Automatic Coupler Design Based on Artificial Neural Network With Self-Adaptive Local Surrogates

Liu, Anlan; Leng, Maoheng; Pan, Guangyuan; Yu, Ming

doi:10.1109/tmtt.2022.3184024

Cited by 6 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, NN can be used for repetitive designs once it is well-trained. Recently, in [7] and [8], NN inverse modeling is applied to the design of directional couplers. However, these approaches used conventional (shallow) NN techniques which are not suitable for high-dimensional problems with many input variables because the model training in this case becomes too complicated.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Neural Network for Design of Dual-Band Coupled-Line Trans-Directional Coupler

Sallam

Eldesouki

Attiya

2023

Preprint

View full text Add to dashboard Cite

A deep-learning-based model to automate the design of dual-band coupled-line trans- directional (CL-TRD) coupler can greatly improve upon the current techniques that rely on complicated analysis. In this paper, we propose a convolutional neural network (CNN), which is a type of deep learning, which can rapidly output the parameters of dual-band directional couplers corresponding to theoretical (ideal) specifications of the electrical parameters through an inverse model. The neural network training data is generated by the use of electromagnetic simulation tool HFSS by varying the geometrical design parameters of the coupler. In order to validate the robustness of the CNN inverse model, it is applied on a 3-dB dual-band CL-TRD coupler operating at 1.2/4 GHz, and compared with a shallow neural network namely, radial basis function neural network (RBFNN). The coupler parameters designed by both neural networks are verified by HFSS. The results reveal that the CNN simulated S-parameters and output ports phase difference are in good agreements with the ideal ones compared to those of RBFNN with more accuracy and speed. The designed coupler is fabricated and measured for verification.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Neural Network for Design of Dual-Band Coupled-Line Trans-Directional Coupler

Sallam

Eldesouki

Attiya

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, artificial neural network (ANN) techniques and optimization algorithms [26,27] have helped electronics designers to improve the performances of their devices [28][29][30][31][32], which also have been used in the designing of the couplers [33][34][35]. In [33], a feedforward network was used to predict the BLC transfer function.…”

Section: Introductionmentioning

confidence: 99%

A Compact Filtering Coupler with Unwanted Harmonic Rejection Using LC Composite Lines for Communication Systems Applications

Roshani

Yahya

Mezaal

et al. 2022

Systems

View full text Add to dashboard Cite

In this paper, new LC lumped components and composite lines are used to create a filtering branch line coupler (FBLC) with a small size and wide suppression band. New composite lines are proposed using applied LC lumped components, which are used as the coupler main branches. The proposed FBLC suppresses second to sixth harmonics with high attention level and provides a wide stopband from 1.6 GHz to 5 GHz with more than 20 dB of attention. The presented coupler is analyzed, designed, simulated, and implemented. The measured results show that the proposed FBLC correctly operates at 800 MHz with less than 0.25 dB of insertion loss. In addition, more than 29 dB of return loss and isolation is measured at operating frequency, which shows the correct performance of the proposed design. The size of the proposed FBLC is equal to 23.7 mm × 25.5 mm (0.086λ × 0.093λ), which shows an 87% size reduction. The proposed FBLC with the designed frequency can be used in the communication systems for narrow-band Internet of things (NB-IoT) and traffic control radar applications.

show abstract

Deep-learning-based neural network for design of a dual-band coupled-line trans-directional coupler

2023

View full text Add to dashboard Cite

Automatic Coupler Design Based on Artificial Neural Network With Self-Adaptive Local Surrogates

Cited by 6 publications

References 29 publications

Deep-Learning-Based Neural Network for Design of Dual-Band Coupled-Line Trans-Directional Coupler

Deep-Learning-Based Neural Network for Design of Dual-Band Coupled-Line Trans-Directional Coupler

A Compact Filtering Coupler with Unwanted Harmonic Rejection Using LC Composite Lines for Communication Systems Applications

Deep-learning-based neural network for design of a dual-band coupled-line trans-directional coupler

Contact Info

Product

Resources

About