Skip to Main content Skip to Navigation
Theses

Modèles Probabilistes de Séquences Temporelles et Fusion de Décisions.
Application à la Classification de Défauts de Rails et à leur Maintenance

Abstract : This Ph. D. work is related to the railway application domain and more precisely to the diagnosis of the rail faults and the optimal maintenance decision to restore the rails.
In that way, the contribution is formalized on two complementary points of view:
- for improving the existing diagnosis system on the fault classification in order to obtain more reliable results on the degration states of the rail. A new approach is proposed which is based on the merging of two different flow of informations (local and global).
- for proposing a new approach of conditional maintenance optimisation of the rails by integrating not only technical criterion but also economic and functional ones.
The modelling techniques used for supporting these formalisation are mainly Bayesian Networks and MDP.
Document type :
Theses
Complete list of metadatas

Cited literature [156 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00325011
Contributor : Benoit Iung <>
Submitted on : Thursday, September 25, 2008 - 7:01:16 PM
Last modification on : Friday, October 23, 2020 - 8:38:02 AM
Long-term archiving on: : Friday, June 4, 2010 - 11:49:01 AM

Identifiers

  • HAL Id : tel-00325011, version 1

Collections

Citation

Abdeljabbar Ben Salem. Modèles Probabilistes de Séquences Temporelles et Fusion de Décisions.
Application à la Classification de Défauts de Rails et à leur Maintenance. Automatique / Robotique. Université Henri Poincaré - Nancy I, 2008. Français. ⟨tel-00325011⟩

Share

Metrics

Record views

635

Files downloads

895