Rapid calculation method for broadband electromagnetic performance of microstrip line and microstrip-like two-port structure

By combining convolutional neural networks and second-order analytical models, the broadband electromagnetic performance of microstrip lines and microstrip-like structures can be quickly calculated, solving the problem of high computational cost of traditional methods and achieving fast and accurate electromagnetic performance evaluation.

CN122287516APending Publication Date: 2026-06-26ZHEJIANG UNIV +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202610390175.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-27
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies are computationally expensive and time-consuming in evaluating the electromagnetic performance of microstrip lines and microstrip-like structures. They are difficult to evaluate impedance matching, insertion loss and resonance characteristics quickly and accurately over a wide bandwidth. Furthermore, traditional methods rely on full-wave simulation, which results in high computational overhead.

Method used

A convolutional neural network is used to predict the complex modal eigenvalues ​​of a microstrip structure, and then combined with a second-order analytical model for extension to generate broadband electromagnetic performance calculation results, reducing reliance on full-wave simulation and lowering computational overhead.

Benefits of technology

It enables rapid calculation of broadband electromagnetic performance of microstrip lines and microstrip-like structures, reduces computational overhead, improves evaluation efficiency, and is suitable for rapid pre-evaluation and scheme selection in the EMC design stage.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a broadband electromagnetic performance rapid calculation method for a microstrip line and a microstrip-like two-port structure. The method relates to the technical field of electromagnetic calculation and electromagnetic compatibility aided design, and comprises the following steps: obtaining layout data of a to-be-tested microstrip port conductor and preprocessing the layout data to generate a binary layout image; inputting the binary layout image into a pre-trained convolutional neural network, and outputting a real number coding prediction vector of a complex mode characteristic value of a dominant mode at a preset sampling frequency point; carrying out destandardization and decoding on the prediction vector to obtain a complex mode characteristic value sample; identifying the complex modal characteristic value sample based on a second-order analytical model, and analyzing and continuating to obtain the broadband modal impedance of the target frequency band; a port impedance matrix is obtained according to the reconstruction relation, and broadband scattering parameters and electromagnetic performance results are converted and output. According to the method, the full-wave frequency scanning calculation overhead can be greatly reduced, and the micro-strip line simulation efficiency and the EMC design iteration speed are improved.
Need to check novelty before this filing date? Find Prior Art