This paper studies the effectiveness of joint compression and denoising strategies with realistic, long-term guided wave structural health monitoring data. We leverage the high correlation between nearby collections of guided waves in time to create sparse and low-rank representations. While compression and denoising schemes are not new, they are almost exclusively designed and studied with relatively simple datasets. In contrast, guided wave structural health monitoring datasets have much more complex operational and environmental conditions, such as temperature, that distort data and for which the requirements to achieve effective compression and denoising are not well understood. The paper studies how to optimize our data collection and algorithms to best utilize guided wave data for compression, denoising, and damage detection based on seven million guided wave measurements collected over 2 years.
HarleyJBMouraJM. Scale transform signal processing for optimal ultrasonic temperature compensation. IEEE Trans Ultrason Ferroelectr Freq Control2012; 59(10): 2226–2236.
2.
GiurgiutiuVXuBLiuW. Development and testing of high-temperature piezoelectric wafer active sensors for extreme environments. Struct Health Monit2010; 9(6): 513–525.
3.
ShangZSunLXiaY, et al. Vibration-based damage detection for bridges by deep convolutional denoising autoencoder. Struct Health Monit2021; 20(4): 1880–1903.
4.
FanWQiaoP. Vibration-based damage identification methods: a review and comparative study. Struct Health Monit2011; 10(1): 83–111.
5.
ZhangYMiyamoriYMikamiS, et al. Vibration-based structural state identification by a 1-dimensional convolutional neural network. Comput-Aided Civ Infrastruct Eng2019; 34(9): 822–839.
6.
BaoYGuoYLiH. A machine learning—based approach for adaptive sparse time—frequency analysis used in structural health monitoring. Struct Health Monit2020; 19(6): 1963–1975.
7.
LiJDackermannUXuYL, et al. Damage identification in civil engineering structures utilizing PCA-compressed residual frequency response functions and neural network ensembles. Struct Control Health Monit2011; 18(2): 207–226.
8.
WangZHuangSWangS, et al. Compressed sensing method for health monitoring of pipelines based on guided wave inspection. IEEE Trans Instrum Meas2019; 69(7): 4722–4731.
9.
LuYMichaelsJE. A methodology for structural health monitoring with diffuse ultrasonic waves in the presence of temperature variations. Ultrasonics2005; 43(9): 717–731.
10.
CawleyPCeglaFGalvagniA. Guided waves for NDT and permanently-installed monitoring. Insight Non-Destr Test Cond Monit2012; 54(11): 594–601.
11.
CroxfordAJMollJWilcoxPD, et al. Efficient temperature compensation strategies for guided wave structural health monitoring. Ultrasonics2010; 50(4–5): 517–528.
12.
JiQJian-BinLFan-RuiL, et al. Stress evaluation in seven-wire strands based on singular value feature of ultrasonic guided waves. Struct Health Monit2021; 21(2): 518–533.
13.
LiuCHarleyJO’DonoughueN, et al. Robust change detection in highly dynamic guided wave signals with singular value decomposition. In: IEEE international ultrasonics symposium, Dresden, Germany, 2012, pp. 483–486. IEEE.
14.
LiuCHarleyJBBergésM, et al. Robust ultrasonic damage detection under complex environmental conditions using singular value decomposition. Ultrasonics2015; 58: 75–86.
15.
LuYLiJYeL, et al. Guided waves for damage detection in rebar-reinforced concrete beams. Constr Build Mater2013; 47: 370–378.
16.
YangKKimSYueR, et al. Long-term guided wave structural health monitoring in an uncontrolled environment through long short-term principal component analysis. Struct Health Monit2021; 21(4): 1501–1517.
17.
QuirogaJMujicaLVillamizarR, et al. PCA based stress monitoring of cylindrical specimens using PZTs and guided waves. Sensors2017; 17(12): 2788.
18.
WuJTangZLvF, et al. Ultrasonic guided wave-based switch rail monitoring using independent component analysis. Meas Sci Technol2018; 29(11): 115102.
19.
DobsonJCawleyP. Independent component analysis for improved defect detection in guided wave monitoring. Proc IEEE2015; 104(8): 1620–1631.
20.
