Microstrip Antenna Design for 2.4 GHz RF Energy Harvesting Circuits with Artificial Neural Networks

Burak Dökmetaş; Mehmet Ali Belen

Article Details

Microstrip Antenna Design for 2.4 GHz RF Energy Harvesting Circuits with Artificial Neural Networks

Authors:

Burak Dökmetaş | Mehmet Ali Belen

Publisher:

Izmir Katip Celebi University

Main Topics:

Veri Madenciliği ve Bilgi Keşfi

Journal:

Journal of Artificial Intelligence and Data Science Vol.4 Issue 1, pp.33-38

Document Type:

Article

Publication Date:

6/2024

Document Language:

English

Document ID (Org No.):

2001320140

pISSN:

2791-8335

Keywords:

Abstract:

 This study explores the synthesis of microstrip antennas designed for 2.4 GHz RF energy harvesting circuits through the integration of artificial neural networks ANNs. Utilizing a 3D electromagnetic EM simulation tool, extensive datasets were generated for training and testing the ANN model. A meticulous trial-and-error process was employed to optimize critical hyperparameters, including the number of hidden layers, neurons per layer, and activation function types. The outcome of this process was the identification of an optimal ANN model, proficient in accurately capturing complex relationships between antenna design parameters and energy harvesting efficiency. The integration of the 3D EM simulation tool and the tuned ANN model facilitated a computationally efficient approach to antenna optimization, reducing reliance on resource-intensive simulations. This research contributes to the advancement of RF energy harvesting systems, showcasing the potential of artificial intelligence in streamlining the design process for optimal microstrip antennas in 2.4 GHz applications. The demonstrated methodology provides insights into the future of computational design, offering a swift and efficient path for meeting the evolving demands of wireless communication and sensor technologies.

 This study explores the synthesis of microstrip antennas designed for 2.4 GHz RF energy harvesting circuits through the integration of artificial neural networks ANNs. Utilizing a 3D electromagnetic EM simulation tool, extensive datasets were generated for training and testing the ANN model. A meticulous trial-and-error process was employed to optimize critical hyperparameters, including the number of hidden layers, neurons per layer, and activation function types. The outcome of this process was the identification of an optimal ANN model, proficient in accurately capturing complex relationships between antenna design parameters and energy harvesting efficiency. The integration of the 3D EM simulation tool and the tuned ANN model facilitated a computationally efficient approach to antenna optimization, reducing reliance on resource-intensive simulations. This research contributes to the advancement of RF energy harvesting systems, showcasing the potential of artificial intelligence in streamlining the design process for optimal microstrip antennas in 2.4 GHz applications. The demonstrated methodology provides insights into the future of computational design, offering a swift and efficient path for meeting the evolving demands of wireless communication and sensor technologies.

 This study explores the synthesis of microstrip antennas designed for 2.4 GHz RF energy harvesting circuits through the integration of artificial neural networks ANNs. Utilizing a 3D electromagnetic EM simulation tool, extensive datasets were generated for training and testing the ANN model. A meticulous trial-and-error process was employed to optimize critical hyperparameters, including the number of hidden layers, neurons per layer, and activation function types. The outcome of this process was the identification of an optimal ANN model, proficient in accurately capturing complex relationships between antenna design parameters and energy harvesting efficiency. The integration of the 3D EM simulation tool and the tuned ANN model facilitated a computationally efficient approach to antenna optimization, reducing reliance on resource-intensive simulations. This research contributes to the advancement of RF energy harvesting systems, showcasing the potential of artificial intelligence in streamlining the design process for optimal microstrip antennas in 2.4 GHz applications. The demonstrated methodology provides insights into the future of computational design, offering a swift and efficient path for meeting the evolving demands of wireless communication and sensor technologies.

 This study explores the synthesis of microstrip antennas designed for 2.4 GHz RF energy harvesting circuits through the integration of artificial neural networks ANNs. Utilizing a 3D electromagnetic EM simulation tool, extensive datasets were generated for training and testing the ANN model. A meticulous trial-and-error process was employed to optimize critical hyperparameters, including the number of hidden layers, neurons per layer, and activation function types. The outcome of this process was the identification of an optimal ANN model, proficient in accurately capturing complex relationships between antenna design parameters and energy harvesting efficiency. The integration of the 3D EM simulation tool and the tuned ANN model facilitated a computationally efficient approach to antenna optimization, reducing reliance on resource-intensive simulations. This research contributes to the advancement of RF energy harvesting systems, showcasing the potential of artificial intelligence in streamlining the design process for optimal microstrip antennas in 2.4 GHz applications. The demonstrated methodology provides insights into the future of computational design, offering a swift and efficient path for meeting the evolving demands of wireless communication and sensor technologies.

Article Details

Microstrip Antenna Design for 2.4 GHz RF Energy Harvesting Circuits with Artificial Neural Networks

Authors: Burak Dökmetaş | Mehmet Ali Belen

Publisher: Izmir Katip Celebi University

Main Topics: Veri Madenciliği ve Bilgi Keşfi

Journal: Journal of Artificial Intelligence and Data Science Vol.4 Issue 1, pp.33-38

Document Type: Article

Publication Date: 6/2024

Document Language: English

Document ID (Org No.): 2001320140

pISSN: 2791-8335

ANN

Microstrip Antenna

Artificial Neural Networks

Issues

Authors:

Burak Dökmetaş | Mehmet Ali Belen

Publisher:

Izmir Katip Celebi University

Main Topics:

Veri Madenciliği ve Bilgi Keşfi

Journal:

Journal of Artificial Intelligence and Data Science Vol.4 Issue 1, pp.33-38

Document Type:

Article

Publication Date:

6/2024

Document Language:

English

Document ID (Org No.):

2001320140

pISSN:

2791-8335