We present a method for automatically extracting a health indicator of an industrial component from a set of signals measured during operation. Differently from traditional feature extraction and selection methods, which are labor-intensive and based on expert knowledge, the method proposed is automatic and completely unsupervised. Run-to-failure data collected during the component life are fed to a Sparse AutoEncoder (SAE), and the various features extracted from the hidden layer are evaluated to identify those providing the most accurate quantification of the component degradation. The method is applied to a synthetic and a bearing vibration dataset. The results show that the developed SAE-based method is able to automatically extract an efficient health indicator.

Automatic Extraction of a Health Indicator from Vibrational Data by Sparse Autoencoders

Yang Z.;Baraldi P.;Zio E.
2019-01-01

Abstract

We present a method for automatically extracting a health indicator of an industrial component from a set of signals measured during operation. Differently from traditional feature extraction and selection methods, which are labor-intensive and based on expert knowledge, the method proposed is automatic and completely unsupervised. Run-to-failure data collected during the component life are fed to a Sparse AutoEncoder (SAE), and the various features extracted from the hidden layer are evaluated to identify those providing the most accurate quantification of the component degradation. The method is applied to a synthetic and a bearing vibration dataset. The results show that the developed SAE-based method is able to automatically extract an efficient health indicator.
2019
Proceedings - 2018 3rd International Conference on System Reliability and Safety, ICSRS 2018
978-1-7281-0238-2
deep learning; Feature extraction; health indicator; sparse autoencoder; vibration data
File in questo prodotto:
File Dimensione Formato  
2019_ICSRS_Yang_Baraldi_Zio_autoencoders.pdf

accesso aperto

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 435.78 kB
Formato Adobe PDF
435.78 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1122904
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 6
social impact