An anomaly detection method for spacecraft solar arrays based on the ILS-SVM model

doi:10.23919/JSEE.2023.000011

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (2): 515-529.doi: 10.23919/JSEE.2023.000011

• RELIABILITY • Previous Articles

An anomaly detection method for spacecraft solar arrays based on the ILS-SVM model

Yu WANG¹^,²(), Tao ZHANG¹^,²(), Jianjiang HUI³(), Yajie LIU¹^,²^,*()

¹ College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
² Hunan Key Laboratory of Multi-energy System Intelligent Interconnection Technology, Changsha 410073, China
³ Beijing Institute of Tracking and Telecommunication Technology, Beijing 100094, China

Received:2021-06-15 Online:2023-04-18 Published:2023-04-18
Contact: Yajie LIU E-mail:794936379@qq.com;zhangtao@nudt.edu.cn;172175263@qq.com;liuyajie@nudt.edu.cn
About author:
WANG Yu was born in 1997. He received his B.S. degree in automation from Northeastern University in 2019, and M.S. degree in management science and engineering from National University of Defense Technology in 2021. He is pursuing his Ph.D. degree in National University of Defense Technology. His research interests include health assessment and anomaly detection of spacecraft components.E-mail: 794936379@qq.com

ZHANG Tao was born in 1976. He received his B.S., M.S., and Ph.D. degrees from National University of Defense Technology (NUDT), Changsha, China, in 1998, 2001, and 2004, respectively. He is a full professor with the College of System Engineering, NUDT. He is also the Director of the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology. His current research interests include optimal scheduling, data mining, and optimization methods on energy Internet. E-mail: zhangtao@nudt.edu.cn

HUI Jianjiang was born in 1979. He is a master of the University of Chinese Academy of Sciences and is currently an assistant professor at Beijing Institute of Tracking and Telecommunication Technology. His research interest is space operation. E-mail: 172175263@qq.com

LIU Yajie was born in 1975. He is a Ph.D. and professor in National University of Defense Technology. He was a visiting scholar at the Mechanical and Industrial Engineering Department of the University of Toronto from September 2008 to October 2009. His research interests are emergency logistics design and optimization, and materiel integrated logistics support. E-mail: liuyajie@nudt.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (71901210; 61973310)

Abstract

Abstract:

Solar arrays are important and indispensable parts of spacecraft and provide energy support for spacecraft to operate in orbit and complete on-orbit missions. When a spacecraft is in orbit, because the solar array is exposed to the harsh space environment, with increasing working time, the performance of its internal electronic components gradually degrade until abnormal damage occurs. This damage makes solar array power generation unable to fully meet the energy demand of a spacecraft. Therefore, timely and accurate detection of solar array anomalies is of great significance for the on-orbit operation and maintenance management of spacecraft. In this paper, we propose an anomaly detection method for spacecraft solar arrays based on the integrated least squares support vector machine (ILS-SVM) model: it selects correlated telemetry data from spacecraft solar arrays to form a training set and extracts n groups of training subsets from this set, then gets n corresponding least squares support vector machine (LS-SVM) submodels by training on these training subsets, respectively; after that, the ILS-SVM model is obtained by integrating these submodels through a weighting operation to increase the prediction accuracy and so on; finally, based on the obtained ILS-SVM model, a parameter-free and unsupervised anomaly determination method is proposed to detect the health status of solar arrays. We use the telemetry data set from a satellite in orbit to carry out experimental verification and find that the proposed method can diagnose solar array anomalies in time and can capture the signs before a solar array anomaly occurs, which reflects the applicability of the method.

Key words: spacecraft solar array, anomaly detection, integrated least squares support vector machine (ILS-SVM), induced ordered weighted average (IOWA) operator, integrated model

Yu WANG, Tao ZHANG, Jianjiang HUI, Yajie LIU. An anomaly detection method for spacecraft solar arrays based on the ILS-SVM model[J]. Journal of Systems Engineering and Electronics, 2023, 34(2): 515-529.

