Computational Technology Resources - CCC

J.-Y. Shih, M. Entezami, N. Zhao, M.R. Salami, Y. Liu, J. Ye, X. Lyu, E. Stewart, "Real-Time Damage Assessment of Bridge Strike Events Using a Bayesian Digital Twin", 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 2.1, 2026, doi:10.4203/ccc.15.2.1

Keywords: bridge strike, finite element, digital twin, Bayesian, railway bridge dynamics, collision risk assessment.

Abstract

Bridge strikes represent a persistent and growing challenge for rail infrastructure in the UK with an average of five incidents occurring daily and up to ten during peak periods. Approximately 2,000 strikes annually lead to significant service disruption and an estimated economic cost of £23 million. This paper presents a real-time Digital Twin framework for post-impact structural assessment of railway bridges. The proposed system integrates LiDAR sensing, AI-enhanced computer vision for real-time telemetry, synchronised via edge computing with a Bayesian inference model informed by high-fidelity finite element (FE) simulations. A total of 144 impact scenarios were simulated for a representative heritage steel bridge, enabling the construction of a Bayesian Inference Table capable of rapidly estimating damage states in terms of rail alignment and permanent steel deformation. The framework translates probabilistic damage predictions into operational decisions using a Red-Orange-Yellow-Green (ROYG) classification, supporting immediate and risk-informed post-strike interventions.

download the full-text of this paper (PDF, 7 pages, 814 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 2.1 Real-Time Damage Assessment of Bridge Strike Events Using a Bayesian Digital Twin J.-Y. Shih^1,2, M. Entezami¹, N. Zhao¹, M.R. Salami¹, Y. Liu¹, J. Ye¹, X. Lyu¹ and E. Stewart¹ ¹, University of Birmingham, United Kingdom ², Zynamic Engineering AB, Stockholm, Sweden doi:10.4203/ccc.15.2.1 Full Bibliographic Reference for this paper J.-Y. Shih, M. Entezami, N. Zhao, M.R. Salami, Y. Liu, J. Ye, X. Lyu, E. Stewart, "Real-Time Damage Assessment of Bridge Strike Events Using a Bayesian Digital Twin", 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 2.1, 2026, doi:10.4203/ccc.15.2.1 Keywords: bridge strike, finite element, digital twin, Bayesian, railway bridge dynamics, collision risk assessment. Abstract Bridge strikes represent a persistent and growing challenge for rail infrastructure in the UK with an average of five incidents occurring daily and up to ten during peak periods. Approximately 2,000 strikes annually lead to significant service disruption and an estimated economic cost of £23 million. This paper presents a real-time Digital Twin framework for post-impact structural assessment of railway bridges. The proposed system integrates LiDAR sensing, AI-enhanced computer vision for real-time telemetry, synchronised via edge computing with a Bayesian inference model informed by high-fidelity finite element (FE) simulations. A total of 144 impact scenarios were simulated for a representative heritage steel bridge, enabling the construction of a Bayesian Inference Table capable of rapidly estimating damage states in terms of rail alignment and permanent steel deformation. The framework translates probabilistic damage predictions into operational decisions using a Red-Orange-Yellow-Green (ROYG) classification, supporting immediate and risk-informed post-strike interventions. download the full-text of this paper (PDF, 7 pages, 814 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