Computational Technology Resources - CCC

P. Hadraba¹, R. Krcek¹, J. Chalupa¹, M. Hruzikova², F. Kšica¹ and Z. Hadas¹

¹Faculty of Mechanical Engineering, Brno University of Technology, Czech Republic
²Faculty of Cvil Engineering, Brno University of Technology, Czechia

doi:10.4203/ccc.15.17.11

P. Hadraba, R. Krcek, J. Chalupa, M. Hruzikova, F. Kšica, Z. Hadas, "Low-Power Edge Processing of MFC Sensor Signals for Wayside Railway Monitoring", 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 17.11, 2026, doi:10.4203/ccc.15.17.11

Keywords: wayside railway monitoring, edge computing, macro fiber composite sensor, vehicle–track interaction, low-power sensing, axle detection, anomaly indication.

Abstract

This paper presents a low-power edge measurement node for rail-mounted Macro Fiber Composite (MFC) sensing in railway wayside monitoring. The system acquires train-passage responses directly at the rail, performs local passage detection, axle localization, vehicle-context extraction and anomaly indication, and reports compact diagnostic payloads instead of complete high-rate waveforms. The paper discusses the coupled vehicle--track interpretation of the measured signal, compares charge-amplifier and current-converter readout of the MFC sensor, and demonstrates event-based edge processing on field data. The results show that passage-level and bogie-level descriptors can be extracted locally, reducing communication requirements while preserving information relevant to both infrastructure monitoring and vehicle running gear assessment.

download the full-text of this paper (PDF, 14 pages, 380 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 17.11 Low-Power Edge Processing of MFC Sensor Signals for Wayside Railway Monitoring P. Hadraba¹, R. Krcek¹, J. Chalupa¹, M. Hruzikova², F. Kšica¹ and Z. Hadas¹ ¹Faculty of Mechanical Engineering, Brno University of Technology, Czech Republic ²Faculty of Cvil Engineering, Brno University of Technology, Czechia doi:10.4203/ccc.15.17.11 Full Bibliographic Reference for this paper P. Hadraba, R. Krcek, J. Chalupa, M. Hruzikova, F. Kšica, Z. Hadas, "Low-Power Edge Processing of MFC Sensor Signals for Wayside Railway Monitoring", 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 17.11, 2026, doi:10.4203/ccc.15.17.11 Keywords: wayside railway monitoring, edge computing, macro fiber composite sensor, vehicle–track interaction, low-power sensing, axle detection, anomaly indication. Abstract This paper presents a low-power edge measurement node for rail-mounted Macro Fiber Composite (MFC) sensing in railway wayside monitoring. The system acquires train-passage responses directly at the rail, performs local passage detection, axle localization, vehicle-context extraction and anomaly indication, and reports compact diagnostic payloads instead of complete high-rate waveforms. The paper discusses the coupled vehicle--track interpretation of the measured signal, compares charge-amplifier and current-converter readout of the MFC sensor, and demonstrates event-based edge processing on field data. The results show that passage-level and bogie-level descriptors can be extracted locally, reducing communication requirements while preserving information relevant to both infrastructure monitoring and vehicle running gear assessment. download the full-text of this paper (PDF, 14 pages, 380 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