A Near-Field Technique Based on PZMI, GA, and ANN: Application to Power Electronics Systems

In this paper, we propose a new method for modeling the electromagnetic radiation of power electronics systems. This method is based on coupling three powerful techniques: the genetic algorithm (GA) used for the optimization problem, the pseudo-Zernike moment invariant (PZMI) descriptors for pattern recognition, and the neural networks for classification of radiating sources. This modeling approach has been applied to recognize the radiating sources of a dc-dc converter. The model has been validated using measurement results of the magnetic radiation above the converter. The results of the experimental measurements have shown that the characteristics provided by the PZMI descriptors are very robust. So, the proposed method can greatly accelerate the convergence of the inverse method based on GA.