Computational Technology Resources - CCC

Paper 8.7

Hybrid Modelling Based on Non Homogeneous Poisson Process for Predictive Maintenance

doi:10.4203/ccc.15.8.7

D. Collot, V. Laurent, O. Vo Van, "Hybrid Modelling Based on Non Homogeneous Poisson Process for Predictive Maintenance", 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 8.7, 2026, doi:10.4203/ccc.15.8.7

Keywords: rail, squats, rolling contact fatigue, machine learning, hybrid model, Poisson process.

Abstract

Predictive maintenance requires models that can predict the occurrence of defaults on a network. The method described in this paper overcomes two limitations of classical models. First it also predicts the effect of the maintenance on the lifespan, in a way easy to infer from a dataset. Second it includes inputs from physics models, that reinforce the confidence in extrapolation. This method is based on Non Homogeneous Poisson process and has been tested on squats default occurring on rails in the French railroad network.

download the full-text of this paper (PDF, 8 pages, 453 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 8.7 Hybrid Modelling Based on Non Homogeneous Poisson Process for Predictive Maintenance D. Collot¹, V. Laurent¹ and O. Vo Van² ¹MewsLabs, MewsPartner, France ², SNCF, France doi:10.4203/ccc.15.8.7 Full Bibliographic Reference for this paper D. Collot, V. Laurent, O. Vo Van, "Hybrid Modelling Based on Non Homogeneous Poisson Process for Predictive Maintenance", 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 8.7, 2026, doi:10.4203/ccc.15.8.7 Keywords: rail, squats, rolling contact fatigue, machine learning, hybrid model, Poisson process. Abstract Predictive maintenance requires models that can predict the occurrence of defaults on a network. The method described in this paper overcomes two limitations of classical models. First it also predicts the effect of the maintenance on the lifespan, in a way easy to infer from a dataset. Second it includes inputs from physics models, that reinforce the confidence in extrapolation. This method is based on Non Homogeneous Poisson process and has been tested on squats default occurring on rails in the French railroad network. download the full-text of this paper (PDF, 8 pages, 453 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