Lacking of the management of simultaneous fault is one of the limitations of condition monitoring for a gas turbine, which is critical for the safety and decision-making of aircraft operation. To this end, this paper employed a multi-label (ML) learning strategy to address the simultaneous fault issues. Moreover, a feature selection algorithm is proposed, which is based on the viewpoint that different class labels might be distinguished by certain specific characteristics of their own. The proposed algorithm achieves the goal of label-specific feature selection by iteratively optimizing the weight reconstruction matrix, and the learned label-specific features for the corresponding label can be used for multi-label classification. As thus, sensor data for different components of aircraft engines can be determined by the proposed algorithm to deal with the simultaneous fault diagnosis. Finally, comprehensive experiments on the benchmark data sets of multi-label learning validate the advantages and feasibility of the presented approaches, and the effectiveness of their application to simultaneous fault diagnosis of aircraft engines is also proved by extensive experiments.
TahanMTsoutsanisEMuhammadM, et al.Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: a review. Appl Energy2017; 198: 122–144.
2.
BaradS GPVRRKG, et al.Neural network approach for a combined performance and mechanical health monitoring of a gas turbine engine. Mech Syst Signal Process2012; 27: 729–742.
3.
TsoutsanisEMeskinNBenammarM, et al.Transient gas turbine performance diagnostics through nonlinear adaptation of compressor and turbine maps. J Eng Gas Turbines Power2015; 137: 091201.
4.
Sadough VaniniZ NKhorasaniKMeskinN. Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach. Inf Sci2014; 259: 234–251.
5.
Sina Tayarani-BathaieSKhorasaniK. Fault detection and isolation of gas turbine engines using a bank of neural networks. J Process Control2015; 36: 22–41.
6.
AmozegarMKhorasaniK. An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines. Neural Networks2016; 76: 106–121.
7.
ZhaoY-PSongF-QPanY-T, et al.Retargeting extreme learning machines for classification and their applications to fault diagnosis of aircraft engine. Aerosp Sci Technol2017; 71: 603–618.
8.
NaderiEKhorasaniK. Data-driven fault detection, isolation and estimation of aircraft gas turbine engine actuator and sensors. Mech Syst Signal Process2018; 100: 415–438.
9.
MarzatJPiet-LahanierHDamongeotF, et al.Model-based fault diagnosis for aerospace systems: a survey. Proc Inst Mech Eng G: J Aerosp Eng2012; 226: 1329–1360.
10.
KhanSYairiT. A review on the application of deep learning in system health management. Mech Syst Signal Process2018; 107: 241–265.
11.
LiuRYangBZioE, et al.Artificial intelligence for fault diagnosis of rotating machinery: A review. Mech Syst Signal Process2018; 108: 33–47.
12.
LiKWuYSongS, et al.A novel method for spacecraft electrical fault detection based on FCM clustering and WPSVM classification with PCA feature extraction. Proc Inst Mech Eng G: J Aerospace Eng2017; 231: 98–108.
13.
YélamosIGraellsMPuigjanerL, et al.Simultaneous fault diagnosis in chemical plants using a multilabel approach. Aiche J2010; 53: 2871–2884.
14.
VongC-MWongP-KIpW-F. A new framework of simultaneous-fault diagnosis using pairwise probabilistic multi-label classification for time-dependent patterns. IEEE Trans Ind Electron2013; 60: 3372–3385.
15.
PooyanNShahbazianMsalahshoorK, et al.Simultaneous fault diagnosis using multi class support vector machine in a dew point process. J Nat Gas Sci Eng2015; 23: 373–379.
16.
LiSCaoHYangY. Data-driven simultaneous fault diagnosis for solid oxide fuel cell system using multi-label pattern identification. J Power Sourc2018; 378: 646–659.
17.
WongP KZhongJYangZ, et al.Sparse Bayesian extreme learning committee machine for engine simultaneous fault diagnosis. Neurocomputing2016; 174: 331–343.
18.
ZhangM-LZhouZ-H. A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng2014; 26: 1819–1837.
