A Hybrid Data Generation Approach for the Development of an AI-based EMC Interference Recognition Method

This paper presents the results of a research project that aims to develop an AI platform that recognizes and identifies EMC problems based on far-field electrical data. A hybrid approach is used to generate the training data, which involves far and near field measurements as well as electromagnetic field simulations. Since all methods differ in their nature, the challenge was to standardize the type of data and to consider the respective characteristics of each method.