As structural damage patterns and service environments become increasingly complex, digital twin (DT)-based structural health monitoring, with its unique advantages, can compensate for the limitations of data-driven methods regarding data dependency and model interpretability. However, it still faces challenges in modeling complexity, simulation accuracy, and the discrepancies between real and virtual features. This study proposes a balanced fidelity DT for structural damage monitoring based on Lamb wave multilevel feature enhancement and adaptive space interaction. Firstly, multilevel refined features are extracted from few-shot guided wave signals obtained in physical and digital space, and the adversarial synthetic balancing algorithm is proposed for feature enhancement. Additionally, the learning phase of the damage monitoring model based on the feature-mapping convolutional network is driven by virtual samples of readily accessible balanced fidelity in digital space. To reduce the feature distribution difference between the two spaces, an interactive transfer strategy is introduced to establish a shared DT feature space. The model is further updated by accurate but elusive experimental data from the physical space, making it adaptable for damage diagnosis tasks of real structures in the shared space. This method reduces the dependence on experimental data and the cost of simulations, without compromising prediction accuracy. The case study shows that the damage localization accuracy of this DT system is increased by 22.67–30.55% and the quantification accuracy by 14.23–17.11% compared to a single space. Overall, this study provides a feasible technique to enhance the accessibility and generalizability of DTs for real engineering structures.
WangYWangMWuD, et al. Time series analysis and sparse sensor network-based impact monitoring for aircraft complex structures. Struct Heal Monit Int J2023; 22: 4069–4088.
2.
WangYLiaoYCuiX, et al. A heterogeneous decision voting-based transfer domain adaptation method for damage localization of CFRP composite structures. Mech Syst Signal Process2025; 224: 112015.
3.
Gonzalez-JimenezALomazziLJungesR, et al. Enhancing Lamb wave-based damage diagnosis in composite materials using a pseudo-damage boosted convolutional neural network approach. Struct Heal Monit Int J2024; 23: 1514–1529.
4.
LiuYHongXZhangB.Contact delamination detection of anisotropic composite plates using non-elliptical probability imaging of nonlinear ultrasonic guided waves. Struct Heal Monit Int J2023; 22: 276–295.
5.
QingXPBeardSJKumarA, et al. Built-in sensor network for structural health monitoring of composite structure. J Intell Mater Syst Struct2007; 18: 39–49.
6.
LiaoYHuangYWangY, et al. Complex CFRP damage detection with dual multiscale 1DCNNs and self-selective fusion technique of guided waves. Compos Struct2024; 335: 117993.
7.
ShaoWSunHZhouQ, et al. A novel Lamb wave-based multi-damage dataset construction and quantification algorithm under the framework of multi-task deep learning. Struct Heal Monit Int J2024; 23: 1148–1169.
8.
AbbassiARomgensNTritschelFF, et al. Evaluation of machine learning techniques for structural health monitoring using ultrasonic guided waves under varying temperature conditions. Struct Heal Monit Int J2023; 22: 1308–1325.
9.
LiaoYWangYZengX, et al. Multiscale 1-DCNN for damage localization and quantification using guided waves with novel data fusion technique and new self-attention module. IEEE Trans Ind Informs2024; 20: 492–502.
10.
SikdarSOstachowiczWKunduA. Deep learning for automatic assessment of breathing-debonds in stiffened composite panels using non-linear guided wave signals. Compos Struct2023; 312: 116876.
11.
BooyseWWilkeDNHeynsS. Deep digital twins for detection, diagnostics and prognostics. Mech Syst Signal Process2020; 140: 106612.
12.
DangHTatipamulaMNguyenHX.Cloud-based digital twinning for structural health monitoring using deep learning. IEEE Trans Ind Inform2022; 18: 3820–3830.
13.
RittoTGRochinhaFA.Digital twin, physics-based model, and machine learning applied to damage detection in structures. Mech Syst Signal Process2021; 155: 107614.
14.
ZhouXSbarufattiCGiglioM, et al. A fuzzy-set-based joint distribution adaptation method for regression and its application to online damage quantification for structural digital twin. Mech Syst Signal Process2023; 191: 110164.
15.
LovedayPW.Simulation of piezoelectric excitation of guided waves using waveguide finite elements. IEEE Trans Ultrason Ferroelectr Freq Control2008; 55: 2038–2045.
16.
ShenYGiurgiutiuV.WaveFormRevealer: an analytical framework and predictive tool for the simulation of multi-modal guided wave propagation and interaction with damage. Struct Heal Monit Int J2014; 13: 491–511.
17.
De LucaAPerfettoDPolverinoA, et al. Finite element modeling approaches, experimentally assessed, for the simulation of guided wave propagation in composites. Sustain2022; 14: 6924.
18.
LeckeyCACRoggeMDRaymond ParkerF. Guided waves in anisotropic and quasi-isotropic aerospace composites: three-dimensional simulation and experiment. Ultrasonics2014; 54: 385–394.
19.
SongYQuZLiaoH, et al. Material twins generation of woven polymer composites based on ResL-U-Net convolutional neural networks. Compos Struct2023; 307: 116672.
