Real-time condition monitoring (CM) utilizing vibration measurements offers a proactive approach to detect faults and enable predictive maintenance. The robustness and accuracy of CM applications significantly rely on the quality of training datasets. While numerical model-generated data is commonly used in current solutions, the efficiency of CM frameworks is greatly influenced by dataset quality. This research addresses the challenge by employing data-driven modeling to enhance the efficiency and accuracy of CM frameworks. A Hierarchical Bayesian Modeling (HBM) framework is introduced to estimate uncertainties in finite element (FE) model parameters at the healthy state. The HBM is particularly adept at addressing uncertainties in model parameters caused by variations in experimental data, material characteristics, assembly processes, and nonlinear mechanisms under diverse loading scenarios. These uncertainties in the parameters of the FE model obtained at the healthy state of the structure are maintained for the model representing the damaged state of the structure. The FE model with the associated uncertainties is used to generate data for training a convolution neural network model for the different health states. Such training based only on observed/inferred uncertainties at the healthy state significantly enhances the robustness and overall accuracy of the CM framework against previous approaches based on arbitrarily imposed uncertainties at the healthy and damaged state of the structure. To validate the effectiveness of the proposed method, multiple experimental structural dynamics tests on a small-scale laboratory truss are conducted at the healthy and damaged states. The results demonstrate the applicability and effectiveness of the developed approach in improving the structural health monitoring process.
MechbalNUribeJSRebillatM.A probabilistic multi-class classifier for structural health monitoring. Mech Syst Sig Process2015; 60–61: 106–123.
2.
SatpalSKhandareYGuhaA, et al. Structural health monitoring (SHM) of cantilever beam using support vector machine. Int J Adv Eng2013; 5(1): 2.
3.
BullLAWordenKDervilisN.Towards semi-supervised and probabilistic classification in structural health monitoring. Mech Syst Sig Process2020; 140: 106653.
4.
TcherniakDMolgaardL.Active vibration-based structural health monitoring system for wind turbine blade: Demonstration on an operating Vestas V27 wind turbine. Struct Health Monit2017; 16(5): 536–550.
5.
SonySGamageSSadhuA, et al.. Vibration-based multiclass damage detection and localization using long short-term memory networks. Structures2022; 35: 436–451.
6.
MendlerADöhlerMVenturaCE.A reliability-based approach to determine the minimum detectable damage for statistical damage detection. Mech Syst Sig Process2021; 154: 107561.
7.
RosafalcoLTorzoniMManzoniA, et al. Online structural health monitoring by model order reduction and deep learning algorithms. Comput Struct2021; 255: 106604.
8.
BigoniCHesthavenJS.Simulation-based anomaly detection and damage localization: An application to structural health monitoring. Comput Methods Appl Mech Eng2020; 363(1): 112896.
9.
DaneshvarMHSarmadiH.Unsupervised learning-based damage assessment of full-scale civil structures under long-term and short-term monitoring. Eng Struct2022; 256: 114059.
10.
GordanMSabbagh-YazdiSRIsmailZ, et al. State-of-the-art review on advancements of data mining structural health monitoring. Measurement2022; 193: 110939.
11.
UmarSVafaeiMAlihSC.Sensor clustering-based approach for structural damage identification under ambient vibration. Autom Constr2021; 121: 103433.
12.
SeventekidisPGiagopoulosD.Model error effects in supervised damage identification of structures with numerically trained classifiers. Mech Syst Sig Process2023; 184.
13.
YeZYuJ.Deep morphological convolutional network for feature learning of vibration signals and its applications to gearbox fault diagnosis. Mech Syst Sig Process2021; 161: 107984.
JoshuvaASugumaranV.A lazy learning approach for condition monitoring of wind turbine blade using vibration signals and histogram features. Measurement2020; 152: 107295.
16.
KaryofyllasGGiagopoulosD.Condition monitoring framework for damage identification in CFRP rotating shafts using model-driven machine learning techniques. Eng Fail Anal2024; 158: 108052.
17.
CaiCGuoXRenJ, et al. Small-sample damage detection of bleacher structure based on GAN and MSS-CNN models. Struct Health Monit2024; 0(0). doi:10.1177/1 4759217241252756
18.
AhmadzadehMZahraiSMBitarafM, et al. An integrated deep neural network model combining 1D CNN and LSTM for structural health monitoring utilizing multisensor time-series data. Struct Health Monit2025; 24(1): 447–465.
19.
DoroudiRLavassaniSHHShahrouziM.Optimal tuning of three deep learning methods with signal processing and anomaly detection for multi-class damage detection of a large-scale bridge. Struct Health Monit2024; 23(5): 3227–3252.
20.
Di MucciVMCardellicchioARuggieriS, et al. Artificial intelligence in structural health management of existing bridges. Autom Constr2024; 167: 105719.
21.
ChaYJAliRLewisJ, et al. Deep learning-based structural health monitoring. Autom Constr2024; 161: 105328.
22.
LozanoFEmadiSKomarizadehaslA, et al. Enhancing the accuracy of low-cost inclinometers with artificial intelligence. Buildings2024; 14(2): 519.
23.
YessoufouFZhuJ.Classification and regression-based convolutional neural network and long short-term memory configuration for bridge damage identification using long-term monitoring vibration data. Struct Health Monit2023; 22(6): 4027–4054.
24.
StandoliGSalachorisGPMasciottaMG, et al. Modal-based FE model updating via genetic algorithms: Exploiting artificial intelligence to build realistic numerical models of historical structures. Constr Build Mater2021; 303: 124393.
25.
