HyperHyperNetworks for the Design of Antenna Arrays
- URL: http://arxiv.org/abs/2105.03838v1
- Date: Sun, 9 May 2021 05:21:28 GMT
- Title: HyperHyperNetworks for the Design of Antenna Arrays
- Authors: Shahar Lutati, Lior Wolf
- Abstract summary: We present deep learning methods for the design of arrays and single instances of small antennas.
In the case of a single antenna, the solution is based on a composite neural network that combines a simulation network, a hypernetwork, and a refinement network.
The learning objective is based on measuring the similarity of the obtained radiation pattern to the desired one.
- Score: 91.3755431537592
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: We present deep learning methods for the design of arrays and single
instances of small antennas. Each design instance is conditioned on a target
radiation pattern and is required to conform to specific spatial dimensions and
to include, as part of its metallic structure, a set of predetermined
locations. The solution, in the case of a single antenna, is based on a
composite neural network that combines a simulation network, a hypernetwork,
and a refinement network. In the design of the antenna array, we add an
additional design level and employ a hypernetwork within a hypernetwork. The
learning objective is based on measuring the similarity of the obtained
radiation pattern to the desired one. Our experiments demonstrate that our
approach is able to design novel antennas and antenna arrays that are compliant
with the design requirements, considerably better than the baseline methods. We
compare the solutions obtained by our method to existing designs and
demonstrate a high level of overlap. When designing the antenna array of a
cellular phone, the obtained solution displays improved properties over the
existing one.
Related papers
- Compositional Generative Inverse Design [69.22782875567547]
Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem.
We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples.
In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
arXiv Detail & Related papers (2024-01-24T01:33:39Z) - Image Classifier Based Generative Method for Planar Antenna Design [33.121376096111355]
We propose a method to extend the antenna design on printed circuit boards (PCBs) for more engineers of interest.
By taking two separate steps to decide their geometric dimensions and positions, antenna prototypes can be facilitated with no experience required.
arXiv Detail & Related papers (2023-12-16T19:43:05Z) - NeuRBF: A Neural Fields Representation with Adaptive Radial Basis
Functions [93.02515761070201]
We present a novel type of neural fields that uses general radial bases for signal representation.
Our method builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals.
When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.
arXiv Detail & Related papers (2023-09-27T06:32:05Z) - Multi-agent Reinforcement Learning with Graph Q-Networks for Antenna
Tuning [60.94661435297309]
The scale of mobile networks makes it challenging to optimize antenna parameters using manual intervention or hand-engineered strategies.
We propose a new multi-agent reinforcement learning algorithm to optimize mobile network configurations globally.
We empirically demonstrate the performance of the algorithm on an antenna tilt tuning problem and a joint tilt and power control problem in a simulated environment.
arXiv Detail & Related papers (2023-01-20T17:06:34Z) - Antenna Array Calibration Via Gaussian Process Models [0.0]
Antenna array calibration is necessary to maintain the high fidelity of beam patterns across a wide range of advanced antenna systems.
We formulate antenna calibration in an alternative way, namely as a task of functional approximation, and address it via Bayesian machine learning.
Our contributions are three-fold. Firstly, we define a parameter space, that captures the underlying hardware impairments corresponding to each radiating element, their positional offsets, as well as the mutual coupling effects between antenna elements.
Once deployed, the learned non-parametric models effectively serve to continuously transform the beamforming weights of the system, resulting in corrected beam patterns.
arXiv Detail & Related papers (2023-01-16T19:40:50Z) - A Machine Learning Generative Method for Automating Antenna Design and
Optimization [9.438718097561061]
We introduce a flexible geometric scheme with the concept of mesh network that can form any arbitrary shape by connecting different nodes.
For a dual resonance antenna design with wide bandwidth, our proposed method is in par with Trust Region Framework and much better than the other mature machine learning algorithms.
arXiv Detail & Related papers (2022-02-28T21:30:37Z) - A Reusable Framework Based on Reinforcement Learning to Design Antennas
for Curved Surfaces [0.0]
This work pursues a methodology to identify small antennas and consequently presents some similarities.
The objective is to identify antennas that can be efficiently mounted on the surface of metal tubes.
The motivation is to reduce the visual impact and optimize the radiation pattern of the antenna.
arXiv Detail & Related papers (2020-11-24T14:35:23Z) - Learning to Beamform in Heterogeneous Massive MIMO Networks [48.62625893368218]
It is well-known problem of finding the optimal beamformers in massive multiple-input multiple-output (MIMO) networks.
We propose a novel deep learning based paper algorithm to address this problem.
arXiv Detail & Related papers (2020-11-08T12:48:06Z) - Deep Learning Optimized Sparse Antenna Activation for Reconfigurable
Intelligent Surface Assisted Communication [54.72880662623178]
Reconfigurable intelligent surface (RIS) usually works in passive mode.
Due to the cascaded channel structure and the lack of signal processing ability, it is difficult for RIS to obtain the individual channel state information.
In this paper, we add signal processing units for a few antennas at RIS to partially acquire the channels.
arXiv Detail & Related papers (2020-09-03T12:27:22Z) - Machine Learning-aided Design of Thinned Antenna Arrays for Optimized
Network Level Performance [19.17059890143665]
We propose a Machine Learning framework that enables a simulation-based optimization of the antenna design.
We show how learning methods are able to emulate a complex simulator with a modest dataset.
Overall, our results show that the proposed methodology can be successfully applied to the optimization of thinned antenna arrays.
arXiv Detail & Related papers (2020-01-25T15:34:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.