Aerospace and Electronic Systems Magazine April 2017 - 39
Nassar, Hussein, and Medhat
pretation of the process (describe and identify which variables are
responsible for the faults and why).
The innovation of this work comes from proposing a novel supervised PLS-DA classifier algorithm to monitor and detect anomaly
of the spacecraft operations status via practical application on
ADCS. The algorithm based on the multivariate projection technique is applied to spacecraft telemetry data in order to manage the
nominal and off-nominal status of the spacecraft operations and to
overcome faulty states in the space mission operation. The algorithm exploits telemetry data for model building and validating.
The analysis results show that the algorithm has the capability to
create data clusters, compare the characteristics of each one, and
the capability to correlate the clusters with low cardinalities to their
corresponding trigger events. Furthermore, the analysis results
were compared with both the SIMCA-P software and the nonlinear
SVMs algorithm, as well as the results show an evident agreement
regarding results accuracy.
Based on the above analysis and discussion in this study, it is
presumed that the novel PLS-DA algorithm proves that it can be
used as an effective tool for monitoring ADCS SOH because it gives
information about the system outputs as well as adding more insight
into physical explanations and interpretation of the process which
overcome the black-box problem of SVMs and ANNs techniques.
In addition, the performance of the PLS-DA algorithm needs to be
adopted and evolved by extending the work to be implemented for
more faulty states and in addition to be applied for monitoring two
or more subsystems. These and other problems in this research field
need to be further studied, with the aim of qualitatively analyzing
the efficiency and reliability of the classifiers algorithms.
Bay, S. D., and Schwabacher, M. Mining distance-based outliers in
near linear time with randomization and a simple pruning rule. In
Proceedings of the Ninth ACM SIGKDD International Conference on
Knowledge Discovery and Data Mining, New York, Association for
Computing Machinery, 2003.
Iverson, D. L. Inductive system health monitoring. In Proceedings of
the International Conference on Artificial Intelligence, 2004, IC-AI
'04, Vol. 2.
Iverson, D. L., Martin, R., Schwabacher, M., Spirkovska, L., Taylor,
W., Mackey, R., et al. General purpose data-driven system monitoring
for space operations. In Proceedings of AIAA Infotech and Aerospace
Conference, Seattle, WA, Oct. 2010.
Martin, R., Schwabacher, M., Oza, N., and Srivastava, A. Comparison
of unsupervised anomaly detection methods for systems health management using space shuttle main engine data. In Proceedings of the
Joint Army Navy NASA Air Force Conference on Propulsion, 2007.
Iverson, D. L. Data mining applications for space mission operations
system health monitoring. In Proceedings of Space Operations Conference, 2008.
Iverson, D. L. System health monitoring for space mission operations.
In Proceedings of Aerospace Conference, Washington DC, 2008.
IEEE A&E SYSTEMS MAGAZINE
Schwabacher, M., Nikunj, O., and Mattthews, B. Unsupervised anomaly detection for liquid-fueled rocket propulsion health monitoring.
Journal of Aerospace Computing, Information and Communication,
Vol. 6 (July 2009).
Yairi, T., Inui, M., Yoshiki, A., Kawahara, Y., and Takata, N. Spacecraft telemetry data monitoring by dimensionality reduction techniques. In Proceedings of SICE Annual Conference, 2010.
Verzola, I., Lagny, A., and Biswas, J. A predictive approach to failure estimation and identification for space systems operations. In
Proceedings of 13th International Conference on Space Operations,
Pasadena, CA, May 2014.
MacGregor, J., and Cinarc, A. Monitoring, fault diagnosis, fault-tolerant control and optimization: Data driven methods. Journal of Computers and Chemical Engineering, Vol. 47 (June 2012).
Peng, J., Fan, L., Xiao, W., and Tang, J. Anomaly monitoring method
for key components of satellite. Scientific World Journal, Vol. 2014
(Jan. 2014), Article ID 104052
Upadhyaya, S., and Singh, K. Classification based outlier detection
techniques. International Journal of Computer Trends and Technology, Vol. 3 (Feb. 2012).
Schwabacher, M., Aguilar, R., and Figueroa, F. Using decision trees
to detect and isolate simulated leaks in the J-2x rocket engine. In Proceedings of the 2008 IEEE Aerospace Conference, Yellowstone, Big
Sky, MT, 2008.
Bishop, C. M. Neural Networks for Pattern Recognition. Oxford University Press, Oxford, United Kingdom, 1995.
He, F., and Shi, W. WPT-SVMs based approach for fault detection of
valves in reciprocating pumps. In Proceedings of the American Control Conference, 2002.
Kourti, T., Ralston, P., DePuy, G., and Graham, J. Computer-based
monitoring and fault diagnosis: A chemical process case study. Instrument Society of America Transactions, Vol. 40 (2003), 85-98.
Eriksson, L., Johansson, E., Kettaneh, N., and Wold, S. Multi-and
Megavariate Data Analysis. Sweden, Umetrics Publishing, 2006.
Hussein, W. Machining process monitoring using multivariate latent
variable methods. PhD thesis, McMaster University, Hamilton, Ontario, Canada, Jan. 2007.
Simar, L., and Hardle, W. Applied multivariate statistical analysis. Tech Method and Data Technologies. Berlin: Springer Verlag,
Jackson, J. E. A User's Guide to Principal Components. New York:
Vanpik, V. Statistical Learning Theory. New York: Wiley, 1998.
Fletcher, T. Support vector machines explained. Tutorial paper, Mar.
2009. [Online]. Available: http://www. tristanfletcher.co.uk.
Hofmann, T., Scholkopf, B., and Smola, A. J. Kernel methods in machine learning. Annals of Statistics, Vol. 36, 3 (2008), 1171-1220.
Yon, S., Landry, J., Wold, N. K., and Wold, S. Multivariate process
monitoring and early fault detection using PCA and PLS. In Proceedings of Plan Automation and Decision Support Conference, San Antonio, TX, Sept. 21-24, 2003.
Hotelling, H. Analysis of a complex of statistical variables into principal components. Journal of Educational Psychology, Vol. 24 (1933),
Qin, S. Statistical process monitoring: Basics and beyond. Journal of
Chemometrics, Vol. 17, 8/9 (2003), 480-502.