Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

A multi-physics informed antenna sensor model through the deep neural network regression

  • Cho, Chunhee (Department of Civil and Environmental Engineering, University of Hawaii at Manoa) ;
  • Long, LeThanh (Information Technology Department, Duy Tan University) ;
  • Park, JeeWoong (Department of Civil and Environmental Engineering and Construction, University of Nevada at Las Vegas) ;
  • Jang, Sung-Hwan (Department of Civil and Environmental Engineering, Hanyang University (ERICA Campus))
  • Received : 2020.09.14
  • Accepted : 2021.05.15
  • Published : 2021.09.25
⟨ Previous Next ⟩

Abstract

A passive wireless strain sensing method using antenna sensors has significantly advanced structural health monitoring systems. Since the dimensions of antenna sensors are sensitive to their strain sensing performance and operating frequency, an iterative tuning process is required to achieve a final optimized design. Although multi-physics finite element simulation enables accurate estimation of antenna performance for each turning iteration, the simulation process requires high computational resources. Therefore, antenna tuning processes are recognized as obstacles to delay the final design process. In this study, we explore the potential of multi-physics informed models as an alternative approach for analyzing antenna sensors. Through deep neural networks, as a branch of the machine-learning algorithms, we formulate multi-physics informed models with six input parameters (antenna dimensions) and two outputs (resonance frequency and strain sensitivity). Twenty-two hundred high fidelity data sets are prepared by simulating multi-physics models: 1,600, 400, and 200 data sets are applied to deep neural network regression (DNNR) training, validating, and testing, respectively. From extensive data investigation, an optimized DNNR architecture is obtained to be two layers, with 16 neurons in each layer. Its training, validating, and testing values of mean square errors are 13.01, 44.22, 37.27, respectively. Finally, the proposed multi-physics informed model predicts the resonance frequency and strain sensitivity with errors of 0.1% and 0.07%, respectively. In addition, since the average computation speed for each tuning process is 0.007 seconds, the practical usefulness of the proposed method is also proven.

Keywords

Acknowledgement

This work was supported by the research fund of Hanyang University (HY-2020-N).

