This study investigates a structural health monitoring method for impacted composite stiffened panels based on experimental data and the random forest (RF) algorithm. Various types of impact damage are introduced into the composite stiffened panels. An RF model is then developed, utilizing the strain data to accurately detect and identify the damage that traditional methods, such as visual inspection, struggle to recognize. A damage-equivalent methodology is employed to construct a finite element model (FEM). Based on the experimental results, the feasibility of using the FEM as a supplement to experimental data in training machine learning models has been substantiated. Furthermore, FEMs are developed for entirely new types of damage, and the trained machine learning model proficiently identifies the presence and specific type of damage. This research underscores the robustness and adaptability of strain-based SHM, providing a dependable and meticulous approach for assessing structural integrity.
FalcetelliFYueNDi SanteR, et al. Probability of detection, localization, and sizing: the evolution of reliability metrics in structural health monitoring. Struct Health Monit2022; 21: 2990–3017.
2.
BondRUnderwoodSAdamsDE, et al. Structural health monitoring–based methodologies for managing uncertainty in aircraft structural life assessment. Struct Health Monit2014; 13(6): 621–628.
3.
YueNAliabadiMH.Hierarchical approach for uncertainty quantification and reliability assessment of guided wave-based structural health monitoring. Struct Heal Monit2021; 20(5): 2274–2299.
4.
GomesGFMendézYADda Silva Lopes AlexandrinoP, et al. The use of intelligent computational tools for damage detection and identification with an emphasis on composites – a review. Compos Struct2018; 196(April): 44–54.
5.
Rubio-GonzálezCde Urquijo-VenturaMdelPRodríguez-GonzálezJA.Damage progression monitoring using self-sensing capability and acoustic emission on glass fiber/epoxy composites and damage classification through principal component analysis. Compos Part B Eng2023; 254: 110608.
6.
KumarCSFotouhiMSaeedifarM, et al. Acoustic emission based investigation on the effect of temperature and hybridization on drop weight impact and post-impact residual strength of hemp and basalt fibres reinforced polymer composite laminates. Compos Part B Eng2019; 173(December): 106962.
7.
SunWGuanZLiZ, et al. Modelling and simulating of the compressive behavior of T-stiffened composite panels subjected to stiffener impact. Compos Struct2018; 186(September): 221–232.
8.
OuyangTSunWGuanZ, et al. Experimental study on delamination growth of stiffened composite panels in compression after impact. Compos Struct2018; 206(May): 791–800.
9.
GhelliDMinakG.Low velocity impact and compression after impact tests on thin carbon/epoxy laminates. Compos Part B Eng2011; 42(7): 2067–2079.
10.
HariziWChakiSBourseG, et al. Damage mechanisms assessment of Glass Fiber-Reinforced Polymer (GFRP) composites using multivariable analysis methods applied to acoustic emission data. Compos Struct2022; 289(December): 115470.
11.
LiangQLiuJWangX, et al. Flexural progressive failure mechanism of hybrid 3D woven composites: combination of X-ray tomography, acoustic emission and digital image correlation. Compos Struct2021; 280(September): 114894.
12.
ChangHYYuanFG.Damage imaging in a stiffened curved composite sandwich panel with wavenumber index via Riesz transform. Struct Heal Monit2020; 19(3): 902–916.
13.
SarhadiAAlbuquerqueRQDemleitnerM, et al. Machine learning based thermal imaging damage detection in glass-epoxy composite materials. Compos Struct2022; 295: 115786.
14.
ZengXLiuXYanJ, et al. Lamb wave-based damage localization and quantification algorithms for CFRP composite structures. Compos Struct2022; 295: 115849.
15.
WuJXuXLiuC, et al. Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform. Compos Struct2021; 276(August): 114590.
16.
LiYWangKWangQ, et al. Acousto-ultrasonics-based health monitoring for nano-engineered composites using a dispersive graphene-networked sensing system. Struct Heal Monit2021; 20(1): 240–254.
17.
YuMHKimHS.Deep-learning based damage sensing of carbon fiber/polypropylene composite via addressable conducting network. Compos Struct2021; 267: 113871.
18.
JacobsEWYangCDemirKG, et al. Vibrational detection of delamination in composites using a combined finite element analysis and machine learning approach. J Appl Phys2020; 128(12): 125104.
19.
ZhangZPanJLuoW, et al. Vibration-based delamination detection in curved composite plates. Compos Part A Appl Sci Manuf2019; 119(December): 261–274.
20.
