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

Liu, Anlan1; Leng, Maoheng2,3; Pan, Guangyuan4; Yu, Ming2,3

2022-07-01

10.1109/TMTT.2022.3184024

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES   Impact Factor & Quartile

0018-9480

1557-9670

A new artificial neural network (ANN) inverse modeling method with self-adaptive local surrogates, called ANN-SALS, is presented in this article, for a large-scale beam-forming network (BFN). To get accurate dimensions of the huge number of directional couplers, constituting a large BFN could be computationally expensive. Here, we develop an automated and more efficient algorithm to design multiple couplers with different specifications simultaneously using shared data for local surrogate modeling. While the result predicted by ANN serves as the starting point, a Gaussian process (GP) local surrogate model is built around it for fine-tuning. Then, ANN database is updated by selected GP training samples as well as the fine-tuned solution. After carefully setting the design specification, GP training data can be shared among the design of multiple couplers despite different specifications so that the design of one coupler is improved by the other ones. What is more, the size of region where GP is built is corrected by a quasi-sensitivity analysis method to improve the local optimization success rate. To verify the algorithm, four different couplers with different design requirements are designed, showing the proposed technique could unravel various multiple coupler design problems automatically and is much more efficient compared with existing methods.

Training Inverse problems Computational modeling Databases Directional couplers Scattering parameters Prediction algorithms Artificial neural network (ANN) directional coupler Gaussian process regression (GPR) multispecification design problem surrogate-assisted design

SCI ; EI

English

Corresponding

Shenzhen Key Laboratory of Electromagnetic (EM) Information[ZDSYS20210709113201005] ; National Natural Science Foundation of China[62103177]

Engineering

Engineering, Electrical & Electronic

WOS:000826058300001

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20222912379698

Directional couplers ; Gaussian distribution ; Gaussian noise (electronic) ; Neural networks ; Sensitivity analysis ; Specifications

Waveguides:714.3 ; Codes and Standards:902.2 ; Mathematics:921 ; Probability Theory:922.1 ; Mathematical Statistics:922.2

ENGINEERING

Web of Science

1.Chinese Univ Hong Kong, Dept Elect Engn, Hong Kong, Peoples R China
2.Southern Univ Sci & Technol, Shenzhen Key Lab EM Informat, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China
4.Linyi Univ, Dept Automat & Elect Engn, Linyi 276000, Shandong, Peoples R China

Liu, Anlan,Leng, Maoheng,Pan, Guangyuan,et al. Automatic Coupler Design Based on Artificial Neural Network With Self-Adaptive Local Surrogates[J]. IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES,2022,PP(99):1-15.

Liu, Anlan,Leng, Maoheng,Pan, Guangyuan,&Yu, Ming.(2022).Automatic Coupler Design Based on Artificial Neural Network With Self-Adaptive Local Surrogates.IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES,PP(99),1-15.

Liu, Anlan,et al."Automatic Coupler Design Based on Artificial Neural Network With Self-Adaptive Local Surrogates".IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES PP.99(2022):1-15.