In this study acoustic emission monitoring was used for detection and classification of damage mechanisms during mode I delamination test of glass/polyester composites. For this purpose, the integration of harmony search and k-means algorithms was applied to cluster acoustic signals generated during delamination test. The clustering analysis represented three clusters, each one related to a distinct damage mechanism. Considering the relationship between acoustic emission parameters and damage mechanisms, the acoustic emission signals of each cluster were assigned to a distinct damage mode. Furthermore, the dominance of various damage types was investigated based on the distribution of signals in different clusters. Finally, scanning electron microscopic observation was employed to verify the obtained results. The results indicate good performance of proposed algorithms in damage classification procedure.
PaganoNJSchoeppnerGA. Delamination of polymer matrix composites: problems and assessment. Compr Compos Mater2000; 2(13): 433–528.
2.
RonnieKM. Handbook of nondestructive testing, vol.5 Acoustic emission, 2nd edn. Columbus, OH: American Society for Nondestructive Testing, 1987.
3.
ElyTMHillEK. Longitudinal splitting and fibre breakage characterization in graphite/epoxy using acoustic emission data. Mater Eval1995; 53(2): 288–294.
4.
UenoyaT. Acoustic emission analysis on interfacial fracture of laminated fabric polymer matrix composite. J Acoust Emiss1995; 13(3-4): 95–102.
5.
MorscherGNMartinez-FernandezJPurdyMJ. Determination of interfacial properties using a single-fibre microcomposite test. J Am Ceram Soc1996; 79(4): 1083–1091.
6.
BarréSBenzeggaghML. On the use of acoustic emission to investigate damage mechanisms in glass-fibre-reinforced poly-propylene. Compos Sci Technol1994; 52(3): 369–376.
7.
AtivitavasNFowlerTPothisiriT. Acoustic emission characteristics of pultruded fibre reinforced plastics under uniaxial tensile stress. In: Proceedings of European WG on AE, Berlin, 2004, pp. 447–454.
8.
Refahi OskoueiAZucchelliAAhmadiM. An integrated approach based on acoustic emission and mechanical information to evaluate the delamination fracture toughness at mode I in composite laminate. Mater Design2011; 32(3): 1444–1455.
9.
YamaguchiKOyaizuHJohkajiJ. Acoustic emission technology using multi-parameter analysis of waveform and application to GFRP tensile tests. In: Acoustic Emission, Current Practice and Future Directions, ASTM STP 1077, Philadelphia, PA, 1991, pp. 123–143.
10.
PappasYZMarkopoulosYPKostopoulosV. Failure mechanisms analysis of 2D carbon/carbon using acoustic emission monitoring. NDT&E Int1998; 31(3): 157–163.
11.
KostopoulosVLoutasTHKontsosA. On the identification of the failure mechanisms in oxide/oxide composites using acoustic emission. NDT&E Int2003; 36(8): 571–580.
12.
KenjiKOnoK. Pattern recognition of acoustic emission signals from carbon fibre/epoxy composites. In: 7th International Acoustic Emission Symposium, Zao, Japan, 1987.
13.
MoevusMGodinNR’MiliM. Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si–B–C] composites exhibiting different tensile behaviours. Part II: Unsupervised acoustic emission data clustering. Compos Sci Technol2008; 68(6): 1258–1265.
14.
YanTHolfordKCarterD. Classification of acoustic emission signatures using a self-organization neural network. J Acoust Emiss1999; 17(1/2): 49–59.
15.
De OliveiraRMarquesAT. Health monitoring of FRP using acoustic emission and artificial neural networks. Comput Struct2008; 86(3-5): 367–373.
16.
PhilippidisTPNikolaidisVNAnastassopoulosAA. Damage characterization of carbon/carbon laminates using neural networks techniques on AE signals. NDT&E Int1998; 31(5): 329–340.
17.
GodinNHuguetSGaeertnerR. Integration of the Kohonen’s self-organizing map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composites. NDT&E Int2005; 38(4): 299–309.
18.
HaykinS. Neural networks - a comprehensive foundation, 2nd edn. New York: Macmillan College, 1994.
19.
NiQQIwamotoM. Wavelet transform of acoustic emission signals in failure of model composites. Eng Fract Mech2002; 69(6): 717–728.
20.
LoutasTHKostopoulosVRamirez-JimenezC. Damage evolution in centre-holed glass/polyester composites under quasi-static loading using time/frequency analysis of acoustic emission monitored waveforms. Compos Sci Technol2006; 66: 1366–1375.
21.
OskoueiARAhmadiMHajikhaniM. Wavelet-based acoustic emission characterization of damage mechanisms in composite materials under mode I delamination at different interfaces. eXPRESS Polym Lett2009; 3(12): 804–813.
22.
MarecAThomasJHEl GuerjoumaR. Damage characterization of polymer-based composite materials: multivariable analysis and wavelet transform for clustering acoustic emission data. Mech Syst Signal Process2008; 22(6): 1441–1464.
23.
GeemZWKimJHLoganathanGV. A new heuristic optimization algorithm. Harmony Search Simul2001; 76(2): 60–68.
24.
ASTM D5528: Standard test method for mode I interlaminar fracture toughness of unidirectional fibre reinforced polymer matrix composites. West Conshohocken: ASTM, 1994.
25.
JolliffeIT. Principal component analysis, 2nd edn. New York: Springer Series in Statistics, 2002.
26.
LikasAVlassisNVerbeekJ. The global k-means clustering algorithm. Pattern Recognit2003; 366(2): 451–461.
27.
DaviesDLBouldinDW. A cluster separation measure. IEEE Trans Pattern Anal Mach Intell1979; 1(4): 224–227.
28.
PashmforoushFFotouhiMAhmadiM. Damage characterization of glass/epoxy composite under three-point bending test using acoustic emission technique. J Mater Eng Perform2011(accessed 05 August 2011). DOI: 10.1007/s11665-011-0013-2.
29.
BohseJ. Acoustic emission characteristics of micro-failure processes in polymer blends and composites. Compos Sci Technol2000; 60(8): 1213–1226.
