Multiparameter Modeling With ANN for Antenna Design

Xiao, Liye; Shao, Wei; Jin, Fu-Long; Wang, Bing‐Zhong

doi:10.1109/tap.2018.2823775

Cited by 122 publications

(55 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using these algorithms and dataset of a considerable size, a model representing the mapping function of the non‐linear relationship between the antenna's geometrical parameters and characteristics can be derived. The most widely used ML algorithms for antenna design are ANNs 92‐95 and SVR 96,97 . Other regression methods that are less widely used are LR, LASSO, Gaussian process regression (GPR), 98,99 and Kriging Regression 100,101 .…”

Section: Building Regression Models With Learning Algorithmsmentioning

confidence: 99%

A review on the design and optimization of antennas using machine learning algorithms and techniques

Misilmani

Naous

Khatib

2020

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

This paper presents a focused and comprehensive literature survey on the use of machine learning (ML) in antenna design and optimization. An overview of the conventional computational electromagnetics and numerical methods used to gain physical insight into the design of the antennas is first presented. The major aspects of ML are then presented, with a study of its different learning categories and frameworks. An overview and mathematical briefing of regression models built with ML algorithms is then illustrated, with a focus on those applied in antenna synthesis and analysis. An in‐depth overview on the different research papers discussing the design and optimization of antennas using ML is then reported, covering the different techniques and algorithms applied to generate antenna parameters based on desired radiation characteristics and other antenna specifications. Various investigated antennas are sorted based on antenna type and configuration to assist the readers who wish to work with a specific type of antennas using ML.

show abstract

Section: Building Regression Models With Learning Algorithmsmentioning

confidence: 99%

A review on the design and optimization of antennas using machine learning algorithms and techniques

Misilmani

Naous

Khatib

2020

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

show abstract

“…In one of the recent studies, a metamaterial absorber structure is designed and integrated to a four-element array antenna for 1.27 GHz band by Zhang et al [14]. With these developed techniques, artificial neural networks provide accurate solutions and are used in many areas [16][17][18][19][20]. Srivastava et al used artificial neural network for analyzing and estimating microstrip circular patch antenna parameters in S frequency band regime [16].…”

Section: Of 10mentioning

confidence: 99%

“…In the same way, Nayak and Kumar used a artificial neural network approach to design a microstrip patch antenna with possible optimization values [18]. In another study, a novel artificial neural network model was developed to estimate antenna performance parameters in X band antenna applications [19]. As shown in a literature review, various structures were designed and developed for reducing the mutual coupling of cross antennas, while neural network approaches were used to enhance and estimate antenna performance parameters.…”

Section: Of 10mentioning

confidence: 99%

Mutual Coupling Reduction of Cross-Dipole Antenna for Base Stations by Using a Neural Network Approach

et al. 2020

View full text Add to dashboard Cite

In this manuscript, a resonator layer is presented for the purpose of reducing the mutual coupling effect between each antenna element of a cross dipole antenna. In design processes, an artificial neural network approach was used for various resonator designs. In the operating frequency band of 2.2–2.7 GHz, 48 different 6 × 6 resonator layers were created and integrated into the cross dipole antenna to reduce transmission and improve isolation between each antenna elements. Moreover, when training an artificial neural network in the Matlab program, 48 different resonator layers were used with the return losses and transmission values of cross dipole antenna elements. After training process, eight unknown resonator designs were tested and accurate results were obtained. Finally, one of the resonator planes, which was obtained from the artificial neural network, was fabricated and experimentally tested, then an accurate result was obtained. This study provides a good solution, especially for improving isolation in multiport antenna systems, using an artificial neural network approach.

show abstract

“…Here, the back propagation learning algorithm [10]is used which is also called the gradient descent algorithm that provides the modification in w ij(k) in the form of weighted connection among neurons iand j in this way: ∆ = α + µ∆ (k -1)…………… (2) Where α denotes the learning coefficient, x j represent the input value, µ designates as the momentum coefficient, and belongs to a term depending on whether neuron iis a hidden neuron or a output neuron [11] [12]. In the training of neural network, gradient descent with adaptive learning rate algorithm is used and Kfold cross-validation is used for the test result to be more valuable .This method is used for finding the best ANN structural design.…”

Section: Optimization Using Neural Networkmentioning

confidence: 99%

Design and Optimization of Microstrip Patch Antenna using Artificial Neural Networks

2019

IJITEE

View full text Add to dashboard Cite

In this paper a Neural Network model for the design of a Microstrip Patch Antenna for an Ultrawideband frequency range is presented. The reduced ground size is used to enhance bandwidth in proposed design. The results obtained from the proposed method are compared with the results of EM simulation software and are found to be in good agreement. The advantage of the proposed method lies with the fact that the various parameters required for the design of a Microstrip Patch Antenna at a particular frequency of interest can be easily extracted without going into the rigorous time consuming, iterative design procedures using a costly software package. In the paper staircase patch design is considered for ultra-wideband matching of Antenna. The results obtained from artificial neural network when compared with experimental and simulation results, found satisfactory and also it is concluded that Radial Basis Function (RBF) network is more accurate and fast for the proposed design.

show abstract

Multiparameter Modeling With ANN for Antenna Design

Cited by 122 publications

References 34 publications

A review on the design and optimization of antennas using machine learning algorithms and techniques

A review on the design and optimization of antennas using machine learning algorithms and techniques

Mutual Coupling Reduction of Cross-Dipole Antenna for Base Stations by Using a Neural Network Approach

Design and Optimization of Microstrip Patch Antenna using Artificial Neural Networks

Contact Info

Product

Resources

About