LiYXuKLiY, et al. Deep learning analysis of ultrasonic guided waves for cortical bone characterization. IEEE Trans Ultrason Ferroelectr Freq Control2020; 68(4): 935–951.
21.
CuiRAzuaraGLanzadiScaleaF, et al. Damage imaging in skin-stringer composite aircraft panel by ultrasonic-guided waves using deep learning with convolutional neural network. Struct Health Monit2021; 21(3): 1123–1138.
22.
ZhangBHongXLiuY. Distribution adaptation deep transfer learning method for cross-structure health monitoring using guided waves. Struct Health Monit2021; 21(3): 853–871.
23.
SongHYangY. Noncontact super-resolution guided wave array imaging of subwavelength defects using a multiscale deep learning approach. Struct Health Monit2021; 20(4): 1904–1923.
24.
EwaldVGrovesRMBenedictusR. DeepSHM: a deep learning approach for structural health monitoring based on guided lamb wave technique. In: Sensors and smart structures technologies for civil, mechanical, and aerospace systems, vol. 10970. International Society for Optics and Photonics, 2019, Vol. 10970, pp. 84–99. Denver: SPIE.
25.
CaiG. Big data analytics in structural health monitoring. PhD dissertation, Vanderbilt University, 2017.
26.
JayawardhanaMZhuXLiyanapathiranaR, et al. Compressive sensing for efficient health monitoring and effective damage detection of structures. Mech Syst Sig Process2017; 84: 414–430.
27.
BaoYBeckJLLiH. Compressive sampling for accelerometer signals in structural health monitoring. Struct Health Monit2011; 10(3): 235–246.
28.
WongKYNiYQ. Modular architecture of SHM system for cable-supported bridges. Chichester, UK: John Wiley & Sons, Ltd, 2009.
29.
ZhangYLiJ. Wavelet-based vibration sensor data compression technique for civil infrastructure condition monitoring. J Comput Civil Eng2006; 20(6): 390–399.
30.
XuNRangwalaSChintalapudiKK, et al. A wireless sensor network for structural monitoring. In: Proceedings of the 2nd international conference on embedded networked sensor systems, Baltimore, USA, pp. 13–24.
31.
LynchJPSundararajanALawKH, et al. Power-efficient data management for a wireless structural monitoring system. In: Proceedings of the 4th international workshop on structural health monitoring, USA, vol. 1, pp. 15–17. Citeseer.
32.
PerelliADi IanniTMarzaniA, et al. Model-based compressive sensing for damage localization in lamb wave inspection. IEEE Trans Ultrason Ferroelectr Freq Control2013; 60(10): 2089–2097.
33.
LiebgottHProstRFribouletD. Pre-beamformed RF signal reconstruction in medical ultrasound using compressive sensing. Ultrasonics2013; 53(2): 525–533.
34.
YangYNagarajaiahS. Output-only modal identification by compressed sensing: non-uniform low-rate random sampling. Mech Syst Sig Process2015; 56: 15–34.
35.
GilbertACIndykPIwenM, et al. Recent developments in the sparse Fourier transform: a compressed Fourier transform for big data. IEEE Signal Process Mag2014; 31(5): 91–100.
36.
YangYNagarajaiahS. Data compression of structural seismic responses via principled independent component analysis. J Struct Eng2014; 140(7): 04014032.
37.
YangYNagarajaiahSNiYQ. Data compression of very large-scale structural seismic and typhoon responses by low-rank representation with matrix reshape. Struct Control Health Monit2015; 22(8): 1119–1131.
38.
GuptaMGargAK. Analysis of image compression algorithm using DCT. Int J Eng Res Appl2012; 2(1): 515–521.
39.
TelagarapuPNaveenVJPrasanthiAL, et al. Image compression using DCT and wavelet transformations. Int J Signal Process, Image Process Pattern Recognit2011; 4(3): 61–74.
40.
WatsonAB. Image compression using the discrete cosine transform. Math J1994; 4(1): 81.
41.
RamkumarMAkansuANAlatanAA. A robust data hiding scheme for images using DFT. In: Proceedings 1999 international conference on image processing (Cat. 99CH36348), Kobe, Japan, vol. 2, pp. 211–215. IEEE.
