Investigation of uncertainty treatment capability of model-based and data-driven prognostic methods using simulated data

Piero Baraldi; Francesca Mangili; Enrico Zio

doi:10.1016/j.ress.2012.12.004

Investigation of uncertainty treatment capability of model-based and data-driven prognostic methods using simulated data

Piero Baraldi ¹ Francesca Mangili ¹ Enrico Zio ²

2 SSEC - Chaire Sciences des Systèmes et Défis Energétiques EDF/ECP/Supélec

Abstract : We look at different prognostic approaches and the way of quantifying confidence in equipment Remaining Useful Life (RUL) prediction. More specifically, we consider: (1) a particle filtering scheme, based on a physics-based model of the degradation process; (2) a bootstrapped ensemble of empirical models trained on a set of degradation observations measured on equipments similar to the one of interest; (3) a bootstrapped ensemble of empirical models trained on a sequence of past degradation observations from the equipment of interest only. The ability of these three approaches in providing measures of confidence for the RUL predictions is evaluated in the context of a simulated case study of interest in the nuclear power generation industry and concerning turbine blades affected by developing creeps. The main contribution of the work is the critical investigation of the capabilities of different prognostic approaches to deal with various sources of uncertainty in the RUL prediction.

Type de document :

Article dans une revue

Reliability Engineering and System Safety, Elsevier, 2013, 112, pp.94-108. 〈10.1016/j.ress.2012.12.004〉

Domaine :

Sciences de l'ingénieur [physics]

Liste complète des métadonnées

Littérature citée [54 références] Voir Masquer Télécharger

https://hal-supelec.archives-ouvertes.fr/hal-00934547
Contributeur : Yanfu Li <>
Soumis le : mercredi 22 janvier 2014 - 13:45:03
Dernière modification le : jeudi 5 avril 2018 - 12:30:14
Document(s) archivé(s) le : mercredi 23 avril 2014 - 01:25:10

RESS_Preprint_Uncertainty_trea...

Fichiers produits par l'(les) auteur(s)

Investigation of uncertainty treatment capability of model-based and data-driven prognostic methods using simulated data

Fichier

Identifiants

Collections

Citation

Exporter

Métriques

259

393

Contact

Investigation of uncertainty treatment capability of model-based and data-driven prognostic methods using simulated data

Fichier

Identifiants

Collections

Citation

Exporter

Partager

Métriques

259

393

Contact