This study investigates the dynamic properties of aluminum plates repaired with composite patches, focusing on how natural frequencies change after repairs on plates with various crack configurations. To predict these changes, an Artificial Intelligence (AI) model was developed using data from 2000 Finite Element (FE) analyses conducted in ANSYS. A Deep Neural Network (DNN) was trained using this dataset, which included 2000 damage scenarios based on four parameters: defect length (L), radius (r), depth (h), and the defect region.
The optimal network configuration (11-[15-15-5]-4) was trained to predict the first four natural frequencies of these single-sidedly patch-repaired, cracked plates. The model’s accuracy was rigorously validated using an unseen test sample (Region 6, L = 35 mm, r = 2.5 mm, h = 5 mm) not included in the training data. The AI’s predictions were compared against both numerical results and an Experimental Modal Analysis (EMA). The results confirmed the high success rate of the model, showing minimal differences from the numerical simulations (max 0.39% error) and experimental results (max 3.15% error).
ChongHMWuZANgSP, et al.Influence of double vacuum debulking process on co-cured soft-patch carbon fibre composite repairs. Composites Part B2019; 168: 367–374.
2.
LiuXHeYQiuD, et al.Numerical optimizing and experimental evaluation of stepwise rapid highpressure microwave curing carbon fiber/epoxy composite repair patch. Compos Struct2019; 230: 111529.
3.
SarmahADasariSSNagabandiN, et al.Patch repair of composites using dielectric barrier Discharge-induced heating and curing. Appl Mater Today2023; 32: 101821.
4.
ŞenM. A comprehensive review study on composite patch applications. J Reinforc Plast Compos2025; 0(0): 07316844251350226.
5.
BakerAA. Development of a hard-patch approach for scarf repair of composite structure. Defence Science and Technology Organisation Report TR-1892. 2006; 19.
6.
WhittinghamBBakerAAHarmanA, et al.Micrographic studies on adhesively bonded scarf repairs to thick composite aircraft structure. Composites Part A2009; 40: 1419–1432.
7.
SunCZhaoWZhouJ, et al.Mechanical behaviour of composite laminates repaired with a stitched scarf patch. Compos Struct2021; 255: 112928.
8.
OkaforACBhogapurapuH. Design and analysis of adhesively bonded thick composite patch repair of corrosion grind-out and cracks on 2024 T3 clad aluminum aging aircraft structures. Compos Struct2006; 76: 138–150.
9.
BenzianeMMWahabSAAZahloulH, et al.Finite element analysis of the integrity of an API X65 pipeline with a longitudinal crack repaired with single- and double-bonded composites. Composites Part B2015; 77: 431e439.
10.
IvanezIBraunM. Numerical analysis of surface cracks repaired with single and double patches of composites. J Compos Mater2018; 52(8): 1113–1120.
11.
CoelhoSRMReisPNBFerreiraJAM, et al.Effects of external patch configuration on repaired composite laminates subjected to multi-impacts. Compos Struct2017; 168: 259–265.
12.
LiCZhaoQYuanJ, et al.Simulation and experiment on the effect of patch shape on adhesive repair of composite structures. J Compos Mater2019; 53(28–30): 4125–4135.
13.
OuinasDHebbarABachir BouiadjraB, et al.Numerical analysis of the stress intensity factors for repaired cracks from a notch with bonded composite semicircular patch. Composites Part B2009; 40: 804–810.
14.
RachidMSerierBBachir BouiadjraB, et al.Numerical analysis of the patch shape effects on the performances of bonded composite repair in aircraft structures. Composites Part B2012; 43: 391–397.
15.
GongXJChengPAivazzadehS, et al.Design and optimization of bonded patch repairs of laminated composite structures. Compos Struct2015; 123: 292–300.
16.
RamjiMSrilakshmiRPrakashMB. Towards optimization of patch shape on the performance of bonded composite repair using FEM. Composites Part B2013; 45: 710–720.
17.
HarmelMWZouggarKMadaniK, et al.Novel concepts optimization for functionally graded adhesives used in bonded composite patch repairs techniques. J Adhes2025: 1–30.
18.
ZhaoYXuanSWangY, et al.Reliability-based multi-objective optimization design of composite patch repair structure using artificial neural networks. Compos Struct2025; 352: 118692.
19.
WangWCHsuJS. Investigation of the size effect of composite patching repaired on edge-cracked plates. Compos Struct2000; 49: 415–423.
20.
WangWCChenCH. Investigation of vibration behavior of patched edge-cracked composite plates. J Reinforc Plast Compos2002; 21(6): 533–557.
21.
