Triple-Band Patch Antenna Design with Machine Learning Algorithms
Abstract views: 4
/ 
PDF downloads: 4
Keywords:
Antenna Design, Machine Learning, Triple-Band, Microstrip Patch, Wideband, CommunicationAbstract
Wireless communication is crucial in many fields, such as engineering, transportation, inventory
tracking, industrial automation, IoT, and mobile communication, due to advancing technology. Antennas
are essential for signal transmission and reception in wireless communication, playing a vital role in
ensuring the effective operation and efficiency of these technologies. Antenna design is essential for
achieving objectives such as enhancing efficiency, improving communication quality, and extending
communication range in communication systems. Machine learning algorithms can serve as powerful tools
for optimizing the antenna design process and achieving more accurate results. This study presents the
design of an antenna that operates in three bands and can be used in wireless communication technology
with the support of machine learning. The antenna was designed using an FR-4 substrate with a dielectric
constant of 4.4, a loss tangent of 0.02, and a thickness of 1.6 mm. Copper was used for the patch and ground
sections. The antenna provides three impedance bandwidths: 856.81 MHz with a bandwidth of 158.27
MHz, 1298.4 MHz with a bandwidth of 38.5 MHz, and 2164.8 GHz with a bandwidth of 958.5 MHz. The
geometric parameters of the antenna were input into the ML model. The data set comprises 1024 samples
and the output data represents the magnitude of the reflection parameter (S11). Twelve regression
algorithms were applied and compared, with the Random Forests algorithm producing the best result.
Downloads
References
Palandöken, M., Sondas, A. (2014). Compact Metamaterial Based Bandstop Filter. Microwave Journal, 57(10).
Palandoken, M., Gocen, C. (2019). A modified Hilbert fractal resonator based rectenna design for GSM900 band RF energy harvesting applications. International Journal of RF and Microwave Computer‐Aided Engineering, 29(1), e21643.
Rymanov, V., Palandöken, M., Lutzmann, S., Bouhlal, B., Tekin, T., & Stöhr, A. (2012, September). Integrated photonic 71–76 GHz transmitter module employing high linearity double mushroom-type 1.55 μm waveguide photodiodes. In 2012 IEEE International Topical Meeting on Microwave Photonics (pp. 253-256).
Al-Gburi, A. A., Zakaria, Z., Palandoken, M., Ibrahim, I. M., Althuwayb, A. A., Ahmad, S., & Al-Bawri, S. S. (2022). Super compact UWB monopole antenna for small IoT devices. Comput. Mater. Contin, 73, 2785-2799.
Belen, A., Güneş, F., Mahouti, P., & Palandöken, M. (2020). A novel design of high performance multilayered cylindrical dielectric lens antenna using 3D printing technology. International Journal of RF and Microwave Computer‐Aided Engineering, 30(1), e21988.
Wang, B. (2015). A compact antenna design for UHF RFID applications. Progress In Electromagnetics Research Letters, 53, 83-88.
Irsigler, M., Hein, G. W., & Schmitz-Peiffer, A. (2004). Use of C-Band frequencies for satellite navigation: benefits and drawbacks. GPS Solutions, 8, 119-139.
Al-Hraishawi, H., Chougrani, H., Kisseleff, S., Lagunas, E., & Chatzinotas, S. (2022). A survey on nongeostationary satellite systems: The communication perspective. IEEE Communications Surveys & Tutorials, 25(1), 101-132.
Balanis, C. A. (2016). Antenna theory: analysis and design. John wiley & sons.
Ranjan, P., Yadav, S., Gupta, H., & Bage, A. (2023). Design and Development of Machine Learning Assisted Cylindrical Dielectric Resonator Antenna.
Mahouti, M., Kuskonmaz, N., Mahouti, P., Belen, M. A., & Palandoken, M. (2020). Artificial neural network application for novel 3D printed nonuniform ceramic reflectarray antenna. International journal of numerical modelling: electronic networks, devices and fields, 33(6), e2746.
