Unsupervised anomaly detection for Aircraft Condition Monitoring System - Université Paris Cité Accéder directement au contenu
Ouvrages Année : 2015

Unsupervised anomaly detection for Aircraft Condition Monitoring System

Mohamed Cherif Dani
  • Fonction : Directeur scientifique
  • PersonId : 969083
François-Xavier Jollois
  • Fonction : Directeur scientifique
  • PersonId : 761224
  • IdRef : 076085791
Freixo Cassiano
  • Fonction : Directeur scientifique
Mohamed Nadif

Résumé

Anomaly detection is an important field for the anticipation of aircraft maintenance operations, working as an enabler of diagnostic and prognostic functions. A method has been implemented to detect abnormal data in Aircraft Condition Monitoring System (ACMS) records. Rather than using already known and usual detection triggers which are partial detectors and insensitive to new flight and system conditions, this method automatically extracts abnormal data points without requiring any a priori information about the system and its conditions. To accomplish this objective, we propose to combine a segmentation based and density clustering approaches for detecting and filtering anomalies. This method was applied on A340 ACMS data recordings. The detection logics associated with the new anomalies can be used as new detection conditions to be potentially implemented onboard, further extending legacy detection capabilities.
Fichier non déposé

Dates et versions

hal-01186955 , version 1 (25-08-2015)

Identifiants

Citer

Mohamed Cherif Dani, François-Xavier Jollois, Freixo Cassiano, Mohamed Nadif (Dir.). Unsupervised anomaly detection for Aircraft Condition Monitoring System . , 2015, 10.1109/AERO.2015.7119138. ⟨10.1109/AERO.2015.7119138⟩. ⟨hal-01186955⟩

Collections

LIPADE UP-SCIENCES
122 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More