Artificial Neural Network Models for the Bend Discontinuities in Stripline Circuits

Abstract

Stripline discontinuities are basic elements of many stripline circuits, such as the multilayer microwave monolithic ICs and the interconnect systems in high-speed digital circuits. Bend as one type of the stripline discontinuities will be modeled in this paper. A multilayer perceptron neural network(MLPNN) is used to model the bend discontinuities in stripline circuits. The MLPNN is electromagnetically developed with a set of training data that are produced by the full-wave finite-difference time-domain (FDTD) method. The full-factor design of experiments is used to determine the size of the training data.