Bearing Fault Diagnosis Based on Multi-Sensor Information Fusion with SVM

Xue Jun Li; D.L. Yang; Ling Li Jiang

doi:10.4028/www.scientific.net/AMM.34-35.995

Paper Titles

Software Design of On-Line Measuring System
p.971

Mechanical Property Analysis of Micro-Contact Resistance of Surface Coating
p.976

Design Task Decomposition in the Servo Press
p.981

Life Cycle Assessment in Different Product Design Stages - A Coffee Pot Case Study
p.988

Bearing Fault Diagnosis Based on Multi-Sensor Information Fusion with SVM
p.995

Rotor Crack Detection Based on Multi-Vibration Signal Fusion Collected from the Basement of Machinery Using SVM and Statistical Characteristics Methodology
p.1000

Research on Feature Extraction Experiment for Acoustic Emission Signal of Rotor Crack Fault
p.1005

Research on Arrangement of Sensors on Rotating Machinery Base Based on ANSYS
p.1010

Mechanical Response of Laminate (Glass/Epoxy) at Different Periods of Environmental Conditioning (Saturation and Ageing)
p.1015

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 34-35Bearing Fault Diagnosis Based on Multi-Sensor...

Bearing Fault Diagnosis Based on Multi-Sensor Information Fusion with SVM

Abstract:

This paper proposed a fault diagnosis based on multi-sensor information fusion for rolling bearing. This method used the energy value of multiple sensors is used as feature vector and a binary tree support vector machine (Binary Tree Support Vector Machine, BT-SVM) is used for pattern recognition and fault diagnosis. By analyzing the training samples, penalty factor and the kernel function parameters have effects on the recognition rate of bearing fault, then a approximate method to determine optimum value are proposed, Compared with the traditional single sensor by using the components energy of EMD as feature, the results show that the proposed method in this paper significantly reduce feature extraction time, and improve diagnostic accuracy, which is up to99.82%. This method is simple, effective and fast in feature extraction and meets the bearing diagnosis requirement of real-time fault diagnosis.

You might also be interested in these eBooks

Mechanical Engineering and Green Manufacturing

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 34-35)

Pages:

995-999

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.34-35.995

Citation:

Cite this paper

Online since:

October 2010

Authors:

Xue Jun Li, D.L. Yang, Ling Li Jiang

Keywords:

Fault Diagnosis, Information Fusion, Multi-Sensor, Rolling Bearing, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] X.K. Wei, Y.H. Li, J.X. Liu and J.M. Lu: Systems Engineering and Electronics. Vol. 27-9(2005), P. 1665-1668.

Google Scholar

[2] Z.X. Shen, X.Y. Huang and X.X. Ma: Control and Decisio. Vol: 24-6(2009),P. 889-893.

Google Scholar

[3] V. Valpnik: Statistical learning theory(John Wiley and Sons, New York 1998).

Google Scholar

[4] N.Y. Deng, Y.J. Tian: A new method of data mining - support vector machine(Science press Bei-jing 2004).

Google Scholar

[5] J.M. Yang，Y. Tian: Journal of Vibration, Measurement & Diagnosis. Vol. 29-2(2009),P. 155-158.

Google Scholar

[6] S.F. Yuan F.L. Zhu: Journal of Vibration and Shock. Vol. 28-3 (2009), P. 51-54.

Google Scholar

[7] B.S. Yang, T. Han, W.W. Huang: Journal of Mechanical Science and Technology. Vol. 19-3(2005),P. 848-859.

Google Scholar

[8] M. Li, J.M. Yang X.P. Zhang: Journal of Vibration, Measurement & Diagnosis. Vol. 29-1(2009),P. 83-85.

Google Scholar

[9] J.Y. Tang Y.B. Shi: Journal of Electronic Measurement and Instrument. Vol. 23-6(2009),P. 7-12.

Google Scholar