Fault Diagnosis Method Based on Supervised Incremental Local Tangent Space Alignment and SVM

Guang Bin Wang; Xian Qiong Zhao; Yu Hui He

doi:10.4028/www.scientific.net/AMM.34-35.1233

Paper Titles

Reliability Modeling and Simulation of Mechanical Equipment Undergoing Maintenance
p.1211

Contour Features Based Comfort Evaluation Criterion on School Chair Surface
p.1217

Computer-Aided Working Space Design for Driller Control Cab
p.1223

A DSP-Based Design for Generating Limited White Noise Wave
p.1228

Fault Diagnosis Method Based on Supervised Incremental Local Tangent Space Alignment and SVM
p.1233

Computer Aided Geometric Tolerance Specification in 3D-CAD System
p.1238

Study on Nonlinear Energy Pumping of the Vibration System with Cubic Damping Absorber
p.1243

Research on Semi-Passive Shunted Piezoelectric Membrane for Sound Isolation with FEM
p.1248

The Analysis of Energy and Environmental Efficiency Based on Input-Output Model
p.1253

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 34-35Fault Diagnosis Method Based on Supervised...

Fault Diagnosis Method Based on Supervised Incremental Local Tangent Space Alignment and SVM

Abstract:

To enhance the effect of fault diagnosis, a new fualt diagnosis method based on supervised incremental local tangent space alignment (SILTSA) and support vector machine (SVM) is proposed. The supervised learning approach is embedded into the incremental local tangent space alignment algorithm, to realize fault feature extraction and new data processing for equipment fault signal, and then correctly classify the faults by non-linear support vector machines. The experiment result for roller bearing fault diagnosis shows that SILTSA-SVM method has better diagnosis effect to related methods

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:

1233-1237

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.34-35.1233

Citation:

Cite this paper

Online since:

October 2010

Authors:

Guang Bin Wang, Xian Qiong Zhao, Yu Hui He

Keywords:

Fault Diagnosis, Supervised Incremental LTSA, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] H.S. Seung and D.L. Daniel. Science. 290(2000), pp.2268-2269.

Google Scholar

[2] S. Roweis and L. Saul. Science. 290(2000), pp.2323-2326.

Google Scholar

[3] M. Belkin and P. Niyogi. Neural Computation. 15(2003), pp.1373-1396.

Google Scholar

[4] Zhang Zhenyue and Zha Hongyuan. SIAM Journal on Scientific Computing. 26(2005), pp.313-338.

Google Scholar

[5] M.H. Law and A.K. Jain. Pattern Analysis and Machine Intelligence, IEEE Transcations on, 28(2006), pp.377-391.

Google Scholar

[6] O. Kouropteva, O. Okun and N. IPietik. Pattern recognition. 38(2005), pp.1764-1767.

Google Scholar

[7] Xiaoming Liu, Jianwei Yin and Zhilin Feng, etl. Artificial Neural Networks in Pattern Recognition, Ulm, Germany, 2006: 107-121.

Google Scholar

[8] D. Ridder, O. Kouropreva and O. Okun. Proceedings of Artifical Neural Networks and Neural Information Processing, 2003, LNCS2714, Springer, 333-341.

Google Scholar

[9] L. Saul and S. Roweis. Journal of Machine Learning Research, 4(2002), pp.119-155.

Google Scholar

[10] Information on http: /www. eecs. case. edu/laboratory/bearing 12 13 14 15 16 17 18 19 20 0.

Google Scholar

9 1 近近近邻 k siltsa-svm iltsa-svm 18 19 20 21 22 23 24 25 26 0.

Google Scholar

9 1 近近近邻 k siltsa-svm iltsa-svm 20 21 22 23 24 25 26 27 28 0.

Google Scholar

9 1 近近近邻 k siltsa-svm iltsa-svm 12 13 14 15 16 17 18 19 20 0.

Google Scholar

9 1 近近近邻 k siltsa-svm iltsa-svm 18 19 20 21 22 23 24 25 26 0.

Google Scholar

9 1 近近近邻 k siltsa-svm iltsa-svm 20 21 22 23 24 25 26 27 28 0.

Google Scholar

9 1 近近近邻 k 正正正识识 siltsa-svm iltsa-svm m=12 m=12 m=18 m=18 m=20 m=20 The highest correct recognition rate Number of neighbors k Fig 1. The result of the fualt diagnosis to training samples (left) and test samples(right).

Google Scholar