Reconstruction of 3D Permittivity Profile of a Dielectric Sample Using Artificial Neural Network Mathematical Model and FDTD Simulation

  • Mikhail Abrosimov
  • Alexander Brovko
  • Ruslan Pakharev
  • Anton Pudikov
  • Konstantin Reznikov
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 765)


The paper presents a new method of determining 3D permittivity profile using electromagnetic measurements in the closed waveguide system. The method is based on the application of artificial neural network as a numerical inverter, and on the approximation of 3D profile with quadratic polynomial function. The neural network is trained with numerical data obtained with FDTD modeling of the electromagnetic system. Special criteria for choice of a number of hidden layer neurons are presented. The results of numerical modeling show possibility of determination of permittivity profile with a relative error less than 10%.


Artificial neural network FDTD method Training algorithm for artificial neural network Nondestructive evaluation and testing 


  1. 1.
    Li, X., Davis, S.K., Hagness, S.C., Van Der Weide, D.W., Van Veen, B.D.: Microwave imaging via space-time beamforming: experimental investigation of tumor detection in multilayer breast phantoms. IEEE Trans. Microw. Theor. Tech. 52(8), 1856–1865 (2004)CrossRefGoogle Scholar
  2. 2.
    Belkebir, K., Kleinman, R.E., Pichot, C.: Microwave imaging: location and shape reconstruction from multifrequency scattering data. IEEE Trans. Microw. Theory Tech. 45(4), 469–476 (1997)CrossRefGoogle Scholar
  3. 3.
    Qaddoumi, N., Carriveau, G., Ganchev, S., Zoughi, R.: Microwave imaging of thick composite panels with defects. Mater. Eval. 53(8), 926–929 (1995)Google Scholar
  4. 4.
    Bykov, Y.V., Rybakov, K.I., Semenov, V.E.: High-temperature microwave processing of materials. J. Phys. D Appl. Phys. 34(13), R55–R57 (2001)CrossRefGoogle Scholar
  5. 5.
    Brovko, A.V., Murphy, E.K., Yakovlev, V.V.: Waveguide microwave imaging: neural network reconstruction of functional 2-D permittivity profiles. IEEE Trans. Microw. Theory Tech. 57(2), 406–414 (2009)CrossRefGoogle Scholar
  6. 6.
    Myers, R.H., Montgomery, D.C., Anderson-Cook, C.M.: Response Surface Methodology Process and Product Optimization Using Designed Experiments, 3rd edn. Wiley, New York (2009)zbMATHGoogle Scholar
  7. 7.
    Schwenker, F., Kestler, H.A., Palm, G.: Three learning phases for radial-basis-function networks. Neural Netw. 14, 439–458 (2001)CrossRefGoogle Scholar
  8. 8.
    QuickWave-3 DTM, QWED Sp. z o.o., ul. Nowowiejska 28, lok. 32, 02-010 Warsaw, Poland. Accessed 16 Dec 2017

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Yuri Gagarin State Technical University of SaratovSaratovRussia

Personalised recommendations