42.
CohenL. Time-frequency analysis, vol. 778. New Jersey: Prentice Hall, 1995.
43.
KantzHSchreiberT. Nonlinear time series analysis, vol. 7. Cambridge: Cambridge University Press, 2004.
44.
SkodrasAChristopoulosCEbrahimiT. The jpeg 2000 still image compression standard. IEEE Signal Process Mag2001; 18(5): 36–58.
45.
FoggCLeGallDJMitchellJL, et al. MPEG video compression standard. Berlin: Springer Science & Business Media, 2007.
46.
KimSShiveleySDouglassAC, et al. Efficient storage and processing of large guided wave data sets with random projections. Struct Health Monit. Epub ahead of print 15October2019. DOI: 10.1177/1475921720960196.
47.
YangWXPeterWT. Development of an advanced noise reduction method for vibration analysis based on singular value decomposition. NDT & E Int2003; 36(6): 419–432.
48.
ClarkeTSimonettiFCawleyP. Guided wave health monitoring of complex structures by sparse array systems: influence of temperature changes on performance. J Sound Vib2010; 329(12): 2306–2322.
49.
BruniVVitulanoD. Combined image compression and denoising using wavelets. Signal Process Image Commun2007; 22(1): 86–101.
50.
ChappelierVGuillemotC. Oriented wavelet transform for image compression and denoising. IEEE Trans Image Process2006; 15(10): 2892–2903.
51.
ChowdhuryMMHKhatunA. Image compression using discrete wavelet transform. Int J Comput Sci Issues2012; 9(4): 327.
52.
WoodringJMniszewskiSBrislawnC, et al. Revisiting wavelet compression for large-scale climate data using jpeg 2000 and ensuring data precision. In: IEEE symposium on large data analysis and visualization, New Orleans, LA, USA, 2011, pp. 31–38. IEEE.
53.
MamaghanianHKhaledNAtienzaD, et al. Compressed sensing for real-time energy-efficient ecg compression on wireless body sensor nodes. IEEE Trans Biomed Eng2011; 58(9): 2456–2466.
54.
PolaniaLFCarrilloREBlanco-VelascoM, et al. Compressed sensing based method for ECG compression. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, 2011, pp. 761–764. IEEE.
55.
AviyenteS. Compressed sensing framework for eeg compression. In: IEEE/SP 14th Workshop on statistical signal processing, Prague, Czech Republic, 2007 pp. 181–184. IEEE.
56.
ChenFChandrakasanAPStojanovicVM. Design and analysis of a hardware-efficient compressed sensing architecture for data compression in wireless sensors. IEEE J Solid-State Circuits2012; 47(3): 744–756.
57.
ChenJRostamiJPeterWT, et al. The design of a novel mother wavelet that is tailor-made for continuous wavelet transform in extracting defect-related features from reflected guided wave signals. Measurement2017; 110: 176–191.
58.
SamaratungaDJhaRGopalakrishnanS. Wavelet spectral finite element for modeling guided wave propagation and damage detection in stiffened composite panels. Struct Health Monit2016; 15(3): 317–334.
SharmaLDandapatSMahantaA. Multichannel ECG data compression based on multiscale principal component analysis. IEEE Trans Inf Technol Biomed2012; 16(4): 730–736.
61.
PadhySSharmaLDandapatS. Multilead ECG data compression using SVD in multiresolution domain. Biomed Signal Process Control2016; 23: 10–18.
62.
NandiDAshourASSamantaS, et al. Principal component analysis in medical image processing: a study. Int J Image Min2015; 1(1): 65–86.
63.
SchanzeT. Compression and noise reduction of biomedical signals by singular value decomposition. Int Fed Autom Control2018; 51(2): 361–366.
64.
de SouzaJCSAssisTMLPalBC. Data compression in smart distribution systems via singular value decomposition. IEEE transactions on smart grid2015; 8(1): 275–284.
65.
LorenteLVegaJVelazquezA. Compression of aerodynamic databases using high-order singular value decomposition. Aerosp Sci Technol2010; 14(3): 168–177.
66.
RufaiAMAnbarjafariGDemirelH. Lossy image compression using singular value decomposition and wavelet difference reduction. Digital Signal Process2014; 24: 117–123.
