IMPROVING CONVERGENCE TIME OF THE ELECTROMAGNETIC INVERSE METHOD BASED ON GENETIC ALGORITHM USING THE PZMI AND NEURAL NETWORK

In this paper we present a methodology to guarantee the convergence of the electromagnetic inverse method. This method is applied to electromagnetic compatibility (EMC) in order to overcome the di-culties of measuring the radiated electromagnetic fleld and to reduce the cost of the EMC analysis. It consists in using Genetic Algorithms (GA) to identify a model that will be used to estimate the electric and magnetic fleld radiated by the device under test. This method is based on the recognition of the equivalent radiation sources using the Near Field (NF) cartography radiated by the device. Our contribution in this fleld is to improve the ability and the convergence of the electromagnetic inverse method by using the Pseudo Zernike Moment Invariant (PZMI) descriptor and the Artiflcial Neural Network (ANN). The validation of the proposed method is performed using the NF emitted by known electric and magnetic dipoles. Our results have proved that the proposed method guarantees the convergence of the electromagnetic inverse method and that the convergence speeds up while retaining all the other performances.