This paper amalgamates two uncorrelated techniques namely finite difference time domain technique (FDTD) and nonlinear autoregressive with exogenous input (NARX) neural network to achieve a faster computation of radar cross section (RCS). It generates only a limited number of FDTD data and uses them to train a NARX neural network. The data beyond this limited number for the FDTD come from the NARX prediction. Comparison of the performance of FDTD-NARX hybrid with other methods indicates good matching with better timing for RCS of electrically larger objects.
Nihar Kanta Sahoo,
Dhruba Charan Panda,
Rabindra Kishore Misra,
Amit Kumar Sahu,
"RCS Calculation Using Hybrid FDTD-NARX Technique," Progress In Electromagnetics Research M,
Vol. 82, 73-84, 2019. doi:10.2528/PIERM19041007
1. Knott, E. F., J. F. Shaeffer, and M. T. Tuley, Radar Cross Section, 2nd Ed., corr. reprinting, SciTech Pub., Raleigh, NC, 2004.
2. Fan, T. and L. Guo, "OpenGL-based hybrid GO/PO computation for RCS of electrically large complex objects," IEEE Antennas and Wireless Propagation Letters, Vol. 13, 666-669, 2014. doi:10.1109/LAWP.2014.2352372
3. Fan, T., L. Guo, B. Lv, and W. Liu, "An improved backward SBR-PO/PTD hybrid method for the backward scattering prediction of an electrically large target," IEEE Antennas and Wireless Propagation Letters, Vol. 15, 512-515, 2016. doi:10.1109/LAWP.2015.2456031
4. Jin, K. S., T. I. Suh, S. H. Suk, B. C. Kim, and H. T. Kim, "Fast ray tracing using a space-division algorithm for RCS prediction," Journal of Electromagnetic Waves and Applications, Vol. 20, No. 1, 119-126, 2006. doi:10.1163/156939306775777341
5. Algar, M., L. Lozano, J. Moreno, I. González, and F. Cátedra, "An efficient hybrid technique in RCS predictions of complex targets at high frequencies," Journal of Computational Physics, Vol. 345, 345-357, 2017. doi:10.1016/j.jcp.2017.05.035
6. Wu, B. and X. Sheng, "Application of asymptotic waveform evaluation to hybrid FE-BI-MLFMA for fast RCS computation over a frequency band," IEEE Transactions on Antennas and Propagation, Vol. 61, No. 5, 2597-2604, 2013. doi:10.1109/TAP.2013.2246532
7. Antyufeyeva, M. S., A. Yu. Butrym, N. N. Kolchigin, M. N. Legenkiy, A. A. Maslovskiy, and G. G. Osinovy, "Specific RCS for describing the scattering characteristic of complex shape objects," Progress In Electromagnetics Research M, Vol. 52, 191-200, 2016. doi:10.2528/PIERM16042907
8. Taflove, A. and S. C. Hagness, "Finite-difference time-domain solution of Maxwell's Equations," Wiley Encyclopedia of Electrical and Electronics Engineering, 1-33, American Cancer Society, 2016.
9. Elsherbeni, A. Z. and V. Demir, The Finite-Difference Time-Domain Method for Electromagnetics with Matlab Simulations, 2nd Ed., SciTech, 2016.
10. Liu, J.-X., L. Ju, L.-H. Meng, Y.-J. Liu, Z.-G. Xu, and H.-W. Yang, "FDTD method for the scattered-field equation to calculate the radar cross-section of a three-dimensional target," Journal of Computational Electronics, Vol. 17, No. 3, 1013-1018, 2018. doi:10.1007/s10825-018-1162-4
11. Chen, W., L. Guo, J. Li, and S. Liu, "Research on the FDTD method of electromagnetic wave scattering characteristics in time-varying and spatially nonuniform plasma sheath," IEEE Transactions on Plasma Science, Vol. 44, No. 12, 3235-3242, 2016. doi:10.1109/TPS.2016.2617680
12. Panda, D. C., S. S. Pattnaik, S. Devi, and R. K. Mishra, "Application of FIR neural network on finite difference time domain technique to calculate input impedance of microstrip patch antenna," International Journal of RF and Microwave Computer Aided Engineering, Vol. 20, No. 2, 158-162, 2010.
13. Delgado, H. J. and M. H. Thursby, "A novel neural network combined with FDTD for the synthesis of a printed dipole antenna," IEEE Transactions on Antennas and Propagation, Vol. 53, No. 7, 2231-2236, 2005. doi:10.1109/TAP.2005.850706
14. Mishra, R. K. and P. S. Hall, "NFDTD concept," IEEE Transactions on Neural Networks, Vol. 16, No. 2, 484-490, 2005. doi:10.1109/TNN.2004.841799
15. Siegelmann, H. T., B. G. Horne, and C. L. Giles, "Computational capabilities of recurrent NARX neural networks," IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics: A Publication of the IEEE Systems, Man, and Cybernetics, Vol. 27, No. 2, 208-215, 1997. doi:10.1109/3477.558801
16. Zhu, Y. and Z. Q. Lang, "Design of nonlinear systems in the frequency domain: An output frequency response function-based approach," IEEE Transactions on Control Systems Technology, Vol. 26, No. 4, 1358-1371, 2018. doi:10.1109/TCST.2017.2716379
17. Zhao, W., H. Chen, and W. X. Zheng, "Recursive identification for nonlinear ARX systems based on stochastic approximation algorithm," IEEE Transactions on Automatic Control, Vol. 55, No. 6, 1287-1299, 2010. doi:10.1109/TAC.2010.2042236
18. Shirangi, M. G. and A. A. Emerick, "An improved TSVD-based Levenberg-Marquardt algorithm for history matching and comparison with Gauss-Newton," Journal of Petroleum Science and Engineering, Vol. 143, 258-271, 2016. doi:10.1016/j.petrol.2016.02.026
19. Wilamowski, B. M. and H. Yu, "Improved computation for Levenberg-Marquardt training," IEEE Transactions on Neural Networks, Vol. 21, No. 6, 930-937, 2010. doi:10.1109/TNN.2010.2045657
20. Martin, T., "An improved near- to far-zone transformation for the finite-difference time-domain method," IEEE Transactions on Antennas and Propagation, Vol. 46, No. 9, 1263-1271, 1998. doi:10.1109/8.719968