No CrossRef data available.
Design of ultra-wideband antenna based on one-dimensional convolutional neural network
Published online by Cambridge University Press: 21 March 2025
Abstract
This paper presents a notched ultra-wideband antenna designed to suppress interference from narrowband communication systems. The antenna features a defected ground structure and a stepped microstrip feedline for improved impedance matching and enhanced bandwidth. A bent slot structure is incorporated into the radiating patch to achieve the band-notched characteristic. It has a wide tunable frequency range which allows for flexible adjustment of the notch frequency. Traditional optimization methods, such as numerical analysis, are computationally expensive and inefficient, while heuristic algorithms are less precise. To address these challenges, an improved one-dimensional convolutional neural network (1DCNN-IPS) model is proposed for optimizing the bent slot design more efficiently. The trained 1DCNN-IPS model can accurately predict the antenna’s electromagnetic parameters, reducing mean squared error and training times compared to traditional methods. This provides an efficient and precise solution for antenna structural optimization.
Keywords
- Type
- Research Paper
- Information
- Copyright
- © The Author(s), 2025. Published by Cambridge University Press in association with The European Microwave Association.