Restricted accessResearch articleFirst published online 2024-3
A deep neural network for electrical resistance calibration of self-sensing carbon fiber polymer composites compatible with edge computing structural monitoring hardware electronics
The self-sensing ability of materials, in particular carbon fiber polymer composites (SSCFPC), is a must-have requirement when designing a structural monitoring network for remote assessment of structural serviceability. This work presents a study using an Artificial Deep Neural Network (ADNN) wherein is evaluated the electrical resistance (R) output of specimens subjected to an unchanged deformation state of 2.86% strain for prolonged periods of time. Six ADNN architectures are evaluated with varying numbers of neurons on pre-defined hidden layers, sharing the same four data inputs and one output. The dataset is based on 3276 data points collected during the experimental campaign of an innovative electrode design embedded in SSCFPC specimens. The effect of the number of iterations and the architecture of the neural network is investigated in proposed ADNN models. Simple moving average, and moving Standard Deviation, , are determined and plotted in terms of z-score to assist in performance evaluation of proposed ADNN models. The optimal ADNN architecture is found among six proposed architectures and for each of the four SSCFPC mixtures. Results show the proposed model architectures are able to predict values of R with greater accuracy than traditional regression mathematical methods when traditional statistical coefficients are used. However, when analyzing data in a time-series manner, results show further research is needed to achieve optimal accuracy results. The analysis presented focused on the structural monitoring network infrastructure and hardware electronics compatibility for further development of this type of SSCFPC as a self-sensing composite material with ability of automatic calibration and suitable for real-time data acquisition and artificial intelligence modeling.
ShiWCaoJZhangQ, et al. Edge computing: vision and challenges. J IEEE Internet Things2016; 3(5): 637–646.
2.
KumarADhanagopalRAlbreemMA, et al. A comprehensive study on the role of advanced technologies in 5G based smart hospital. Alexandria Eng J2021; 60(6): 5527–5536.
3.
SatyanarayananMEiszlerTHarkesJ, et al. Edge computing for legacy applications. IEEE Pervasive Comput2020; 19(4): 19–28.
4.
XuDLiTLiY, et al. Edge intelligence: architectures, challenges, and applications. arXiv:2003.1217 2v2, 2020.
5.
AlnomanAKrishna SharmaSEjazW, et al. Emerging edge computing technologies for distributed internet of things (IoT) Systems, arXiv:1811.11268v1, 2018.
6.
YuanAPengMZhangK, et al. Edge computing technologies for internet of things: a primer. J Digital Commun Networks2018; 4(2): 77–86.
7.
MirazMHAliMExcellPS, et al. A review on internet of things (IoT), internet of everything (IoE) and internet of nano things (IoNT). In: Internet Technologies and Applications, Glyndwr University, UK, 2018, pp. 219–224.
8.
AbdoGFremeijer-HoltzM.Worldwide content delivery networks forecast 2021–2025. Massachussets, USA: International Data Corporation (IDC), 2021.
9.
PatelKKPatelSMScholorPG, et al. Internet of things IoT: definition, characteristics, architecture, enabling technologies, application future challenges. Int J Eng Sci Comput2016; 6(5): 6122–6131.
10.
JainR.A congestion control system based on VANET for small length roads. Ann Emerg Technol Comput2018; 2(1): 17–21.
11.
MahmudSHAssanLIslamR, et al. Potentials of internet of things (IoT) in Malaysian construction industry. Ann Emerg Technol Comput2018; 2(1): 44–52.
12.
AlhashimiAW.Statistical sensor calibration algorithms. PhD Thesis, Department of Computer Science Electrical and Space Engineering, Division of Signals and Systems, Luleå University of Technology, Sweden, 2018.
13.
FradenJ. Handbook of modern sensors: physics, designs, and applications. New York, USA: Springer Science & Business Media, 2004.
14.
WangLHChengLH.Piezoresistive effect of a carbon nanotube silicone-matrix composite. Carbon2014; 71(0): 319–331.
