Assessment Using Dynamic, Geometric, and Contextual Information W. Queiroz¹, P. Pizzigatti Correa¹, R. Motta², P. Pereira², O. Gogliano¹ and L. Bernucci² ¹Department of Computer Engineering, Polytechnic School, University of São Paulo (USP), Brazil ²Department of Civil Engineering, Polytechnic School, University of São Paulo (USP), Brazil doi:10.4203/ccc.15.17.9 Full Bibliographic Reference for this paper W. Queiroz, P. Pizzigatti Correa, R. Motta, P. Pereira, O. Gogliano, L. Bernucci, "Composite Severity Score for Heavy-Haul Railway Track Assessment Using Dynamic, Geometric, and Contextual Information", 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 17.9, 2026, doi:10.4203/ccc.15.17.9 Keywords: railway infrastructure, condition monitoring, severity classification, serverity classification, composite score, predictive maintenance, railway track geometry, instrumented vehicle, dynamic response. Abstract We propose a composite severity score for track condition assessment on heavy-haul railways that combines multisensor dynamic response, structural context, geometric non-compliance, and recurrence in a formulation that remains applicable when some data sources are unavailable. The method is evaluated on approximately 11,000 track segments from August 2020 using instrumented-vehicle measurements, control-car geometry data, and a ground-truth log of confirmed defects and operational restrictions from the Estrada de Ferro Vitoria a Minas (EFVM), a Brazilian heavy-haul railway. Compared with the legacy fixed-threshold method, the proposed score increases recall for expert-confirmed critical segments from 52.3% to 81.6% and reduces the tendency to overclassify isolated signal peaks as high severity. In practical terms, the combined use of dynamic, geometric, and contextual information produces a more stable ranking for maintenance prioritisation. download the full-text of this paper (PDF, 14 pages, 1340 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