Conducted electromagnetic emission current source modelling by artificial neural networks

A simple and efficient method of modelling conducted electromagnetic emission (EME) current sources at integrated circuit (IC) level by using artificial neural networks (ANN) is presented. The universal approximation property of ANN provides a basis for representing the nonlinear, dynamic EME current sources overcoming the accuracy limitations in conventional models. A simple and effective way to obtain necessary data for training the artificial neural network used in EME modelling is presented. The presented methodology ensures a simple, fast and accurate modelling. As a test case, the EME model of conducted emissions of a simple local interconnect (LIN) interface is presented.