Presentation Details
A Fault-Mechanism Knowledge Integration-Based Method for Constructing Incipient Fault Early Warning Indicators in Bearings
ID：106
View Protection：ATTENDEE
Updated Time：2025-11-10 15:32:16 Hits：76
Poster Presentation
Start Time：Pending（Asia/Shanghai）
Duration：Pending
Session：No Session »
No files
Abstract
Bearing fault early warning methods based on signal characteristic values are commonly used for condition monitoring of industrial equipment. However, challenges such as the difficulty in establishing multi-parameter threshold warning rules, the presence of false alarms and missed detections, and the requirement for extensive experience in signal analysis continue to pose obstacles to accurate equipment early warning. Therefore, this paper proposes a construction methodology for bearing health warning indicators that integrates knowledge of fault mechanisms, providing an application foundation for machinery condition early warning. Firstly, based on the mechanisms underlying various bearing fault types, the patterns of time-frequency signal characteristics are analyzed to identify the behavioral patterns of multiple feature indicators for major fault types. Secondly, a fused bearing health indicator termed Health Integration Indicators (HII) is constructed based on the average weighting of envelope harmonic energy amplitude ratios. The 3σ upper threshold warning model using baseline values from healthy data is established to distinguish between the healthy and warning states of bearing operation. Then, the relative influence weight of each characteristic index on HII is quantified to help confirm the fault type of the bearing and realize the interpretable auxiliary diagnosis of fault type. Finally, validation is conducted using the IMS Bearing Data and the Case Western Reserve University (CWRU) dataset. Experimental results demonstrate that the proposed indicator offers more robust analytical outcomes and quantitative justification than warning methods based on kurtosis and RMS values.
Keywords
Fault mechanism, Health integration indicators, Condition monitoring, Early warning, Fault diagnosis
Speaker
Changkun Han
Engineer Beizisuo (Beijing) Technology Development Co., Ltd Beijing, ChinaSubmission Author
All Comments
Important Date
-
Conference Date
Nov 21
2025
toNov 23
2025
-
Oct 20 2025
Draft paper submission deadline
-
Dec 08 2025
Registration deadline
Sponsored By
IEEE Instrumentation and Measurement Society
South China University of Technology
South China University of Technology
Organized By
South China University of Technology
Contact Information
Previous Conferences
-
2026-11-13 China Chengdu
2026 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) -
2026-11-06 China Chengdu
2026 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2023-11-02 China China
International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2023-11-02 China Xi'an
2023 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2022-11-30 China Harbin
International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2021-10-21 China Nanjing
2021 International Conference on Sensing, Measurement and Data Analytics in the era of Artificial Intelligence -
2020-10-15 China Xi'an
International Conference on Sensing, Measurement and Data Analytics in the era of Artificial Intelligence
Submit Comment