Neural Network for the Prediction of Electric Field Intensity Applied to a Simple Scenario

In response to the escalating challenges in Electromagnetic Compatibility (EMC) driven by the increase of electronic devices, the risk based approach is made mandatory in the EMC Directive. Showing the role of Artificial Intelligence (AI), particularly neural networks (NN), in EMC, this paper explores how NNs can be used for a specific case study of predicting the behaviour of the electric field in a simple scenario. The dataset was created by using Full-wave modeling software. Multiple assumptions and steps are taken for the creation of the NN and the adaptation of such a case study to this research. The results show the performance of the NN for different cases in which the model can make good predictions and when it lacks accuracy.