Data-Driven Roller Bearing Diagnosis Using Degree of Randomness and Laplace Test

Bo Ling, Michael Khonsari, and Ross Hathaway
Publication Issue: 
1
Submission Type: 
Full Paper
Supporting Agencies (optional): 
NASA
AttachmentSizeTimestamp
phmc_09_018.pdf346.04 KBSeptember 14, 2009 - 11:08am

In this paper, we present a new diagnosis and prognosis method using degree of randomness (DoR) measure and Laplace test procedure. The abnormal events are detected through the measure of change of randomness of vibration signals. The changes of randomness are resulted from the faulty components such as roller bearings. We aim at the early detection of semi-failure events through the use of Laplace test statistic which measures the rate changes of the abnormal event occurrence. Test results using roller bearing data downloaded from NASA Prognostic Data Repository have shown that our algorithms can detect the roller bearing faults 10 days in advance of the occurrence of failure.

Publication Year: 
2009
Publication Volume: 
0
Publication Control Number: 
018
Submission Keywords: 
bearings
detection
Submission Topic Areas: 
Component-level PHM
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