Deep Transfer Learning for Machine Diagnosis: From Sound and Music Recognition to Bearing Fault Detection

Eugenio Brusa,Luigi Gianpio Di Maggio,Cristiana Delprete

doi:10.3390/app112411663

Eugenio Brusa, Luigi Gianpio Di Maggio + Show 1 more

Open Access

PDF Available

https://doi.org/10.3390/app112411663

Copy DOI

Export

Save

Cite

Journal: Applied Sciences	Publication Date: Dec 8, 2021
Citations: 27	License type: CC BY 4.0

Affiliation: Polytechnic University of Turin

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

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.

Highlights

Regular and scheduled maintenance strategies are still employed in many industrial contexts, the needs to rely on condition-based monitoring for machine health management have become increasingly pronounced due to several reasons
This study shows that this knowledge transfer efficiently works for a small dataset containing vibration signals
This study aimed at investigating the capabilities of deep networks pre-trained on sound events in fulfilling bearing fault diagnosis

Summary

Introduction

Regular and scheduled maintenance strategies are still employed in many industrial contexts, the needs to rely on condition-based monitoring for machine health management have become increasingly pronounced due to several reasons. The useful life of some machine components is characterized by a marked statistical scatter, as in the case of rolling element bearings (REBs) [1]. The structural health of rotors and REBs affect each other in actual operating conditions, given the underlying coupling between their dynamic behavior. These issues hardly comply with the requirements of modern industry, which increasingly tends to embrace the advantages offered by condition-based monitoring in terms of cost savings and production targets attainment [3]. Machine fault diagnosis concerns the study of techniques aimed at detecting, isolating, and identifying machinery faults on the basis of monitoring data [4,5]

Objectives

Findings

Discussion

Conclusion