Contextualisation of Datasets for better classification models: Application to Airbus Helicopters Flight Data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Contextualisation of Datasets for better classification models: Application to Airbus Helicopters Flight Data

Marie Le Guilly
Nassia Daouayry
  • Fonction : Auteur
  • PersonId : 1076683
Pierre-Loic Maisonneuve
  • Fonction : Auteur
  • PersonId : 963941
  • IdRef : 192202499
Ammar Mechouche
  • Fonction : Auteur
  • PersonId : 964591
Jean-Marc Petit
Vasile-Marian Scuturici

Résumé

For helicopters, anticipating failures is crucial. To this end, the analysis of flight data allows to develop predictive maintenance approaches , for which Airbus Helicopters (AH) has proposed several solutions , some based on machine learning using predictive models. One recurrent problem in this setting is the contextualization of the data, that is to identify the data better fitting the phenomenon being mod-eled. Indeed, helicopters are complex systems going through different flight phases. Experts therefore have to identify the adequate ones, in which the selected flight parameters are stable and consistent with the studied problem. In this paper, we propose a generic solution to con-textualize classification data, and present an experimental study on AH flight data: the results are encouraging and allow to keep domain experts involved the process.
Fichier principal
Vignette du fichier
ADBIS_2020_paper47.pdf (255.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02933410 , version 1 (08-09-2020)

Identifiants

Citer

Marie Le Guilly, Nassia Daouayry, Pierre-Loic Maisonneuve, Ammar Mechouche, Jean-Marc Petit, et al.. Contextualisation of Datasets for better classification models: Application to Airbus Helicopters Flight Data. ADBIS - 24th European Conference on Advances in Databases and Information Systems, Aug 2020, Lyon, France. ⟨10.1007/978-3-030-54623-6_4⟩. ⟨hal-02933410⟩
139 Consultations
339 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More