Subject Area
Electronics and Communication Engineering
Article Type
Original Study
Abstract
In this paper, a general design procedure is suggested for the microstrip antennas using artificial neural networks and this is demonstrated using the rectangular patch geometry. The model was analyzed for 1733 data sets of input output parameters. 1300 samples for training and 433 samples for testing and 1500 epoch, learning rate from (0.003 to 0.005). Python was used to create and implement the ANN algorithm model. The mean error in detection of resonance frequencies (return loss peaks) was 0.144GHz on train set, and 0.116GHz on test set. The outputs of the radial basis function are optimized by varying the number of neurons and hidden layers. The proposed method's results are compared with the results of CST and found to be in good agreement.
Keywords
Return Loss, Computer Simulation Technology (CST), Microstrip Patch Antenna (MPA), Radial Basic Function (RBF), Artificial Neural Network (ANN)
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Shoeab, Hadeer. A; A.Mohamed, Mohamed; El Said A, Marzouk; and Kabeel, Ahmed. A.
(2023)
"Microstrip Antenna Design Using CST Optimized By Neural Network Algorithm,"
Mansoura Engineering Journal: Vol. 48
:
Iss.
3
, Article 4.
Available at:
https://doi.org/10.58491/2735-4202.3045
Included in
Electromagnetics and Photonics Commons, Systems Engineering and Multidisciplinary Design Optimization Commons