Credibility Evaluation of Electromagnetic Simulation Results Based on Convolutional Neural Network

Abstract

The core idea of the credibility evaluation method of electromagnetic simulation results is to replace the experts with an electromagnetic computing professional background to evaluate the credibility of simulation results. The representative algorithm is the feature selective validation (FSV) method proposed by the IEEE Standards Association. However, the existing credibility assessment methods all use statistical indicators or signal processing methods to simulate the real thoughts of experts and have not achieved true artificial intelligence. In this letter, a credibility evaluation method of simulation results based on a convolutional neural network is proposed, which aims to integrate the real ideas of experts (background knowledge of electromagnetic calculation) into the evaluation, instead of just mechanical numerical calculation, and to avoid evaluation errors caused by nonprofessional.