Research of bearing fault diagnosis method based on wavelet singular entropy and support vector machine

Haohua Xia

doi:10.1117/12.2641513

19 October 2022 Research of bearing fault diagnosis method based on wavelet singular entropy and support vector machine

Haohua Xia

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 1229407 (2022) https://doi.org/10.1117/12.2641513
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

Electric Motors play a vital role in various aspects of production and life. Once a motor fails, the loss will be incalculable, and the state of motor bearings will directly affect the reliability of motor operation. Due to the high failure rate of motor bearings and the difficulty of accurately identifying fault types, a fault diagnosis method based on Wavelet Singular Entropy (SEM) and Support Vector Machine (SVM) was proposed. The fault was implanted into the motor bearing by electro-discharge machining (EDM), and the vibration signal samples of 4 different state types were measured. The characteristics of the four state type vibration signals are extracted with wallet singular entropy, and the state classification of the data after feature extraction is carried out by the support vector machine classifier. The experimental research shows that the fault diagnosis method of motor bearing based on wavelet singular entropy and support vector machine can greatly improve the fault diagnosis accuracy.

Citation Download Citation

Haohua Xia "Research of bearing fault diagnosis method based on wavelet singular entropy and support vector machine", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 1229407 (19 October 2022); https://doi.org/10.1117/12.2641513

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available