Figures/Tables 13

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Table 1

Table 2

Fig 6

Table 3

Fig 7

Fig 8

Fig 9

Fig 10

References 31

1	PATEL M R. Spacecraft power systems. Boca Raton: CRC Press, 2004.
2	CAO M D, ZHANG T, LIU Y J, et al A performance degradation model of solar cells in an on-orbit resource satellite based on peak currents. Solar Energy, 2019, 189, 26- 34. doi: 10.1016/j.solener.2019.07.030
3	CHEN Q, LIU Z G, ZHANG X F, et al. Spacecraft power system technologies. Berlin: Springer, 2020.
4	PENG X Y, PANG J Y, PENG Y, et al Review on anomaly detection of spacecraft telemetry data. Chinese Journal of Scientific Instrument, 2016, 37 (9): 1929- 1945.
5	YAIRI T, KAWAHARA Y, FUJIMAKI R, et al Telemetry-mining: a machine learning approach to anomaly detection and fault diagnosis for space systems. Proc. of the IEEE 2nd International Conference on Space Mission Challenges for Information Technology, 2006, 1- 8. doi: 10.1109/SMC-IT.2006.79
6	HASHIMOTO M, NISHIGORI N, MIZUTANI M Anomaly detective ground support system for Mars probe NOZOMI. Proc. of the 5th International Symposium on Artificial Intelligence, Robotics and Automation in Space, 1999, 440- 483.
7	KURIEN J, NAYAK P P Back to the future for consistency-based trajectory tracking. Proc. of the National Conference on Artificial Intelligence, 2000, 370- 377.
8	NARASIMHAN S, HYDE B L A general framework for stochastic and hybrid model-based diagnosis. Proc. of the International Workshop on Principles of Diagnosis, 2007, 29- 31.
9	WILLIAMS B C, INGHAM M D, CHUNG S, et al Model-based programming of fault-aware systems. AI Magazine, 2003, 24 (4): 61.
10	MATHUR A, DEB S, PATTIPATI K R Modeling and real-time diagnostics in TEAMS-RT. Proc. of the American Control Conference, 1998, 1610- 1614.
11	BUNUS P, ISAKSSON O, FREY B, et al RODON-a model-based diagnosis approach for the DX diagnostic competition. Proc. of the 20th International Workshop on Principles of Diagnosis, 2009, 423- 430.
12	SCHAEFER P, COLGREN R D, ABBOTT R J, et al. Technologies for reliable autonomous control (TRAC) of UAVs. Proc. of the 19th Digital Avionics Systems Conference, 2000. DOI: 10.1109/DASC.2000.886896.
13	BARRETT A. Model compilation for real-time planning and diagnosis with feedback. Proc. of the 19th International Joint Conference on Artificial Intelligence, 2005. http://hdl.handle.net/2014/40205.
14	MARTINEZ J. Drmust-a data mining approach for anomaly investigation. SpaceOps, 2012. DOI: https://doi.org/10.2514/6.2012-1275109.
15	TRUONG C D, ANH D T An efficient method for motif and anomaly detection in time series based on clustering. International Journal of Business Intelligence and Data Mining, 2015, 10 (4): 356- 377. doi: 10.1504/IJBIDM.2015.072212
16	REN W W, HU L, ZHAO K An efficient parallel anomaly detection algorithm based on hierarchical clustering. Journal of Networks, 2013, 8 (3): 672- 679.
17	LIU Z P, PI D C, JIANG J F Density-based trajectory outlier detection algorithm. Journal of Systems Engineering and Electronics, 2013, 24 (2): 335- 340. doi: 10.1109/JSEE.2013.00042
18	SUN M Y Research on discords detect on time series based on distance and density. Computer Engineering and Applications, 2012, 48 (20): 11- 17.
19	LIU D T, PANG J Y, SONG G, et al Fragment anomaly detection with prediction and statistical analysis for satellite telemetry. IEEE Access, 2017, 5, 19269- 19281. doi: 10.1109/ACCESS.2017.2754447
20	LI X J, ZHANG T, LIU Y J Detection of voltage anomalies in spacecraft storage batteries based on a deep belief network. Sensors, 2019, 19 (21): 4702. doi: 10.3390/s19214702
21	HUNDMAN K, CONSTANTINOU V, LAPORTE C, et al Detecting spacecraft anomalies using LSTMS and nonparametric dynamic thresholding. Proc. of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, 387- 395.
22	JIN W H, SUN B, LI Z D, et al Detecting anomalies of satellite power subsystem via stage-training denoising autoencoders. Sensors, 2019, 19 (14): 3216. doi: 10.3390/s19143216
23	SU Y, ZHAO Y J, NIU C H, et al Robust anomaly detection for multivariate time series through stochastic recurrent neural network. Proc. of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data mining, 2019, 2828- 2837.
24	VON KRANNICHFELDT L, WANG Y, HUG G Online ensemble learning for load forecasting. IEEE Trans. on Power Systems, 2020, 36 (1): 545- 548.
25	QIAN H U, CHEN H, SUN Z An ensemble learning predictive model for short-term wind speed forecasting. Proc. of the Chinese Society of Universities for Electric Power System and its Automation, 2016, 1, 1- 4.
26	SHI J Q, MA L Y, LI C C, et al Daily peak load forecasting based on sequential-parallel ensemble learning. Proc. of the Chinese Society for Electrical Engineering, 2020, 40 (14): 4463- 4472.
27	DONG J Y, PANG J Y, PENG Y, et al Spacecraft telemetry data anomaly detection method based on ensemble LSTM. Chinese Journal of Scientific Instrument, 2019, 40 (7): 22- 29.
28	SUYKENS J A K, VANDEWALLE J Least squares support vector machine classifiers. Neural Processing Letters, 1999, 9 (3): 293- 300. doi: 10.1023/A:1018628609742
29	BREIMAN L Bagging predictors. Machine Learning, 1996, 24 (2): 123- 140.
30	YAGER R R Induced aggregation operators. Fuzzy Sets and Systems, 2003, 137 (1): 59- 69. doi: 10.1016/S0165-0114(02)00432-3
31	OMAR B M, SAMIR H, AHMED Z S, et al A comparative investigation of maximum power point tracking techniques for grid connected PV system under various weather conditions. Proc. of the 5th International Conference on Electrical Engineering, 2017, 1- 5.

