Application of Time-Frequency Distributions to the Blind Source Separation of Mechanical Fault Signals

Zhi Hua Hao; Hong Xia Tian; Li Xin Tian

doi:10.4028/www.scientific.net/AMR.383-390.395

Paper Titles

Design of a New Structure for Anti-Upsetting of Axle-End in Wheelset Disassembly and Assembly
p.372

Stress Distribution of Strip at the Parts in Contact with Roll in Continuous Annealing Furnace
p.379

A Hybrid Algorithm to Solute the Problem of the Robot Path Planning
p.385

Study on Start Burning Performance of Micro-ICP Using Stereo Spiral Coil
p.390

Application of Time-Frequency Distributions to the Blind Source Separation of Mechanical Fault Signals
p.395

The Study on a New Type of Full-Voltage Starting Method of Asynchronous Motors
p.400

Extracting of Weak Periodic Impact Feature Based on Mean Filtering and Wavelet Transform
p.408

Research on Design Key Technologies for High-Power Submersible Motor
p.414

Experiment the Influence of Subsection on Leakage Reactance in Submersible Motor
p.420

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 383-390Application of Time-Frequency Distributions to the...

Application of Time-Frequency Distributions to the Blind Source Separation of Mechanical Fault Signals

Abstract:

In this study, blind source separation (BSS) method was applied to separate the multi-channel fault vibration signals generated by a rotor. As the signals were non-stationary, an algorithm based on spatial time-frequency distributions was applied to the experimental vibration signals to obtain the non-stationary vibration sources that were mutually independent. Further, AR modeling estimates of these sources were calculated with BURG method. A neural network was applied to the AR modeling parameters to perform the fault classification. The separation results of an experiment on a rotor’s multi-fault show that this method is feasible for fault diagnosis.

You might also be interested in these eBooks

Manufacturing Science and Technology, ICMST2011

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 383-390)

Pages:

395-399

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.383-390.395

Citation:

Cite this paper

Online since:

November 2011

Authors:

Zhi Hua Hao, Hong Xia Tian, Li Xin Tian

Keywords:

AR Modeling, Blind Source Separation, Mechanical Fault Signals, Time-Frequency Distribution

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] G. Betta, C. Liguori, A. Paolillo, A. Pietrosanto. A DSP-based FFT analyzer for the fault diagnosis of rotating machine based on vibration analysis. Proc. IEEE Conf. on Instrumentation and Measurement Technology. IEEE Transactions on Instrumentation and Measurement, vol. 51. pp: 1316-1321, June (2002).

DOI: 10.1109/tim.2002.807987

Google Scholar

[2] R.F.M. Marcal, M. Negreiros, A.A. Susin, J.L. Kovaleski. Detecting faults in rotating machines, IEEE Instrumentation & Measurement Magazine, vol. 3. pp.24-26, April (2000).

DOI: 10.1109/5289.887456

Google Scholar

[3] P.A. Lagan, Vibration Monitoring, Proc. IEE Colloquium on Understanding your Condition Monitoring, p.1–11, (1999).

DOI: 10.1049/ic:19990653

Google Scholar

[4] A. Belouchrani, M. G. Amin. Blind source separation based on time-frequency signal representations, IEEE Trans. Signal Processing, vol. 46. p.2888–2897, November (1998).

DOI: 10.1109/78.726803

Google Scholar

[5] A. Bousbia-Salah, A. Belouchrani, A. Cichocki. Application of time-frequency distributions to the independent component analysis of ECG signals, International symposium on signal processing and its applications, pp.238-241, January (2001).

DOI: 10.1109/isspa.2001.949821

Google Scholar

[6] L. Cohen. Time-frequency analysis. Prentice Hall, (1995).

Google Scholar