Optimisation of reflection coefficient of microstrip antennas based on KBNN exploiting GPR model

Abstract

When microstrip antennas (MSAs) are optimised, the full‐wave electromagnetic simulation takes long time to get the result which is very time consuming. Hence, the knowledge‐based neural network (KBNN) is used here to replace the electromagnetic simulation to shorten the calculating time and raise efficiency. However, prior knowledge of KBNN is always obtained by empirical formulas and neural networks, both of them are heavy and complicated. In this study, Gaussian process regression (GPR) is proposed to get the prior knowledge. The modelling of MSA is realised by the prior knowledge input method. The short optimal time and excellent optimal results prove that the proposed KBNN is a fast and effective method for the optimisation of MSAs.

Antenna Modeling Based on Two-Stage Gaussian Process Considering Sensitivity Information

“…The structure of the ultra-wideband planar monopole antenna in [40] is shown in Figure 6(a), and HFSS model is shown in Figure 6 [2.4,3.6]mm, R1= [5.4,6.6] mm, R2= [9,10.2]mm. Among them, the upper and lower limit width of the design variables are determined according to the empirical values of [26]. The optimization indexes are that the value of S11 in the 3GHz~11GHz frequency band is less than -10dB.…”

“…In contrast, GP has a strict statistical theoretical basis, which is suitable for dealing with small samples, high dimensions, nonlinear and other complex problems [24]. The strong modeling capabilities of GP make it possible to adaptively obtain hyper-parameters and realize probabilistic prediction that is different from other regression models, so it is more and more widely used in the analysis of antenna modeling problems [25], [26], [27], [28], [29]. When electromagnetic performance is evaluated and calculated by electromagnetic simulation software, if HFSS or CST software is used, the simulation results not only include conventional electromagnetic performance, but also provide sensitivity information [30], [31], [32], [33].…”

Resonant Frequency Modeling of Microstrip Antenna Based on Deep Kernel Learning

“…Therefore, using a surrogate model instead of electromagnetic simulation software to evaluate the fitness of electromagnetic components can save optimization time, which is a popular topic of electromagnetic optimization design at present. Many modeling methods have been proposed by researchers, such as artificial neural network (ANN) [3][4][5], support vector machine (SVM) [6,7], extreme learning machine (ELM) [8][9][10], Gaussian process (GP) [11][12][13].…”

Optimal Design of Multiband Microstrip Antennas by Self-Renewing Fitness Estimation of Particle Swarm Optimization Algorithm

“…Neog et al calculated the antenna pattern through the ANN and combined the genetic algorithm (GA) to analyze the resonant frequency of the antenna [12]. Chen et al proposed a GPR-based knowledge neural network in [13] and applied it in MSAs. Roy et al used the SVM to calculate the performance parameters such as the resonant frequency, gain, and directivity of the slotted MSA and achieved good agreement between the predicted results and the measured results [14].…”