Low-velocity impact damage significantly compromises the structural integrity and residual strength of carbon fiber-reinforced polymer (CFRP) composites. This study proposes a hybrid approach integrating progressive damage finite element modeling with convolutional neural networks (CNNs) to accurately predict compressive strength after impact (CAI). A 3D continuum damage model was developed to characterize interlaminar damage, employing a bilinear traction-separation law combined with the Benzeggagh-Kenane (B-K) criterion for delamination simulation. Finite element results under varying impact energies demonstrated strong agreement with experimental data in terms of force-time and force-displacement responses. A dataset pairing delamination damage profiles with corresponding CAI values was constructed from simulations across different impact scenarios. A deep CNN architecture achieved an Root Mean Square Error (RMSE) of 2.5197 MPa in mapping damage images to residual strength, eliminating the need for manual feature extraction or material parameter dependency. This image-driven method enables high-fidelity strength prediction and shows promising potential for intelligent health monitoring of composite structures.
DhimanBGuleriaVSharmaP. Applications and future trends of carbon fiber reinforced polymer composites: a review. Int Res J Eng Technol2020; 7(10): 1–7.
3.
RazaliNSultanMTHMustaphaF, et al.Impact damage on composite structures–a review. Int J Eng Sci2014; 3(7): 08–20.
4.
KawareKKotambkarM. Low velocity impact response and influence of parameters to improve the damage resistance of composite structures/materials: a critical review. Int J Crashworthiness2022; 27(4): 1232–1256.
5.
ChenYYangJPengJ, et al.Low-velocity impact (LVI) and post-impact fatigue properties of GLARE laminates with holes. Int J Fatig2023; 167: 107318.
6.
TalrejaRPhanN. Assessment of damage tolerance approaches for composite aircraft with focus on barely visible impact damage. Compos Struct2019; 219: 1–7.
7.
TakatoyaTSusukiI. In-plane and out-of-plane characteristics of three-dimensional textile composites. J Compos Mater2005; 39(6): 543–556.
8.
ZhouYZhengC. Impact resistance performance and structural optimization of lightweight composite target plate. Polym Compos2024; 45(7): 6482–6497.
9.
LinSRanatungaVWaasAM. Experimental study on the panel size effects of the low-velocity impact (LVI) and compression after impact (CAI) of laminated composites, part I: LVI. Compos Struct2022; 296: 115822.
10.
Wronkowicz-KatuninAKatuninADraganK. Reconstruction of barely visible impact damage in composite structures based on non-destructive evaluation results. Sensors2019; 19(21): 4629.
11.
BriggsTMLoyolaBRLohKJ, et al.Comparative study of non-destructive damage evaluation methodologies for CFRP low velocity impact damage. Sandia National Lab. (SNL-CA), 2012.
12.
ZhangYZhuPLaiX. Finite element analysis of low-velocity impact damage in composite laminated plates. Mater Des2006; 27(6): 513–519.
13.
TuoHLuZMaX, et al.Damage and failure mechanism of thin composite laminates under low-velocity impact and compression-after-impact loading conditions. Compos B Eng2019; 163: 642–654.
14.
PhilippidisTPAssimakopoulouTT. Using acoustic emission to assess shear strength degradation in FRP composites due to constant and variable amplitude fatigue loading. Compos Sci Technol2008; 68(3-4):840–847.
15.
CaprinoGTetiRIorioID. Predicting residual strength of pre-fatigued glass fibre-reinforced plastic laminates through acoustic emission monitoring - ScienceDirect. Compos Part B Eng2005; 36(5):365–371.
16.
RajendraboopathySSasikumarTUshaKM, et al.Artificial neural network a tool for predicting failure strength of composite tensile coupons using acoustic emission technique. Int J Adv Manuf Technol2009; 44(3-4):399–404.
17.
ArumugamVShankarRNSridharBTN, et al.Ultimate strength prediction of carbon/epoxy tensile specimens from acoustic emission data. J Mater Sci Technol2010; 26(8): 725–729.
18.
RamasamyPSampathkumarS. Prediction of impact damage tolerance of drop impacted WGFRP composite by artificial neural network using acoustic emission parameters. Compos B Eng2014; 60: 457–462.
19.
HeZCHuoSLLiE, et al.Data-driven approach to characterize and optimize properties of carbon fiber non-woven composite materials. Compos Struct2022; 297: 115961.
20.
KaruppusamyMThirumalaisamyRPalanisamyS, et al. A review of machine learning applications in polymer composites: advancements, challenges, and future prospects. J Mater Chem A. 2025; 13(22): 16290–16308.
21.
QiuCYangJ. Machine learning applications in composites: manufacturing, design, and characterization Machine learning in materials informatics: Methods and applications. Am Chem Soc2022; 218: 65–85.
22.
LiangYWeiXPengY, et al.A review on recent applications of machine learning in mechanical properties of composites. Polym Compos2025; 46(3): 1939–1960.
23.
KhorramiMSMianroodiJRSiboniNH, et al.An artificial neural network for surrogate modeling of stress fields in viscoplastic polycrystalline materials. NPJ Computational Materials2023; 9(1): 37.
24.
AlzubaidiLZhangJHumaidiAJ, et al.Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of big Data2021; 8: 1–74.
25.
GuptaSMukhopadhyayTKushvahaV. Microstructural image based convolutional neural networks for efficient prediction of full-field stress maps in short fiber polymer composites. Def Technol2023; 24: 58–82.
26.
RezasefatMHoganJD. A finite element-convolutional neural network model (FE-CNN) for stress field analysis around arbitrary inclusions. Mach Learn: Sci Technol2023; 4(4): 045052.
27.
ShokrollahiYNikahdMMGholamiK, et al.Deep learning techniques for predicting stress fields in composite materials: a superior alternative to finite element analysis. J Compos Sci2023; 7(8): 311.
28.
YangCKimYRyuS, et al.Prediction of composite microstructure stress-strain curves using convolutional neural networks. Mater Des2020; 189: 108509.
29.
NiQQIwamotoM. Wavelet transform of acoustic emission signals in failure of model composites. Eng Fract Mech2002; 69(6): 717–728.
30.
RussellSSHennekeEG. Signature analysis of acoustic emission from graphite/epoxy composites. NASA Contractor Report, NSG-1238. 1977.
31.
ZhouWZhangPZhangY. Acoustic emission based on cluster and sentry function to monitor tensile progressive damage of carbon fiber woven composites. Applied Sciences2018; 8(11): 2265.
32.
LiLSwolfsYStraumitI, et al.Cluster analysis of acoustic emission signals for 2D and 3D woven carbon fiber/epoxy composites. J Compos Mater2016; 50(14): 1921–1935.
