Restricted accessResearch articleFirst published online 2025
Efficient edge intelligence for onboard data anomaly classification in wireless structural health monitoring using knowledge distillation on low-cost IoT nodes
Internet of Things (IoTs) systems with wireless data transmission have been increasingly adopted by structural health monitoring. However, sensor malfunctions and data anomalies have been identified frequently in these systems for long-term deployment, especially in harsh environments. Advances in machine learning (ML) offer promising solutions for effectively detecting, classifying and recovering data anomalies. Most state-of-the-art ML-based solutions rely on powerful workstations or cloud servers, where large amounts of datasets are assumed to be transmitted to a centralized station, leading to the issues of heavy load of data transmission and long delay of subsequent data analytics. To address the issues, this article proposed a novel decentralized approach integrating machine learning with edge computing, aka, edge intelligence, for efficient onboard data anomaly classification. The key innovations lie in the development of an effective ML-based feature extractor adapted to low-cost IoT nodes and an efficient edge computing deployment for ML execution suitable for resource-constrained microcontroller unit-based devices. The proposed solution has been successfully deployed on a newly developed IoT node, LiftNode, which is by first time to realize low-cost onboard data anomaly classification in structural health monitoring (SHM) community. Using the dataset collected from a real long-span cable-stayed bridge in China, the proposed solution is found to achieve the accuracy of 96.37% in PC with the model size of 0.29 MB, and comparably, the accuracy of 96.36% in LiftNode. The framework and deployment strategies are elaborated, highlighting the potential of edge intelligence for improving SHM systems’ responsiveness and resource utilization.
ScuroCLamonacaFPorzioS, et al. Internet of Things (IoT) for masonry structural health monitoring (SHM): overview and examples of innovative systems. Construc Build Mater2021; 290: 123092.
2.
PoornimaIGAParamasivanB. Anomaly detection in wireless sensor network using machine learning algorithm. Comput Commun2020; 151: 331-337.
3.
MaoJSuXWangH, et al. Automated Bayesian operational modal analysis of the long-span bridge using machine-learning algorithms. Eng Struct2023; 289: 116336.
4.
YuXFuYLiJ, et al. Recent advances in wireless sensor networks for structural health monitoring of civil infrastructure. J Infrastruct Intell Res2023; 3: 100066.
5.
SuXMaoJWangH, et al. Deep learning-based automated identification on vortex-induced vibration of long suspenders for the suspension bridge. Mech Syst Signal Process2025; 224: 112070.
6.
ZhouG-DYiT-HRecent developments on wireless sensor networks technology for bridge health monitoring. Math Probl Eng2013; 1: 947867.
7.
RassamMAZainalAMaarofMA.Advancements of data anomaly detection research in wireless sensor networks: a survey and open issues. Sensors2013; 13: 10087–10122.
8.
YiT-HHuangH-BLiH-NDevelopment of sensor validation methodologies for structural health monitoring: a comprehensive review. Measurement2017; 109: 200–214.
9.
BaoYLiHSunX, et al. Compressive sampling–based data loss recovery for wireless sensor networks used in civil structural health monitoring. Struct Health Monit2013; 12: 78–95.
10.
MoLLiJWangG., et al. Passive diagnosis for WSNs using time domain features of sensing data. Int J Distrib Sens Netw2015; 11: 590430.
11.
SamudraSBarboshMSadhuA.Machine learning-assisted improved anomaly detection for structural health monitoring. Sensors2023; 23: 3365.
12.
BaoYLiJNagayamaT, et al. The 1st international project competition for structural health monitoring (IPC-SHM, 2020): a summary and benchmark problem. Struct Health Monit2021; 20: 2229–2239.
13.
FuYPengCGomezF, et al. Sensor fault management techniques for wireless smart sensor networks in structural health monitoring. Struct Control Health Monit2019; 26: e2362.
14.
MaoJSuXGuiG, et al. ResNet transfer learning for accurate and efficient anomaly detection of bridge vibration data. Smart Struct Syst2024; 34(6): 415.
15.
ChouJ-YFuYHuangS-K, et al. SHM data anomaly classification using machine learning strategies: a comparative study. Smart Struct Syst2022; 29: 77–91.
Al-amriRMurugesanRKManM, et al. A review of machine learning and deep learning techniques for anomaly detection in IoT data. Appl Sci2021; 11: 5320.
18.
ChaY-JAliRLewisJ, et al. Deep learning-based structural health monitoring. Autom Constr2024; 161: 105328.
19.
MaoJWangHSpencerBFJr.Toward data anomaly detection for automated structural health monitoring: Exploiting generative adversarial nets and autoencoders. Struct Health Monit2021; 20: 1609–1626.
20.
NiFZhangJNooriMN.Deep learning for data anomaly detection and data compression of a long-span suspension bridge. Comput Aid Civ Infrastruct Eng2020; 35: 685–700.
21.
ArulMKareemA.Data anomaly detection for structural health monitoring of bridges using shapelet transform. arXiv preprint, arXiv:2009.00470, 2020.
