Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

Xiao, Yuqi; Leung, Kwok Wa; Lu, Kai; Leung, C. M.

doi:10.1109/tap.2022.3146860

Cited by 7 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, ANN are known as a powerful modeling tool and have been widely studied and used in the design and optimization of RF circuits such as filters [13] [14], sensor [15], loop antenna [16], dual and multi-band antennas [17]- [21], ultra wideband antenna [22], antenna in dielectric environment [23], dielectric resonators [24] [25], base station antenna tilting [26], Yagi Uda antenna [27] and array antennas [28]- [34]. Through a training process, the ANN are capable to learn, map and generalize complex nonlinear relationship between synthesis variables and their corresponding electromagnetic (EM) responses.…”

Section: Introductionmentioning

confidence: 99%

A Global Optimization Method for Wideband and Small Supergain Arrays Design Using Artificial Neural Network

Touhami,

Collardey,

Sharaiha

2023

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

This paper introduces an efficient approach for compact, wideband and supergain arrays design using artificial neural network (ANN) based optimization. The proposed method optimize at the same time the distance inter-elements of the array antenna, its input impedance as well as its directivity. Such global optimization considerably improves the performances of superdirective arrays in terms of gain, bandwidth and efficiency. The proposed method is used afterwards to synthesize a three-elements array using two different unit elements. The comparison of the achieved performances and the Harrington limit reveals that the developed antennas can be qualified as supergain antennas. To our knowledge, this is the first demonstration of a wideband supergain array with more than two elements in the open literature. To validate the results, a prototype was manufactured and measured. The measurements show that the antenna has a wide impedance bandwidth of 22.6 %, a peak directivity of 8.3 dBi and a total efficiency greater than 80%.

show abstract

Section: Introductionmentioning

confidence: 99%

A Global Optimization Method for Wideband and Small Supergain Arrays Design Using Artificial Neural Network

Touhami,

Collardey,

Sharaiha

2023

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

show abstract

“…The feedforward DNN is applied to microwave passive components such as a three-pole H-plane filter and a fifth-order waveguide bandpass filter in [19]. The mode recognition of dielectric resonator antenna is performed using a DNN technique to improve the antenna's performance in [20]. The DNN-based approach has proven to be highly effective in modeling microwave circuits, and the researchers are additionally exploring the application of the DNN-based approach in a high-speed interconnect design in [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

Fast Synthesis Method for High-Dimensional Electromagnetic Bandgap Structure Using Deep Neural Network for Power/Ground Noise Suppression

Sim

Kim

2023

Electronics

View full text Add to dashboard Cite

A deep neural network (DNN)-based method is proposed for the fast synthesis of a high-dimensional electromagnetic bandgap structure (HD-EBG) suppressing the power/ground noise in high-speed packages and printed circuit boards (PCBs). In recent EBG structures, a highly flexible design with high dimensionality is required, which is challenging to rapidly achieve an optimal solution. The proposed synthesis method is developed to solve this issue efficiently. The DNN hyperparameter optimization (HPO) associated with the HD-EBG structure is devised using the orthogonal array of the Taguchi method. By using this approach, the search space for HPO is reduced. For the efficient synthesis of the HD-EBG structure, an inverse modeling approach based on a DNN forward model and genetic algorithm optimization is proposed. The proposed DNN inverse modeling (DIM) is applied to two design examples where the HD-EBG structures with a constant fractional bandwidth and stopband bandwidth extension are synthesized. In the demonstration cases, the proposed DIM achieves the fast and accurate synthesis of the HD-EBG structures compared to the conventional method. With the proposed method, the synthesis time is maximally reduced up to 99.8% compared to conventional synthesis based on the forward model of full-wave simulation.

show abstract

“…In [23], a hybrid DNN model was proposed to model and simulate microwave filters, leading to a higher accurate result with fewer samples than traditional ANNs. To further improve training efficiency, domain knowledge was employed to assist DNNs with the design of metalens antenna [24], metasurfaces [25][26][27][28], frequency selective surface (FSS) [29], [30], mode recognition [31], and reflectarray [32]. Moreover, a multibranch DNN-assisted strategy [33] was presented to enhance the algorithm robustness by searching for multiple different branches.…”

mentioning

confidence: 99%

Fully Automated Design Method Based on Reinforcement Learning and Surrogate Modeling for Antenna Array Decoupling

Wei

Zhou

Wang

et al. 2023

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

Modern electromagnetic (EM) device design generally relies on extensive iterative optimizations by designers using simulation software (e.g. CST), which is a very timeconsuming and tedious process. To relieve human engineers and boost productivity, we proposed a machine learning framework to solve the problem of automated design for EM tasks. The proposed approach combines advanced reinforcement learning (RL) algorithms and deep neural networks (DNNs) in an attempt to simulate the decision-making process of human designers to realize automation learning. Specifically, the RL-based agent can interact with the EM design software without engaging human designers, allowing for automated design. Besides, the data accumulated during EM software simulation in the early design stage are reused as training data to build a DNN surrogate model to replace the time-consuming EM simulation and further accelerate the training of RL to achieve better optimization of EM design. Two types of antenna array decoupling including 1×2 and 1×4 arrays working at 3.5 GHz are used as test vehicles to validate the proposed method. The decoupling metasurfaces designed by the proposed fully automated method based on RL showed satisfactory results comparable to the results achievable by human designers. This indicates that the proposed method can be used to build powerful tools to boost the design efficiency of EM devices.

show abstract

Mode Recognition of Rectangular Dielectric Resonator Antenna Using Artificial Neural Network

Cited by 7 publications

References 19 publications

A Global Optimization Method for Wideband and Small Supergain Arrays Design Using Artificial Neural Network

A Global Optimization Method for Wideband and Small Supergain Arrays Design Using Artificial Neural Network

Fast Synthesis Method for High-Dimensional Electromagnetic Bandgap Structure Using Deep Neural Network for Power/Ground Noise Suppression

Fully Automated Design Method Based on Reinforcement Learning and Surrogate Modeling for Antenna Array Decoupling

Contact Info

Product

Resources

About