Feature Extraction for Bearing Prognostics using Correlation Coefficient Weight

Seokgoo Kim, Chaeyoung Lim, and Joo-Ho Choi
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_17_047.pdf546.81 KBAugust 22, 2017 - 5:40pm

Bearing is an essential mechanical component in rotary machineries. To prevent its unpredicted failures and undesired downtime cost, many researches have been made in the field of Prognostics and Health Management (PHM). Key issues in bearing PHM is to establish a proper health indicator (HI) reflecting its current health state properly at the early stage. However, the conventional features have shown some limitations that make them less useful for early diagnostics and prognostics. This paper proposes a feature extraction method based on the traditional envelope analysis and weighted sum with correlation coefficient. The developed methods are demonstrated using the IMS bearing data from NASA Ames Prognostics Data Repository. In the end, the characteristics of the proposed feature are compared with those of traditional time domain features.

Publication Year: 
2017
Publication Volume: 
8
Publication Control Number: 
047
Submission Keywords: 
bearing fault diagnosis; Vibration; Feature extraction
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed