A hierarchical decision-making framework for the assessment of the prediction capability of prognostic methods - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability Année : 2017

A hierarchical decision-making framework for the assessment of the prediction capability of prognostic methods

Résumé

8 In Prognostics and Health Management (PHM), the prediction capability of a prognostic method refers to its 9 ability to provide trustable predictions of the Remaining Useful Life (RUL), with the quality characteristics 10 required by the related maintenance decision making. The prediction capability heavily influences the decision 11 maker's attitude towards taking the risk of using the predicted RUL to inform the maintenance decisions. In this 12 paper, a four-layer, top-down, hierarchical decision making framework is proposed to assess the prediction 13 capability of prognostic methods. In the framework, prediction capability is broken down into two criteria (Layer 2), 14 six sub-criteria (Layer 3) and 19 basic sub-criteria (Layer 4). Based on the hierarchical framework, a bottom-up, 15 quantitative approach is developed for the assessment of the prediction capability, using the information and data 16 collected at the Layer-4 basic sub-criteria level. Analytical Hierarchical Process (AHP) is applied for the evaluation 17 and aggregation of the sub-criteria and Support Vector Machine (SVM) is applied to develop a classification-based 18 approach for prediction capability assessment. The framework and quantitative approach are applied on a simulated 19 case study to assess the prediction capabilities of three prognostic methods of literature: fuzzy similarity, 20 feed-forward neural network and hidden semi-Markov model. The results show the feasibility of the practical 21 application of the framework and its quantitative assessment approach, and that the assessed prediction capability 22 can be used to support the selection of the suitable prognostic method for a given application.
Fichier principal
Vignette du fichier
Draft_Maturity of prognostic methods_20161014-2ndRevision.pdf (1.43 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01632275 , version 1 (09-11-2017)

Identifiants

Citer

Zhiguo Zeng, Francesco Di Maio, Enrico Zio, Rui Kang. A hierarchical decision-making framework for the assessment of the prediction capability of prognostic methods. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2017, 231 (1), pp.36 - 52. ⟨10.1177/1748006X16683321⟩. ⟨hal-01632275⟩
102 Consultations
204 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More