A taguchi neural network-based optimization of a dual-port, dual-band MIMO antenna encompassing the 28/34 GHz millimeter wave regime

被引：0

作者：

Dwivedi, Ajay Kumar ^{[1
]}

Singh, Vivek ^{[1
]}

Alzahrani, Yazeed ^{[2
]}

Chaitanya, R. Krishna ^{[3
]}

Singh, Suyash Kumar ^{[4
]}

Singh, Subhav ^{[5
]}

Parashar, Komal ^{[6
]}

Tolani, Manoj ^{[7
]}

机构：

[1] Nagarjuna Coll Engn & Technol, Dept Elect & Commun Engn, Bengaluru, India

[2] Prince Sattam Bin Abdulaziz Univ Wadi Addwasir, Coll Engn, Dept Comp Engn & Informat, Wadi Addwasir, Saudi Arabia

[3] Sagi Ramakrishnam Raju Engn Coll, Dept Elect & Commun Engn, Bhimavaram, Andhra Pradesh, India

[4] Indian Inst Informat Technol Allahabad, Dept Elect & Commun, Prayagraj, Uttar Pradesh, India

[5] Chitkara Univ, Chitkara Ctr Res & Dev, Kalujhanda 174103, Himachal Prades, India

[6] Chitkara Univ, Ctr Res Impact & Outcome, Rajpura 140417, Punjab, India

[7] Manipal Inst Technol, Manipal Acad Higher Educ, Dept Informat & Commun Technol, Manipal, Karnataka, India

来源：

SCIENTIFIC REPORTS | 2025年 / 15卷 / 01期

关键词：

ARRAY; REDUCTION; SYSTEM;

D O I：

10.1038/s41598-025-90103-2

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

This study presents a novel printed antenna design that operates at the millimeter-wave frequencies of 28 and 34 GHz, which are crucial for the current and upcoming mobile communication generations. The radiating component in the antenna is a slot-etched rectangular ring that is fed through a stepped impedance microstrip line feed. Using advanced machine learning techniques, the design parameters of the suggested antenna have been fine-tuned to ensure optimal impedance matching at 28 GHz within the frequency range of 27.61-28.49 GHz. Additionally, the antenna also provides excellent impedance matching at 34.5 GHz within the frequency range of 33.61-34.27 GHz. Using the designated antenna, a Multiple Input Multiple Output (MIMO) system with two ports is constructed. The MIMO system's performance is evaluated by analyzing channel capacity loss (CCL), diversity gain (DG), and envelope correlation coefficient (ECC), which showcases outstanding outcomes. The study further explores the optimization of a antenna's structure using a Taguchi-based Neural Network (Taguchi NN) approach to predict the reflection coefficient (|S11|) across a frequency range of 27-35 GHz. By systematically varying the gap width (triangle w) and shift (triangle t), a dataset was generated and used to train the network. The optimal model configuration achieved a validation Mean Square Error (MSE) of 2.244 and an R-2 of 0.848 enabling reliable prediction of the reflection coefficient (|S11|) without extensive simulations. The findings further highlight the construction and experimental assessment of a single-element antenna and MIMO system, which exhibit excellent impedance matching across both lower and higher frequency bands. The antenna displays a maximum gain of 8.75 and 5.5 dBi at frequencies of 28 and 34 GHz, respectively. The recommended antenna exhibits excellent radiation efficiency across both lower and higher frequency bands, with rates of 98.46% and 99.17%, respectively. In addition, the experimental measurements of the coupling coefficients between the MIMO antenna systems indicate extremely low coupling values. This results in an efficient MIMO system that is well-suited for future millimeter-wave (mm-wave) applications.

引用

页数：19

共 33 条

[11] Wang Z., Zhao L., Cai Y., Zheng S., Yin Y., A Meta-surface antenna array decoupling (MAAD) Method for Mutual Coupling reduction in a MIMO Antenna System, Sci. Rep., 8, 1, (2018)
[12] Kumar N., Usha Kiran K., Meander-line electromagnetic bandgap structure for UWB MIMO antenna mutual coupling reduction in E-plane, AEU - Int. J. Electron. Commun., 127, (2020)
[13] Vasu Babu K., Anuradha B., Design of Wang shape neutralization line antenna to reduce the mutual coupling in MIMO antennas, Analog Integr. Circuits Signal. Process., 101, 1, pp. 67-76, (2019)
[14] Abdullah M., Et al., Isolation enhancement of MIMO antennas using shorting pins, J. Electromagn. Waves Appl, 33, 10, pp. 1249-1263, (2019)
[15] Jafargholi A., Jafargholi A., Choi J.H., Mutual Coupling Reduction in an Array of Patch Antennas Using CLL Metamaterial Superstrate for MIMO Applications, IEEE Trans. Antennas Propag., 67, 1, pp. 179-189, (2019)
[16] Singh S.K., Yadav A.N., Machine Learning Approach in Optimal localization of Tumor using a novel SIW-Based antenna for improvement of ablation zone in Hepatocellular Carcinoma, IEEE Access, 11, pp. 26964-26978, (2023)
[17] Qi-Jun Zhang K.C., Devabhaktuni V.K., Artificial neural networks for rf and microwave design-from theory to practice, IEEE Trans. Microw. Theory Tech, 51, 4, pp. 1339-1350, (2003)
[18] Rayas-Sanchez J.E., & EM-Based Optimization of Microwave Circuits Using Artificial Neural Networks, The State-Of-The-Art, 52, 1, pp. 420-435, (2004)
[19] Singh S.K., Yadav A.N., Novel tumor localization model and prediction of ablation zone using an intertwined helical antenna for the treatment of hepatocellular carcinoma, Int. J. Numer. Method Biomed. Eng., 39, 4, (2023)
[20] Jin J., Et al., Deep Neural Network Technique for High-Dimensional Microwave Modeling and Applications to Parameter Extraction of Microwave Filters, IEEE Trans. Microw. Theory Tech, 67, 10, pp. 4140-4155, (2019)

← 1 2 3 4 →