Performance of prognosis indicators for superimposed renewal processes - Université de technologie de Troyes Accéder directement au contenu
Article Dans Une Revue Probability in the Engineering and Informational Sciences Année : 2020

Performance of prognosis indicators for superimposed renewal processes

Résumé

The paper deals with prognosis estimation for industrial systems in a series configuration, modeled by superimposed renewal processes (SRP), when the cause of failures is not available. In the presence of missing information, an SRP is commonly approximated by a Poisson process or a virtual age model. The performance of the approximations was assessed in the ideal configuration where all parameters of the models are known. The current article adopts a practitioner's perspective by assuming that the parameters of the models are unknown and must be estimated. In addition to inference procedures, the assessment of the prognosis indicators, such as the remaining useful life, is discussed. Finally, we investigate a fleet of infrastructure components of the Norwegian railway network operated by Bane NOR.
Fichier principal
Vignette du fichier
liu2020.pdf (632.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04453678 , version 1 (20-02-2024)

Identifiants

Citer

Xingheng Liu, Yann Dijoux, Jørn Vatn, Håkon Toftaker. Performance of prognosis indicators for superimposed renewal processes. Probability in the Engineering and Informational Sciences, 2020, 36 (1), pp.17-40. ⟨10.1017/S0269964820000327⟩. ⟨hal-04453678⟩
20 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More