Skip to main content Accessibility help
  • Print publication year: 2016
  • Online publication date: July 2016

6 - Characterization of Planar Transmission Lines Using ANN


Advancements in microwave integrated circuits (MIC) are occurring at a rapid pace. Features of MIC such as small size and the possibility of realization of entire systems on a single chip have led to the increase in the usage of these devices in communication systems. One of the integral elements of these MICs is transmission lines. Transmission lines are not just used to connect individual modules inside the MIC but they are also essential in the realization of components like filters, mixers, couplers, and power dividers. Popular types of transmission lines used include microstrip lines, strip lines, grounded waveguides, slotlines, etc. As a result, these transmission lines must be designed carefully and analyzed; deviations in the design will lead to errors in the operation of the MIC. Traditional methods of analysis of transmission lines include conformal transformation, variational method, spectral domain method, and numerical methods like finite element method (FEM), finite difference method, and finite difference time domain method. These methods are extremely accurate and have been documented to produce results that concur with experimental observations. However, complex mathematical formulation and iterative nature imply high computational time requirement [Bhatt and Koul, 1990; Schellenberg, 1995]. This quality limits the application of these techniques in situations where quick solutions are required such as CAD packages for transmission line design. The algorithms based on artificial intelligence could be used in order to create such CAD packages. Yildiz et al. [Yildiz et al., 2004] used neural network for analysis of co-planar waveguide. The same algorithm was further used for the analysis of inverted microstrip lines [Yildiz and Saracogulu, 2003]. Although the analysis of planar transmission lines using neural network has been explored, the design of various configurations of transmission lines using NN is yet to be done.

In this chapter, the analysis and the design of various configurations of transmission lines, namely the microstrip line and the slotline, are conducted using artificial neural networks. The corresponding formulation and ANN implementation are discussed in detail.

Planar Transmission Lines

As mentioned earlier, different types of transmission lines are used in the fabrication of MIC depending upon the requirement. In this chapter, the focus is limited to two types of planar transmission lines viz. microstrip transmission lines and slotline transmission line.

Bhatt, B. and S. K., Koul, Stripline-like Transmission lines for Microwave Integrated Circuits, Wiley Eastern Limited, Delhi, Dec. 1990.
Devabhaktuni, V. K., M. C. E., Yagoub, Y., Fang, J., Xu, and Q., Zhang, “Neural networks for microwave modeling: Model development issues and nonlinear modeling techniques,” International Journal of RF and Microwave Computer Aided Engineering, vol. 11, pp. 4–21, 2001.
Haykins, S., Neural Networks: A Comprehensive Foundation, Prentice Hall International, NJ, ISBN: 9780139083853, 842p., 1999.
Patnaik, A., R. K., Mishra, G. K., Patra, and S. K., Dash, “An artificial neural network model for effective dielectric constant of microstripline,” IEEE Transactions on Antennas and Propagation, vol. 45, no. 11, pp. 1697, 1997.
Pattanayak, S., B., Choudhury, and A., Patnaik, “Characterization of planar transmission lines using ANN,” Silver Jublee conference on Communication and VLSI Design, CommV-2009, Oct. 08-10, Vellore, India.
Raida, Z., “Modeling EM structures in neural network toolbox of Matlab,” IEEE Antennas and Propagation Magazine, vol. 45, no. 1, pp. 46–67, 2003.
Schellenberg, J. M., “CAD models for suspended and inverted microwave microstrip,” IEEE Transactions on Microwave Theory and Technique, vol. 43, pp. 1247–1252, June 1995.
Wheeler, H. A., “Transmission-line properties of parallel wide strips by a conformal-mapping approximation,” IEEE Transactions of Microwave Theory and Techniques, vol. 12, pp. 280–289, May 1964.
Yildiz, C. and O., Saracogulu, “Simple models based on neural networks for suspended and inverted microstrip lines,” Microwave and Optical Technology Letters, vol. 39, no.5, pp. 383–389, Dec. 2003.
Yildiz, C., S., Sagiroglu, and M., Turkmen, “Neural model for coplanar waveguide sandwiched between two dielectric substrates,” IEE Microwave Antennas and Propagation, vol. 151, no.1, pp. 7–12, Feb. 2004.
Zhang, Q. J., and K. C., Gupta, Neural Networks for RF and Microwave Design, Artech House, ISBN: 9781580531009, 369p., 2000