In this article, a novel propagative broad learning approach is proposed for nonparametric modeling of the ambient effects on structural health indicators. Structural health indicators interpret the structural health condition of the underlying dynamical system. Long-term structural health monitoring on in-service civil engineering infrastructures has demonstrated that commonly used structural health indicators, such as modal frequencies, depend on the ambient conditions. Therefore, it is crucial to detrend the ambient effects on the structural health indicators for reliable judgment on the variation of structural integrity. However, two major challenging problems are encountered. First, it is not trivial to formulate an appropriate parametric expression for the complicated relationship between the operating conditions and the structural health indicators. Second, since continuous data stream is generated during long-term structural health monitoring, it is required to handle the growing data efficiently. The proposed propagative broad learning provides an effective tool to address these problems. In particular, it is a model-free data-driven machine learning approach for nonparametric modeling of the ambient-influenced structural health indicators. Moreover, the learning network can be updated and reconfigured incrementally to adapt newly available data as well as network architecture modifications. The proposed approach is applied to develop the ambient-influenced structural health indicator model based on the measurements of 3-year full-scale continuous monitoring on a reinforced concrete building.
NagayamaTSpencerBFJr. Structural health monitoring using smart sensors. Report no. 1940-9826, November2007. Urbana, IL: Newmark Structural Engineering Laboratory, University of Illinois at Urbana-Champaign.
2.
NtotsiosEPapadimitriouCPanetsosP, et al. Bridge health monitoring system based on vibration measurements. B Earthq Eng2009; 7: 469–483.
3.
YiTHLiHNGuM. Recent research and applications of GPS-based monitoring technology for high-rise structures. Struct Control Hlth2013; 20: 649–670.
4.
LiHNYiTHRenL, et al. Reviews on innovations and applications in structural health monitoring for infrastructures. Struct Monit Maint2014; 1: 1–45.
5.
BaoYChenZWeiS, et al. The state of the art of data science and engineering in structural health monitoring. Engineering2019; 5: 234–242.
6.
LamHFZhangFLNiYC, et al. Operational modal identification of a boat-shaped building by a Bayesian approach. Eng Struct2017; 138: 381–393.
7.
ChatziENPapadimitriouC. Identification methods for structural health monitoring. Cham: Springer, 2016.
8.
SohnHWordenKFarrarCR. Statistical damage classification under changing environmental and operational conditions. J Intel Mat Syst Str2002; 13: 561–574.
9.
BrownjohnJM. Structural health monitoring of civil infrastructure. Philos T Roy Soc A2007; 365: 589–622.
10.
LeiYZhengZP. Review of physical based monitoring techniques for condition assessment of corrosion in reinforced concrete. Math Probl Eng2013; 2013: 953930.
11.
LiHNRenLJiaZG, et al. State-of-the-art in structural health monitoring of large and complex civil infrastructures. J Civ Struct Health Monit2016; 6: 3–16.
12.
ZhangFLXiongHBShiWX, et al. Structural health monitoring of Shanghai Tower during different stages using a Bayesian approach. Struct Control Hlth2016; 23: 1366–1384.
13.
YangDHYiTHLiHN. Coupled fatigue-corrosion failure analysis and performance assessment of RC bridge deck slabs. J Bridge Eng2017; 22: 04017077.
14.
YiTHLiHGuM. Full-scale measurements of dynamic response of suspension bridge subjected to environmental loads using GPS technology. Sci China Technol Sci2010; 53: 469–479.
15.
SuJZXiaYChenL, et al. Long-term structural performance monitoring system for the Shanghai Tower. J Civ Struct Health Monit2013; 3: 49–61.
16.
ZhangFLNiYQNiYC, et al. Operational modal analysis of Canton Tower by a fast frequency domain Bayesian method. Smart Struct Syst2016; 17: 209–230.
17.
YuenKVKuokSC. Ambient interference in long-term monitoring of buildings. Eng Struct2010; 32: 2379–2386.
18.
