Fault detection and diagnosis is widely recognized as a crucial task for satellite attitude control systems (ACS) within the field. Any faults within the ACS can result in degraded system performance, disruption of satellite missions, and reduced lifespan. However, traditional fault feature extraction diagnosis faces challenges in the ACS due to the nonlinear characteristics of the data and the high dimensionality of the pattern features. Furthermore, the manifold structure of the data is unknown. In order to address these issues, a novel learning method that utilizes Riemannian metric is proposed,and Generalized Least Squares(GLS) is utilized to new sample extention, these methods preserve the intrinsic structure of the data and performs fault diagnosis within its feature space. Two statistical methods, T2 and SPE, are employed, along with Kernel density estimation (KDE) to calculate the control limit. The effectiveness of the proposed method is validated through mathematical simulation on a fault simulation system for attitude control systems, demonstrating superior diagnostic capabilities compared to conventional approaches.
MiaoYLiCZhangB. Application of a coarse-to-fine minimum entropy deconvolution method for rotating machines fault detection. Mech Syst Signal Process2023; 198: 110431.
2.
ZijianQShuaiCZhihuiL, et al.Harmonic-Gaussian double-well potential stochastic resonance with its application to enhance weak fault characteristics of machinery. Nonlinear Dyn2023; 8: 7293–7307.
3.
ZhihuaCYongchunX. Stability analysis of the closed-loop system of a phase-plane controlled rigid satellite. Aerosp Control Appl2018; 44: 1–14.
4.
SaritaKDevarapalliRKumarS, et al.Principal component analysis technique for early fault detection. J Intell Fuzzy Syst2022; 42: 861–872.
5.
PuleMMatsebeOSamikannuR. Application of PCA and SVM in fault detection and diagnosis of bearings with varying speed. Math Probl Eng2022; 2022: 1–12.
6.
BalasubramanianMSchwartzEL. The isomap algorithm and topological stability. Science2002; 295: 7.
7.
LiYGengZ. Fault diagnosis of industrial process based on LLE and K-means clustering algorithm. Xi Tong Fang Zhen Xue Bao/J Syst Simul2021; 33: 2066–2073.
8.
LiBLiYRZhangXL. A survey on Laplacian eigenmaps based manifold learning methods. Neurocomputing2019; 335: 336–351.
9.
BelkinMNiyogiP. Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Advances in Neural Information Processing Systems, 2002. Epub ahead of print 2002. DOI: 10.7551/mitpress/1120.003.0080.
10.
HuYZZhangZL. Research on fault diagnosis method based on diffusion map and extreme learning machine. In: Advancements in mechatronics and intelligent robotics, 2021, pp. 423–431.
11.
ZhangCGuoQXFengLW, et al.Fault detection strategy based on density standard error associated with locality preserving projections. Kongzhi Lilun Yu Yingyong/Control Theory Appl2020; 37: 1757–1765.
12.
MiaoAChengZLiP, et al.Locality-preserving data modelling and its application in fault classification. Can J Chem Eng2022; 100: 491–502.
13.
WuJJiangBChenH, et al.Sensors information fusion sys-tem with fault detection based on multi-manifold regular-ization neighborhood preserving embedding. Sensors (Basel)2019; 19: 1440.
Perrault-joncasDMeilMSaulL, et al.Metric learning of manifolds. Semisupervised Learn2006; 1: 293–306.
16.
ShahMZHHuLAhmedZ. Modified LPP based on Riemannian metric for feature extraction and fault detection. Meas J Int Meas Confed2022; 193: 110923.
17.
Perraul-JoncasDMeilaM. Non-linear dimensionality reduction: Riemannian metric estimation and the problem of geometric discovery. arXiv Prepr arXiv130572552013; 1–32.
18.
YangWTReisMSBorodinV, et al.An interpretable unsupervised Bayesian network model for fault detection and diagnosis. Control Eng Pract2022; 127: 105304.
19.
HashimHCliffordERyan PC. False alarm moderation for performance monitoring in industrial water distribution systems. Adv Eng Informatics2022; 52: 101592.
20.
ChenYC. A tutorial on kernel density estimation and recent advances. Biostat Epidemiol2017; 1: 161–187.
21.
PatsatzisDGRussoLKevrekidisIG. Data-driven control of agent-based models: an equation/variable-free machine learning approach. J Comput Phys2023; 478: 111953.
22.
SamsonJK. Geometric algorithms for interpretable manifold learning. PhD Thesis, University of Washington, USA, 2022.
23.
AizenbudYBermanisAAverbuchA. PCA-based out-of-sample extension for dimensionality reduction2015. DOI: 10.48550/arXiv.1511.00831.
24.
McQueenJMeilaMPerrault-JoncasD. Nearly isometric embedding by relaxation. In: Advances in Neural Information Processing systems, 2016, pp. 2639–2647.
25.
HarrouFSunYHeringA, et al.Statistical process monitoring using advanced data-driven and deep learning approaches: theory and practical applications. Chantilly: Elsevier.
26.
StiefABaranowskiJ. Fault diagnosis using interpolated kernel density estimate. Measurement2021; 176: 109230.
27.
MansellJRSpencerDA. Deep learning fault diagnosis for spacecraft attitude determination and control. J Aerosp Inf Syst2021; 18: 102–115.
28.
BorahKaustav Jyoti.Analysis of Actuators Prognostic Health Monitoring in Spacecraft Attitude Control Systems. Lecture Notes in Mechanical Engineering. Springer Science and Business Media Deutschland GmbH, 2021, pp. 195–204.
29.
HennaHToubakhHKafiMR, et al.Towards fault-tolerant strategy in satellite attitude control systems: a review. Proc Annu Conf Progn Heal Manag Soc PHM2020; 12: 14.
30.
GuoXGTianMELiQ, et al.Multiple-fault diagnosis for spacecraft attitude control systems using RBFNN-based observers. Aerosp Sci Technol2020; 106: 106195.
