Computational Technology Resources - CCP

Keywords: prognosis, diagnosis, predictive maintenance, dynamic Bayesian networks, graphical duration models, algorithm.

Summary

Transport systems are more and more complex and the number of users is increasing. So, it is necessary both to increase the availability of the material and to guarantee a high level of security while ensuring reasonable maintenance costs. For this reason, the maintenance optimization of transport systems has become a key issue. Currently, industry jointly use systematic maintenance and corrective maintenance. For the reasons mentioned above, to optimize the logistic behind the maintenance, industry seeks to anticipate the failure time. That is why industry is now interested in predictive maintenance based on the prognostic concept. Dynamic Bayesian networks (DBN) are powerful mathematical tools that can model the behaviour of complex systems. The Markov property in a DBN implies that the time spent in each degradation state is exponentially distributed. To overcome this limitation, duration variables are introduced in and adapted by have been used. The Diagnostic and Maintenance group from IFSTTAR-GRETTIA developed a model called VirMaLab (Virtual Maintenance Laboratory) based on DBN and GDM to describe the degradation of a system and this diagnosis/maintenance process). This approach was already successfully applied to evaluate and optimize maintenance strategies of several railway systems, from various rail applications to some rolling stock components. If Bayesian networks were already used in some prognosis applications, their contribution was generally limited to provide some static decision making, not to estimate directly the RUL. The originality of the proposed study described in this paper lies in the integration of a dynamic RUL estimation represented with an explicit node in a DBN. In this paper, an online prognosis algorithm and its representation in a dynamic Bayesian network are presented. This algorithm is a first step towards the development of a online predictive maintenance policy that could be optimized using its representation in the VirMaLab DBN.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £65 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 104 PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 101 A Specific Dynamic Bayesian Network for a Prognosis based Maintenance Strategy J. Foulliaron¹, L. Bouillaut¹, P. Aknin¹ and A. Baros² ¹Université Paris-Est, IFSTTAR, GRETTIA, Cité Descartes, Marne-la-Vallée, Paris, France ²Université de Technologie de Troyes, Institut Charles Delaunay, Troyes, France doi:10.4203/ccp.104.101 purchase the full-text of this paper Full Bibliographic Reference for this paper J. Foulliaron, L. Bouillaut, P. Aknin, A. Baros, "A Specific Dynamic Bayesian Network for a Prognosis based Maintenance Strategy", in J. Pombo, (Editor), "Proceedings of the Second International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Stirlingshire, UK, Paper 101, 2014. doi:10.4203/ccp.104.101 Keywords: prognosis, diagnosis, predictive maintenance, dynamic Bayesian networks, graphical duration models, algorithm. Summary Transport systems are more and more complex and the number of users is increasing. So, it is necessary both to increase the availability of the material and to guarantee a high level of security while ensuring reasonable maintenance costs. For this reason, the maintenance optimization of transport systems has become a key issue. Currently, industry jointly use systematic maintenance and corrective maintenance. For the reasons mentioned above, to optimize the logistic behind the maintenance, industry seeks to anticipate the failure time. That is why industry is now interested in predictive maintenance based on the prognostic concept. Dynamic Bayesian networks (DBN) are powerful mathematical tools that can model the behaviour of complex systems. The Markov property in a DBN implies that the time spent in each degradation state is exponentially distributed. To overcome this limitation, duration variables are introduced in and adapted by have been used. The Diagnostic and Maintenance group from IFSTTAR-GRETTIA developed a model called VirMaLab (Virtual Maintenance Laboratory) based on DBN and GDM to describe the degradation of a system and this diagnosis/maintenance process). This approach was already successfully applied to evaluate and optimize maintenance strategies of several railway systems, from various rail applications to some rolling stock components. If Bayesian networks were already used in some prognosis applications, their contribution was generally limited to provide some static decision making, not to estimate directly the RUL. The originality of the proposed study described in this paper lies in the integration of a dynamic RUL estimation represented with an explicit node in a DBN. In this paper, an online prognosis algorithm and its representation in a dynamic Bayesian network are presented. This algorithm is a first step towards the development of a online predictive maintenance policy that could be optimized using its representation in the VirMaLab DBN. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £65 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions