Microstrip patch antenna modeling using neural networks with knowledge-based regularization

Date

2024-01-01

Author

Saçın, Ekin Su
Durgun, Ahmet Cemal

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

21
views

0
downloads

Cite This

Neural networks (NNs) have proven a useful surrogate model for the design and optimization of high frequency structures including antennas. Black-box NNs are known to have scalability and accuracy problems as the dimension of the problem increases. This study proposes knowledge-based regularization methods, referred to as derivative, spectral, and magnitude regularization to address these issues. The proposed methods utilize the functional properties of S-parameters to improve the accuracy and prevent unphysical predictions. The NNs are trained and tested using a data set of 5000 samples generated by Latin Hypercube Sampling and simulated by Ansys HFSS. The goodness of fit is evaluated using Relative Squared Error. Derivative and spectral regularizations reduce the RSE loss from 0.052 to 0.046 and 0.043, respectively. When combined with magnitude regularization, up to 17% and 88% reduction in loss and passivity violations can be achieved, at the expense of a 37% increase in training time. Moreover, 25% less data is required, to maintain a similar loss to the reference NN.

Subject Keywords

Microstrip patch antenna, Neural network, Regularization, Surrogate model

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85212408836&origin=inward
https://hdl.handle.net/11511/113263

Collections

Department of Electrical and Electronics Engineering, Article