References

  1. Adams, A.T. (1974), "An introduction to the method of moments", Comput. Phys. Commun., 68(1), 1-18. https://doi.org/10.1016/0010-4655(91)90191-M
  2. Balanis, C.A. (1989), Advanced Engineering Electromagnetics, New York: Wiley & Sons, Inc.
  3. Bushyager, N.A. and Tentzeris, M.M. (2005), Multi resolution time domain method in electromagnetics, Morgan & claypool, USA.
  4. Celebi, M. (2002), "Seismic instrumentation of buildings (with Emphasis on Federal Buildings)", United States Geological Survey, Menlo Park, CA Report No. 0-7460-68170.
  5. Chang, F.-K. and Guemes, A. (2013), "Structural heath monitoring 2013: a roadmap to intelligent structures", Lancaster, PA, USA.
  6. Cho, C., Yi, X., Li, D., Wang, Y. and Tentzeris, M.M. (2016), "Passive frequency doubling antenna sensor for strain and crack sensing", Sensors J., IEEE, 16(14), 5725-5733. https://doi.org/10.1109/JSEN.2016.2567221
  7. Cho, C., Yi, X., Li, D., Wang, Y. and Tentzeris, M.M. (2017), "An eigenvalue perturbation solution for the multi-physics simulation of antenna strain sensors", IEEE J. Multiscale Multiphys. Computat. Tech., 2, 49-57. https://doi.org/10.1109/JMMCT.2017.2698338
  8. Clemens, M. and Weiland, T. (2001), "Discrete electromagnetism with the finite integration technique", Progress in Electromagn. Res., 32, 65-87. https://doi.org/10.2528/PIER00080103
  9. COMSOL (2020), COMSOL multiphysics reference guide, COMSOL, Inc., Burlington, MA, USA.
  10. Derkevorkian A., Pena, F., Masri, S. and Richards W. (2017), "Operation load estimation of chain-like structures using fiber optic strain sensors", Smart Struct. Syst., Int. J., 20(3), 385-396. https://doi.org/10.12989/sss.2017.20.3.385
  11. Huo, L., Li, X., Chen, D. and Li, H. (2017), "Structural health monitoring using piezoceramic transducers as strain gauges and acoustic emission sensors simultaneously", Comput. Concrete, Int. J., 20(5), 595-603. https://doi.org/10.12989/cac.2017.20.5.595
  12. Jin, J.M. (2002), The finite element method in electromagnetics, (2nd ed.), John Wiley & Sons, Inc., New York, USA.
  13. Li, D. and Wang, Y. (2020), "Thermally-stable wireless patch antenna sensor for strain and crack sensing", Sensors, 20(14), 3835. https://doi.org/10.3390/s20143835
  14. Lopato, P. and Herbko, M. (2018), "A circular microstrip antenna sensor for direction sensitive strain evaluation", Sensors, 18(1), 310. https://doi.org/10.3390/s18010310
  15. MATLAB (2019), Natick, Massachusetts: The MathWorks Inc.
  16. Ney, M.M. (1985), "Method of moments as applied to electromagnetics problems", IEEE Transcations on Microwave Theory and techniques, 33(10), 972-980. https://doi.org/10.1109/TMTT.1985.1133158
  17. Sohn, H., Farrar, C.R., Hemez, F.M., Shunk, D.D., Stinemates, D.W. and Nadler, B.R. (2003), "A Review of structural health monitoring literature: 1996-2001", Los Alamos National Laboratory, Los Alamos, NM Report No. LA-13976-MS.
  18. Taflove, A. (1988), "Review of the formulation and applications of the finite-difference time-domain method for numerical modeling of electromagnetic wave interactions with arbitrary structures", Wave Motion, 10(6), 547-582. https://doi.org/10.1016/0165-2125(88)90012-1
  19. Tchafa, F. and Huang, H. (2019), "Microstrip patch antenna for simultaneous temperature sensing and superstrate characterization", Smart Mater. Struct., 28, 105009. https://doi.org/10.1088/1361-665X/ab2213
  20. Vapnik, V. (1995), The nature of statistical learning theory, Springer, New York, USA.
  21. Villarrubia, G., Paz, J.F., Chamoso, P. and Prieta, F. (2017), "Artificial neural networks used in optimization problems", Neurocomputing, 272(10), 10-16. https://doi.org/10.1016/j.neucom.2017.04.075
  22. Volakis, J.L., Chatterjee A. and Kempel, L.C. (1998), "Finite element method for electromagnetics: with applications to antenna, microwave circuits, and scattering", The Institute of Electrical and Electronics Engineers, Inc., New York, USA.
  23. Yee, K.S. (1966), "Numerical solution of initial boundary-value problems involving Maxwell's equations in isotropic media", IEEE Transactions on Antennas and Propagation, 14, 302-307. https://doi.org/10.1109/TAP.1966.1138693
  24. Yi, X., Wu, T., Wang, Y., Leon, R.T., Tentzeris, M.M. and Lantz, G. (2011), "Passive wireless smart-skin sensor using RFID-based folded patch antennas", Int. J. Smart Nano Mater., 2(1), pp. 22-38. https://doi.org/10.1080/19475411.2010.545450
  25. Yi, X., Cho, C., Cooper, J., Wang, Y., Tentzeris, M.M. and Leon, R.T. (2013), "Passive wireless antenna sensor for strain and crack sensing-electromagnetic modeling, simulation, and testing", Smart Mater. Struct., 22(8), p. 085009. https://doi.org/10.1088/0964-1726/22/8/085009
  26. Yi, X., Cho, C., Cook, B., Wang Y., Tentzeris, M.M. and Leon, R.T. (2014), "A slotted patch antenna for wireless strain sensing", Proceedings of the ASCE 2014 Structures Congress, Boston, MA, USA.
  27. Zhang, J., Huang, B., Zhang, G. and Tian, G.Y. (2018), "Wireless passive ultra-high frequency RFID antenna sensor for surface crack monitoring and quantitative analysis", Sensors, 18(7), 2130. https://doi.org/10.3390/s18072130
  28. Zoeller, M. and Huber, M. (2019), "Survey on automated machine learning", arXiv preprint, arXiv: 1904.12054. https://doi.org/10.1613/jair.1.11854