This paper proposes a laminate mode shape curvature (MSC) analysis method combining 2D continuous wavelet transform (2D-CWT) and convolutional neural network (CNN) technologies to address the delamination damage detection in composite laminated plates. This method constructs a new network model based on the emerging CNN technology and achieves good results by detecting delamination damage through learning the MSC images processed by 2D-CWT. The train in this study is constructed by inserting randomly generated delamination with varying geometric sizes, depth positions, and geometric positions into a specified 16-layer carbon fiber-reinforced plastic finite-element model. In addition, the method of establishing the finite-element model has been verified by experiments, the error of the simulation frequency is less than 10%, and the mode shape is consistent. The results show that the proposed method can effectively detect the depth position of the delamination with a detection accuracy of 93.89% ± 2.74% using the comprehensive dataset. Compared with the Resnet-50 backbone network, the proposed network improves detection performance by 0.86%. This finding expands the range of tasks that can be accomplished by mode shape detection methods and has broad prospects for subsequent engineering applications.
FerreiraAJMCastroLMSBertoluzzaS. A high order collocation method for the static and vibration analysis of composite plates using a first-order theory. Compos Struct2009; 89(3): 424–432.
2.
FerreiraAJMFasshauerGE. Analysis of natural frequencies of composite plates by an RBF-pseudospectral method. Compos Struct2007; 79(2): 202–210.
3.
LiuCXuXWuJ, et al. Deep transfer learning-based damage detection of composite structures by fusing monitoring data with physical mechanism. Eng Appl Artif Intell2023; 123: 106245.
4.
BretheeKFUwayedANAlden QwamAY.A novel index for vibration-based damage detection technique in laminated composite plates under forced vibrations: experimental study. Struct Health Monit2023; 22: 3109–3125.
5.
DingZLiJHaoH.Structural damage identification by sparse deep belief network using uncertain and limited data. Struct Control Health Monit2020; 27(5): e2522.
6.
KarshPKMukhopadhyayTDeyS.Spatial vulnerability analysis for the first ply failure strength of composite laminates including effect of delamination. Compos Struct2018; 184: 554–567.
7.
PanJShankarKSinghHK, et al. Vibration-based detection of skin-stiffener debonding on composite stiffened panels using surrogate-assisted algorithms. Compos Struct2021; 270: 114090.
8.
PanJZhangZWuJ, et al. A novel method of vibration modes selection for improving accuracy of frequency-based damage detection. Compos B Eng2019; 159: 437–446.
9.
CarraroPAMaragoniLQuaresiminM.Stiffness degradation of symmetric laminates with off-axis cracks and delamination: an analytical model. Int J Solids Struct2021; 213: 50–62.
10.
OginSLBrøndstedPZangenbergJ.Composite materials: constituents, architecture, and generic damage. In: TalrejaRVarnaJ (eds.) Modeling damage, fatigue and failure of composite materials, Woodhead Publishing Series in Composites Science and Engineering. 2016, pp. 3–23. Sawston, Cambridge: Woodhead Publishing.
11.
SkovsgaardSPHHeide-JørgensenS. Three-dimensional mechanical behavior of composite with fibre-matrix delamination through homogenization of micro-structure. Compos Struct2021; 275: 114418.
12.
DuchenePChakiSAyadiA, et al. A review of non-destructive techniques used for mechanical damage assessment in polymer composites. J Mater Sci2018; 53: 7915–7938.
13.
SaadatmoradMJafari-TalookolaeiRAPashaeiMH, et al. Damage detection on rectangular laminated composite plates using wavelet based convolutional neural network technique. Compos Struct2021; 278: 114656.
14.
HassaniSMousaviMGandomiAH.Structural health monitoring in composite structures: a comprehensive review. Sensors2022; 22(1): 153.
15.
PandeyAKBiswasMSammanMM.Damage detection from changes in curvature mode shapes. J Sound Vib1991; 145(2): 321–332.
16.
QiaoPLuKLestariW, et al. Curvature mode shape-based damage detection in composite laminated plates. Compos Struct2007; 80(3): 409–428.
17.
Moreno-GarcíaPLopesHdos SantosJVA, et al. Damage localisation in composite laminated plates using higher order spatial derivatives. In: Proceedings of the eleventh international conference on computational structures technology, Dubrovnik, Croatia, 2012, pp. 4–7. Stirlingshire, Scotland: Civil-Comp Press.
