A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling
This study investigates the use of deep learning techniques for building a generalized surrogate model that can accurately and very efficiently predict antenna performance parameters. Notably, we focus on applications where a substantial amount of simulation time is required and prior data is availa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10472507/ |
| _version_ | 1797243265556152320 |
|---|---|
| author | Md Rayhan Khan Constantinos L. Zekios Shubhendu Bhardwaj Stavros V. Georgakopoulos |
| author_facet | Md Rayhan Khan Constantinos L. Zekios Shubhendu Bhardwaj Stavros V. Georgakopoulos |
| author_sort | Md Rayhan Khan |
| collection | DOAJ |
| description | This study investigates the use of deep learning techniques for building a generalized surrogate model that can accurately and very efficiently predict antenna performance parameters. Notably, we focus on applications where a substantial amount of simulation time is required and prior data is available for deep learning use. Specifically, for these applications, we introduce deep learning models that efficiently and reliably model the near-field of the antenna. These models, in turn, accurately predict far-field properties and essential antenna metrics, such as the reflection coefficient. To demonstrate the efficiency of our method, the widely used rectangular patch antenna is considered, encompassing variations in several important geometrical parameters, dielectric constant, and frequency. Based on our results, the proposed model, once trained, is over 200 times faster than conventional full-wave simulations with a nominal average root mean square error (RMSE) of 0.0174 in predicting all the necessary antenna parameters, such as resonant frequency, radiation pattern, and directivity. |
| first_indexed | 2024-04-24T18:52:22Z |
| format | Article |
| id | doaj.art-0aa11ddef69e4c9fa0261b455f4178a5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:52:22Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0aa11ddef69e4c9fa0261b455f4178a52024-03-26T17:47:55ZengIEEEIEEE Access2169-35362024-01-0112397373974710.1109/ACCESS.2024.337721910472507A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate ModelingMd Rayhan Khan0https://orcid.org/0000-0001-9097-3540Constantinos L. Zekios1https://orcid.org/0000-0002-3195-8612Shubhendu Bhardwaj2Stavros V. Georgakopoulos3https://orcid.org/0000-0002-1626-6589Department of Electrical and Computer Engineering, Florida International University, Miami, FL, USADepartment of Electrical and Computer Engineering, Florida International University, Miami, FL, USADepartment of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USADepartment of Electrical and Computer Engineering, Florida International University, Miami, FL, USAThis study investigates the use of deep learning techniques for building a generalized surrogate model that can accurately and very efficiently predict antenna performance parameters. Notably, we focus on applications where a substantial amount of simulation time is required and prior data is available for deep learning use. Specifically, for these applications, we introduce deep learning models that efficiently and reliably model the near-field of the antenna. These models, in turn, accurately predict far-field properties and essential antenna metrics, such as the reflection coefficient. To demonstrate the efficiency of our method, the widely used rectangular patch antenna is considered, encompassing variations in several important geometrical parameters, dielectric constant, and frequency. Based on our results, the proposed model, once trained, is over 200 times faster than conventional full-wave simulations with a nominal average root mean square error (RMSE) of 0.0174 in predicting all the necessary antenna parameters, such as resonant frequency, radiation pattern, and directivity.https://ieeexplore.ieee.org/document/10472507/Antennaselectromagneticsdeep learningsurrogate modeling |
| spellingShingle | Md Rayhan Khan Constantinos L. Zekios Shubhendu Bhardwaj Stavros V. Georgakopoulos A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling IEEE Access Antennas electromagnetics deep learning surrogate modeling |
| title | A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling |
| title_full | A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling |
| title_fullStr | A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling |
| title_full_unstemmed | A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling |
| title_short | A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling |
| title_sort | deep learning convolutional neural network for antenna near field prediction and surrogate modeling |
| topic | Antennas electromagnetics deep learning surrogate modeling |
| url | https://ieeexplore.ieee.org/document/10472507/ |
| work_keys_str_mv | AT mdrayhankhan adeeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT constantinoslzekios adeeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT shubhendubhardwaj adeeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT stavrosvgeorgakopoulos adeeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT mdrayhankhan deeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT constantinoslzekios deeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT shubhendubhardwaj deeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling AT stavrosvgeorgakopoulos deeplearningconvolutionalneuralnetworkforantennanearfieldpredictionandsurrogatemodeling |