Over the last several decades, structural health monitoring systems have grown into increasingly diverse applications. Structural health monitoring excels with large data sets that can capture the typical variability, novel events, and undesired degradation over time. As a result, the efficient storage and processing of these large, guided wave data sets have become a key feature for successful application of structural health monitoring. This article describes a series of investigations into the use of random projection theory to significantly reduce storage burdens and improve computational complexity while not significantly affecting common damage detection strategies. Random projections are used as a lossy compression scheme that approximately retains metrics of distance or similarity between data records. Random projection compression is evaluated using a large 1,440,000 measurement data set, which was collected over 5 months in an unprotected outdoor environment. Accurate damage detection, after the compression process, is achieved through correlation analysis and singular value decomposition. The results indicate consistent detection performance with over 95% of storage compression and more than a 477 times speed improvement in computational cost for singular value decomposition–based damage detection.
MitraMGopalakrishnanS. Guided wave based structural health monitoring: a review. Smart Mater Struct2016; 25(5): 053001.
2.
RaghavanACesnikCE. Review of guided-wave structural health monitoring. Shock Vib Digest2007; 39(2): 91–116.
3.
HarleyJBChiaCC. Statistical partial wavefield imaging using Lamb wave signals. Struct Health Monit2018; 17(4): 919–935.
4.
AttarianVACeglaFBCawleyP. Long-term stability of guided wave structural health monitoring using distributed adhesively bonded piezoelectric transducers. Struct Health Monit2014; 13(3): 265–280.
5.
HerdovicsBCeglaF. Long-term stability of guided wave electromagnetic acoustic transducer systems. Struct Health Monit2018; 19: 3–11.
6.
DeraemaekerAReyndersEDe RoeckG, et al. Vibration-based structural health monitoring using output-only measurements under changing environment. Mech Syst Signal Process2008; 22(1): 34–56.
7.
LiuCHarleyJBBergesM, et al. Robust ultrasonic damage detection under complex environmental conditions using singular value decomposition. Ultrasonics2015; 58: 75–86.
8.
DobsonJCawleyP. Independent component analysis for improved defect detection in guided wave monitoring. Proc of the IEEE2016; 104(8): 1620–1631.
9.
CaiG. Big data analytics in structural health monitoring. PhD Thesis, Vanderbilt University, Nashville, TN, 2017.
10.
ParkSYunCBRohY, et al. PZT-based active damage detection techniques for steel bridge components. Smart Mater Struct2006; 15(4): 957.
11.
SiqueiraMGattsCDa SilvaR, et al. The use of ultrasonic guided waves and wavelets analysis in pipe inspection. Ultrasonics2004; 41(10): 785–797.
12.
CiangCCLeeJRBangHJ. Structural health monitoring for a wind turbine system: a review of damage detection methods. Measure Sci Technol2008; 19(12): 122001.
13.
DubeyARMieleSAAgarwalV, et al. Acoustic data analysis for detecting alkali-silica reaction degradation in concrete. In: ASME 2018 Pressure vessels and piping conference, Prague, 15–20 July 2018, p. V005T09A002. New York: American Society of Mechanical Engineers.
14.
AgarwalVNealKDMahadevanS, et al. Concrete structural health monitoring in nuclear power plants (Technical report). Idaho Falls, ID: Idaho National Lab, 2017.
15.
QingXPChanHLBeardSJ, et al. An active diagnostic system for structural health monitoring of rocket engines. J Intell Mater Syst Struct2006; 17(7): 619–628.
16.
IhnJBChangFK. Detection and monitoring of hidden fatigue crack growth using a built-in piezoelectric sensor/actuator network: I. Diagnostics. Smart Mater Struct2004; 13(3): 609.
17.
BaoYShiZWangX, et al. Compressive sensing of wireless sensors based on group sparse optimization for structural health monitoring. Struct Health Monitor2018; 17(4): 823–836.
18.
SabetiSHarleyJB. Spatio-temporal undersampling: recovering ultrasonic guided wavefields from incomplete data with compressive sensing. Mech Syst Sig Process2020; 140: 106694.