GhiasiRGhasemiMRNooriM.Comparative studies of metamodeling and AI-based techniques in damage detection of structures. Adv Eng Softw2018; 125: 101–112.
26.
KongQJiKGuJ, et al. A CNN-integrated percussion method for detection of FRP–concrete interfacial damage with FEM reconstruction. Struct Health Monit2023; 22(1): 216–231.
27.
AwadallahOSadhuA.Automated multiclass structural damage detection and quantification using augmented reality. J Infrastruct Intell Resil2023; 2(1): 100024.
28.
BattuRSAgathosKLondoño MonsalveJM, et al. Combining transfer learning and numerical modelling to deal with the lack of training data in data-based SHM. J Sound Vib2025; 595: 118710.
29.
SvendsenBTØisethOFrøsethGT, et al. A hybrid structural health monitoring approach for damage detection in steel bridges under simulated environmental conditions using numerical and experimental data. Struct Health Monit2023; 22(1): 540–561.
30.
HielscherTKhalilSVirgonaN, et al. A neural network based digital twin model for the structural health monitoring of reinforced concrete bridges. Structures2023; 57: 105248.
31.
DuranBEmoryDEftekhar AzamY, et al. A novel CNN architecture for robust structural damage identification via strain measurements and its validation via full-scale experiments. Measurement2025; 239: 115393.
32.
MeiLFYanWJYuenKV, et al. Streaming variational inference-empowered Bayesian nonparametric clustering for online structural damage detection with transmissibility function. Mech Syst Signal Process2025; 222: 111767.
33.
FengZZhangJXuanX, et al. Bayesian time domain approach for damping identification and uncertainty quantification in stay cables using free vibration response. Eng Struct2024; 315: 118477.
34.
ZhaoXYuanSZhouH, et al. An evaluation on the multi-agent system based structural health monitoring for large scale structures. Expert Syst Appl2009; 36(3): 4900–4914.
35.
LiHZhengSShenY, et al. Hydro-steel structure digital twins: application in structural health monitoring and maintenance of large-scale reservoir. Adv Eng Inform2024; 62(D): 102922.
36.
MaYChunQZhangC, et al. Structural health monitoring and quantitative safety evaluation methods for ancient stone arch bridges. J Cult Herit2024; 70: 366–380.
37.
PingMJiaXPapadimitriouC, et al. A hierarchical Bayesian modeling framework for identification of non-Gaussian processes. Mech Syst Signal Process2024; 208: 110968.
38.
JiaSSedehiMPapadimitriouC, et al. Two-stage hierarchical Bayesian framework for finite element model validation and uncertainty quantification. Model Valid Uncertainty Quantif2020; 3: 383–387.
39.
MoaveniBBehmaneshI.Effects of changing ambient temperature on finite element model updating of the Dowling Hall Footbridge. Eng Struct2012; 43: 58–68.
40.
JensenCPapadimitriouC.Bayesian finite element model updating. In: Sub-structure coupling for dynamic analysis: application to complex simulation-based problems involving uncertainty. Springer, 2019, pp.179–227.
41.
KurumbhatiMMRamanchaMKAakashBS, et al. Hierarchical Bayesian modeling for calibration and uncertainty quantification of constitutive material models: application to a uniaxial steel material model. Eng Struct2024; 318: 118409.
42.
LiuXWLuDG.Uncertainties quantification of fatigue load mixture model using hierarchical Bayesian models. Int J Fatigue2023; 174: 107734.
43.
RamanchaMKAstrozaRMadarshahianR, et al. Bayesian updating and identifiability assessment of nonlinear finite element models. Mech Syst Signal Process2022; 167(A): 108517.
44.
JiaSSedehiMPapadimitriouC, et al. Hierarchical Bayesian modeling framework for model updating and robust predictions in structural dynamics using modal features. Mech Syst Signal Process2022; 170: 108784.
45.
YanWJKatafygiotisLS.A two-stage fast Bayesian spectral density approach for ambient modal analysis. Part II: Mode shape assembly and case studies. Mech Syst Signal Process2015; 54–55: 156–171.
46.
ZhuZPengGChenY, et al. A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis. Neurocomputing2019; 323: 62–75.
47.
AbdeljaberOAvciOKiranyazS, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vib2017; 388: 154–170.
48.
MoJYanWJYuenKV, et al. Efficient non-probabilistic parallel model updating based on analytical correlation propagation formula and derivative-aware deep neural network metamodel. Comput Methods Appl Mech Eng2025; 433(A): 117490.
49.
DöhlerMHilleFMevelL, et al. Structural health monitoring with statistical methods during progressive damage test of S101 Bridge. Eng Struct2014; 69: 183–193.
50.
GarcíaDTcherniakD.An experimental study on the data-driven structural health monitoring of large wind turbine blades using a single accelerometer and actuator. Mech Syst Signal Process2019; 127: 102–119.
51.
PadilKHBakharyNAbdulkareemM, et al. Non-probabilistic method to consider uncertainties in frequency response function for vibration-based damage detection using artificial neural network. J Sound Vib2020; 467: 115069.
52.
BehmaneshIMoaveniBLombaertG, et al. Hierarchical Bayesian model updating for structural identification. Mech Syst Signal Process2015; 64: 360–376.
53.
GiagopoulosDArailopoulosA.Computational framework for model updating of large scale linear and nonlinear finite element models using state-of-the-art evolution strategy. Comput Struct2017; 192: 210–232.
54.
LyeACicirelloAPatelliE.An efficient and robust sampler for Bayesian inference: transitional ensemble Markov chain Monte Carlo. Mech Syst Signal Process2022; 167(B): 108471.
