Research Article
BibTex RIS Cite

Selçuklu Yıldızı Şekilli Mikroşerit Anten İçin Ateş Böceği Algoritmalı Yapay Sinir Ağı Modeli

Year 2020, Ejosat Special Issue 2020 (ICCEES), 251 - 256, 05.10.2020
https://doi.org/10.31590/ejosat.802914

Abstract

Bu çalışmada, 0.5-3.5 GHz aralığındaki frekans değerleri için hibrit Yapay Sinir Ağı modeline dayalı Selçuklu Yıldızı mikroşerit anten (SSMA) tasarımı gerçekleştirilmiştir. Bu çalışmada, bir geri yayılma (BP) ve bir meta-sezgisel algoritmayı birleştirerek sinir ağı eğitimi için yeni bir algoritma geliştirilmiştir. Geri yayılmanın çözüm bulmadaki en büyük dezavantajı, küresel minimumdan ziyade yerel minimuma sıkışmasıdır. Bu yeni hibrit eğitim algoritmasında, yerel ve global arama eş zamanlı olarak yapılmıştır. Başlangıçta, uzun atlama sayesinde yerel minimuma yakalanma olasılığının düşük olması nedeniyle sinir ağlarının ağırlıklarını elde etmek için Ateş Böceği Algoritması (FA) kullanıldı. Daha sonra, bu algoritma, Firefly Algoritmasının gelişmiş küresel arama yeteneğinin ve BP algoritmasının yerel arama yeteneğinin nöral ağ eğitiminde kullanılması için geri yayılma (BP) ile birleştirilmiştir. Yapay Sinir Ağının eğitim aşamasında Levenberg-Marquardt geri yayılma algoritması kullanılmıştır. Bu çalışmada Selçuklu Yıldızı mikroşerit anteni, çift yüzlü 1.55mm dielektrik ve 35um iletken kalınlığında, 4.37 elektrik iletkenliğine ve 0.002 kayıp tanjantına sahip DE104 üzerine tasarlanmıştır. 272 mikroşerit anten tasarımı için HFSS anten simülasyon programı kullanılmıştır. Veri setinin %90'ı eğitim, %10'u test verisi olarak kullanılmıştır. Ateş Böceği Algoritması ile YSA sonuçları simülasyon sonuçlarıyla daha uyumludur.

References

  • Balanis, C. A. (2016). Antenna theory: analysis and design: John wiley & sons.
  • Guney, K., Sarikaya, N. J. I. T. o. A., & Propagation. (2007). A hybrid method based on combining artificial neural network and fuzzy inference system for simultaneous computation of resonant frequencies of rectangular, circular, and triangular microstrip antennas. 55(3), 659-668.
  • Kaur, R., & Rattan, M. J. W. P. C. (2015). Optimization of the return loss of differentially fed microstrip patch antenna using ANN and firefly algorithm. 80(4), 1547-1556.
  • Kumar, K. A., Ashwath, R., Kumar, D. S., & Malmathanraj, R. (2010). Optimization of multislotted rectangular microstrip patch antenna using ANN and bacterial foraging optimization. Paper presented at the 2010 Asia-Pacific International Symposium on Electromagnetic Compatibility.
  • Pandey, A. (2019). Practical Microstrip and Printed Antenna Design: Artech House.
  • Sagiroglu, S., Güney, K. J. M., & Letters, O. T. (1997). Calculation of resonant frequency for an equilateral triangular microstrip antenna with the use of artificial neural networks. 14(2), 89-93.
  • Thakare, V. V., & Singhal, P. (2009). Microstrip antenna design using artificial neural networks. International Journal of RF and Microwave Computer-Aided Engineering, vol. 20, no. 1, pp. 76–86.
  • Uzer, D., Gültekin, S. S., Top, R., Uğurlu, E., Dündar, Ö. J. I. J. o. A. M., Electronics, & Computers. (2016). A Comparison of Different Patch Geometry Effects on Bandwidth. (Special Issue-1), 421-423.
  • Vilović, I., Burum, N., & Brailo, M. (2013). Microstrip antenna design using neural networks optimized by PSO. Paper presented at the ICECom 2013.
  • Yang, X.-S. (2010). Nature-inspired metaheuristic algorithms: Luniver press.

