Computational Technology Resources - CCC

J.-Y. Shih^1,2, C.-M. Kuo¹, L.-W. Chen³, K.-Y. Liu⁴, C.-K. Chen⁴ and M. Wang⁴

¹, National Cheng Kung University, Taiwan
², Zynamic Engineering AB, Stockholm, Sweden
³, Grand Wisdom Technology Ltd., Taiwan
⁴, China Engineering Consultants, Inc., Taiwan

doi:10.4203/ccc.15.6.9

J.-Y. Shih, C.-M. Kuo, L.-W. Chen, K.-Y. Liu, C.-K. Chen, M. Wang, "Real-Time IoT-Driven Predictive Maintenance: An Integrated Monitoring System for Railway Turnouts and Infrastructure", 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 6.9, 2026, doi:10.4203/ccc.15.6.9

Keywords: turnouts, wireless, IoT, track geometry, predictive maintenance, condition monitoring.

Abstract

Railway turnouts are critical infrastructure requiring precise maintenance. This paper introduces an integrated Internet of Things (IoT) system utilizing wireless vibration nodes and solar-powered gateways. To optimize network efficiency and minimize power consumption, the nodes perform initial edge processing, including low-pass filtering and downsampling, to transmit only peak acceleration and processed datasets. The gateway then process the second analysis, applying a time-window during the train passage to calculate acceleration RMS values, train speed via harmonic frequencies, and sleeper displacement through double integration. These metrics enable the real-time derivation of track geometry parameters, specifically level, twist, lateral, and vertical irregularities. Field results conducted in Kaohsiung Taiwan has validate the system’s performance. It successfully identified a loss of lateral resistance in sleepers during heavy rain and quantified vibration mitigation following bolt and joint maintenance. Furthermore, the system captured a significant reduction in both vertical and lateral irregularities immediately following tamping operations. The proposed system facilitates a transition toward predictive maintenance, enhancing operational safety while significantly reducing lifecycle costs for railway infrastructure.

download the full-text of this paper (PDF, 9 pages, 854 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 6.9 Real-Time IoT-Driven Predictive Maintenance: An Integrated Monitoring System for Railway Turnouts and Infrastructure J.-Y. Shih^1,2, C.-M. Kuo¹, L.-W. Chen³, K.-Y. Liu⁴, C.-K. Chen⁴ and M. Wang⁴ ¹, National Cheng Kung University, Taiwan ², Zynamic Engineering AB, Stockholm, Sweden ³, Grand Wisdom Technology Ltd., Taiwan ⁴, China Engineering Consultants, Inc., Taiwan doi:10.4203/ccc.15.6.9 Full Bibliographic Reference for this paper J.-Y. Shih, C.-M. Kuo, L.-W. Chen, K.-Y. Liu, C.-K. Chen, M. Wang, "Real-Time IoT-Driven Predictive Maintenance: An Integrated Monitoring System for Railway Turnouts and Infrastructure", 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 6.9, 2026, doi:10.4203/ccc.15.6.9 Keywords: turnouts, wireless, IoT, track geometry, predictive maintenance, condition monitoring. Abstract Railway turnouts are critical infrastructure requiring precise maintenance. This paper introduces an integrated Internet of Things (IoT) system utilizing wireless vibration nodes and solar-powered gateways. To optimize network efficiency and minimize power consumption, the nodes perform initial edge processing, including low-pass filtering and downsampling, to transmit only peak acceleration and processed datasets. The gateway then process the second analysis, applying a time-window during the train passage to calculate acceleration RMS values, train speed via harmonic frequencies, and sleeper displacement through double integration. These metrics enable the real-time derivation of track geometry parameters, specifically level, twist, lateral, and vertical irregularities. Field results conducted in Kaohsiung Taiwan has validate the system’s performance. It successfully identified a loss of lateral resistance in sleepers during heavy rain and quantified vibration mitigation following bolt and joint maintenance. Furthermore, the system captured a significant reduction in both vertical and lateral irregularities immediately following tamping operations. The proposed system facilitates a transition toward predictive maintenance, enhancing operational safety while significantly reducing lifecycle costs for railway infrastructure. download the full-text of this paper (PDF, 9 pages, 854 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