Recent Advances in em Parametric Modeling Using Combined Neural Network and Transfer Function
This paper provides an overview of the recent advances in electromagnetic (EM) modeling approaches using combined neural network and transfer function (neuro-transfer function or neuro-TF) and its application to antenna design. In this technique, neural networks are trained to learn the relationship between pole/residues of the transfer functions and geometrical parameters. After the modeling process, the trained model can be used to provide accurate and fast prediction of the EM behavior with geometrical parameters as variables. This technique is illustrated by a example of EM parametric modeling of an ultra-wideband antenna.
|Artificial neural networks (ANNs), parametric modeling, transfer function, ultra-wideband antenna|
|2019 International Symposium on Antennas and Propagation, ISAP 2019|
|Organisation||Department of Electronics|
Feng, F. (Feng), Zhang, W. (Wei), Zhang, J. (Jianan), Zhao, Z. (Zhihao), Jin, J. (Jing), & Zhang, Q.J. (2019). Recent Advances in em Parametric Modeling Using Combined Neural Network and Transfer Function. In 2019 International Symposium on Antennas and Propagation, ISAP 2019 - Proceedings.