Artificial Neural Network Model with Firefly Algorithm for Seljuk Star Shaped Microstrip Antenna

Year 2020, Ejosat Special Issue 2020 (ICCEES), 251 - 256, 05.10.2020
https://doi.org/10.31590/ejosat.802914

Abstract

In this study, Seljuk Star microstrip antenna (SSMA) design based on the hybrid Artificial Neural Network model for frequency values in the range of 0.5-3.5 GHz has been performed. In the present study, a new algorithm is developed for neural network training by combining a back propagation (BP) and a meta-heuristic algorithm. The major disadvantage of back propagation in finding solutions is that it stuck local minima rather than global one. In this new hybrid training algorithm, local and global search made simultaneously. Initially, Firefly Algorithm (FA) was utilized to obtain weights of neural network due to the lower probability of entrapment into local minima thanks to long jump. Then, this algorithm is combined with back propagation (BP) to use the advantages of enhanced global search ability of Firefly Algorithm and local search ability of BP algorithm in training neural network. Levenberg-Marquardt back propagation algorithm was used in the training phase of the Artificial Neural Network. In this paper, Seljuk Star microstrip antenna has been designed on DE104, double faced with 1.55mm dielectric and 35um conductor thickness, which has an electrical conductivity of 4.37 and a loss tangent of 0.002. HFSS antenna simulation program was used to design for 272 microstrip antennas. 90% of the data set was used as training and 10% as test data. The ANN with Firefly Algorithm results are more in agreement with the simulating results.

References

  • Balanis, C. A. (2016). Antenna theory: analysis and design: John wiley & sons.
  • Guney, K., Sarikaya, N. J. I. T. o. A., & Propagation. (2007). A hybrid method based on combining artificial neural network and fuzzy inference system for simultaneous computation of resonant frequencies of rectangular, circular, and triangular microstrip antennas. 55(3), 659-668.
  • Kaur, R., & Rattan, M. J. W. P. C. (2015). Optimization of the return loss of differentially fed microstrip patch antenna using ANN and firefly algorithm. 80(4), 1547-1556.
  • Kumar, K. A., Ashwath, R., Kumar, D. S., & Malmathanraj, R. (2010). Optimization of multislotted rectangular microstrip patch antenna using ANN and bacterial foraging optimization. Paper presented at the 2010 Asia-Pacific International Symposium on Electromagnetic Compatibility.
  • Pandey, A. (2019). Practical Microstrip and Printed Antenna Design: Artech House.
  • Sagiroglu, S., Güney, K. J. M., & Letters, O. T. (1997). Calculation of resonant frequency for an equilateral triangular microstrip antenna with the use of artificial neural networks. 14(2), 89-93.
  • Thakare, V. V., & Singhal, P. (2009). Microstrip antenna design using artificial neural networks. International Journal of RF and Microwave Computer-Aided Engineering, vol. 20, no. 1, pp. 76–86.
  • Uzer, D., Gültekin, S. S., Top, R., Uğurlu, E., Dündar, Ö. J. I. J. o. A. M., Electronics, & Computers. (2016). A Comparison of Different Patch Geometry Effects on Bandwidth. (Special Issue-1), 421-423.
  • Vilović, I., Burum, N., & Brailo, M. (2013). Microstrip antenna design using neural networks optimized by PSO. Paper presented at the ICECom 2013.
  • Yang, X.-S. (2010). Nature-inspired metaheuristic algorithms: Luniver press.
There are 10 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Erdem Yelken 0000-0001-9307-2959

Dilek Uzer 0000-0003-3850-3810

Publication Date October 5, 2020
Published in Issue Year 2020 Ejosat Special Issue 2020 (ICCEES)

Cite

APA Yelken, E., & Uzer, D. (2020). Artificial Neural Network Model with Firefly Algorithm for Seljuk Star Shaped Microstrip Antenna. Avrupa Bilim Ve Teknoloji Dergisi251-256. https://doi.org/10.31590/ejosat.802914