Flat-plate crack antenna modelling approach based on SVMR

Abstract

The invention provides a method for modeling the planar slot antenna based on a supporting vector regression; according to the main mechanical structure parameters and value range of functional components of a planar slot antenna, Latin Hypercube Sample method is utilized to select proper test data, and then simulated numerical computation of electromagnetic fields is applied to modeled objects so as to obtain training samples for a model of the supporting vector regression and then to establish the model for the supporting vector regression of f(x)= (sigma) summation of i=1(a-a<*>)K(x,x)+b. A genetic algorithm is used for optimizing the parameters of the established model to obtain an optimal model, and then a test sample generated randomly is used for validating the performance of the sample. The method provided by the invention for modeling the planar slot antenna based on the supporting vector regression can accurately and rapidly estimate the electrical property values of the planar slot antenna with arbitrary structure parameters, avoid electromagnetic numerical computation, and solve mechanism research in influence of the mechanical structure factor of the planar slot antenna on the electrical property and the problem of design and optimization of the planar slot antenna, thus establishing a reliable foundation and basis for selecting the modeling and the processing precision of the planar slot antenna.

Description

technical field [0001] The invention relates to a non-mechanism modeling method in the field of microwave antenna engineering application research, more specifically, the invention relates to a method for establishing a plate crack antenna model based on a support vector regression machine. Background technique [0002] The flat plate slot antenna has significant advantages such as low sidelobe, high gain, small size, light weight, strong anti-interference ability and good installation conditions. With the improvement of the working frequency band, especially the millimeter-wave frequency band, its electrical performance is very sensitive to the fluctuation of mechanical structural factors, so the research on the mechanism of mechanical structural factors on the electrical performance of the planar slot antenna can improve its development level. Like other electromagnetic engineering applications, to accurately simulate the electrical performance of the physical structure of...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method that can accurately and quickly estimate the randomness of the flat-panel slot antenna, aiming at the problems that the complex and changeable mechanical structure factors of the existing flat-panel slot antenna have a great influence on the electrical performance index, the model parameters are difficult to determine, and the electromagnetic numerical calculation takes a long time. The electrical performance value under the condition of structural parameters can avoid a large number of electromagnetic field numerical calculation processes based on the non-mechanism modeling method of the support vector regression machine, so as to overcome the problem of difficult determination of the model parameters in the application of the support vector regression machine, so as to solve the problem of flat plate Research on the Influence Mechanism of Slot Antenna's Complex and Variable Mechanical Structure Factors on Electrical Performance

Images