An artificial intelligence-based electromagnetic simulation method and its electromagnetic brain

Abstract

The invention discloses an artificial intelligence-based electromagnetic simulation method and its electromagnetic brain. The present invention puts the geometric, physical, and excitation data corresponding to the engineering structure into the full-wave electromagnetic calculation solver to obtain the S parameter information corresponding to the engineering structure, and then forms a training data set and imports it into the convolutional neural network for offline training . Add the new structural electronic device to be analyzed to the data server, no longer need to use the full-wave electromagnetic simulation method with slow calculation speed, but use geometry, physics, and excitation as input, take scattering S-parameter as output, and use trained convolution The neural network analyzes the electromagnetic performance and obtains the corresponding scattering S parameter results. Compared with the existing full-wave electromagnetic simulation software, once the convolutional neural network training is completed, the present invention can obtain the simulation results without relying on the full-wave electromagnetic field solver, so the calculation efficiency is more than a thousand times higher than that of the existing software.

Description

technical field [0001] The invention belongs to the technical field of electromagnetic simulation, and relates to an artificial intelligence-based electromagnetic simulation method and its electromagnetic brain. Background technique [0002] The third wave of information driven by wireless communication, mobile portable and Internet of Things, etc., wireless and mobile portable communication are its fundamental features, and radio frequency integrated circuits are its most critical core technology. The core basic hardware of modern high-speed wireless communication is radio frequency integrated circuit chips. As the information society enters the era of 5G communication and cloud computing, the market demand for radio frequency integrated circuit chips will continue to grow rapidly in the future, which increases the demand for radio frequency circuit design and simulation software. demand. [0003] Document 1 (from C.C.Weng, J.J.Li, Overview of Large-Scale Computing: The Pa...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the prior art, to provide an artificial intelligence algorithm that can obtain results similar to accurate electromagnetic simulations without rigorous full-wave electromagnetic field numerical simulations after deep learning, that is, using Artificial intelligence algorithms conduct supervised learning on the results of electromagnetic simulations, thereby training an electromagnetic brain that can perform electromagnetic analysis on circuits

Images