Attenuation constant and characteristic impedance calculation of top metal-covered CPW transmission line using neural networks
Tóm tắt
A technique for calculating the characteristic impedance of top metal-covered coplanar waveguide (TCPW) transmission lines using a neural network is presented in this paper. Additionally, the technique is extended to calculate their attenuation constant. Analytical expressions based on conformal mapping techniques are not applicable when the top cover height is < 3 µm. Further, there are no analytical expressions available to calculate their attenuation constant. We used a feed-forward artificial neural network to calculate the characteristic impedance and attenuation constant of TCPWs. The results are compared with those obtained using ANSYS HFSS full-wave simulation software, which shows good agreement. This technique will be useful for equivalent circuit modeling of RF-MEMS.
Tài liệu tham khảo
Lyons, M.R., Gilb, J.P.K., Balanis, C.A.: Enhanced domain mode operation of a shielded multilayer coplanar waveguide via substrate compression. IEEE Trans. Microw. Theory Tech. 41, 1589–1592 (1993)
Chen, E., Chou, S.Y.: Characteristics of coplanar transmission lines on multilayer substrates: modeling and experiments. IEEE Trans. Microw. Theory Tech. 45, 939–945 (1997)
Ciric, T., Dhuri, R., Marinkovic, Z., Pronic-Rancic, O., Markovic, V., Vietzorreck, L.: Neural based lumped element model of capacitive RF MEMS switches. Frequenz 72, 539–546 (2018)
Simons, R.N.: Coplanar Waveguide Circuits, Components and Systems. Wiley, New York (2001)
Gupta, K.C., Garg, R., Bahl, I., Bhartia, P.: Microstrip Lines and Slotlines. Artech House, Norwood (1996)
Hoffmann, R.K.: Handbook of Microwave Integrated Circuits. Artech House, Norwood (1987)
Root, D.E.: Future device modeling trends. IEEE Microw. Mag. 13(7), 45–59 (2012)
Zhang, H.C., Jin, J., Na, W., Zhang, Q., Yu, M.: Multivalued neural network inverse modeling and applications to microwave filters. IEEE Trans. Microw. Theory Tech. 66(8), 3781–3797 (2018)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)
Wilamowski, B.M., Yu, H.: Improved computation for Levenberg–Marquardt training. IEEE Trans. Neural Netw. 21, 930–937 (2010)
ANSYS Corporation: “HFSS–High Frequency Structure Simulator,” Suite v15. Pittsburg, PA, USA (2014)