With the advancement of deep learning, data-driven structural damage identification (SDI) has shown considerable development. However, collecting vibration signals related to structural damage poses certain challenges, which can undermine the accuracy of the identification results produced by data-driven SDI methods in scenarios where data is scarce. This paper introduces an innovative approach to bridge SDI in a few-shot context by integrating an adaptive simulated annealing particle swarm optimization-convolutional neural network (ASAPSO-CNN) as the foundational framework, augmented by data enhancement techniques. Firstly, three specific types of noise are introduced to augment the source signals used for training. Subsequently, the source signals and augmented signals are recombined to construct a four-dimensional matrix as the input to the CNN, while defining the damage feature vector as the output. Secondly, a CNN is constructed to establish the mapping relationship between the input and output. Then, an adaptive fitness function is proposed that simultaneously considers the accuracy of SDI, model complexity, and training efficiency. The ASAPSO is employed to adaptively optimize the hyperparameters of the CNN. The proposed method is validated on an experimental model of a three-span continuous beam. It is compared with four other data-driven methods, demonstrating good effectiveness and robustness of SDI under cases of scarce data. Finally, the effectiveness of this SDI method is validated in a real-world case of a steel truss bridge.
HuangMSZhangJWHuJL, et al. Nonlinear modeling of temperature-induced bearing displacement of long-span single-pier rigid frame bridge based on DCNN-LSTM. Case Stud Therm Eng2024; 53: 103897.
2.
DengZHHuangMSWanN, et al. The current development of structural health monitoring for bridges: a review. Buildings2023; 13(6): 1360.
3.
HuangMSChengXHLeiYZ. Structural damage identification based on substructure method and improved whale optimization algorithm. J Civ Struct Health2021; 11: 351–380.
4.
LuoJHuangMSLeiYZ. Temperature effect on vibration properties and vibration-based damage identification of bridge structures: a literature review. Buildings2022; 12(8): 1209.
5.
CawleyPAdamsRD. The location of defects in structures from measurements of natural frequencies. J Strain Anal Eng1979; 14: 49–57.
6.
HuangMSGülMZhuHP. Vibration-based structural damage identification under varying temperature effects. J Aerospace Eng2018; 31(3): 04018014.
7.
ModenaCSondaDZontaD. Damage localization in reinforced concrete structures by using damping measurements. Key Eng Mater1999; 167–168: 132–141.
8.
HuangMSLingZZSunC, et al. Two-stage damage identification for bridge bearings based on sailfish optimization and element relative modal strain energy. Struct Eng Mech2023; 86: 715–730.
9.
DasSSahaPPatroS. Vibration-based damage detection techniques used for health monitoring of structures: a review. J Civ Struct Health2016; 6: 477–507.
10.
AzimiMEslamlouADPekcanG. Data-driven structural health monitoring and damage detection through deep learning: state-of-the-art review. Sensors2020; 20: 2778.
11.
AvciOAbdeljaberOKiranyazS, et al. A review of vibration-based damage detection in civil structures: from traditional methods to machine learning and deep learning applications. Mech Syst Signal Pr2021; 147: 107077.
12.
AbdeljaberOAvciOKiranyazS, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vib2017; 388: 154–170.
13.
WangXShahzadMM. A novel structural damage identification scheme based on deep learning framework. Structures2021; 29: 1537–1549.
14.
LiuTWXuHRagulskisM, et al. A data-driven damage identification framework based on transmissibility function datasets and one-dimensional convolutional neural networks: verification on a structural health monitoring benchmark structure. Sensors2020; 20: 1059.
15.
LiMYJiaDWWuZY, et al. Structural damage identification using strain mode differences by the iFEM based on the convolutional neural network (CNN). Mech Syst Signal Pr2022; 165: 108289.
16.
DuanYFChenQYZhangHM, et al. CNN-based damage identification method of tied-arch bridge using spatial-spectral information. Smart Struct Syst2019; 23: 507–520.
17.
ZhangWDWangDP. Damage identification using deep learning and long-gauge fiber Bragg grating sensors. Appl Optics2020; 59: 10532–10540.
18.
SonySGamageSSadhuA, et al. Multiclass damage identification in a full-scale bridge using optimally tuned one-dimensional convolutional neural network. J Comput Civil Eng2022; 36: 04021035.
19.
TengSChenGFGongPP, et al. Structural damage detection using convolutional neural networks combining strain energy and dynamic response. Meccanica2020; 55: 945–959.
20.
LinYZNieZHMaHW. Structural damage detection with automatic feature-extraction through deep learning. Comput-Aided Civ Inf2017; 32: 1025–1046.
21.
PathirageCSNLiJLiL, et al. Structural damage identification based on autoencoder neural networks and deep learning. Eng Struct2018; 172: 13–28.
22.
DingZHLiJHaoH. Structural damage identification by sparse deep belief network using uncertain and limited data. Struct Control Hlth2020; 27: e2522.
23.
Fernandez-NavamuelAZamora-SánchezDOmellaÁJ, et al. Supervised deep learning with finite element simulations for damage identification in bridges. Eng Struct2022; 257: 114016.
24.
TruongTTDinh-CongDLeeJ, et al. An effective deep feedforward neural networks (DFNN) method for damage identification of truss structures using noisy incomplete modal data. J Build Eng2020; 30: 101244.
