作者: Sami Bedra , Siham Benkouda , Tarek Fortaki
DOI: 10.1108/COMPEL-10-2012-0225
关键词: Acoustics 、 Moment (mathematics) 、 Engineering 、 Spectral domain 、 Quality (physics) 、 Microstrip antenna 、 Artificial neural network 、 Electronic engineering 、 Anisotropic substrate 、 Central processing unit 、 Isotropy
摘要: Purpose – The paper aims to propose an artificial neural network (ANN) in conjunction with spectral domain formulation for fast and accurate determination of the resonant frequency quality factor circular microstrip antenna printed on isotropic or anisotropic substrate. This neurospectral approach reduces problem complexity. Design/methodology/approach moment method implemented provides good accuracy but its computational cost is high due evaluation slowly decaying integrals iterative nature solution process. introduces electromagnetic knowledge combined ANN analysis uniaxially substrate reduce complexity minimize CPU time necessary obtain numerical results. Findings results obtained from model are very agreement experimental theoretical ava...