Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications
Phased Array Antenna (PAA) technology plays an important role in fields such as radar, 5G and satellite or any application which requires wide bandwidth and high gain. However, achieving such design is a difficult and complex task that requires an accurate calculation and combination of results obta...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10285868/ |
_version_ | 1797654045653991424 |
---|---|
author | Mehmet Akif Tulum Ahmet Serdar Turk Peyman Mahouti |
author_facet | Mehmet Akif Tulum Ahmet Serdar Turk Peyman Mahouti |
author_sort | Mehmet Akif Tulum |
collection | DOAJ |
description | Phased Array Antenna (PAA) technology plays an important role in fields such as radar, 5G and satellite or any application which requires wide bandwidth and high gain. However, achieving such design is a difficult and complex task that requires an accurate calculation and combination of results obtained for varying phase and amplitude of each unit and coupling effects between these elements of the PAA structure is a task that can only be obtained using full wave EM simulation tools. This comes at the price of a significant increase for the computational cost of the design process which is a well-known drawback of forward EM modeling of microwave stages most especially in case of repetitive analysis’s such as yield analyses or optimization tasks. Data-driven surrogate models have emerged as a powerful and versatile solution that bridges the gap between computationally expensive simulations and rapid, reliable prediction models suitable for deployment in applications such as optimization and/or yield analyses. Herein, for having a high-performance broadband PAA for millimeter band in a computationally efficient manner, artificial intelligence based surrogate model assisted optimization approach is deployed. A series of state-of-the-art surrogate modeling algorithms are deployed to create a surrogate model of the studied PAA design for the prediction of radiation pattern characteristic with respect to the input phase values of each array element. As a result, a drastic reduction in computational time of almost 90% for the optimization of three PAA designs is achieved. Thus, the proposed approach offers promising avenues for further exploration in computational electromagnetics, most especially in simulation expensive problems with complex designs. |
first_indexed | 2024-03-11T16:53:41Z |
format | Article |
id | doaj.art-b607c5d2d86e41b4beab63f5d3e8588c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-11T16:53:41Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-b607c5d2d86e41b4beab63f5d3e8588c2023-10-20T23:00:25ZengIEEEIEEE Access2169-35362023-01-011111441511442310.1109/ACCESS.2023.332473310285868Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band ApplicationsMehmet Akif Tulum0https://orcid.org/0000-0003-2844-7798Ahmet Serdar Turk1https://orcid.org/0000-0002-7806-5467Peyman Mahouti2https://orcid.org/0000-0002-3351-4433Department of Electronic and Communication Engineering, Yıldız Technical University, Istanbul, TurkeyDepartment of Electronic and Communication Engineering, Yıldız Technical University, Istanbul, TurkeyDepartment of Electronic and Communication Engineering, Yıldız Technical University, Istanbul, TurkeyPhased Array Antenna (PAA) technology plays an important role in fields such as radar, 5G and satellite or any application which requires wide bandwidth and high gain. However, achieving such design is a difficult and complex task that requires an accurate calculation and combination of results obtained for varying phase and amplitude of each unit and coupling effects between these elements of the PAA structure is a task that can only be obtained using full wave EM simulation tools. This comes at the price of a significant increase for the computational cost of the design process which is a well-known drawback of forward EM modeling of microwave stages most especially in case of repetitive analysis’s such as yield analyses or optimization tasks. Data-driven surrogate models have emerged as a powerful and versatile solution that bridges the gap between computationally expensive simulations and rapid, reliable prediction models suitable for deployment in applications such as optimization and/or yield analyses. Herein, for having a high-performance broadband PAA for millimeter band in a computationally efficient manner, artificial intelligence based surrogate model assisted optimization approach is deployed. A series of state-of-the-art surrogate modeling algorithms are deployed to create a surrogate model of the studied PAA design for the prediction of radiation pattern characteristic with respect to the input phase values of each array element. As a result, a drastic reduction in computational time of almost 90% for the optimization of three PAA designs is achieved. Thus, the proposed approach offers promising avenues for further exploration in computational electromagnetics, most especially in simulation expensive problems with complex designs.https://ieeexplore.ieee.org/document/10285868/Artificial intelligencedata driven modellingsurrogate modellingoptimizationphased array antenna |
spellingShingle | Mehmet Akif Tulum Ahmet Serdar Turk Peyman Mahouti Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications IEEE Access Artificial intelligence data driven modelling surrogate modelling optimization phased array antenna |
title | Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications |
title_full | Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications |
title_fullStr | Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications |
title_full_unstemmed | Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications |
title_short | Data Driven Surrogate Modeling of Phase Array Antennas Using Deep Learning for Millimetric Band Applications |
title_sort | data driven surrogate modeling of phase array antennas using deep learning for millimetric band applications |
topic | Artificial intelligence data driven modelling surrogate modelling optimization phased array antenna |
url | https://ieeexplore.ieee.org/document/10285868/ |
work_keys_str_mv | AT mehmetakiftulum datadrivensurrogatemodelingofphasearrayantennasusingdeeplearningformillimetricbandapplications AT ahmetserdarturk datadrivensurrogatemodelingofphasearrayantennasusingdeeplearningformillimetricbandapplications AT peymanmahouti datadrivensurrogatemodelingofphasearrayantennasusingdeeplearningformillimetricbandapplications |