15.
TomásMJalaliS.Piezoresistivity in micro carbon fiber silicone composites for electrical resistance to strain sensing. Adv Eng Forum2017; 23: 45–55.
16.
TomásMJalaliSSilva de VargasA.Creep evaluation and temperature dependence in self-sensing micro carbon polymer-based composites for further development as an Internet of Things Sensor device. J Compos Mater2022; 56(6): 961–973.
17.
WangYEdgellJGrahamN, et al. Self-healing of structural carbon fibres in polymer composites. Cogent Eng2020; 7: 1.
18.
WilliamsGTraskRBondI, et al. A self-healing carbon fibre reinforced polymer for aerospace applications. Compos Part A: Appl Sci Manuf2007; 38(6): 1525–1532.
19.
RibeiroB. Support vector machines for quality monitoring in a plastic injection molding process. In: IEEE transactions on systems, man and cybernetics, Part C (Applications and Reviews), 2005, vol. 35, no. 3, pp. 401–410.
20.
LarrañagaPAtienzaDDiaz-RozoJ, et al. Industrial applications of machine learning, 1st ed. Florida, USA: CRC Press, 2018.
21.
AlexanderYSBridgetRS.How can Big Data and machine learning benefit environment and water management: a survey of methods, applications, and future directions. Environ Res Lett2019; 14: 073001.
22.
BockFAydinRCyronCJ, et al. A review of the application of machine learning and data mining approaches in continuum materials mechanics. Front Mater2019; 6: 110.
23.
SalehiHBurgueñoR.Emerging artificial intelligence methods in structural engineering. Eng Struct2018; 171: 170–189.
24.
CherkasskyVKrasnopolskyVSolomatineDP, et al. Computational intelligence in earth sciences and environmental applications: issues and challenges. Neural Networks2006; 19(2): 113–121.
25.
SchmidtJMarquesMRGBottiS, et al. Recent advances and applications of machine learning in solid-state materials science. NPJ Comput Mater2019; 5: 83.
26.
KoumoulosEPTofailSAMSilenC, et al. Metrology and nano -mechanical tests for nano-manufacturing and nano -bio interface: challenges & future perspectives. Mater Design2018; 137: 446–462.
ZhangDQianLMaoB, et al. A data-driven design for fault detection of wind turbines using random forests and XGboost. IEEE Access2018; 6: 21020–21031.
29.
LuísaRVEduardoLCDe MedeirosR.Artificial neural networks applying to detect damage in carbon fiber/epoxy composites. Brazilian Conf Compos Mater2018.
30.
KonstantopoulosGKoumoulosEPCharitidisCA.Classification of mechanism of reinforcement in the fiber-matrix interface: application of machine learning on nanoindentation data. Mater Design2020; 192: 108705.
31.
SammonsDWinfreeWPBurkeE, et al. Segmenting delaminations in carbon fiber reinforced polymer composite CT using convolutional neural networks. AIP Conf Proc2016; 1706: 110014.
32.
HassanHTallmanTN.Precise damage shaping in self-sensing composites using electrical impedance tomography and genetic algorithms. J Struct Health Monit2022; 22(1): 372–387.
33.
HassanHTallmanTN.Failure prediction in self-sensing nanocomposites via genetic algorithm-enabled piezoresistive inversion. J Struct Health Monit2020; 19(3): 765–780.
34.
LantzB.Machine Learning with R, 3rd ed.Birmingham: Packt Publishing Ltd., 2019.
35.
GuptaBShengQZ.Machine learning for computer and cyber security: principles, algorithms, and practices. Boca Raton, FL: Taylor & Francis Group, 2019.
36.
WangFSahanaMPahlevanzadehB, et al. Applying different resampling strategies in machine learning models to predict head-cut gully erosion susceptibility. Alexandria Eng J2021; 60(6): 5813–5829.
37.
PanesarA.Machine learning and AI for healthcare. Coventry: Apress, 2019.