20.
BisharaDXieYLiuWK, et al. A state-of-the-art review on machine learning-based multiscale modeling, simulation, homogenization and design of materials. Arch Comput Methods Eng2023; 30: 191–222.
21.
HuangWXuRYangJ, et al. Data-driven multiscale simulation of FRP based on material twins. Compos Struct2021; 256: 113013.
22.
LuleciFCatbasFNAvciO.Generative adversarial networks for labeled acceleration data augmentation for structural damage detection. J Civ Struct Heal Monit2023; 13: 181–198.
23.
ZareapoorMShamsolmoaliPYangJ.Oversampling adversarial network for class-imbalanced fault diagnosis. Mech Syst Signal Process2021; 149: 107175.
24.
LiangPDengCWuJ, et al. Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network. Meas J Int Meas Confed2020; 159: 107768.
25.
Soleimani-BabakamaliMHSoleimani-BabakamaliRSarloR.A general framework for supervised structural health monitoring and sensor output validation mitigating data imbalance with generative adversarial networks-generated high-dimensional features. Struct Heal Monit Int J2022; 21: 1167–1182.
26.
AliakbariMMahmoudiMVadaszP, et al. Predicting high-fidelity multiphysics data from low-fidelity fluid flow and transport solvers using physics-informed neural networks. Int J Heat Fluid Flow2022; 96: 109002.
27.
GiannakeasINKhodaeiZSAliabadiFMH. Effect of detection and localization uncertainty on damage size estimation using guided wave based SHM. Procedia Struct Integr2024; 52: 655–666.
28.
LiTLomazziLCadiniF, et al. Numerical simulation-aided particle filter-based damage prognosis using Lamb waves. Mech Syst Signal Process2022; 178: 109326.
29.
ZhaoFZhouXWangC, et al. Setting adaptive inspection intervals in helicopter components, based on a digital twin. AIAA J2023; 61: 2675–2688.
30.
ChenJYuanSWangH.On-line updating Gaussian process measurement model for crack prognosis using the particle filter. Mech Syst Signal Process2020; 140: 106646.
31.
LiCMahadevanSLingY, et al. Dynamic Bayesian network for aircraft wing health monitoring digital twin. AIAA J2017; 55: 930–941.
32.
GardnerPBullLADervilisN, et al. Domain-adapted Gaussian mixture models for population-based structural health monitoring. J Civ Struct Heal Monit2022; 12: 1343–1353.
33.
NerlikarVMiorelliRRecoquillayA, et al. A physics-embedded deep-learning framework for efficient multifidelity modeling applied to guided wave based structural health monitoring. Ultrasonics2024; 141: 107325.
34.
AbsiGNMahadevanS.Multi-fidelity approach to dynamics model calibration. Mech Syst Signal Process2016; 68–69: 189–206.
35.
ContiPGuoMManzoniA, et al. Multi-fidelity surrogate modeling using long short-term memory networks. Comput Methods Appl Mech Eng2023; 404: 115811.
36.
MitraMGopalakrishnanS. Guided wave based structural health monitoring: A review. SMART Mater Struct2016; 25: 053001.
37.
KudelaPRadzienskiMOstachowiczW.Impact induced damage assessment by means of Lamb wave image processing. Mech Syst Signal Process2018; 102: 23–36.
38.
LiSBrunMGravouilA, et al. Explicit/implicit multi-time step simulation of bridge crane under earthquake with frictional contacts and high-frequency Rayleigh damping. Finite Elem Anal Des2023; 220: 103946.
39.
WangYCuiXLiuQ, et al. An adaptive damage monitoring method based on transfer features mapped for advanced composite structures. Compos Struct2024; 329: 117742.
40.
Fabila-CarrascoJSTanCEscuderoJ.Permutation entropy for graph signals. IEEE Trans Signal Inf Process Over Netw2022; 8: 288–300.
41.
FengGLaoK-W.Wasserstein adversarial learning for identification of power quality disturbances with incomplete data. IEEE Trans Ind Inform2023; 19: 10401–10411.
42.
TianJLiuMXiaoH, et al. Optimized ultrasonic total focusing imaging of diverse and multiple defects in crossply CFRP: floquet wave theory, numerical simulation, and experimental validation. Mech Syst Signal Process2023; 199: 110486.
43.
HervinFFrommeP.Anisotropy influence on guided wave scattering for composite structure monitoring. Struct Heal Monit Int J2023; 22: 2626–2640.
44.
HuoHHeJGuanX.A Bayesian fusion method for composite damage identification using Lamb wave. Struct Heal Monit Int J2021; 20: 2337–2359.
45.
LeckeyCACWheelerKRHafiychukVN, et al. Simulation of guided-wave ultrasound propagation in composite laminates: benchmark comparisons of numerical codes and experiment. Ultrasonics2018; 84: 187–200.
46.
AsadzadehMZourarisGE.On the convergence of a linearly implicit finite element method for the nonlinear Schrödinger equation. Stud Appl Math2024; 153: e12743.
47.
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.