67.
TanHRTanAKhongP, et al. Best wavelet function identification system for ECG signal denoise applications. In: International conference on intelligent and advanced systems, Kuala Lumpur, Malaysia, 2007, pp. 631–634. IEEE.
68.
AlfaouriMDaqrouqK. ECG signal denoising by wavelet transform thresholding. Am J Appl Sci2008; 5(3): 276–281.
69.
KabirMAShahnazC. Denoising of ECG signals based on noise reduction algorithms in EMD and wavelet domains. Biomed Signal Process Control2012; 7(5): 481–489.
70.
MetzlerCAMalekiABaraniukRG. From denoising to compressed sensing. IEEE Trans Inf Theory2016; 62(9): 5117–5144.
71.
NagarajaiahSYangY. Modeling and harnessing sparse and low-rank data structure: a new paradigm for structural dynamics, identification, damage detection, and health monitoring. Struct Control Health Monit2017; 24(1): e1851.
72.
DongWLiXZhangL, et al. Sparsity-based image denoising via dictionary learning and structural clustering. In: The conference on computer vision and pattern recognition, Colorado Springs, CO, USA, 2011, pp. 457–464. IEEE.
73.
HuangSSunHWangS, et al. Sswt and vmd linked mode identification and time-of-flight extraction of denoised sh guided waves. IEEE Sens J2021; 21(13): 14709–14717.
74.
SunHPengLHuangS, et al. Mode identification of denoised sh guided waves using variational mode decomposition method. In: IEEE sensors conference, Rotterda, Netherlands, 2020, pp. 1–3. IEEE.
75.
RizzoPCammarataMBartoliI, et al. Ultrasonic guided waves-based monitoring of rail head: laboratory and field tests. Adv Civil Eng2010; 2010: 291293.
76.
HarleyJBMouraJM. Sparse recovery of the multimodal and dispersive characteristics of lamb waves. J Acoust Soc Am2013; 133(5): 2732–2745.
77.
KaskiS. Dimensionality reduction by random mapping: fast similarity computation for clustering. In: IEEE international joint conference on neural networks proceedings. IEEE world congress on computational intelligence (Cat. No. 98CH36227), Anchorage, Alaska, USA, 1998, vol. 1, pp. 413–418. IEEE.
78.
AndersonEBaiZBischofC, et al. LAPACK Users’ Guide. 3rd ed. Philadelphia, PA: Society for Industrial and Applied Mathematics, 1999.
79.
LuYMichaelsJE. Feature extraction and sensor fusion for ultrasonic structural health monitoring under changing environmental conditions. IEEE Sens J2009; 9(11): 1462–1471.
80.
KohBDykeS. Structural health monitoring for flexible bridge structures using correlation and sensitivity of modal data. Comput Struct2007; 85(3–4): 117–130.
81.
LiuCDobsonJCawleyP. Efficient generation of receiver operating characteristics for the evaluation of damage detection in practical structural health monitoring applications. Proc R Soc A: Math Phys Eng Sci2017; 473(2199): 20160736.
82.
HarleyJBChiaCC. Statistical partial wavefield imaging using lamb wave signals. Struct Health Monit2018; 17(4): 919–935.
83.
YueNAliabadiM. Hierarchical approach for uncertainty quantification and reliability assessment of guided wave-based structural health monitoring. Struct Health Monit. Epub ahead of print 28August2020. DOI: 10.1177/1475921720940642.
84.
StullCJHemezFMFarrarCR. On assessing the robustness of structural health monitoring technologies. Struct Health Monit2012; 11(6): 712–723.
85.
BradleyAP. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognit1997; 30(7): 1145–1159.
86.
BracewellRNBracewellRN. The Fourier transform and its applications, vol. 31999. New York: McGraw-Hill, 1986.
87.
CrochiereR. A weighted overlap-add method of short-time Fourier analysis/synthesis. IEEE Trans Acoust Speech Signal Process1980; 28(1): 99–102.
88.
MuramatsuSKiyaH. Extended overlap-add and-save methods for multirate signal processing. IEEE Trans Signal Process1997; 45(9): 2376–2380.