19.
GolatoASanthanamSAhmadF, et al. Multimodal exploitation and sparse reconstruction for guided-wave structural health monitoring. Proc SPIE2015: 9484: 94840L.
20.
Di IanniTDe MarchiLPerelliA, et al. Compressive sensing of full wave field data for structural health monitoring applications. IEEE Trans Ultrason Ferroelectric Frequen Contr2015; 62(7): 1373–1383.
21.
NagarajaiahSYangY. Modeling and harnessing sparse and low-rank data structure: a new paradigm for structural dynamics, identification, damage detection, and health monitoring. Struct Contr Health Monitor2017; 24(1): e1851.
22.
YangYNagarajaiahSNiYQ. Data compression of very large-scale structural seismic and typhoon responses by low-rank representation with matrix reshape. Struct Contr Health Monitor2015; 22(8): 1119–1131.
23.
BinghamEMannilaH. Random projection in dimensionality reduction: applications to image and text data. In: Proceedings of the ACM international conference on knowledge discovery and data mining, pp. 245–250, http://users.ics.aalto.fi/ella/publications/randproj_kdd.pdf
24.
CevherVBeckerSSchmidtM. Convex optimization for big data: scalable, randomized, and parallel algorithms for big data analytics. IEEE Signal Process Mag2014; 31(5): 32–43.
25.
SohnH. Effects of environmental and operational variability on structural health monitoring. Phil Trans R Soc A Math Phys Eng Sci2006; 365(1851): 539–560.
26.
KaskiS. Dimensionality reduction by random mapping: fast similarity computation for clustering. Proc IEEE Int Joint Conf Neural Netw1998; 1: 413–418.
27.
JohnsonWBLindenstraussJ. Extensions of Lipschitz mappings into a Hilbert space. Contemp Math1984; 26(1): 189–206.
28.
ArriagaRIVempalaS. An algorithmic theory of learning: robust concepts and random projection. Mach Learn2006; 63: 616–623.
29.
ZhangKZhangLYangMH. Real-time compressive tracking. In: Proceedings of the European conference on computer vision, Florence, 7–13 October 2012, pp. 864–877. Berlin: Springer.
AchlioptasD. Database-friendly random projections. In: Proceedings of the SIGMOD-SIGACT-SIGART symposium on principles of database systems, pp. 274–281. ACM, http://people.ee.duke.edu/~lcarin/p93.pdf
32.
ShiveleySDouglassAPoschB, et al. Guided wave structural health monitoring with large data sets. In: Proceedings of the IEEE international ultrasonics symposium, Tours, 18–21 September 2016, pp. 1–4. New York: IEEE.
33.
KangKHookerG. Improving the recovery of principal components with semi-deterministic random projections. In: Proceedings of the annual conference on information science and systems (CISS), Princeton, NJ, 16–18 March 2016, pp. 596–601. New York: IEEE.
34.
MichaelsJELeeSJCroxfordAJ, et al. Chirp excitation of ultrasonic guided waves. Ultrasonics2013; 53(1): 265–270.
35.
LiHMichaelsJELeeSJ, et al. Quantification of surface wetting in plate-like structures via guided waves. Proc Rev Prog Quant Nondestruct Evaluat2012; 1430(1): 217–224.
36.
HarleyJBMouraJMF. Scale transform signal processing for optimal ultrasonic temperature compensation. IEEE Trans Ultrason Ferroelectr Freq Control2012; 59(10): 2226–2236.
37.
JolliffeITCadimaJ. Principal component analysis: a review and recent developments. Phil Trans R Soc A Math Phys Eng Sci2016; 374(2065): 20150202.
38.
GharibnezhadFMujicaLERodellarJ. Applying robust variant of principal component analysis as a damage detector in the presence of outliers. Mech Syst Signal Process2015; 50: 467–479.
39.
LiuCHarleyJBO’DonoughueN, et al. Ultrasonic scatterer detection in a pipe under operating conditions using singular value decomposition. AIP Conf Proc2013; 1511: 1454–1461.
