BLIND SOURCE SEPARATION: A TOOL FOR ROTATING MACHINE MONITORING BY VIBRATIONS ANALYSIS?

2001 ◽  
Vol 248 (5) ◽  
pp. 865-885 ◽  
Author(s):  
G. GELLE ◽  
M. COLAS ◽  
C. SERVIERE
Keyword(s):  
Blind Source Separation ◽  
Source Separation ◽  
Rotating Machine ◽  
Machine Monitoring

Blind Source Separation Applied to Rotating Machine Monitoring and Fault Detection

2001 ◽  
Vol 32 (9) ◽  
pp. 11-16 ◽  
Author(s):  
Guillaume Gelle ◽  
Maxime Colas
Keyword(s):  
Fault Detection ◽  
Blind Source Separation ◽  
Source Separation ◽  
Processing Technique ◽  
Fault Detection And Diagnosis ◽  
Vibration Monitoring ◽  
Rotating Machine ◽  
Machine Monitoring ◽  
Pre Treatment ◽  
Detection And Diagnosis

This article presents a processing technique called “Blind Source Separation” initially developed for telecommunication applications and now applied to vibration monitoring of mechanical systems. Experimental results illustrate the potential of blind source separation as a pre-treatment to free the signal from its environment (denoising), so as to improve fault detection and diagnosis. An example of bearing faults detection on an experimental test bench is presented.

Rotating Machine Monitoring Based on Blind Source Separation of Correlated Source Signals

2013 ◽  
Vol 321-324 ◽  
pp. 1299-1302
Author(s):  
Ning Li ◽  
Hai Ting Chen ◽  
Shao Peng Liu
Keyword(s):  
Signal Processing ◽  
Blind Source Separation ◽  
Cross Correlation ◽  
Source Separation ◽  
Processing Technique ◽  
Test Stand ◽  
Signal Processing Technique ◽  
Rotating Machine ◽  
Machine Monitoring ◽  
Source Signals

Blind source separation (BSS) which separate the unknown sources from the observed signals is a new signal processing technique. The most methods for solving this problem rely on assumptions of independence or uncorrelation of source signals at least. However, the observed signal is always interfered by signals with common frequency in the rotating machine, and difficult to be separated by the conventional BSS method. In this paper, it is proved that the source signals with common frequencies are correlative, and the separating error brought by the cross-correlation of the source signals is analyzed. A new separating method for the correlated source signals with frequency overlapping is presented and it is successfully applied to separate the monitoring signals of rotor test stand.

Sign in / Sign up

Export Citation Format

Share Document