In structural health monitoring, the rapid detection and classification of structural damage are critical for ensuring the safety and longevity of civil infrastructures. In this context, supervised learning techniques that require extensive labeled undamaged and damaged data are often impractical, given the lack of observation of structural systems under different and exhaustive failure modes. This article introduces a novel unsupervised learning approach that utilizes cepstral coefficients (CCs) as damage sensitive features (DSFs). The aim is to develop a robust, real-time algorithm capable of detecting and classifying structural damage without needing pre-labeled data. This approach is particularly valuable in situations where immediate structural integrity assessment is crucial. Moreover, in addition to enabling binary assessment between damaged and undamaged conditions, such an algorithm can also recognize different levels of damage. The proposed strategy relies on CCs, DSFs extracted from the structure’s vibration response to detect variations in structural behavior. Recent studies have demonstrated the effectiveness of such coefficients in capturing the structural properties of dynamic systems well, and their ease of extraction makes them particularly suitable for real-time monitoring of bridges, buildings, and other infrastructure systems. The proposed methodology consists of an online novelty detection strategy based on principal component analysis of the identified coefficients to enhance differentiation between coefficients extracted from different health conditions. The squared Mahalanobis distance is used as a discrimination threshold tool for outlier detection. Results are presented using real-world data extracted from the Z24 bridge to assess the strategy’s effectiveness. The results demonstrate the algorithm’s performance in differentiating between damaged and undamaged data and its capability to accurately classify incoming data associated with various levels of damage.
FigueiredoEPeresNMoldovanI, et al. Impact of climate change on long-term damage detection for structural health monitoring of bridges. Struct Health Monit202424(4): 14759217231224254.
2.
FarrarCRWordenK.An introduction to structural health monitoring. Philos Trans R Soc A Math Phys Eng Sci2007; 365(1851): 303–315.
3.
BrownjohnJMXiaPQHaoH, et al. Civil structure condition assessment by Fe model updating: methodology and case studies. Finite Elem Anal Des2001; 37(10): 761–775.
4.
FriswellMMottersheadJE.Finite element model updating in structural dynamics, vol. 38. Springer Science & Business Media, 1995.
5.
YingYGarrettJHJrOppenheimIJ, et al. Toward data-driven structural health monitoring: application of machine learning and signal processing to damage detection. J Comput Civ Eng2013; 27(6): 667–680.
6.
Tibaduiza BurgosDAGomez VargasRCPedrazaC, et al. Damage identification in structural health monitoring: a brief review from its implementation to the use of data-driven applications. Sensors2020; 20(3): 733.
7.
CabboiAGentileCSaisiA.From continuous vibration monitoring to fem-based damage assessment: application on a stone-masonry tower. Constr Build Mater2017; 156: 252–265.
8.
WordenKMansonGFiellerNR.Damage detection using outlier analysis. J Sound Vib2000; 229(3): 647–667.
9.
BalafasKKiremidjianAS. Extraction of a series of novel damage sensitive features derived from the continuous wavelet transform of input and output acceleration measurements. In: Sensors and smart structures technologies for civil, mechanical, and aerospace systems, vol. 9061. SPIE, 2014, pp. 386–394.
10.
FarrarCRWordenK.Structural health monitoring: a machine learning perspective. John Wiley & Sons, 2012.
11.
WangZYangDHYiTH, et al. Eliminating environmental and operational effects on structural modal frequency: a comprehensive review. Struct Control Health Monit2022; 29(11): e3073.
12.
RoveriNCarcaterraA.Damage detection in structures under traveling loads by Hilbert–Huang transform. Mech Syst Signal Process2012; 28: 128–144.
13.
TronciEMBettiRDe AngelisM.Damage detection in a rc-masonry tower equipped with a non-conventional TMD using temperature-independent damage sensitive features. Dev Built Environ2023; 15: 100170.
14.
MoughtyJJCasasJR. A state of the art review of modal-based damage detection in bridges: development, challenges, and solutions. Appl Sci2017; 7(5): 510.
15.
TronciE.Multi-stage semi-automated methodology for modal parameters estimation adopting parametric system identification algorithms. Mech Syst Signal Process2022; 165: 108317.
16.
MilanaSRoveriNCarcaterraA, et al. Continuous wavelet transform for structural health monitoring of a pipe. In: Proceedings of ISMA 2018-international conference on noise and vibration engineering and USD 2018-international conference on uncertainty in structural dynamics. Leuven: KU Leuven-Department Werktuigkunde, pp. 3925–3933.
17.
BernagozziGAchilliABettiR, et al. On the use of multivariate autoregressive models for vibration-based damage detection and localization. Smart Struct Syst2021; 27(2): 335–350.
18.
DardenoTWordenKDervilisN, et al. On the hierarchical Bayesian modelling of frequency response functions. Mech Syst Signal Process2024; 208: 111072.
19.
WangSXuM.Modal strain energy-based structural damage identification: a review and comparative study. Struct Eng Int2019; 29(2): 234–248.
20.
García CavaDAvendaño-ValenciaLDMovsessianA, et al. On explicit and implicit procedures to mitigate environmental and operational variabilities in data-driven structural health monitoring. Struct Health Monit Based Data Sci Technique2022; 21: 309–330.
21.
WangZYiTHYangDH, et al. Early warning of abnormal bridge frequencies based on a local correlation model under multiple environmental conditions. J Bridge Eng2023; 28(2): 04022139.
22.
WangZYiTHYangDH, et al. Early warning method of structural damage using localized frequency cointegration under changing environments. J Struct Eng2023; 149(2): 04022230.
23.
BogertBP. The quefrency alanysis of time series for echoes: cepstrum, pseudoautocovariance, cross-cepstrum and saphe cracking. In: RosenblattM (ed.) Proceedings of the symposium time series analysis. New York, London: Wiley, 1963, pp. 209–243.