22.
ZhangYTangZYangR.Data anomaly detection for structural health monitoring by multi-view representation based on local binary patterns. Measurement2022; 202: 111804.
23.
FlahMNunezIBen ChaabeneW, et al. Machine learning algorithms in civil structural health monitoring: a systematic review. Arch Comput Methods Eng2021; 28: 2621–2643.
24.
ZhangHLinJHuaJ, et al. Data anomaly detection for bridge SHM based on CNN combined with statistic features. J Nondestruct Eval2022; 41: 28.
25.
TangZChenZBaoY., et al. Convolutional neural network-based data anomaly detection method using multiple information for structural health monitoring. Struct Control Health Monit2019; 26: e2296.
26.
MondalTGChouJ-YFuY, et al. A hybrid deep neural network compression approach enabling edge intelligence for data anomaly detection in smart structural health monitoring systems. Smart Struct Syst2023; 32: 179–193.
27.
LuoTNagarajanSG. Distributed anomaly detection using autoencoder neural networks in WSN for IoT. In: 2018 IEEE international conference on communications (ICC), Kansas City, MO, pp. 1–6. IEEE.
28.
DingYYangKJiangH, et al. Data abnormal detection using bidirectional long-short neural network combined with artificial experience. Smart Struct Syst Int J2022; 29(1): 117–127.
29.
LiuGNiuYZhaoW, et al. Data anomaly detection for structural health monitoring using a combination network of GANomaly and CNN. Smart Struct Syst2022; 29(1): 53–62.
30.
BaoYTangZLiH, et al. Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit2019; 18: 401–421.
31.
FuYHoangTMechitovK, et al. xShake: intelligent wireless system for cost-effective real-time seismic monitoring of civil infrastructure. Smart Struct Syst2021; 28(4): 483–497.
32.
RajasegararSLeckieCPalaniswamiM., et alQuarter sphere based distributed anomaly detection in wireless sensor networks. In: 2007 IEEE international conference on communications, Glasgow, pp. 3864–3869. IEEE.
33.
ZhangYHammNAMeratniaN, et al. Statistics-based outlier detection for wireless sensor networks. Int J Geographical Inform Sci2012; 26(8): 1373–1392.
34.
BranchJWGiannellaCSzymanskiB, et al. In-network outlier detection in wireless sensor networks. Knowledge Inform Syst2013; 34: 23–54.
35.
RassamMAZainalAMaarofMA.An efficient distributed anomaly detection model for wireless sensor networks. AASRI Proc2013; 5: 9–14.
36.
WangXWuWDuY, et al. Wireless IoT monitoring system in Hong Kong–Zhuhai–Macao bridge and edge computing for anomaly detection. IEEE Internet Things J2023; 11(3): 4763–4774.
37.
GeckCCThamerA-ZElmoursiM, et al. AIoT-enabled decentralized sensor fault diagnosis for structural health monitoring. In: 11th European workshop on structural health monitoring, 2024.
38.
LiuGLiLZhangL, et al. Sensor faults classification for SHM systems using deep learning-based method with Tsfresh features. Smart Mater Struct2020; 29: 075005.
39.
ZhaoRYanRChenZ, et al. Deep learning and its applications to machine health monitoring. Mech Syst Signal Process2019; 115: 213–237.
40.
KimS-YMukhiddinovM.Data anomaly detection for structural health monitoring based on a convolutional neural network. Sensors2023; 23: 8525.
41.
JanSULeeY-DShinJ, et al. Sensor fault classification based on support vector machine and statistical time-domain features. IEEE Access2017; 5: 8682–8690.
42.
LiJChenWFanG.Structural health monitoring data anomaly detection by transformer enhanced densely connected neural networks. Smart Struct Syst2022; 30: 613–626.
43.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: Advances in neural information processing systems, 2017, Los angeles, CA, p. 30.
44.
HintonGVinyalsODeanJ.Distilling the knowledge in a neural network. arXiv preprint; arXiv:1503. 02531, 2015.
45.
GouJYuBMaybankSJ, et al. Knowledge distillation: a survey. Int J Comput Vision2021; 129(6): 1789–1819.
46.
FuYZhuYHoangT, et al. xImpact: intelligent wireless system for cost-effective rapid condition assessment of bridges under impacts. Sensors2022; 22(15): 5701.
47.
Al-QamashASolimanIAbulibdehR, et al. Cloud, fog, and edge computing: a software engineering perspective. In: 2018 International conference on computer and applications (ICCA), Beirut, Lebanon, pp. 276–284. IEEE.
48.
CaoKLiuYMengG, et al. An overview on edge computing research. IEEE Access2020; 8: 85714–85728.
49.
ParkJ-WSimS-HJungH-J, et al. Development of a wireless displacement measurement system using acceleration responses. Sensors2013; 13: 8377–8392.
50.
LynchJPWangYLohKJ, et al. Performance monitoring of the Geumdang bridge using a dense network of high-resolution wireless sensors. Smart Mater Struct2006; 15: 1561.
