Structural health monitoring technology has gradually developed from the research in laboratory to engineering validations and applications. However, the problem of reliable damage evaluation under time-varying conditions is a main obstacle for applying structural health monitoring to real aircraft structures. Among the existing structural health monitoring methods, the guided wave–based structural health monitoring method is popular but the time-varying problem needs to be addressed. Several methods have been proposed to deal with this problem but limitations remain. In this article, an adaptive guided wave-Gaussian mixture model–based damage monitoring method is proposed. It can be used online without any structural mechanical model and a priori knowledge of damage under time-varying conditions. With this method, a baseline guided wave-Gaussian mixture model is constructed first based on the guided wave features obtained under time-varying conditions when the structure is in healthy state. When a new guided wave feature is obtained during an online damage monitoring process, the guided wave-Gaussian mixture model is updated by an adaptive updating mechanism including dynamic learning and Gaussian components split-merge. The mixture probability structure of the guided wave-Gaussian mixture model and the number of Gaussian components can be optimized adaptively. Finally, a probability damage index is proposed to measure the degree of variation between the baseline guided wave-Gaussian mixture model and the online guided wave-Gaussian mixture model to reveal the damage-induced weak cumulative variation trend of the guided wave-Gaussian mixture model so as to increase the damage evaluation reliability. The method is validated in a full-scale aircraft fatigue test, and the results indicate that the reliable crack growth monitoring of the right landing gear spar and the left wing panel under the fatigue load condition is achieved.
BollerCChangFKFujinoY.Encyclopedia of structural health monitoring. New York: Wiley, 2009.
2.
ARP6461: guidelines for implementation of structural health monitoring on fixed wing aircraft. London: SAE International, 2013.
3.
BuderathMMcFeatJAzzamH.The need for guidance on integrating structural health monitoring within military aircraft systems. Struct Health Monit2014; 13(6): 581–590.
4.
LopezISarigul-KlijnN.A review of uncertainty in flight vehicle structural damage monitoring, diagnosis and control: challenges and opportunities. Prog Aerosp Sci2010; 46(7): 247–273.
5.
LiFSuZYeL. A correlation filtering-based matching pursuit (CF-MP) for damage identification using Lamb waves. Smart Mater Struct2006; 15(6): 1585.
6.
IhnJBChangFK.Pitch-catch active sensing methods in structural health monitoring for aircraft structures. Struct Health Monit2008; 7(1): 5–19.
7.
StaszewskiWJMahzanSTraynorR.Health monitoring of aerospace composite structures—active and passive approach. Compos Sci Technol2009; 69(11–12): 1678–1685.
8.
GiurgiutiuVLinBSantoni-BottaiG. Space application of piezoelectric wafer active sensors for structural health monitoring. J Intel Mat Syst Str2011; 22(12): 1359–1370.
9.
KoabazMHajzargarbashiTKunduT. Locating the acoustic source in an anisotropic plate. Struct Health Monit2011; 11: 315–323.
10.
ZhouCSuZChengL.Quantitative evaluation of orientation-specific damage using elastic waves and probability-based diagnostic imaging. Mech Syst Signal Pr2011; 60: 2135–2156.
11.
RakowAChangFK.A structural health monitoring fastener for tracking fatigue crack growth in bolted metallic joints. Struct Health Monit2012; 11(3): 253–267.
12.
QiuLLiuMQingX. A quantitative multidamage monitoring method for large-scale complex composite. Struct Health Monit2013; 12: 183–196.
13.
ZhouWLiHYuanFG.Guided wave generation, sensing and damage detection using in-plane shear piezoelectric wafers. Smart Mater Struct2013; 23(1): 015014.
14.
JarmerGFlynnEToddMD.Multi-wave-mode, multi-frequency detectors for guided wave interrogation of plate structures. Struct Health Monit2013; 13: 120–130.
15.
HaynesCToddMDNadabeT. Monitoring of bearing failure in composite bolted connections using ultrasonic guided waves: a parametric study. Struct Health Monit2014; 13(1): 94–105.
16.
AmbrozińskiŁStepinskiTUhlT. Efficient tool for designing 2D phased arrays in lamb waves imaging of isotropic structures. J Intel Mat Syst Str2015; 26(17): 2283–2294.
17.
WandowskiTMalinowskiPOstachowiczW. Embedded damage localization subsystem based on elastic wave propagation. Comput-Aided Civ Inf2015; 30(8): 654–665.
18.
HongMSuZLuY. Locating fatigue damage using temporal signal features of nonlinear Lamb waves. Mech Syst Signal Pr2015; 60: 182–197.
19.
Malfense FierroGPCiampaFGinzburgD. Nonlinear ultrasound modelling and validation of fatigue damage. J Sound Vib2015; 343: 121–130.
20.
CroxfordAJMollJWilcoxPD. Efficient temperature compensation strategies for guided wave structural health monitoring. Ultrasonics2010; 50(4): 517–528.
21.
ClarkeTSimonettiFCawleyP.Guided wave health monitoring of complex structures by sparse array systems: influence of temperature changes on performance. J Sound Vib2010; 329(12): 2306–2322.
22.
WangYGaoLYuanS. An adaptive filter-based temperature compensation technique for structural health monitoring. J Intel Mat Syst Str2014; 25: 2187–2198.
23.
RoySLadpliPChangFK.Load monitoring and compensation strategies for guided-waves based structural health monitoring using piezoelectric transducers. J Sound Vib2015; 351: 206–220.