XiaYChenBZhouXQ, et al. Field monitoring and numerical analysis of Tsing Ma suspension bridge temperature behavior. Struct Control Hlth2013; 20: 560–575.
19.
MuHQYuenKVKuokSC. Relevance feature selection of modal frequency-ambient condition pattern recognition in structural health assessment for reinforced concrete buildings. Adv Mech Eng2016; 8: 1687814016662228.
20.
AsadollahiPLiJ. Statistical analysis of modal properties of a cable-stayed bridge through long-term wireless structural health monitoring. J Bridge Eng2017; 22: 04017051.
21.
YangDHYiTHLiHN, et al. Correlation-based estimation method for cable-stayed bridge girder deflection variability under thermal action. J Perform Constr Fac2018; 32: 04018070.
22.
ChenZYuXYangG, et al. Wind-induced self-excited loads on bridges. J Struct Eng2005; 131: 1783–1793.
23.
AuSKZhangFLToP. Field observations on modal properties of two tall buildings under strong wind. J Wind Eng Ind Aerod2012; 101: 12–23.
24.
WangHLiANiuJ, et al. Long-term monitoring of wind characteristics at Sutong Bridge site. J Wind Eng Ind Aerod2013; 115: 39–47.
25.
KuokSCYuenKV. Bayesian nonparametric modeling of structural health indicators under severe typhoons. J Aerospace Eng2019; 32: 04019036.
26.
LuNNooriMLiuY. Fatigue reliability assessment of welded steel bridge decks under stochastic truck loads via machine learning. J Bridge Eng2016; 22: 04016105.
27.
KongXLiJBennettC, et al. Thin-film sensor for fatigue crack sensing and monitoring in steel bridges under varying crack propagation rates and random traffic loads. J Aerospace Eng2018; 32: 04018116.
28.
SongMMoaveniBPapadimitriouC, et al. Accounting for amplitude of excitation in model updating through a hierarchical Bayesian approach: application to a two-story reinforced concrete building. Mech Syst Signal Pr2019; 123: 68–83.
29.
RezekIARobertsSJ. Parametric model order estimation: a brief review. In : Proceedings of the 1997 IEEE colloquium on the use of model based digital signal processing techniques in the analysis of biomedical signals, London, 16 April 1997, pp. 31–36. New York: IET.
30.
BeckJLYuenKV. Model selection using response measurements: Bayesian probabilistic approach. J Eng Mech2004; 130: 192–203.
31.
GirolamiMCalderheadBVyshemirskyV. System identification and model ranking: the Bayesian perspective. In: LawrenceND (ed.) Learning and inference in computational systems biology. Cambridge, MA: MIT Press, 2010, pp. 201–230.
32.
LamHFYuenKVBeckJL. Structural health monitoring via measured Ritz vectors utilizing artificial neural networks. Comput-Aided Civ Inf2006; 21: 232–241.
33.
YuenKVLamHF. On the complexity of artificial neural networks for smart structures monitoring. Eng Struct2006; 28: 977–984.
34.
ZhouXTNiYQZhangFL. Damage localization of cable-supported bridges using modal frequency data and probabilistic neural network. Math Probl Eng2014; 2014: 837963.
35.
NevesAGonzálezILeanderJ, et al. Structural health monitoring of bridges: a model-free ANN-based approach to damage detection. J Civ Struct Health Monit2017; 7: 689–702.
36.
RafieiMHAdeliH. A novel machine learning-based algorithm to detect damage in high-rise building structures. Struct Des Tall Spec2017; 26: e1400.
37.
ChaYJChoiWBüyüköztürkO. Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Inf2017; 32: 361–378.
38.
BaoYTangZLiH, et al. Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit2019; 18: 401–421.
39.
ZhaoYNooriMAltabeyWA, et al. Deep learning-based damage, load and support identification for a composite pipeline by extracting modal macro strains from dynamic excitations. Appl Sci2018; 8: 2564.
40.
PanHGuiGLinZ, et al. Deep BBN learning for health assessment toward decision-making on structures under uncertainties. KSCE J Civ Eng2018; 22: 928–940.