18.
KimHMelhemH.Damage detection of structures by wavelet analysis. Eng Struct2004; 26(3): 347–362.
19.
YangCOyadijiSO.Delamination detection in composite laminate plates using 2D wavelet analysis of modal frequency surface. Comput Struct2017; 179: 109–126.
20.
ZhouJLiZChenJ.Damage identification method based on continuous wavelet transform and mode shapes for composite laminates with cutouts. Compos Struct2018; 191: 12–23.
21.
ZhouJLiZChenJ.Application of two dimensional Morlet wavelet transform in damage detection for composite laminates. Compos Struct2023; 318: 117091.
22.
SaadatmoradMJafari-TalookolaeiR-APashaeiM-H, et al. Damage detection on rectangular laminated composite plates using wavelet based convolutional neural network technique. Compos Struct2021; 278: 114656.
23.
AzadMMKimSCheonYB, et al. Intelligent structural health monitoring of composite structures using machine learning, deep learning, and transfer learning: a review. Adv Compos Mater2024; 33(2): 162–188.
24.
Gonzalez-JimenezALomazziLJungesR, et al. Enhancing Lamb wave-based damage diagnosis in composite materials using a pseudo-damage boosted convolutional neural network approach. Struct Health Monit2024; 23(3): 1514–1529.
25.
NelonCMyersOHallA.The intersection of damage evaluation of fiber-reinforced composite materials with machine learning: a review. J Compos Mater2022; 56(9): 1417–1452.
26.
KhanAKoD-KLimSC, et al. Structural vibration-based classification and prediction of delamination in smart composite laminates using deep learning neural network. Compos B Eng2019; 161: 586–594.
27.
ModarresCAstorgaNDroguettEL, et al. Convolutional neural networks for automated damage recognition and damage type identification. Struct Control Health Monit2018; 25: e2230.
28.
SaadatmoradMJafari-TalookolaeiRAPashaeiMH, et al. Damage detection in rectangular laminated composite plate structures using a combination of wavelet transforms and artificial neural networks. J Vib Eng Technol2022; 10(5): 1647–1664.
29.
AbrateS. Mechanics of plate. In: AbrateS (ed.) Impact engineering of composite structures. Vienna: Springer Vienna, 2011, pp. 49–70.
30.
ReddyJN.A generalization of two-dimensional theories of laminated composite plates. Commun Appl Numer M1987; 3(3): 173–180.
31.
JuFLeeHPLeeKH.Finite element analysis of free vibration of delaminated composite plates. Compos Eng1995; 5(2): 195–209.
32.
WuDWangYShangL, et al. Experimental and computational investigations of thermal modal parameters for a plate-structure under 1200 C high temperature environment. Measurement2016; 94: 80–91.
33.
ZhangZPanJLuoW, et al. Vibration-based delamination detection in curved composite plates. Compos A Appl Sci Manuf2019; 119: 261–274.
34.
AntoineJ-PMurenziRVandergheynstP, et al. Two-dimensional wavelets and their relatives. Cambridge University Press, 2008.
35.
LiuYLiZZhangW.Crack detection of fibre reinforced composite beams based on continuous wavelet transform. Nondestruct Test Eval2010; 25: 25–44.
36.
Ribeiro JuniorRFGomesGF. On the use of machine learning for damage assessment in composite structures: a review. Appl Compos Mater2024; 31(1): 1–37.
37.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: BajcsyRuzenaLiFei-FeiTuytelaarsTinne (eds) 2016 IEEE Conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778. New York: Institute of Electrical and Electronics Engineers (IEEE).
38.
GaoS-HChengM-MZhaoK, et al. Res2Net: a new multi-scale backbone architecture. In: LeeKM (ed) IEEE transactions on pattern analysis and machine intelligence, 1 February 2021, vol. 43, no. 2, pp. 652–662. New York: Institute of Electrical and Electronics Engineers (IEEE).
39.
ChaupalPRohitSRajendranP.Matrix cracking and delamination detection in GFRP laminates using pre-trained CNN models. J Braz Soc Mech Sci Eng2023; 45(3): 136.
40.
AzadMMKimHS.Hybrid deep convolutional networks for the autonomous damage diagnosis of laminated composite structures. Compos Struct2024; 329: 117792.