19.
GibajaEVenturaS. A tutorial on multilabel learning. ACM Comput Surv2015; 47: 1–38.
20.
BoutellM RLuoJShenX, et al.Learning multi-label scene classification. Pattern Recognit2004; 37: 1757–1771.
21.
WuGTianYZhangC. A unified framework implementing linear binary relevance for multi-label learning. Neurocomputing2018; 289: 86–100.
22.
ZhangM-LLiY-KLiuX-Y, et al.Binary relevance for multi-label learning: an overview. Front Comput Sci2018; 12: 191–202.
23.
ZhangM-LWuL. Lift: Multi-label learning with label-specific features. IEEE Trans Pattern Anal MachIntell2014; 37: 107–120.
24.
ZhangJLiCCaoD, et al.Multi-label learning with label-specific features by resolving label correlations. Knowledge-Based Syst2018; 159: 148–157.
25.
HuangJLiGHuangQ, et al.Learning label specific features for multi-label classification. In IEEE International Conference on Data Mining,Atlantic, 2015, pp. 181–190.
26.
HuangJLiGHuangQ, et al.Learning label-specific features and class-dependent labels for multi-label classification. IEEE Trans Knowl Data Eng2016; 28: 3309–3323.
27.
HuangJLiGHuangQ, et al.Joint feature selection and classification for multilabel learning. IEEE Trans Cybern2017; 48: 876–889.
28.
HuangSJZhouZH. Multi-label Learning by Exploiting Label Correlations Locally. Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012, pp. 949–955.
29.
ZhangMLZhangK. Multi-label learning by exploiting label dependency. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Washington, 2010, pp. 999–1008.
30.
ZhuYKwokJTZhouZH. Multi-Label Learning with Global and Local Label Correlation. IEEE Trans Knowledge Data Eng2017; 30: 1081–1094.
31.
ReadJPfahringerBHolmesG, et al.Classifier chains for multi-label classification. Mach Learn2011; 85: 333–359.
ZhangSLiXZongM, et al.Efficient knn classification with different numbers of nearest neighbors. IEEE Trans Neural Netw Learn Syst2017; 29: 1774–1785.
34.
ZhangSChengDDengZ, et al.A novel k NN algorithm with data-driven k parameter computation. Pattern Recognition Lett2018; 109: 44–54.
35.
BelkinMNiyogiPSindhwaniV. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J Machine Learning Research2006; 7: 2399–2434.
36.
YanSXuDZhangB, et al.Graph embedding and extensions: A general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell, 2007, 29: 40–51.
NesterovY. Introductory Lectures on Convex Optimization: A Basic Course. Springer Science & Business Media, 2013.
39.
RothV. The generalized LASSO. IEEE Trans Neural Netw2004; 15: 16–28.
40.
TibshiraniR. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodological)1996; 58: 267–288.
41.
BeckATeboulleM. Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans Image Process2009; 18: 2419–2434.
42.
BeckATeboulleM. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imaging Sci2009; 2: 183–202.
43.
LinZGaneshAWrightJ, et al.Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix. Report no. UILU-ENG-09-2214, DC-246. Coordinated Science Laboratory, 2009.
44.
ZhangMLZhouZHKNNML-. A Lazy Learning Approach to Multi-Label Learning. Elsevier Science Inc., 2007.
45.
ChangC-CLinC-J. Libsvm. ACM Trans Intell Syst Technol2011; 2: 1–27.
46.
MadjarovGKocevDGjorgjevikjD, et al.An extensive experimental comparison of methods for multi-label learning. Pattern Recognit2012; 45: 3084–3104.
47.
DemšarJ. Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res2006; 7: 1–30.
48.
ViassoloDEAdibhatlaSBrunellBJet al. Advanced Estimation for Aircraft Engines. New York: American Control Conference, 2007, pp. 2807–2821.
49.
BorguetSLéonardO. Comparison of adaptive filters for gas turbine performance monitoring. J Comput Appl Math2010; 234: 2202–2212.