25.
FathnejatHAhmadi-NedushanBHosseininejadS, et al. A data-driven structural damage identification approach using deep convolutional-attention-recurrent neural architecture under temperature variations. Eng Struct2023; 276: 115311.
26.
ChoeD-EKimH-CKimM-H. Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades. Renew Energ2021; 174: 218–235.
27.
TruongTTLeeJNguyen-ThoiT. Joint damage detection of structures with noisy data by an effective deep learning framework using autoencoder-convolutional gated recurrent unit. Ocean Eng2022; 243: 110142.
28.
YangJXYangFZhouYX, et al. A data-driven structural damage detection framework based on parallel convolutional neural network and bidirectional gated recurrent unit. Inform Sciences2021; 566: 103–117.
29.
DangVHVuTCNguyenBD, et al. Structural damage detection framework based on graph convolutional network directly using vibration data. Structures2022; 38: 40–51.
30.
ChenZYWangYZWuJ, et al. Sensor data-driven structural damage detection based on deep convolutional neural networks and continuous wavelet transform. Appl Intell2021; 51: 5598–5609.
31.
LeiYZhangYMiJN, et al. Detecting structural damage under unknown seismic excitation by deep convolutional neural network with wavelet-based transmissibility data. Struct Health Monit2021; 20: 1583–1596.
32.
KoukourakiEVanneschiLPainhoM. Few-shot learning for post-earthquake urban damage detection. Remote Sens Basel2021; 14: 40.
33.
BowmanJYangL. Few-shot learning for post-disaster structure damage assessment. In: Proceedings of the 4th ACM SIGSPATIAL international workshop on AI for geographic knowledge discovery, Beijing, China, 2–5 November 2021, pp. 27–32. New York, NY, USA: ACM.
34.
XueGLiuSFRenL, et al. Adaptive cross-scenario few-shot learning framework for structural damage detection in civil infrastructure. J Constr Eng Manage2023; 149: 04023020.
35.
XuYBaoYQZhangYF, et al. Attribute-based structural damage identification by few-shot meta learning with inter-class knowledge transfer. Struct Health Monit2021; 20: 1494–1517.
36.
CuiZYWangQGuoJJ, et al. Few-shot classification of façade defects based on extensible classifier and contrastive learning. Automat Constr2022; 141: 104381.
37.
DuFWuSWTianZX, et al. An improved prototype network and data augmentation algorithm for few-shot structural health monitoring using guided waves. IEEE Sens J2023; 23: 8714–8726.
38.
CheCCWangHWXiongML, et al. Few-shot fatigue damage evaluation of aircraft structure using neural augmentation and deep transfer learning. Eng Fail Anal2023; 148: 107185.
39.
LuleciFCatbasFNAvciO. Generative adversarial networks for labeled acceleration data augmentation for structural damage detection. J Civ Struct Health2023; 13: 181–198.
40.
LiZWLiuFYangWJ, et al. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst2021; 33: 6999–7019.
41.
GuJXWangZHKuenJ, et al. Recent advances in convolutional neural networks. Pattern Recogn2018; 77: 354–377.
42.
ZhangJWHuangMSWanN, et al. Missing measurement data recovery methods in structural health monitoring: the state, challenges and case study. Measurement2024; 231: 114528.
SajjadMKhanSMuhammadK, et al. Multi-grade brain tumor classification using deep CNN with extensive data augmentation. J Comput Sci2019; 30: 174–182.
45.
HuangHZhouHYangX, et al. Faster R-CNN for marine organisms detection and recognition using data augmentation. Neurocomputing2019; 337: 372–384.
46.
TaylorLNitschkeG. Improving deep learning with generic data augmentation. In: 2018 IEEE symposium series on computational intelligence (SSCI), Bangalore, India, 18–21 November 2018, pp.1542–1547. New York, NY, USA: IEEE.
47.
BochinskiESenstTSikoraT. Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms. In: 2017 IEEE international conference on image processing (ICIP), Beijing, China, 17–20 September 2017, pp. 3924–3928. New York, NY, USA: IEEE.
48.
KumarPBatraSRamanB. Deep neural network hyper-parameter tuning through twofold genetic approach. Soft Comput2021; 25: 8747–8771.
49.
FoysalMFASultanaNRimiTA, et al. Convolutional neural network hyper-parameter optimization using particle swarm optimization. In: Emerging technologies in data mining and information security: proceedings of IEMIS 2020, Singapore, 5 May 2021, pp. 363–373. Singapore: Springer.
50.
GülcüAKuşZ. Multi-objective simulated annealing for hyper-parameter optimization in convolutional neural networks. PeerJ Comput Sci2021; 7: e338.
51.
LiYShenYJiangHJ, et al. Hyper-tune: towards efficient hyper-parameter tuning at scale. arXiv preprint arXiv:220106834, 2022.
52.
KimCWZhangFLChangKC, et al. Ambient and vehicle-induced vibration data of a steel truss bridge subject to artificial damage. J Bridge Eng2021; 26: 04721002.
53.
AlazzawiOWangDS. A novel structural damage identification method based on the acceleration responses under ambient vibration and an optimized deep residual algorithm. Struct Health Monit2022; 21: 2587–2617.