38.
DewapriyaMANRajapakseRKNDDiasWPS, et al. Characterizing fracture stress of defective graphene samples using shallow and deep artificial neural networks. J Carbon2020; 163: 425–440.
39.
FörsterGDCastanALoiseauA, et al. A deep learning approach for determining the chiral indices of carbon nanotubes from high-resolution transmission electron microscopy images. J Carbon2020; 169: 465–474.
40.
DeyNWaghSMahallePN, et al. Applied machine learning for smart data analysis. 1st ed. New York, NY: CRC Press/Taylor & Francis Group, 2019.
41.
WittenHFrankEHallM, et al. Chapter 7-data transformations. In: WittenIHFrankEHallTE (eds) Data management systems, Morgan Kaufmann, Burlington, MA, USA, 2011, pp. 305–349.
42.
ParkJMLeeSIChoiJ-H, et al. Cure monitoring and residual stress sensing of single-carbon fiber reinforced epoxy composites using electrical resistivity. Compos Sci Technol2005; 65: 571–580.
43.
JohnsonTMFullwoodDTHansenG, et al. Strain monitoring of carbon fiber composite via embedded nickel nano-particles. J Composites2012; 43: 1155–1163.
44.
ShuiXChungDDL. A piezoresistive carbon filament polymer-matrix composite strain sensor. Smart Mater Struct1996; 5: 243–246.
45.
ReyTChagnonGLe CamJ-B, et al. Effects of temperature on the mechanical behavior of filled and unfilled silicone rubbers. In: European conference on constitutive models for rubber VIII, San Sebastian, Spain, 2013.
46.
McCarteWJStarrsGChrispTM, et al. Activation energy and conduction in carbon fiber-reinforced cement matrices. J Mater Sci2007; 42: 2200–2203.
47.
ZenerC. Elasticity and anelasticity of metals. Chicago, USA: University of Chicago Press, 1948.
48.
BishopCM.Pattern recognition and machine learning (Information Science and Statistics). New York, USA: Springer-Verlag, 2006.
49.
ZhouRWuDFangL, et al. A Levenberg-Marquardt backpropagation neural network for predicting forest growing stock based on the least-squares equation fitting parameters. J Forests2018; 9(12): 757.
50.
HuynhHTWonY.Training single hidden layer feedforward neural networks by singular value decomposition. In: Proceedings of the 2009 fourth international conference on computer sciences and convergence information technology, Seoul, Korea, 2009, pp. 1300–1304.
51.
YanT-STaoY-QCuiD-W, et al. Research on hand-written numeral recognition method based on improved genetic algorithm and neural network. In: Proceedings of the 2007 international conference on wavelet analysis and pattern recognition, Beijing, China, 2007, vol. 3, pp. 1271–1276.
52.
Al-TaaniAHammadM.Recognition of on-line handwritten Arabic digits using structural features and transition network. J Informatica2008; 32(3): 275–281.
53.
OtairMWalidAS.Speeding up back-propagation neural networks. In: Proceedings of the 2005 informing science and IT education joint conference, Flagstaff, AZ, USA, 2005, vol. 1, pp. 167–173.
54.
NguyenMDPhamBTHoLS, et al. Soft-computing techniques for prediction of soils consolidation coefficient. Catena2020; 195: 104802.
55.
PhamTBSinghSKLyH-B, et al. Using artificial neural network (ANN) for prediction of soil coefficient of consolidation. Vietnam J Earth Sci2020; 42(4): 311–319.
56.
DaoDVAdeliHLyH-B, et al. A sensitivity and robustness analysis of GPR and ANN for high-performance concrete compressive strength prediction using a Monte Carlo simulation. J Sustainability2020; 12(3): 830.
PötschAHammerF. Towards end-to-end latency of LoRaWAN: experimental analysis and IIoT applicability. In: 2019 15th IEEE international workshop on factory communication systems (WFCS), 2019, pp. 1–4.
