A Non-Contact Fault Diagnosis Method for Rolling Bearings Based on Acoustic Imaging and Convolutional Neural Networks

Ran Wang,Fatao Hou,Qilin Hou,Weikang Jiang,Fengkai Liu,Longjing Yu

doi:10.1109/access.2020.3010272

Abstract

Rolling bearing fault diagnosis is conventionally performed by vibration-based diagnosis (VBD). However, VBD is restrained in some cases because vibration measurement usually requires the contact with the machine. Acoustical-based fault diagnosis (ABD) has the advantage of non-contact measurement over VBD. However, ABD has received little attention and rarely applied in bearing fault diagnosis. In this paper, a new non-contact ABD method for rolling bearings using acoustic imaging and convolutional neural networks (CNN) is proposed. Firstly, a microphone array is used to acquire the acoustic field radiated by rolling bearings. Then, acoustic imaging is performed with the wave superposition method (WSM). The reconstructed acoustic images can depict the spatial distribution of the acoustic field, which add a new spatial dimension in the acoustic data representation for fault diagnosis and makes it possible to localize the sound sources. Finally, CNN is applied to accomplish bearing fault diagnosis, which can overcome the problems of handcrafted feature extraction in traditional ABD methods. Experimental results verify the effectiveness of the proposed ABD method. Comparisons with peer state-of-the-art ABD methods further validate that the proposed method can mitigate the drawbacks of the existing ABD methods, and obtain more accurate and reliable diagnosis results.

Highlights

Rolling bearings are one of the vital components in rotating machinery, and their failure is one of the most frequent reasons for machine breakdown [1]
In order to compare with the proposed Acoustical-based fault diagnosis (ABD) method based on wave superposition method (WSM) and convolutional neural networks (CNN), the acoustic imaging tools adopted in these two methods are WSM
ABD method can overcome the limitation of vibration-based diagnosis (VBD) methods by virtue of its non-contact measurement

Summary

INTRODUCTION

Rolling bearings are one of the vital components in rotating machinery, and their failure is one of the most frequent reasons for machine breakdown [1]. Wang et al.: Non-Contact Fault Diagnosis Method for Rolling Bearings method in internal combustion engine fault diagnosis using fast Fourier transform(FFT) and correlation analysis In these studies, acoustic signals were recorded by one or several microphones, and processed by various traditional signal processing methods in the same way as vibration signals. As a powerful sound field visualization tool, the application of acoustic imaging in machinery fault diagnosis can overcome the difficulty of choosing measurement positions, and makes it possible to localize the sound sources in the machinery. WSM-based acoustic imaging facilitates the usage of the sufficient spatial distribution information of acoustic field in bearing fault diagnosis It makes the proposed ABD method possible to localize the sound sources and less sensitive to the measurement positions. Section describes the proposed ABD method for rolling bearings using acoustic imaging and a designed CNN model.

THEORY OF WAVE SUPERPOSITION METHOD

ROLLING BEARING FAUIL DIAGNOSIS USING ACOUSTIC IMAGIG AND CNN

STEP2: ACOUSTIC IMAGING

Findings

CONCLUSION