Impact force magnitude detection and site location for clamped plates have direct relevance to the maintenance of aircraft and spacecraft structures. This article presents the impact identification of an aluminum plate structure based on least squares support vector machines. The structure is equipped with an array of surface-bounded piezoelectric sensors, which receive strain response signals excited by hammer impacts on different sites with varying magnitudes. To identify the magnitude and location of the impact, two features are extracted from each sensor signal by Hilbert transform, and intelligent models are established using least squares support vector machines. The regression models are then validated through experimental studies, which reveal that the least squares support vector machine–based approach achieves more reliable identification result and better detection accuracy than conventional artificial neural networks. In addition, an empirical index is presented to compare the system efficiency in terms of detection accuracy as well as the numbers of sensors and data sets. Results show that the proposed least squares support vector machine–based impact identification system affords a higher efficiency than the existing ones because it accomplishes a moderate detection accuracy along with greatly reduced hardware cost and workload.
QuekSTTuaPSWangQ. Detecting anomalies in beams and plate based on the Hilbert-Huang transform of real signals. Smart Mater Struct2003; 12(3): 447–460.
2.
FarrarCRWordenK. An introduction to structural health monitoring. Philos T Roy Soc A1851; 2007(365): 303–315.
3.
StaszewskiWJMahzanSTraynorR. Health monitoring of aerospace composite structures—active and passive approach. Compos Sci Technol2009; 69(11–12): 1678–1685.
4.
HaywoodJCoverleyPTStaszewskiWJ. An automatic impact monitor for a composite panel employing smart sensor technology. Smart Mater Struct2005; 14(1): 265–271.
5.
AymerichFStaszewskiWJ. Experimental study of impact-damage detection in composite laminates using a cross-modulation vibro-acoustic technique. Struct Health Monit2010; 9(6): 541–553.
6.
WangQDengX. Damage detection with spatial wavelets. Int J Solids Struct1999; 36(23): 3443–3468.
7.
CoverleyPTStaszewskiWJ. Impact damage location in composite structures using optimized sensor triangulation procedure. Struct Health Monit2003; 12(5): 795–803.
8.
ParkJHaSChangFK. Monitoring impact events using a system-identification method. AIAA J2009; 47(9): 2011–2021.
9.
GiurgiutiuV. Tuned Lamb wave excitation and detection with piezoelectric wafer active sensors for structural health monitoring. J Intel Mat Syst Str2005; 16(4): 291–305.
10.
ZhaoXGaoHZhangG. Active health monitoring of an aircraft wing with embedded piezoelectric sensor/actuator network: I. Defect detection, localization and growth monitoring. Smart Mater Struct2007; 16(4): 1208–1217.
11.
ParkSYunCBRohY. PZT-based active damage detection techniques for steel bridge components. Smart Mater Struct2006; 15(4): 957–966.
12.
KesslerSSSpearingSMSoutisC. Damage detection in composite materials using Lamb wave methods. Smart Mater Struct2002; 11(2): 269–278.
13.
WangXLuYTangJ. Damage detection using piezoelectric transducers and the Lamb wave approach: I. System analysis. Smart Mater Struct2008; 17(2): 025033.
14.
SuZYeLLuY. Guided Lamb waves for identification of damage in composite structures: a review. J Sound Vib2006; 295(3–5): 753–780.
15.
ChoiKChangFK. Identification of impact force and location using distributed sensors. AIAA J1996; 34(1): 136–142.
16.
MasriSFSmythAWChassiakosAG. Application of neural networks for detection of changes in nonlinear systems. J Eng Mech: ASCE2000; 126(7): 666–676.
17.
ShanQKingG. Fuzzy techniques for impact locating and magnitude estimating. Insight—Non-Destr Test Cond Monit2003; 45(3): 190–195.
18.
MujicaaLEVehiJStaszewskicW. Impact damage detection in aircraft composites using knowledge-based reasoning. Struct Health Monit2008; 7(3): 215–230.
19.
ZhaoXLiMSongG. Hierarchical ensemble-based data fusion for structural health monitoring. Smart Mater Struct2010; 19(4): 045009.
20.
WatkinsSEAkhavanFDuaR. Impact-induced damage characterization of composite plates using neural networks. Smart Mater Struct2007; 16(2): 515–524.
21.
LeClercJRWordenKStaszewskiWJ. Impact detection in an aircraft composite panel—a neural-network approach. J Sound Vib2007; 299(3): 672–682.
22.
JonesRTSirkisJSFriebeleEJ. Detection of impact location and magnitude for isotropic plates using neural networks. J Intel Mat Syst Str1997; 8(1): 90–99.
23.
WordenKStaszewskiWJ. Impact location and quantification on a composite panel using neural networks and a genetic algorithm. Strain2000; 36(2): 61–68.
24.
SuykensJAK. Support vector machines: a nonlinear modeling and control perspective. Eur J Control2001; 7(2–3): 311–327.
25.
WidodoAYangBS. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Pr2007; 21(6): 2560–2574.
26.
VapnikVN. Statistical learning theory. New York: John Wiley & Sons, Inc., 1998.
27.
SuykensJAKGestelTVBrabanterJD. Least squares support vector machines. Singapore: World Scientific Publishing Company, 2002.
28.
WongPKTamLMLiK. Engine idle-speed system modelling and control optimization using artificial intelligence. Proc IMechE, Part D: J Automobile Engineering2010; 224(1): 55–72.
29.
XuQWongPK. Hysteresis modeling and compensation of a piezostage using least squares support vector machines. Mechatronics2011; 21(7): 1239–1251.
30.
WongPKXuQVongCM. Rate-dependent hysteresis modeling and control of a piezostage using online support vector machine and relevance vector machine. IEEE T Ind Electron2012; 59(4): 988–2001.
31.
XieJ. Kernel optimization of LS-SVM based on damage detection for smart structures. In: Proceedings of IEEE international conference on computer science and information technology, Beijing, China, 8–11 >August 2009, pp. 406–409. New York: IEEE.
32.
MujicaaLEVehiJRuizaM. Multivariate statistics process control for dimensionality reduction in structural assessment. Mech Syst Signal Process2008; 22(1): 155–171.
33.
SuykensJAKVandewalleJ. Least squares support vector machine classifiers. Neural Process Lett1999; 9(3): 293–300.
34.
YangJBouzerdoumAPhungSL. A training algorithm for sparse LS-SVM using compressive sampling. In: Proceedings of IEEE international conference on acoustics speech and signal processing, Dallas, TX, 14–19 March 2010, pp. 2054–2057. New York: IEEE.
35.
Van GestelTSuykensJAKBaestaensDE. Financial time series prediction using least squares support vector machines within the evidence framework. IEEE T Neural Networ2001; 12(4): 809–821.
36.
VongCMWongPKLiYP. Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference. Eng Appl Artif Intel2006; 19(3): 277–287.
37.
De BrabanterKKarsmakersPOjedaF. LS-SVMlab toolbox user’s guide version 1.8. ESAT-SISTA Internal Report no. 10-146, August2011. Leuven: KU Leuven.
38.
NegnevitskyM. Artificial intelligence: a guide to intelligent systems. 2nd ed.London: Addison-Wesley, 2005.
