Skip to Main content Skip to Navigation
Journal articles

NMF-based decomposition for anomaly detection applied to vibration analysis

Abstract : In this paper, vibration analysis of civil aircraft engines in a test-bench to perform anomaly detection is considered. High bandwidth vibration measurements contain essential mechanical information regarding the condition of the engine and the localisation of damage, if present. In this case, vibration data are represented by spectrograms in the frequency domain, which are high-dimensional data that include both instrumental noise and non-discriminating information. Automatic algorithms for detecting specific damage are employed in order to provide a health status; however, these are hard to train. Experts from Snecma consistently perform visual analysis to confirm the health status of the engine. To develop an automatic extraction of relevant information in this high-dimensional context, the authors propose a novel representation of spectrograms based on a dimension reduction under the constraints of positivity, known as non-negative matrix factorisation (NMF). This method is consistent with the physics. In turn, the detection is based on distances in the reduced space. The algorithm is trained and tested with real engine vibration data, among which one engine has a signature representative of a damaged bearing. The method gives some encouraging results.
Document type :
Journal articles
Complete list of metadatas

https://hal-centralesupelec.archives-ouvertes.fr/hal-02526610
Contributor : Delphine Le Piolet <>
Submitted on : Tuesday, March 31, 2020 - 4:45:31 PM
Last modification on : Thursday, July 2, 2020 - 9:12:02 AM

Identifiers

Citation

Mina Abdel-Sayed, Daniel Duclos, Gilles Fay, Jerome Lacaille, Mathilde Mougeot. NMF-based decomposition for anomaly detection applied to vibration analysis. The International Journal of Condition Monitoring, the British Institute of Non-Destructive Testing, 2016, 6 (3), pp.73-81. ⟨10.1784/204764216819708104⟩. ⟨hal-02526610⟩

Share

Metrics

Record views

35