Resonant frequency calculation of circular ring microstrip patch antenna using knowledge based neural network

Abstract

This paper discuss about application of knowledge based neural network to calculate resonant frequency of circular ring microstrip patch antenna. Results obtained using present approach are compared with that of traditional neural network, IE3D and measurement.

Modeling analysis of patch antenna efficiency considering impedance matching characteristics of cable feed end

“…Under the above conditions, since the signal is time-harmonic, we can solve the Helmholtz equation for the electric field vector at any position of the geometric structure, as shown in equation (9). Meanwhile, the calculation of the far-field domain can be performed, and the far-field distribution at infinity can be obtained, and the calculation equation is shown in equation (10). Through the above modeling analysis, the functional characteristics of the balanced patch antenna can be explored.…”

“…In addition, the assumption that the floor of the radiation source is infinite will also cause the equivalent model cannot calculate the rear flap of the antenna. In contrast, the intelligent algorithmic model [9][10][11][12] is not conducive to fast analysis due to its inherent shortcomings, conditional limitations in the antenna parameter model, and complex and time-consuming computations.…”

Artificial Neural Networks for Microwave Computer-Aided Design: The State of the Art

“…Taking advantage of a wide range of existing equivalent circuit models/empirical models for microwave components, KBNNs have been developed for microwave CAD [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53]. The use of knowledge in neural networks helps to reduce the amount of training data needed and enhance the extrapolation capability of the model.…”

“…With a good model accuracy being guaranteed inside the training region, the extrapolation technique [166] can further force the model to be smooth along all the directions outside the training region. Besides various extrapolation methods, the KBNN method [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53] exploits microwave empirical or equivalent models to help the overall KBNN model to achieve better extrapolation capability than pure neural networks. Furthermore, CNN-and LSTM-based neural network structures have been exploited for design space extrapolation and frequency extrapolation [151].…”

“…To improve the accuracy and reliability of ANN modeling and design optimization, the KBNN has been developed [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50]. The knowledge-based approach combines neural networks with prior knowledge to build models.…”