FazilatiJKhalafiV. Dynamic analysis of the composite laminated repaired perforated plates by using multi-patch IGA method. Chin J Aeronaut2021; 34(1): 266–280.
22.
ŞenM. Investigation of vibration characteristics of cracked aluminum plates repaired with carbon fiber composite patches. J Compos Mater2025; 59(24): 2813–2830.
23.
KadamSKumarPShindeH. Repair of pre-cracked aluminium alloy panel with CFRP bonded patch and its comparison with riveted patch. Mater Today Proc2023; 72: 1190–1196.
24.
SohailMAKhanM, BBBBenyahiaF, et al.Analysis of the single overload effect on fatigue crack growth in AA 2024-T3 plates repaired with composite patch. Eng Fract Mech2018; 202: 147–161.
25.
MosayyebiEChakherlouTN. Numerical investigation of patch geometry effect on the fatigue life of aluminum panels containing cracks repaired with CFRP composite patch using XFEM and CZM approach. Int J Adhesion Adhes2025; 136: 103882.
26.
GowdaYUDeviMAPrakashCPS. Analysis of natural frequency of a rectangular beam using finite element analysis and artificial intelligence. International Journal of Scientific Research in Science, Engineering and Technology. 2022; 9(4): 325–333.
27.
HorvathKZeleiA. Predicting natural frequencies of a cantilever using machine learning. Material Strength and Applied Mechanics. 2024; 240533.
28.
SebaMRKebdaniS. Finite element and neural network based predictive model to determine natural frequency of laminated composite plates with eccentric cutouts under free vibration. Adv technol innov2022; 7(2): 131–142.
29.
ParidieAMEneNMMohamedYS. Using neural networks to predict the effect of the preload location on the natural frequencies of a cantilever beam. Heliyon2022; 8: e11242.
30.
YildirimS. Free vibration of axially or transversely graded beams using finite-element and artificial intelligence. Alex Eng J2022; 61: 2220–2229.
31.
ChengXAl-KhafajiSHHashemianM, et al.Statistical analysis and neural network modeling of functionally graded porous nanobeams vibration in an elastic medium by considering the surface effects. Eng Appl Artif Intell2023; 123: 106313.
32.
ThadaAPanchalSDubeyA, et al.Machine learning based frequency modelling. Mech Syst Signal Process2021; 160: 107915.
33.
SahaPYangM. A neural network approach to estimate the frequency of a cantilever beam with random multiple damages. Sensors2023; 23: 7867.
34.
AliFChowdaryBV. Natural frequency prediction of FDM manufactured parts using ANN approach. IFAC Pap OnLine2019; 52: 403–408.
35.
TariqAUzunBDeliktaşB, et al.Vibration analysis of embedded porous nanobeams under thermal effects using boosting machine learning algorithms and semi-analytical approach. Mech Adv Mater Struct2024; 31(29): 12320–12343.
36.
Mat NormanMASivakumarKAb PatarMNA, et al.A prediction model for natural frequencies on Kevlar/Glass hybrid laminated composite using Artificial Neural Networks (ANN). International Journal of Integrated Engineering2022; 14(5): 207–214.
37.
ReddyMRSReddyBSReddyVN, et al.Prediction of natural frequency of laminated composite plates using artificial neural networks. Engineering2012; 04: 329–337.
38.
HavaranAMahmoudiMEbrahimpourR. Extraction of the structural mode shapes utilizing image processing method and data fusion. Mech Syst Signal Process2021; 151: 107380.
39.
LiuYCaoRXuS, et al.A deep learning-based method for structural modal analysis using computer vision. Eng Struct2024; 301: 117285.
40.
Al-QudahSBaiXYangM, et al.Deep learning-based structural health monitoring through the infusion of optical photos and vibration data. Adv Struct Eng2025; 28(3): 532–552.
41.
WordenKGreenPL. A machine learning approach to nonlinear modal analysis. Mech Syst Signal Process2017; 84: 34–53.
42.
OzdagliAIKoutsoukosX. Machine learning based novelty detection using modal analysis. Comput Aided Civ Inf2019; 34: 1119–1140.
43.
ZhouKXieDLXuK, et al.A machine learning-based stochastic subspace approach for operational modal analysis of civil structures. J Build Eng2023; 76: 107187.
44.
HasaniHFreddiF. Artificial neural network-based automated finite element model updating with an integrated graphical user interface for operational modal analysis of structures. Buildings2024; 14: 3093.
45.
NohKChangJH. Deep neural network ensemble for reducing artificial noise in bandwidth extension. Digit Signal Process2020; 102: 102760.