ChaupalPRajendranP.A review on recent developments in vibration-based damage identification methods for laminated composite structures: 2010–2022. Compos Struct2023; 311: 116809.
21.
KesavanAJohnSLiH, et al. A comparative study of statistical outlier analysis and ANN methods for damage detection and assessment in composite structures. J Intell Mater Syst Struct2010; 21(3): 337–347.
22.
MilanoskiDPLoutasTH.Strain-based health indicators for the structural health monitoring of stiffened composite panels. J Intell Mater Syst Struct2021; 32(3): 255–266.
23.
El KadiH. Modeling the mechanical behavior of fiber-reinforced polymeric composite materials using artificial neural networks—a review. Compos Struct2006; 73(1): 1–23.
24.
BaoYLiH.Machine learning paradigm for structural health monitoring. Struct Heal Monit2021; 20(4): 1353–1372.
25.
LimDKMustaphaKBPagwiwokoCP.Delamination detection in composite plates using random forests. Compos Struct2021; 278(May): 114676.
26.
CuiRAzuaraGLanzadiScaleaF, et al. Damage imaging in skin-stringer composite aircraft panel by ultrasonic-guided waves using deep learning with convolutional neural network. Struct Heal Monit2022; 21(3): 1123–1138.
27.
LiaoYQingXWangY, et al. Damage localization for composite structure using guided wave signals with Gramian angular field image coding and convolutional neural networks. Compos Struct2023; 312: 116871.
28.
LinMGuoSHeS, et al. Structure health monitoring of a composite wing based on flight load and strain data using deep learning method. Compos Struct2022; 286(December): 115305.
29.
KhanSYairiT.A review on the application of deep learning in system health management. Mech Syst Signal Process2018; 107: 241–265.
30.
CastroOYeniceliSCBerringP, et al. Experimental demonstration of strain-based damage method for optimized fatigue testing of wind turbine blades. Compos Struct2022; 293(May): 115683.
31.
GrassiaLIannoneMCalifanoA, et al. Strain based method for monitoring the health state of composite structures. Compos Part B Eng2019; 176(August): 107253.
32.
WangYHuSXiongT, et al. Recent progress in aircraft smart skin for structural health monitoring. Struct Health Monit2022; 21: 2453–2480.
33.
BergmayrTHöllSKralovecC, et al. Local residual random forest classifier for strain-based damage detection and localization in aerospace sandwich structures. Compos Struct2023; 304(P1): 116331.
34.
Alvarez-MontoyaJCarvajal-CastrillónASierra-PérezJ.In-flight and wireless damage detection in a UAV composite wing using fiber optic sensors and strain field pattern recognition. Mech Syst Signal Process2020; 136: 106526.
35.
FrövelMCarriónGPintadoJM, et al. Health and usage monitoring of Spanish National Institute for Aerospace Technology unmanned air vehicles. Struct Health Monit2017; 16: 486–493.
36.
SilionisNEAnyfantisKN.Static strain-based identification of extensive damages in thin-walled structures. Struct Heal Monit2022; 21(5): 2026–2047.
37.
TanRXuJGuanZ, et al. Experimental study on effect of impact locations on damage formation and compression behavior of stiffened composite panels with L-shaped stiffener. Thin Walled Struct2020; 150(February): 106707.
38.
WangGZhangLXuX, et al. Real-time detection of barely visible defects on composite structures based on surface reconstruction. Compos Struct2023; 311: 116852.
39.
TabatabaeianAJerkovicBHarrisonP, et al. Barely visible impact damage detection in composite structures using deep learning networks with varying complexities. Compos Part B Eng2023; 264: 110907.
40.
TopacOTGozlukluBGursesE, et al. Experimental and computational study of the damage process in CFRP composite beams under low-velocity impact. Compos Part A2017; 92: 167–182.
41.
SjoÈgrenAKrasnikovsAVarnaJ.Experimental determination of elastic properties of impact damage in carbon fibre/epoxy laminates. Compos Part A2001; 32: 1237–1242.
42.
LiNChenP.Prediction of compression-after-edge-impact (CAEI) behaviour in composite panel stiffened with I-shaped stiffeners. Compos Part B Eng2017; 110: 402–419.
43.
BaoXWangZFuD, et al. Machine learning methods for damage detection of thermoplastic composite pipes under noise conditions. Ocean Eng2022; 248: 110817.
44.
MukhopadhyayT.A multivariate adaptive regression splines based damage identification methodology for web core composite bridges including the effect of noise. J Sandw Struct Mater2018; 20(7): 885–903.
