The measurement of spacecraft electrical characteristics and multi-label classification issues are generally including a large amount of unlabeled test data processing, high-dimensional feature redundancy, time-consumed computation, and identification of slow rate. In this paper, a fuzzy c-means offline (FCM) clustering algorithm and the approximate weighted proximal support vector machine (WPSVM) online recognition approach have been proposed to reduce the feature size and improve the speed of classification of electrical characteristics in the spacecraft. In addition, the main component analysis for the complex signals based on the principal component feature extraction is used for the feature selection process. The data capture contribution approach by using thresholds is furthermore applied to resolve the selection problem of the principal component analysis (PCA), which effectively guarantees the validity and consistency of the data. Experimental results indicate that the proposed approach in this paper can obtain better fault diagnosis results of the spacecraft electrical characteristics’ data, improve the accuracy of identification, and shorten the computing time with high efficiency.
KobayashiYIkedaMFujisakiY. Stability of large space structures preserved under failures of local controllers. IEEE Transact Autom Ctrl2007; 52: 318–322.
2.
PattonRJChenJ. Review of parity space approaches to fault diagnosis for aerospace systems. J Guid Ctrl Dynam1994; 17: 278–285.
3.
ZhangYMJiangJ. Bibliographical review on reconfigurable fault-tolerant control systems. Ann Rev Ctrl2008; 32: 229–252.
4.
ChenWSaifM. Observer-based fault diagnosis of satellite systems subject to time-varying thruster faults. J Dynam Syst Measure Ctrl2006; 129: 352–356.
5.
Wu Q and Saif M. Robust fault diagnosis for a satellite large angle attitude system using an iterative neuron PID (INPID) observer. In: American Control Conference, 2006.
6.
GaoZDingSX. Actuator fault robust estimation and fault-tolerant control for a class of nonlinear descriptor systems. Automatica2007; 43: 912–920.
7.
ShawSR. System identification techniques and modeling for nonintrusive load diagnostics, Massachusetts Institute of Technology, 2005.
8.
Tao J and Khorasani K. A fault detection, isolation and reconstruction strategy for a satellite’s attitude control subsystem with redundant reaction wheels. In: IEEE international conference on system, man and cybernetics, 2007, pp.3146–3152.
9.
WangJCQiXH. An improved decentralized model for sensor fault detection and isolation demonstrated on an airplane system. IMPG J Aerosp Eng2014; 229: 424–434.
10.
BolandiHAbediMHaghparastM. Fault detection, isolation and accommodation for attitude control system of a three-axis satellite using interval linear parametric varying observers and fault tree analysis. IMPG J Aerosp Eng2013; 228: 1403–1424.
11.
LiuZJLiQLiuXH. An expected-mode augmentation-based approach for multiple-fault detection and diagnosis in flight control systems. IMPG J Aerosp Eng2012; 226: 1202–1203.
FrancescaBRiccardoMGThomasP. Distributed fault detection and isolation of continuous-time non-linear systems. IMPG J Aerosp Eng2011; 47: 603–620.
14.
FengLChenYHuangJ. An integrated nonlinear model-based approach to gas turbine engine sensor fault diagnostics. IMPG J Aerosp Eng2014; 228: 2007–2021.
15.
ZhangYJiangJ. Integrated design of reconfigurable fault-tolerant control systems. J Guid Ctrl Dynam2001; 24: 133–136.
16.
LiKLanWWangC. An improved continuous solar-powered aircraft based on MPPT and fuzzy control technology. International Congress of Renewable Energy and Environmental Materials2012.
17.
Shao JY, Hu W, Huang HZ, et al. Study on modeling and diagnosis of the satellite power system. In: International Conference on Quality, Reliablity, Risk, Maintenance, and Safety Engineering, 2012, pp.607–611.
18.
WuLShiPWangC. Delay-dependent robust H and L2-L filtering for a class of uncertain nonlinear time-delay systems. IEEE Transact Automat Ctrl2003; 48: 1661–1666.
19.
ChenLZhongM. Fault detection for singular TS fuzzy systems with time-delay. In: Proceeding of the 17th IFAC World Congress, World Congress, 2008, pp.10130–10135.
20.
Kulatunge A, Basu K, Lee HC, et al. Network fault prediction and proactive maintenance system. U.S. Patent and Trademark Office, 2002.
21.
