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

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 mul tilayer perceptron neural network (MLPNN) is used to model the double-vias in multilayer stripline circuits. The MLPNN is electromagnetically develope d with a set of training data that are produced by the full-wave finite-dif ference time-domain (FDTD) method. One type of the designs of experiments, the central composite technique, is used to allow for a minimum number of F DTD simulations that is needed to be performed.