Enforcing Causality and Passivity of Neural Network Models of Broadband S-Parameters

Abstract

This paper proposes a method to ensure that S-Parameters generated using neural network (NN) models are physically consistent and can be safely used in subsequent time-domain simulations. This is achieved by introducing causality and passivity enforcement layers as the last two layers of the NN, while minimizing their computational overhead to the training and inference of the NN model. Proposed technique is demonstrated on learning the mapping from 13 dimensional geometrical parameters of a differential plated through hole (PTH) in package core to its corresponding broadband S-Parameters up to 100 GHz.