Artificial neural network models for the double-vias in multilayer stripline circuits

摘要

Multi-vias is a kind of interconnection largely existing in the multi-chip module (MCM) packages for high-speed digital circuits. In this paper, a multilayer perceptron neural network (MLPNN) is used to model the double-vias in multilayer 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. One type of the designs of experiments, the central composite technique, is used to allow for a minimum number of FDTD simulations that is needed to be performed.