Model name	C	Type of kernel functions	$\gamma$
LS-SVM model 1	50	Radial basis function	0.00230
LS-SVM model 2	50	Radial basis function	0.00308
LS-SVM model 3	50	Radial basis function	0.00372
LS-SVM model 4	50	Radial basis function	0.00317
LS-SVM model 5	50	Radial basis function	0.00169

Test set	ILS-SVM	NN-model	SVM	RF-model	MLS-SVM
Test1	0.08261	0.09101	0.11064	0.11278	0.08846
Test2	0.08244	0.08197	0.11780	0.10537	0.08491
Test3	0.08037	0.08292	0.09462	0.09289	0.08208
Test4	0.07142	0.07224	0.08245	0.07441	0.07205
$D_{{\rm{test}}}$	0.07402	0.07677	0.08680	0.07707	0.07530

Date	Prediction error	Date	Prediction error
September 15	0.05723	September 20	0.58733
September 16	0.03971	September 21	0.65214
September 17	0.03735	September 22	0.65062
September 18	0.17064	September 23	0.59968
September 19	0.44278	September 24	0.70046

[1]	Xuan PENG, Xiaoping SHI, Yupeng GONG. Integrated modeling of spacecraft relative motion dynamics using dual quaternion [J]. Journal of Systems Engineering and Electronics, 2018, 29(2): 367-377.
[2]	Tian Xinguang, Duan Miyi, Sun Chunlai & Liu Xin. Detecting network intrusions by data mining and variable-length sequence pattern matching [J]. Journal of Systems Engineering and Electronics, 2009, 20(2): 405-411.
[3]	Tian Xinguang, Duan Miyi, Sun Chunlai & Li Wenfa. Intrusion detection based on system calls and homogeneous Markov chains [J]. Journal of Systems Engineering and Electronics, 2008, 19(3): 598-605.

An anomaly detection method for spacecraft solar arrays based on the ILS-SVM model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 13

References 31

Related Articles 3

Recommended Articles

Metrics

Comments