41.
HuangYLiHWuS, et al. Fractal dimension based damage identification incorporating multi-task sparse Bayesian learning. Smart Mater Struct2018; 27: 075020.
42.
HuangYBeckJLLiH. Multitask sparse Bayesian learning with applications in structural health monitoring. Comput-Aided Civ Inf2019; 34: 732–754.
43.
FigueiredoEParkGFarrarCR, et al. Machine learning algorithms for damage detection under operational and environmental variability. Struct Health Monit2011; 10: 559–572.
44.
MuHQYuenKV. Modal frequency-environmental condition relation development using long-term structural health monitoring measurement: uncertainty quantification, sparse feature selection and multivariate prediction. Measurement2018; 130: 384–397.
45.
KangFLiuXLiJ. Temperature effect modeling in structural health monitoring of concrete dams using kernel extreme learning machines. Struct Health Monit. Epub ahead of print 9September2019. DOI: 10.1177/1475921719872939.
46.
DingZLiJHaoH. Structural damage identification by sparse deep belief network using uncertain and limited data. Struct Control Hlth. Epub ahead of print 3February2020. DOI: 10.1002/stc.2522.
WordenKMansonG. The application of machine learning to structural health monitoring. Philos T Roy Soc A2006; 365: 515–537.
49.
FarrarCRWordenK. Structural health monitoring: a machine learning perspective. Chichester: John Wiley & Sons, 2012.
50.
ChenCPLiuZ. Broad learning system: an effective and efficient incremental learning system without the need for deep architecture. IEEE T Neur Net Lear2018; 29: 10–24.
51.
ChenCPLiuZFengS. Universal approximation capability of broad learning system and its structural variations. IEEE T Neur Net Lear2018; 30: 1191–1204.
52.
ChenCPWanJZ. A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction. IEEE T Syst Man Cy B1999; 29: 62–72.
53.
PaoYHTakefujiY. Functional-link net computing: theory, system architecture, and functionalities. Computer1992; 25: 76–79.
54.
KuokSCYuenKV. Broad learning for nonparametric spatial modeling with application to seismic attenuation. Comput-Aided Civ Inf2020; 35: 203–218.
55.
GoodfellowIBengioYCourvilleA. Deep learning. Cambridge, MA: MIT Press, 2016.
56.
SchmidhuberJ. Deep learning in neural networks: an overview. Neural Networks2015; 61: 85–117.
57.
YuenKV. Bayesian methods for structural dynamics and civil engineering. Singapore; Hoboken, NJ: John Wiley & Sons, 2010, p. xvi.
58.
KatafygiotisLSYuenKV. Bayesian spectral density approach for modal updating using ambient data. Earthq Eng Struct D2001; 30: 1103–1123.
YuenKVKatafygiotisLSBeckJL. Spectral density estimation of stochastic vector processes. Probabilist Eng Mech2002; 17: 265–272.
62.
KuokSCYuenKV. Structural health monitoring of Canton Tower using Bayesian framework. Smart Struct Syst2012; 10: 375–391.
63.
KuokSCYuenKV. Investigation of modal identification and modal identifiability of a cable-stayed bridge with Bayesian framework. Smart Struct Syst2016; 17: 445–470.
64.
BeckJL. Bayesian system identification based on probability logic. Struct Control Hlth2010; 17: 825–847.
65.
GoldsteinTO’DonoghueBSetzerS, et al. Fast alternating direction optimization methods. SIAM J Imaging Sci2014; 7: 1588–1623.
66.
TibshiraniR. Regression shrinkage and selection via the LASSO. J Roy Stat Soc B Met1996; 58: 267–288.
67.
MeyerCD. Matrix analysis and applied linear algebra. Philadelphia, PA: SIAM, 2000.
68.
YuenKVKuokSC. Modeling of environmental influence in structural health assessment for reinforced concrete buildings. Earthq Eng Eng Vib2010; 9: 295–306.
