Vacuum pump fault monitoring system based on wavelet packet energy and improved random forest

Xiaoxu Li; Zhenshan Ji; Yong Wang; Xiaolin Yuan; Shaoqing Liu

doi:10.1117/12.2639688

19 October 2022 Vacuum pump fault monitoring system based on wavelet packet energy and improved random forest

Xiaoxu Li, Zhenshan Ji, Yong Wang, Xiaolin Yuan, Shaoqing Liu

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 1229404 (2022) https://doi.org/10.1117/12.2639688
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

In order to monitor the working condition of vacuum pump in real time and find the fault equipment, implemented a vacuum pump fault monitoring system. The system includes data acquisition, fault diagnosis, information display and other functions. It uses multi-thread and producer-consumer model to realize thread-safe data flow, and has a graphical interface. The system collects data, calculates its wavelet packet energy, selects the feature by mean decrease impurity method, and then uses the improved random forest algorithm for diagnosis after optimizing the weight of decision tree by out of bag estimation. Through testing, the accuracy of the improved model is more than 95%, and the system can realize real-time judgment, which has achieved good effect in practical application.

Citation Download Citation

Xiaoxu Li, Zhenshan Ji, Yong Wang, Xiaolin Yuan, and Shaoqing Liu "Vacuum pump fault monitoring system based on wavelet packet energy and improved random forest", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 1229404 (19 October 2022); https://doi.org/10.1117/12.2639688

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