24.
BalsamoLBettiRBeigiH.A structural health monitoring strategy using cepstral features. J Sound Vib2014; 333(19): 4526–4542.
25.
CiveraMFerrarisMCeravoloR, et al. The Teager-Kaiser energy cepstral coefficients as an effective structural health monitoring tool. Appl Sci2019; 9(23): 5064.
26.
TronciEMBeigiHBettiR, et al. A damage assessment methodology for structural systems using transfer learning from the audio domain. Mech Syst Signal Process2023; 195: 110286.
27.
de SouzaEFBittencourtTNRibeiroD, et al. Feasibility of applying mel-frequency cepstral coefficients in a drive-by damage detection methodology for high-speed railway bridges. Sustainability2022; 14(20): 13290.
28.
LiZLinWZhangY.Drive-by bridge damage detection using mel-frequency cepstral coefficients and support vector machine. Struct Health Monit2023; 22(5): 14759217221150932.
29.
MorgantiniMBettiRBalsamoL.Structural damage assessment through features in quefrency domain. Mech Syst Signal Process2021; 147: 107017.
30.
LiLMorgantiniMBettiR.Structural damage assessment through a new generalized autoencoder with features in the quefrency domain. Mech Syst Signal Process2023; 184: 109713.
31.
StagiLSclafaniLTronciEM, et al. Enhancing the damage detection and classification of unknown classes with a hybrid supervised–unsupervised approach. Infrastructures2024; 9(3): 40.
32.
FugateMLSohnHFarrarCR. Unsupervised learning methods for vibration-based damage detection. In: Proceedings of 18th international modal analysis conference–IMAC, vol. 18. CiteSeer, 2000, pp. 1–2.
33.
WangZChaYJ.Unsupervised machine and deep learning methods for structural damage detection: a comparative study. Eng Rep2022; 7(1): e12551.
34.
RoveriNCarcaterraA.Unsupervised identification of damage and load characteristics in time-varying systems. Continuum Mech Thermodyn2015; 27: 531–550.
35.
SilvaMSantosAFigueiredoE, et al. A novel unsupervised approach based on a genetic algorithm for structural damage detection in bridges. Eng Appl Artif Intell2016; 52: 168–180.
36.
García-MacíasEUbertiniF.Integrated SHM systems: damage detection through unsupervised learning and data fusion. In: Structural health monitoring based on data science techniques. Springer, Berlin, Germany, 2021, pp. 247–268.
37.
TibaduizaDAMujicaLERodellarJ, et al. Structural damage detection using principal component analysis and damage indices. J Intell Mater Syst Struct2016; 27(2): 233–248.
38.
JolliffeITCadimaJ.Principal component analysis: a review and recent developments. Philos Trans R Soc A Math Phys Eng Sci2016; 374(2065): 20150202.
39.
JapkowiczNMyersCGluckM, et al. A novelty detection approach to classification. In:Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (I)IJCAI-95 Contents Vol 1. Proceedings of the Fourteenth International. Joint Conference on Artificial Intelligence. Montreal, Quebec, Canada August 20-25,1995 Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (I)IJCAI-95 Contents, vol 1. Montreal, Quebec, CanadaAugust 20–25,1995, pp. 518–523.
40.
ZhouYLFigueiredoEMaiaN, et al. Damage detection in structures using a transmissibility-based mahalanobis distance. Struct Control Health Monit2015; 22(10): 1209–1222.
41.
YeagerMGregoryBKeyC, et al. On using robust mahalanobis distance estimations for feature discrimination in a damage detection scenario. Struct Health Monit2019; 18(1): 245–253.
42.
PimentelMACliftonDACliftonL, et al. A review of novelty detection. Signal Process2014; 99: 215–249.
DeraemaekerAWordenK.A comparison of linear approaches to filter out environmental effects in structural health monitoring. Mech Syst Signal Process2018; 105: 1–15.
VerveridisDKotropoulosC.Information loss of the mahalanobis distance in high dimensions: application to feature selection. IEEE Trans Pattern Anal Mach Intell2009; 31(12): 2275–2281.
48.
LeysCLeyCKleinO, et al. Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median. J Exp Soc Psychol2013; 49(4): 764–766.
49.
PeetersBDe RoeckG.One-year monitoring of the z24-bridge: environmental effects versus damage events. Earthq Eng Struct Dyn2001; 30(2): 149–171.
50.
RoeckGD.The state-of-the-art of damage detection by vibration monitoring: the SIMCES experience. J Struct Control2003; 10(2): 127–134.
51.
BrinckerRAndersenPCantieniR.Identification and level i damage detection of the z24 highway bridge. Exp Tech2001; 25: 51–57.
52.
MaeckJPeetersBDe RoeckG.Damage identification on the z24 bridge using vibration monitoring. Smart Mater Struct2001; 10(3): 512.
53.
KullaaJ.Damage detection of the z24 bridge using control charts. Mech Syst Signal Process2003; 17(1): 163–170.
54.
GiglioniVPooleJVenanziI, et al. A domain adaptation approach to damage classification with an application to bridge monitoring. Mech Syst Signal Process2024; 209: 111135.
55.
ShiHWordenKCrossEJ.A nonlinear cointegration approach with applications to structural health monitoring. J Phys Conf Ser2016; 744(1): 012025.
56.
SantanielloPRussoP.Bridge damage identification using deep neural networks on time–frequency signals representation. Sensors2023; 23(13): 6152.
57.
StagiLSclafaniLTronciEM, et al. An unsupervised damage detection strategy for recognizing unseen health conditions in monitoring bridges. In: International operational modal analysis conference. Cham, Springer Nature Switzerland, 2024, pp. 196–207.
