An Integrated Fault Diagnosis Method Based on the ICA-SVM

Zhen Ping Ji; Xiao Jie Zhang

doi:10.4028/www.scientific.net/AMM.740.523

Paper Titles

Study on a New Type of HVDC Flexible Digital Pulse Width Modulated Carrier Frequency Selection
p.503

Design of Frequency Selection Circuit of Advanced Detector Receiving Device in Coal Mine Roadway
p.507

Study and Design of the Control System for Crop Growth Cabinet
p.511

Aerial Robot-Based System for Monitoring Environmental Nuclear Radiation
p.517

An Integrated Fault Diagnosis Method Based on the ICA-SVM
p.523

Dynamic Modeling and Calibration of the Acceleration Sensor Based on System Identification Theory
p.527

A Study of 3d Coordinate Measuring Based on Binocular Stereo Vision
p.531

Headlight Detection and Error Correction of Measurement Data
p.535

Measuring Method on the Relative Position between the Rack and the Missile with T-Drawbar
p.539

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 740An Integrated Fault Diagnosis Method Based on the...

An Integrated Fault Diagnosis Method Based on the ICA-SVM

Abstract:

For sets of measurements does not follow a Gaussian distribution, the conventional principal component analysis (PCA) method has the disadvantage of low diagnostic yield. An integrated fault diagnosing method based on the independent component analysis (ICA) and support vector machine (SVM) was proposed. The observed data is preprocessed and feature extracted by ICA and a monitoring model was developed. When the fault is detected, SVM is adopted to classifying and diagnosing the type of faults. It is applied for fault diagnosing in the Three-Tank water level control system. The simulation results show that the fault diagnosis rates of this method is 99.8%, which can effectively detect and diagnose the fault.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 740)

Pages:

523-526

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.740.523

Citation:

Cite this paper

Online since:

March 2015

Authors:

Zhen Ping Ji, Xiao Jie Zhang*

Keywords:

Fault Diagnosis, Independent Component Analysis, Principal Component Analysis, Support Vector Machine (SVM), Three-Water Tank

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] P. Kadlec, B. Gabrys and S. Strandt. Computers & Chemical Engineering, vol. 33, 2009, pp.795-814.

DOI: 10.1016/j.compchemeng.2008.12.012

Google Scholar

[2] M. Kano and Y. Nakagawa. Computers and Chemical Engineering, vol. 32, 2008, pp.12-24.

Google Scholar

[3] H. Q. Wang, Z. Song and P. Li. Chinese Journal of Scientific Instrument, vol. 3, 2002, pp.232-235(in Chinese).

Google Scholar

[4] J. M. Lee, C. Yoo and I. B. Lee. Process Control, vol. 14, 2004, pp.467-485.

Google Scholar

[5] M. Kano and S. Hasebe. Computers & Chemical Engineering, vol. 28, 2004, pp.1157-1166.

Google Scholar

[6] Q. Xie, W. Yang and X. Q. Zhao. Industrial Instrumentation & Automation, vol. 5, 2012, pp.3-7(in Chinese).

Google Scholar

[7] J. Cho, J. M. Lee and S. W. Choi. Chemical Engineering Science, vol. 60, 2005, pp.279-288.

Google Scholar

[8] S. X. Du and T. J. Wu. Journal of Zhejiang University: Engineering Science, vol. 37, 2003, pp.521-527(in Chinese).

Google Scholar