24.
WangQYuanS.Baseline-free imaging method based on new PZT sensor arrangements. J Intel Mat Syst Str2009; 20: 1663–1673.
25.
LeeSJGandhiNHallJS. Baseline-free guided wave imaging via adaptive source removal. Struct Health Monit2012; 11(4): 472–481.
26.
LimHJSohnHDeSimioMP. Reference-free fatigue crack detection using nonlinear ultrasonic modulation under various temperature and loading conditions. Mech Syst Signal Pr2014; 45(2): 468–478.
27.
SuZZhouCHongM. Acousto-ultrasonics-based fatigue damage characterization: linear versus nonlinear signal features. Mech Syst Signal Pr2014; 45(1): 225–239.
28.
FigueiredoEParkGFarrarCR. Machine learning algorithms for damage detection under operational and environmental variability. Struct Health Monit2011; 10(6): 559–572.
29.
DaoPBStaszewskiWJ.Cointegration approach for temperature effect compensation in Lamb-wave-based damage detection. Smart Mater Struct2013; 22(9): 095002.
30.
WordenKCrossEJAntoniadouI. A multiresolution approach to cointegration for enhanced SHM of structures under varying conditions—an exploratory study. Mech Syst Signal Pr2014; 47(1–2): 243–262.
31.
TibaduizaDAMujicaLERodellarJ. Structural damage detection using principal component analysis and damage indices. J Intel Mat Syst Str2015; 27: 233–248.
32.
WangDYeLSuZ. Probabilistic damage identification based on correlation analysis using guided wave signals in aluminum plates. Struct Health Monit2010; 9(2): 133–144.
33.
FarrarCRWordenK.Structural health monitoring: a machine learning perspective. Chichester: Wiley, 2012.
34.
HaynesCToddMDFlynnE. Statistically-based damage detection in geometrically-complex structures using ultrasonic interrogation. Struct Health Monit2013; 12(2): 141–152.
35.
LarrosaCLonkarKChangFK.In situ damage classification for composite laminates using Gaussian discriminant analysis. Struct Health Monit2014; 13(2): 190–204.
36.
AnayaMTibaduizaDATorres-ArredondoMA. Data-driven methodology to detect and classify structural changes under temperature variations. Smart Mater Struct2014; 23(4): 045006.
37.
HaynesCToddMD.Enhanced damage localization for complex structures through statistical modeling and sensor fusion. Mech Syst Signal Pr2015; 54: 195–209.
38.
TschöpeCWolffM.Statistical classifiers for structural health monitoring. IEEE Sens J2009; 9(11): 1567–1576.
39.
BanerjeeSQingXBeardS. Prediction of progressive damage state at the hot spots using statistical estimation. J Intel Mat Syst Str2010; 21(6): 595–605.
40.
ChakrabortyDKovvaliNPapandreou-SuppappolaA. An adaptive learning damage estimation method for structural health monitoring. J Intel Mat Syst Str2015; 26(2): 125–143.
41.
SantosASilvaMSantosR. A global expectation-maximization based on memetic swarm optimization for structural damage detection. Struct Health Monit2016; 15(5): 610–625.
42.
QiuLYuanSChangFK. On-line updating Gaussian mixture model for aircraft wing spar damage evaluation under time-varying boundary condition. Smart Mater Struct2014; 23(12): 125001.
43.
QiuLYuanSBaoQ. Crack propagation monitoring in a full-scale aircraft fatigue test based on guided wave-Gaussian mixture model. Smart Mater Struct2016; 25(5): 055048.
44.
BanfieldJRafteryA.Model-based Gaussian and non Gaussian clustering. Biometrics1993; 4: 803–821.
45.
FigueiredoMATJainAK. Unsupervised learning of finite mixture models. IEEE T Pattern Anal2002; 24: 381–396.
46.
McLachlanGKrishnanT.The EM algorithm and extensions. Hoboken, NJ: Wiley, 2007.
47.
LeeDS. Effective Gaussian mixture learning for video background subtraction. IEEE T Pattern Anal2005; 27: 827–832.
48.
BaxterRAOliverJJ. Finding overlapping components with MML. Stat Comput2000; 10(1): 5–16.
49.
UedaNNakanoRGhahramaniZ. SMEM algorithm for mixture models. Neural Comput2000; 12: 2109–2128.
50.
KullbackS.Information theory and statistics. New York: Dover Publications, 1968.
51.
GoldbergerJGordonSGreenspanH. An efficient image similarity measure based on approximations of KL-divergence between two Gaussian mixtures. In: Proceedings of the ninth IEEE international conference on computer vision, Nice, 1–8 December 2013. New York: IEEE.
52.
QiuLYuanSShiX. Design of piezoelectric transducer layer with electromagnetic shielding and high connection reliability. Smart Mater Struct2012; 21(7): 075032.
53.
QiuLYuanS.On development of a multi-channel PZT array scanning system and its evaluating application on UAV wing box. Sensors Actuat A: Phys2009; 151(2): 220–230.
54.
MichaelsJEMichaelsTE.Detection of structural damage from the local temporal coherence of diffuse ultrasonic signals. IEEE T Ultrason Ferr2005; 52: 1769–1782.
55.
ChangFKMarkmillerJFIhnJB. A potential link from damage diagnostics to health prognostics of composites through built-in sensors. J Vib Acoust2007; 129: 718–729.
56.
SuZYeL.Identification of damage using Lamb waves: from fundamentals to applications. London: Springer, 2009.
