The percussion method offers a viable solution for detecting debonding damage in fiber-reinforced polymer (FRP)-reinforced concrete interfaces. Leveraging the percussion method, a nondestructive technique, acoustic signals generated by light tapping on the FRP surface are analyzed to detect debonding. Traditional inspection methods often fail to identify internal structural defects, while our method introduces a dual-branch neural network that combines the strengths of gated recurrent units for temporal feature extraction and convolutional neural networks for spectral feature extraction. The innovation of this study lies in the integration of multimodal feature fusion and multi-head attention mechanisms, which allow the model to capture both temporal and spectral characteristics of the acoustic signals with greater precision. This dual-branch architecture, enhanced by attention mechanisms, significantly improves the accuracy and robustness of debonding detection compared to conventional techniques. Experimental results demonstrate the method’s potential in providing a scalable solution for real-time, noninvasive structural health monitoring of FRP-reinforced concrete structures.
YuanCChenWPhamTM, et al. Experimental and analytical study of flexural behaviour of BFRP sheets strengthened RC beams with new epoxy anchors. Eng Struct2021; 241: 112441.
2.
YeZZhouYZhaoD.Numerical simulations and simplified design approaches for large-rupture-strain FRP-strengthened reinforced concrete beams under impact. J Compos Constr2023; 27(5): 04023037.
3.
YuanCHeCXuJ, et al. Bayesian optimization for selecting efficient machine learning regressors to determine bond-slip model of FRP-to-concrete interface. Structures2022; 39: 351–364.
4.
PhamTMHaoH.Review of concrete structures strengthened with FRP against impact loading. Structures2016; 7: 59–70.
5.
ZhangFGaoLWuY-F, et al. Flexural design of reinforced concrete structures strengthened with hybrid bonded FRP. Compos Struct2021; 269: 113996.
ChenWPhamTMElchalakaniM, et al. Experimental and numerical study of basalt FRP strip strengthened RC slabs under impact loads. Int J Struct Stab Dyn2020; 20(06): 2040001.
8.
NelonCMyersOHallA.The intersection of damage evaluation of fiber-reinforced composite materials with machine learning: A review. J Compos Mater2022; 56(9): 1417–1452.
9.
YuanCKongQChenW, et al. Interfacial debonding detection in externally bonded BFRP reinforced concrete using stress wave-based sensing approach. Smart Mater Struct2020; 29(3): 035039.
10.
KongQGuJXiongB, et al. Vision-aided three-dimensional damage quantification and finite element model geometric updating for reinforced concrete structures. Comput Aided Civ Infrastruct Eng2023; 38: 2378–2390.
11.
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.
12.
YangZHuoLWangJ, et al. Feasibility study of percussion–acoustic-based void identification for underwater concrete. Struct Control Health Monit2022; 29(11): e3101.
13.
YuanCWangSQiY, et al. Automated structural bolt looseness detection using deep learning-based prediction model. Struct Control Health Monit2022; 29(3): e2899.
14.
ZhangDStewartEEntezamiM, et al. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network. Measurement2020; 156: 107585.
15.
WangXMaoDLiX.Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement2021; 173: 108518.
16.
GlowaczATadeusiewiczRLegutkoS, et al. Fault diagnosis of angle grinders and electric impact drills using acoustic signals. Appl Acoust2021; 179: 108070.
17.
DengMMengTCaoJ, et al. Heart sound classification based on improved MFCC features and convolutional recurrent neural networks. Neural Netw2020; 130: 22–32.
18.
DemirFTurkogluMAslanM, et al. A new pyramidal concatenated CNN approach for environmental sound classification. Appl Acoust2020; 170: 107520.
19.
YuZNiuZTangW, et al. Deep learning for daily peak load forecasting–A novel gated recurrent neural network combining dynamic time warping. IEEE Access2019; 7: 17184–17194.
20.
ChenYJiangHLiC, et al. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens2016; 54(10): 6232–6251.
21.
ChungJÇaglarGKyunghyunC, et al. “Empirical evaluation of gated recurrent neural networks on sequence modeling.” arXiv preprint arXiv:abs/1412.3555, 2014.
22.
DeyRSalemFM.Gate-variants of gated recurrent unit (GRU) neural networks. In: 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, 2017, pp.1597–1600.
23.
LechnerMRaminMH. “Learning long-term dependencies in irregularly-sampled time series.” arXiv preprint arXiv:abs/2006.04418, 2020.
AlbawiSMohammedTAAl-ZawiS. Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET). IEEE, 2017, pp.1–6.
26.
TaoCGaoSShangM, et al. Get the point of my utterance! Learning towards effective responses with multi-head attention mechanism. In: International Joint Conference on Artificial Intelligence, Stockholm Sweden, 13–19 July 2018, pp.4418–4424. AAAI Press.
27.
ZhangYXuBZhaoT.Convolutional multi-head self-attention on memory for aspect sentiment classification. IEEE/CAA J Autom Sin2020; 7(4): 1038–1044.
28.
YuanCChenWPhamTM, et al. Dynamic interfacial bond behaviour between basalt fiber reinforced polymer sheets and concrete. Int J Solids Struct2020; 202: 587–604.
29.
YuanCChenWPhamTM, et al. Interfacial bond behaviour between hybrid carbon/basalt fibre composites and concrete under dynamic loading. Int J Adhes Adhes2020; 99: 102569.
MitrovićDZeppelzauerMBreitenederC.Features for content-based audio retrieval. Adv Comput2010; 78: 71–150.
32.
NeelySTGorgaMP.Comparison between intensity and pressure as measures of sound level in the ear canal. J Acoust Soc Am1998; 104(5): 2925–2934.
33.
LoganB.Mel frequency cepstral coefficients for music modeling. In: Proceedings of the ISMIR, Plymouth, MA, 2000, p.11.
34.
MudaLMumtajBIrraivanE. “Voice Recognition Algorithms Using Mel Frequency Cepstral Coefficient (Mfcc) and Dynamic Time Warping (Dtw) Techniques”. arXiv preprint arXiv:abs/1003.4083, 2010.
