In the realm of civil engineering, ensuring the structural integrity of roofing systems is paramount for building safety. Traditional methods for damage detection often fall short in terms of accuracy and efficiency, necessitating advancements in this critical area. This study aims to address these challenges by introducing an encoder-based attention mechanism (EAM) deep learning network designed specifically for the detection of damage within roofing structures. By strategically deploying sensors in a matrix layout and employing Fourier transforms to convert time-domain data into spectral images, the proposed deep learning network can leverage the advantages of convolutional structure and enhance the identification and extraction of damage-related features in roof systems. Furthermore, the integration of the newly designed EAM enables the model to focus on relevant features more effectively, significantly improving damage detection accuracy. Experimental validations conducted on real-world structures demonstrate the model’s capability to accurately and efficiently identify structural damage, marking a significant advancement over conventional methods.
ChaYJWangZ.Unsupervised novelty detection–based structural damage localization using a density peaks-based fast clustering algorithm. Struct Health Monit2018; 17(2): 313–324.
2.
YuYRashidiMDorafshanS, et al. Ground penetrating radar-based automated defect identification of bridge decks: a hybrid approach. J Civ Struct Health Monit2024; 81–23.
3.
WangZChaYJ.Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage. Struct Health Monit2021; 20(1): 406–425.
4.
WanHGaoLYuanZ, et al. A novel transformer model for surface damage detection and cognition of concrete bridges. Expert Syst Appl2023; 213: 119019.
5.
WanHPZhuYKLuoY, et al. Unsupervised deep learning approach for structural anomaly detection using probabilistic features. Struct Health Monit2024; 24: 3–33.
6.
KangDHChaYJ.Efficient attention-based deep encoder and decoder for automatic crack segmentation. Struct Health Monit2022; 21(5): 2190–2205.
7.
AliRChaYJ.Attention-based generative adversarial network with internal damage segmentation using thermography. Autom Constr2022; 141: 104412.
8.
ZouLMaCHuJ, et al. Enhanced predictive modeling of rotating machinery remaining useful life by using separable convolution backbone networks. Appl Soft Comput2024; 156111493.
9.
WangYQiuLLuoY, et al. A piezoelectric sensor network with shared signal transmission wires for structural health monitoring of aircraft smart skin. Mech Syst Signal Process2020; 141: 106730.
10.
ZouLChenHHuJ, et al. A novel meta fusion detective twin network approach for dynamic degradation process in rotating machinery. Expert Syste Appl2024; 268: 126358.
11.
YouZWangD.An extraction method for structural features based on edge detection and multi-conditional filtering: a case study of the steel box girder from engineering blueprints. Signal Image Video Process2024; 18(3): 2819–2828.
ChaYJAliRLewisJ, et al. Deep learning-based structural health monitoring. Autom Constr2024; 161: 105328.
14.
HeYZhangLChenZ, et al. A framework of structural damage detection for civil structures using a combined multi-scale convolutional neural network and echo state network. Eng Comput2023; 39(3): 1771–1789.
15.
DongGSWanHPLuoY, et al. A fast sparsity-free compressive sensing approach for vibration data reconstruction using deep convolutional GAN. Mech Syst Signal Process2023; 188: 109937.
16.
MahmoudiHBitarafMSalkhordehM, et al. A rapid machine learning-based damage detection algorithm for identifying the extent of damage in concrete shear-wall buildings. Structures2023; 47: 482–499.
17.
VoTTLiuMKTranMQ.Harnessing attention mechanisms in a comprehensive deep learning approach for induction motor fault diagnosis using raw electrical signals. Eng Appl Artif Intell2024; 129: 107643.
18.
EppTChaYJ.Air-coupled impact-echo damage detection in reinforced concrete using wavelet transforms. Smart Mater Struct2016; 26(2): 025018.
19.
WeiQTianXCuiL, et al. WSAFormer-DFFN: a model for rotating machinery fault diagnosis using 1D window-based multi-head self-attention and deep feature fusion network. Eng Appl Artif Intell2023; 124: 106633.
20.
LiCLiSWangH, et al. Attention-based deep meta-transfer learning for few-shot fine-grained fault diagnosis. Knowl-Based Syst2023; 264: 110345.
21.
WangHZhouZZhangL, et al. Multiscale deep attention Q network: a new deep reinforcement learning method for imbalanced fault diagnosis in gearboxes. IEEE Trans Instrum Meas2023; 73: 3503512.
22.
NiuZZhongGYuH.A review on the attention mechanism of deep learning. Neurocomputing2021; 452: 48–62.
23.
ChenYPengGZhuZ, et al. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Appl Soft Comput2020; 86: 105919.
24.
ZhaoZZhangWQ.End-to-end keyword search system based on attention mechanism and energy scorer for low resource languages. Neural Netw2021; 139: 326–334.
25.
YanSZhangL.CR-Net: robot grasping detection method integrating convolutional block attention module and residual module. IET Comput Vis2024; 18(3): 420–433.
26.
KongSDengJYangL, et al. An attention-based dual-encoding network for fire flame detection using optical remote sensing. Eng Appl Artif Intell2024; 127: 107238.
27.
XuJZhuXShiL, et al. Squeeze-and-excitation attention and bi-directional feature pyramid network for filter screens surface detection. J Electron Imaging2024; 33(4): 043044–043044.
28.
WangLYiSYuY, et al. Automated ultrasonic-based diagnosis of concrete compressive damage amidst temperature variations utilizing deep learning. Mech Syst Signal Process2024; 221: 111719.
RoyAMBhaduriJ.DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism. Adv Eng Inform2023; 56: 102007.
31.
ZouLLamHFHuJ.Adaptive resize-residual deep neural network for fault diagnosis of rotating machinery. Struct Health Monit2023; 22(4): 2193–2213.
32.
ZouLZhuangKJZhouA, et al. Bayesian optimization and channel-fusion-based convolutional autoencoder network for fault diagnosis of rotating machinery. Eng Struct2023; 280: 115708.
33.
KaraAPekelEOzcetinE, et al. Genetic algorithm optimized a deep learning method with attention mechanism for soil moisture prediction. Neural Comput Appl2024; 36(4): 1761–1772.
34.
HeJXuYPanY, et al. Adaptive weighted generative adversarial network with attention mechanism: a transfer data augmentation method for tool wear prediction. Mech Syst Signal Process2024; 212: 111288.
35.
JinXXieYWeiXS, et al. Delving deep into spatial pooling for squeeze-and-excitation networks. Pattern Recognit2022; 121: 108159.
36.
AstudilloABarreraAGuindelC, et al. DAttNet: monocular depth estimation network based on attention mechanisms. Neural Comput Appl2024; 36(7): 3347–3356.
37.
HuJLamPHFChungKF.Operational modal analysis and Bayesian model updating of a standing seam metal roofing system. Int J Lifecycle Perform Eng2019; 3(1): 4–19.