DuLLiuWWangY. Data acquisition card with variable sampling speed for monitoring overvoltage based on CPLD. High Voltage Eng2008; 34: 1589–1593.
22.
GuJPechtM. Prognostics and health management using physics-of-failure. Annu Rel Maint Sym2008, pp. 481–487.
23.
Swearingen K, Majkowski W, Bruggeman B, et al. An open system architecture for condition based maintenance overview. In: IEEE Aerospace Conference Proceeding, 2007, pp.1–8.
24.
Tuchband BA and Pecht MG. The use of prognostics in military electronic systems. In: Proceedings of the 32nd GOMAC Tech Conference, 2007, pp.157–160.
25.
Chidambaram B, Gilbertson DD and Keller K. Condition-based monitoring of an electro-hydraulic system using open software architectures. In: Aerospace Conference, 2005, pp.3352–3539.
26.
KishoreWCASenSRayG. Disturbance rejection and control allocation of over-actuated systems H. Industrial Technol2006, pp. 1054–1059.
27.
ChienSSherwoodRTranD. Using autonomy flight software to improve science return on Earth Observing One. J Aerosp Comput Inform Commun2005; 2: 196–216.
28.
ChenHGBognerRELimCC. Dual support vector machine with error rate and training size biasing. Acoust Speech Signal Process2011; 2: 1269–1272.
29.
LiKLiuWWangJ. Multi-parameter decoupling and slope tracking control strategy of a large-scale high altitude environment simulation test cabin. Chinese J Aeronaut2014; 27: 1360–1369.
30.
LiKLiuWWangJ. An intelligent control method for a large multi-parameter environmental simulation cabin. Chinese J Aeronaut2013; 26: 1360–1369.
31.
Liu Y, Li K, Huang Y, et al. Spacecraft electrical characteristics identification study based on offline FCM clustering and online SVM classifier. In: International Conference on Multisensor Fusion and Information Integration for Intelligent Systems (MFI), 2014, pp.1–4.
32.
Li k, Liu Y and Du SY. The research of Spacecraft electrical characteristics identification and diagnosis using PCA feature extraction. In: The 12th IEEE international conference on signal processing 2014, pp.1413–1417.
33.
WittenIHFrankEHallMA. Data Mining: Practical machine learning tools and techniques. Biomed Eng Online2011; 51: 95–97.
34.
HuangJSNegnevitskyMNguyenDT. A neural-fuzzy classifier for recognition of power quality disturbances. IEEE Transact Power Deliv2002; 17: 609–616.
35.
WangLLangariR. Complex systems modeling via fuzzy logic. IEEE Transact Syst Man Cybernet1995; 26: 100–106.
36.
CordónOHerreraF. A proposal on reasoning methods in fuzzy rule-based classification systems. Int J Approximate Reason1999; 20: 21–45.
37.
DavidAKZhaoR. An expert system with fuzzy sets for optimal planning [of power system expansion. IEEE Transact Power Syst1991; 6: 59–65.
38.
YangJZhangDFrangiAF. Two-dimensional PCA: A new approach to appearance-based face representation and recognition. IEEE Transact Pattern Anal Mach Intell2004; 26: 131–137.
39.
WeihongDHuJNGuoJ. Gabor feature based classification using LDA/QZ algorithm for face recognition. Lecture Notes Comput Sci2006; 4221: 15–24.
40.
LiWHValle-CervantesSQinSJ. Recursive PCA for adaptive process monitoring. J Process Ctrl2000; 10: 471–486.
41.
LiKLanWLiuWK. Method of controlling the processes of automatic turning-on-and-off and temperature decreasing for air refrigeration turbine. IEEE Int Conference Intell Comput Intell Syst2010; 3: 572–576.
42.
MikaSScholkopfBSmolaA. Kernel PCA and de-noising in feature spaces. Adv Neural Inform Process Systems II1999, pp. 536–542.
43.
DuanKKeerthiSSPooAN. Evaluation of simple performance measures for tuning SVM hyperparameters. Neurocomputing2003; 51: 41–59.
44.
KeerthiSShevadeSBhattacharyyaC. Improvements to Platt’s SMO algorithm for SVM classifier design. Neural Computat1999; 13: 637–649.
45.
YangTYangCSunZ. PSC ship-selecting model based on improved particle swarm optimization and support vector machine algorithm. J Coast Res2015; 73: 692–697.
