Adjoint Sensitivity Optimization of Three-Dimensional Directivity-Enhancing, Size-Reducing GRIN Lenses

Whiting, Eric B.; Mackertich-Sengerdy, Galestan; Campbell, Sawyer D.; Soltani, Saber; Haack, Micah P.; Barrett, John P.; Withrow, Joshua W.; Bossard, Jeremy A.; Werner, Douglas H.

doi:10.1109/lawp.2022.3182900

Cited by 8 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, this is computationally expensive whenever full-wave electromagnetic (EM) models are used for system evaluation. Although there are novel synthesis techniques for design optimization of lens structures which demonstrate promising results 13 , 14 , in the case of array designs, including transmitarrays and reflectarrays, conducting the optimization process directly at the level of full-wave EM models is normally infeasible. Even if the computational model is set with the medium mesh density, the process might take months or years to complete 15 .…”

Section: Introductionmentioning

confidence: 99%

Optimal design of transmitarray antennas via low-cost surrogate modelling

Belen,

Caliskan,

Koziel

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Over the recent years, reflectarrays and transmitarrays have been drawing a considerable attention due to their attractive features, including a possibility of realizing high gain and pencil-like radiation patterns without the employment of complex feeding networks. Among the two, transmitarrays seem to be superior over reflectarrays in terms of achieving high radiation efficiency without the feed blockage. Notwithstanding, the design process of transmitarrays is more intricate due to the necessity of manipulating both the transmission phase and magnitude of its unit elements. For reliability, the design process has to be conducted at the level of full-wave electromagnetic models, which makes direct optimization prohibitive. The most widely used workaround is to employ surrogate modeling techniques to construct fast representations of the unit elements, yet the initial model setup cost is typically high and includes acquisition of thousands of training data points. In this paper, we propose a novel approach to cost-efficient design of transmitarrays. It is based on artificial-intelligence-enabled data-driven surrogates, which can be constructed using only a few hundreds of training data samples, while exhibiting the predictive power sufficient for reliable design. Our methodology is demonstrated by re-using the presented surrogate for the design of high-performance transmitarrays operating at various frequency ranges of 8–14 GHz, 22–28 GHz, and 28–36 GHz.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal design of transmitarray antennas via low-cost surrogate modelling

Belen,

Caliskan,

Koziel

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Conventional inverse design utilizes antenna geometry optimization, for which various techniques have emerged. One approach involves utilizing adjoint sensitivities in gradient-based topology optimization [7], [8]. However, this method is limited to convex optimization problems and lacks support in commercial EM solvers [9].…”

mentioning

confidence: 99%

Rapid Multi-Objective Inverse Design of Antenna Via Deep Neural Network Surrogate-Driven Evolutionary Optimization

Singh,

Panda,

Dash

et al. 2024

Preprint

View full text Add to dashboard Cite

Antenna synthesis is becoming increasingly challenging given the tight requirements for C-SWAP (cost, size, weight and power) reduction while maintaining stringent electromagnetic performance specifications. While recent reports have investigated developments in AI (primarily deep learning) to address this challenge, such methods have limited capability for multi-objective constrained inverse design and the ability to handle large shape sets. We present a multi-objective antenna synthesis methodology employing deep neural network surrogate-driven evolutionary algorithm. Specifically, we propose a branched-output convolutional neural network architecture for creating the surrogate model and showing its ability to predict multiple electromagnetic parameters over an operating frequency range. The proposed methodology and its synthesis capabilities are showcased by considering the set of polygonal-patch antennas for operation in the 2 to 3 GHz spectral band. Specifically, we report the design, fabrication and experimental characterization of three polygon-shaped patch antennas, each fulfilling different objectives, one being a single band with resonance at 2.45 GHz, the second antenna is dual-band with resonance at 2.2 GHz and 2.9 GHz, and the third one being wide-band centered around 2.7 GHz. The reported methodology enables rapid synthesis (in seconds), produces verifiable sound designs and is promising for furthering data-driven design methodologies for electromagnetic wave device synthesis.

show abstract