Neural Network-Based Phase Estimation for Antenna Array Using Radiation Power Pattern

Iye, Tetsuya; Wyk, Pieter van; Matsumoto, Takahiro; Susukida, Yuki; Takaya, Shohei; Fujii, Yoshimi

doi:10.1109/lawp.2022.3167697

Cited by 13 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, it is still undetermined how well that algorithm scales with an increasing number of antenna elements and the complexity of the precoder. In most recent work, Iye et al [7] propose a fully-connected DNN, which utilises a large dataset consisting of measured beam patterns. Once the computationally extensive DNN is trained, the phase errors in the array are estimated using only a single beam pattern as an input.…”

Section: Related Work and Historical Developmentmentioning

confidence: 99%

“…smoothness, periodicity, non-linearity) of GPs are encoded by covariance kernels and their hyperparameters 𝜃, which can be optimised by maximizing the marginal likelihood of the data, conditioned on 𝜃 and x. An example of a commonly used covariance is a rational quadratic (RQ) kernel, (7) where 𝜃 includes length-scale ℓ, magnitude 𝜎 2 and 𝛼 that determines the relative weighting of the large-scale and small-scale variations:…”

Section: Gaussian Process Regressionmentioning

confidence: 99%

See 1 more Smart Citation

Antenna Array Calibration Via Gaussian Process Models

Tambovskiy¹,

Fodor²,

Tullberg³

2023

Preprint

View full text Add to dashboard Cite

Antenna array calibration is necessary to maintain the high fidelity of beam patterns across a wide range of advanced antenna systems and to ensure channel reciprocity in time division duplexing schemes. Despite the continuous development in this area, most existing solutions are optimised for specific radio architectures, require standardised over-the-air data transmission, or serve as extensions of conventional methods. The diversity of communication protocols and hardware creates a problematic case, since this diversity requires to design or update the calibration procedures for each new advanced antenna system. In this study, 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, based on near-field measurements, that captures the underlying hardware impairments corresponding to each radiating element, their positional offsets, as well as the mutual coupling effects between antenna elements. Secondly, Gaussian process regression is used to form models from a sparse set of the aforementioned near-field data. Once deployed, the learned non-parametric models effectively serve to continuously transform the beamforming weights of the system, resulting in corrected beam patterns. Lastly, we demonstrate the viability of the described methodology for both digital and analog beamforming antenna arrays of different scales and discuss its further extension to support real-time operation with dynamic hardware impairments.

show abstract

Section: Related Work and Historical Developmentmentioning

confidence: 99%

Section: Gaussian Process Regressionmentioning

confidence: 99%

Antenna Array Calibration Via Gaussian Process Models

Tambovskiy¹,

Fodor²,

Tullberg³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, the neural network-based models are employed to evaluate the phase of each radiating element from the radiation power pattern of a phased array antenna. 8 Inspired by the investigated applications of ML technique, we propose the neural network-based IDM to estimate the near-field (NF) and far-field (FF) radiation patterns of EUT.…”

Section: Introductionmentioning

confidence: 99%

“…2 Thus, infinitesimal dipole (ID) modeling has been proposed as an attractive alternative to overcome the limitation above because it efficiently characterizes the radiation of electromagnetic sources. [2][3][4][5][6][7][8] The electric and magnetic dipoles on the surface of the EUT modeled have substituted the EMI source causing undesired near-field coupling and far-field radiation. 3 Furthermore, spatial ID modeling (IDM) has been proposed in Reuge et al 4 and Clauzier et al 5 where the properties (position, magnitude, orientation, etc.)…”

Section: Introductionmentioning

confidence: 99%

Deep neural network‐based infinitesimal dipole modeling using either near or far electric‐field

Park,

Kim,

Cho

et al. 2024

Micro & Optical Tech Letters

View full text Add to dashboard Cite

This paper presents the deep neural network‐based infinitesimal dipole model using either near‐ or far‐field radiation patterns. Based on the radiating characteristic of an infinitesimal dipole, we generated a data set including near and far field radiation patterns corresponding to the phases of infinitesimal dipoles. We used the data set to train and validate the deep neural network (DNN) model. After checking the statistic of the fit function and the average error in expecting the phases of the infinite dipoles, we conclude that the proposed infinitesimal dipole modeling using DNN is sufficient to predict the characteristics of electromagnetic radiation.

show abstract

“…Te rapid development of deep learning technology [14][15][16] has drawn the attention of numerous antenna researchers, resulting in the creation of several neural network frameworks aimed at addressing challenges in the feld of antenna [1,17]. When it comes to radiation pattern synthesis, a variety of neural network methods have been proposed and developed [18][19][20], which can be broadly classifed into two main types. Te frst category is the numerous training samples driven method.…”

Section: Introductionmentioning

confidence: 99%

A High-Efficient Method for Synthesizing Multiple Antenna Array Radiation Patterns Simultaneously Based on Convolutional Neural Network

Zhang,

Shi,

Bai

2023

International Journal of Antennas and Propagation

View full text Add to dashboard Cite

This paper proposes a high-efficient method that utilizes deep learning technology for synthesizing multiple antenna array radiation patterns simultaneously. More in details, the mathematical feasibility of using neural networks to optimize and synthesize radiation patterns of antenna arrays is demonstrated. Boundary functions are designed to reshape the important characteristics of target radiation patterns and transform them into a two-channel mask matrix, allowing for the simultaneous input of multiple target radiation patterns into the neural network without sacrificing computational efficiency. During training, the cost function is designed to represent the difference between each synthesized radiation pattern and the corresponding target radiation pattern, guiding self-learning. The main framework of the method is a convolutional neural network, where the convolutional layer is used to reduce the expansion of input parameters due to the simultaneous input of multiple mask matrices. Simulation experiments have been conducted to synthesize multiple incoherent target radiation patterns simultaneously on a patch antenna array layout, and the computation time is compared with the combined time required to compute each one individually. The results demonstrate that this method offers the advantage of computational efficiency for simultaneous synthesis of multiple incoherent radiation patterns.

show abstract

Neural Network-Based Phase Estimation for Antenna Array Using Radiation Power Pattern

Cited by 13 publications

References 22 publications

Antenna Array Calibration Via Gaussian Process Models

Antenna Array Calibration Via Gaussian Process Models

Deep neural network‐based infinitesimal dipole modeling using either near or far electric‐field

A High-Efficient Method for Synthesizing Multiple Antenna Array Radiation Patterns Simultaneously Based on Convolutional Neural Network

Contact Info

Product

Resources

About