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

Ning Li; Hai Ting Chen; Shao Peng Liu

doi:10.4028/www.scientific.net/AMM.321-324.1299

Paper Titles

Condensate Pipe Vibration Analysis in the Air Cooling System
p.1278

Study on Energy Distribution of Single-Hole Blasting Vibration Signal Based on Wavelet Packet Transform
p.1284

Fault Diagnose of Rotor Winding Inter Turn Short Circuit in Generator
p.1290

Sparse Signal Recovery Based on Simulated Annealing
p.1295

Rotating Machine Monitoring Based on Blind Source Separation of Correlated Source Signals
p.1299

A Wideband DDC Design Using Distributed Arithmetic
p.1303

Wideband Beamforming Based on Farrow Structure
p.1307

Research on Feature Extraction for Ultrasonic Echo Signal Based on EEMD Approach
p.1311

The Characteristics Concerning a Class of Orthogonal Multivariate Matrix-Valued Scaling Functions and Frame Packets
p.1317

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 321-324Rotating Machine Monitoring Based on Blind Source...

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

Abstract:

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.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 321-324)

Pages:

1299-1302

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.321-324.1299

Citation:

Cite this paper

Online since:

June 2013

Authors:

Ning Li, Hai Ting Chen, Shao Peng Liu

Keywords:

Blind Source Separation, Correlated Source Signals, Rotating Machine Monitoring

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] H. Valpola, M. Harva, J. Karhunen: Hierarchical models of variance sources, Signal Processing 84(2) (2004), pp.267-282

DOI: 10.1016/j.sigpro.2003.10.014

Google Scholar

[2] A. Hyvärinen, P.O. Hoyer: Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces, Neural Computation 12(7) (2000), pp.1705-1720

DOI: 10.1162/089976600300015312

Google Scholar

[3] P. Comon, Independent component analysis, a new concept? Signal Process. 36 (3) (1994), p.287–314

DOI: 10.1016/0165-1684(94)90029-9

Google Scholar

[4] S.X. Yang, W.D. Jiao, Z.T. Wu: Application of JADE to separation of statistically correlated sources, Journal of Vibration Engineering Vol.16 (4) 12 (2003), pp.498-501.(in Chinese)

Google Scholar

[5] M.R. Aghabozorgi, A.M. Doost-Hoseini, Blind separation of jointly stationary correlated sources, Signal Process. 84 (2004), pp.317-325

DOI: 10.1016/j.sigpro.2003.10.005

Google Scholar