A New Approach to Fault Diagnosis for Satellite Control Systems Based on Machine Learning

Fei Yan; Ming Jian Li

doi:10.4028/www.scientific.net/AMR.457-458.1070

Paper Titles

AHP in the Evaluation of Power Enterprise Assets
p.1052

PSTree-Based Multi-Resolution Model for Buildings Simplification
p.1056

Numerical Simulation of Fluid-Structure Interaction for Tension Membrane Structures
p.1062

Analysis on Organization Networking Logistics Enterprises and Service Value Creation
p.1066

A New Approach to Fault Diagnosis for Satellite Control Systems Based on Machine Learning
p.1070

An Improved Block 2DPCA Face Recognition Algorithm with L1-Norm
p.1077

An Adaptive Clustering and Inter-Cluster Negotiation Protocol for Multi-Target Tracking Based on WSN
p.1083

Non-Autonomous Wheeled Mobile Robot Trajectory Tracking Control Based on the Navigation via WSN
p.1089

Research on the Bearing Capacity of Unsupported Random Launching Site
p.1096

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 457-458A New Approach to Fault Diagnosis for Satellite...

A New Approach to Fault Diagnosis for Satellite Control Systems Based on Machine Learning

Abstract:

Based on the traditional method of analytical redundancy fault diagnosis, the advanced machine learning technology is combined with the model-based fault diagnosis so as to form a new intelligent approach to the fault diagnosis for satellite control systems. The support vector regression technique in statistical learning theory is employed to model the control system with a little sampling data firstly. Then the feasibility of detecting and identifying faults for the satellite attitude control system with the Mahalanobis distance is analyzed in detail. Finally a set of fault-detection observers are designed and implemented based on the residual evaluation. The simulation result indicates that the diagnosing method proposed in this paper is characterized with light computation burden and good real-time performance.

You might also be interested in these eBooks

Advanced Materials and Engineering Materials

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 457-458)

Pages:

1070-1076

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.457-458.1070

Citation:

Cite this paper

Online since:

January 2012

Authors:

Fei Yan, Ming Jian Li

Keywords:

Attitude Control System, Fault Diagnosis, Satellite, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Frank P M: Automatica, Vol. 26 (1990), p.459.

Google Scholar

[2] Venkateswaran N, Siva M S and Goel P S: Acta Astronautica, Vol. 50 (2002), p.535.

Google Scholar

[3] Mehra R, Seereeram S and Bayard D: Proceedings of the 4th IEEE Conference on Control Applications, Albany, NY(1995), p.176.

Google Scholar

[4] Suykens J A K, Vandewalle J and De Moor B: Neural Networks, Vol. 14 (2001), p.23.

Google Scholar

[5] VapnikV N: Statistical Learning Theory (John Wiley, NewYork 1998).

Google Scholar

[6] Robert S, Stanislaw O: IEEE Transactions on Power Systems, Vol. 19 (2004), p.979.

Google Scholar

[7] Xing Yan, Wu Hongxin and Wang Xiaolei: Journal of Astronautics, Vol. 24 (2003), p.221.

Google Scholar

[8] Deng Naiyang and Tian Yingjie: New technique in Data Mining-Support Vector Machine (Science Press, Beijing 2004).

Google Scholar

[9] Zhu leilei, Chen suiyang and Zhou Meng: Mathematical Basis of Computed Intelligence (Science Press, Beijing 2002).

Google Scholar

[10] Chen Xin, Xiang Jianyong and Yang Yihe: Journal of Infrared Millimeter Waves, Vol. 16 (1997), p.39.

Google Scholar

[11] Rika Matsuda, Yoshiki Ikeda and Takashi Kamoshita: Proceedings of the 10th International Space Planes and Hypersonic Systems and Technologies Conference. Kyoto, Japan(2001), p.1.

Google Scholar