In this article, a novel vibration-based damage detection approach is proposed based on selecting effective cepstral coefficients, consisting of three main stages: (1) signal processing and feature extraction, (2) damage detection by combining effective cepstral coefficients through feature selection methods, and (3) performance evaluation. First, two feature extraction techniques are used in damage identification systems, including linear prediction cepstral coefficients and mel frequency cepstral coefficients. Second, to improve the performance of damage detection, the combination of the effective cepstral coefficients is proposed as a damage index. By applying several feature selection methods, the most effective coefficients are found and then combined to create a subset that carries the most significant information about the structural damage. Finally, the support vector machine classifier is performed to evaluate the proposed approach in detecting the structural damage. The proposed technique is verified using a suite of numerical and full-scale studies. Results confirm that the proposed method achieves a significant performance with great accuracy and reduces false alarms.
AlpaydinE (2009) Introduction to Machine Learning. London: MIT press.
2.
AnYChatziESimSH, et al. (2019) Recent progress and future trends on damage identification methods for bridge structures. Structural Control and Health Monitoring26(10): e2416.
3.
ArangioSBontempiF (2015) Structural health monitoring of a cable-stayed bridge with Bayesian neural networks. Structure and Infrastructure Engineering11(4): 575–587.
4.
Babajanian BishehHGhodrati AmiriGNekooeiM, et al. (2019) Damage detection of a cable-stayed bridge using feature extraction and selection methods. Structure and Infrastructure Engineering15(9): 1165–1177.
5.
BagheriAZare HosseinzadehARizzoP, et al. (2017) Time domain damage localization and quantification in seismically excited structures using a limited number of sensors. Journal of Vibration and Control23(18): 2942–2961.
6.
BhattacharjeeU (2013) A comparative study of LPCC and MFCC features for the recognition of assamese phonemes. International Journal of Engineering Research and Technology2(1): 1–6.
7.
DackermannUSmithWARandallRB (2014) Damage identification based on response-only measurements using cepstrum analysis and artificial neural networks. Structural Health Monitoring: An International Journal13(4): 430–444.
8.
DoeblingSWFarrarCRPrimeMB (1998) A summary review of vibration-based damage identification methods. The Shock and Vibration Digest30(2): 91–105.
9.
FarrarCRWordenK (2012) Structural Health Monitoring: A Machine Learning PerspectiveChichester: John Wiley & Sons.
10.
GomesGFMendezYADAlexandrinoPdSL, et al. (2019) A review of vibration based inverse methods for damage detection and identification in mechanical structures using optimization algorithms and ANN. Archives of Computational Methods in Engineering26(4): 883–897.
11.
GuQLiZHanJ (2012) Generalized Fisher Score for Feature Selection. Report no. UAI-P-2011-PG-266-273. USA: Uncertainty in Artificial Intelligence. arXiv preprint arXiv:1202.3725.
12.
GulMCatbasFN (2011) Structural health monitoring and damage assessment using a novel time series analysis methodology with sensor clustering. Journal of Sound and Vibration330(6): 1196–1210.
13.
HariharanM.CheeLSYaacobS (2012) Analysis of infant cry through weighted linear prediction cepstral coefficients and probabilistic neural network. Journal of medical systems36(3): 1309–1315.
14.
Jothi SaravananTGopalakrishnanNPrasad RaoN (2017) Detection of damage through coupled axial-flexural wave interactions in a sagged rod using the spectral finite element method. Journal of Vibration and Control23(20): 3345–3364.
15.
KaloopMRHuJW (2015) Stayed-cable bridge damage detection and localization based on accelerometer health monitoring measurements. Shock and Vibration. 2015: 1–11.
16.
KongXCaiC-SHuJ (2017) The state-of-the-art on framework of vibration-based structural damage identification for decision making. Applied Sciences7(5): 497.
17.
KunwarAJhaRWhelanM, et al. (2013) Damage detection in an experimental bridge model using Hilbert–Huang transform of transient vibrations. Structural Control and Health Monitoring20(1): 1–15.
18.
LeeJChoiHParkD, et al. (2016) Fault detection and diagnosis of railway point machines by sound analysis. Sensors16(4): 549.
19.
LiJHaoHLoJV (2015) Structural damage identification with power spectral density transmissibility: numerical and experimental studies. Smart Structures and Systems15(1): 15–40.
20.
LiQLiD (2017). Structure damage identification under ambient excitation based on wavelet packet analysis. Journal of Physics: Conference Series842(1): 012023.
21.
LiSLiHLiuY, et al. (2014) SMC structural health monitoring benchmark problem using monitored data from an actual cable-stayed bridge. Structural Control and Health Monitoring21(2): 156–172.
22.
LiSZhangLTangJ, et al. (2018) Damage identification in timber structures based on wavelet singular spectrum entropy. Mathematical Problems in Engineering2018: 1–9.
23.
LiangYLiDSongG, et al. (2018) Frequency co-integration-based damage detection for bridges under the influence of environmental temperature variation. Measurement125: 163–175.
24.
LiuH, and YuL (2005) Toward integrating feature selection algorithms for classification and clustering. IEEE Transactions on Knowledge & Data Engineering17(4): 491–502.
25.
MATLAB (2009) MATLAB. Natick, MA: MathWorks.
26.
MengFMokraniBAlalufD, et al. (2018) Damage detection in active suspension bridges: an experimental investigation. Sensors18(9): 3002.
27.
PirboudaghiSTarinejadRAlamiMT (2018) Damage detection based on system identification of concrete dams using an extended finite element-wavelet transform coupled procedure. Journal of Vibration and Control24(18): 4226–4246.
28.
QiaoLEsmaeilyA (2011) An overview of signal-based damage detection. Applied Mechanics and Materials94–96: 834–851.
29.
RandallRB (2009). Cepstral methods of operational modal analysis. Encyclopedia of Structural Health Monitoring: 1–14.
30.
RandallRBAntoniJSmithWA (2019) A survey of the application of the cepstrum to structural modal analysis. Mechanical Systems and Signal Processing118: 716–741.
31.
SalemSBBachaKChaariA (2012) Support vector machine-based decision for induction motor fault diagnosis using air-gap torque frequency response. International Journal of Computer Applications38: 27-33.
32.
SmithWARandallRB (2016) Cepstrum-based operational modal analysis revisited: a discussion on pole-zero models and the regeneration of frequency response functions. Mechanical Systems and Signal Processing79: 30–46.
33.
SuCJiangMLiangJ, et al. (2019) Damage identification in composites based on Hilbert energy spectrum and lamb wave tomography algorithm. IEEE Sensors Journal19(23): 11562-11572.
34.
SunLShangZXiaY, et al. (2020) Review of bridge structural health monitoring aided by big data and artificial intelligence: from condition assessment to damage detection. Journal of Structural Engineering146(5): 04020073.
35.
WangR (2012) AdaBoost for feature selection, classification and its relation with SVM, a review. Physics Procedia25: 800–807.
36.
WangHChenP (2009) A feature extraction method based on information theory for fault diagnosis of reciprocating machinery. Sensors9(4): 2415–2436.
37.
YangZChenXRadzienskiM, et al. (2017) A Fourier spectrum-based strain energy damage detection method for beam-like structures in noisy conditions. Science China Technological Sciences60(8): 1188–1196.
38.
ZhuXCaoMOstachowiczW, et al. (2019) Damage identification in bridges by processing dynamic responses to moving loads: features and evaluation. Sensors19(3): 463.
