Today’s deep learning strategies require ever‐increasing computational efforts and demand for very large amounts of labelled data. Providing such expensive resources for machine diagnosis is highly challenging. Transfer learning recently emerged as a valuable approach to address these issues. Thus, the knowledge learned by deep architectures in different scenarios can be reused for the purpose of machine diagnosis, minimizing data collecting efforts. Existing research provides evidence that networks pre‐trained for image recognition can classify machine vibrations in the time‐frequency domain by means of transfer learning. So far, however, there has been little discussion about the potentials included in networks pre‐trained for sound recognition, which are inherently suited for time‐frequency tasks. This work argues that deep architectures trained for music recognition and sound detection can perform machine diagnosis. The YAMNet convolutional network was designed to serve extremely efficient mobile applications for sound detection, and it was originally trained on millions of data extracted from YouTube clips. That framework is employed to detect bearing faults for the CWRU dataset. It is shown that transferring knowledge from sound and music recognition to bearing fault detection is successful. The maximum accuracy is achieved using a few hundred data for fine‐tuning the fault diagnosis model.

Deep transfer learning for machine diagnosis: From sound and music recognition to bearing fault detection / Brusa, E.; Delprete, C.; Di Maggio, L. G.. - In: APPLIED SCIENCES. - ISSN 2076-3417. - 11:24(2021), p. 11663. [10.3390/app112411663]

Deep transfer learning for machine diagnosis: From sound and music recognition to bearing fault detection

Brusa E.;Delprete C.;Di Maggio L. G.
2021

Abstract

Today’s deep learning strategies require ever‐increasing computational efforts and demand for very large amounts of labelled data. Providing such expensive resources for machine diagnosis is highly challenging. Transfer learning recently emerged as a valuable approach to address these issues. Thus, the knowledge learned by deep architectures in different scenarios can be reused for the purpose of machine diagnosis, minimizing data collecting efforts. Existing research provides evidence that networks pre‐trained for image recognition can classify machine vibrations in the time‐frequency domain by means of transfer learning. So far, however, there has been little discussion about the potentials included in networks pre‐trained for sound recognition, which are inherently suited for time‐frequency tasks. This work argues that deep architectures trained for music recognition and sound detection can perform machine diagnosis. The YAMNet convolutional network was designed to serve extremely efficient mobile applications for sound detection, and it was originally trained on millions of data extracted from YouTube clips. That framework is employed to detect bearing faults for the CWRU dataset. It is shown that transferring knowledge from sound and music recognition to bearing fault detection is successful. The maximum accuracy is achieved using a few hundred data for fine‐tuning the fault diagnosis model.
2021
File in questo prodotto:
File Dimensione Formato  
2021BrusaDeepTransfer.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 27.09 MB
Formato Adobe PDF
27.09 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/11583/2947939