Search

When modelling and optimizing antennas by machine learning (ML) methods, it is the most timeconsuming to obtain the training samples with labels from full-wave electromagnetic simulation software. To address the problem, this paper proposes an optimization method based on the consensus results of multiple independently trained Student's-T Process (STP) with excellent generalization ability. First, the STP is introduced as a surrogate model to replace the traditional Gaussian Process (GP), and the hyperparameters of the STP model are optimized. Afterwards, a consistency algorithm is used to process the results of multiple independently trained STPs to improve the reliability of the results. Furthermore, an aggregation algorithm is adopted to reduce the error obtained in the consistency results if it is greater than the consistency flag. The effectiveness of the proposed model is demonstrated through experiments with rectangular microstrip antennas (RMSA) and circular microstrip antennas (CMSA). The experimental results show that the use of multiple independently trained STPs can accelerate the antenna design optimization process, and improve modelling accuracy while maintaining modelling efficiency, which has high generalization ability. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNN) have a strong feature extraction ability for images and present a high level of efficiency and accuracy in object detection and image recognition. When CNN is used to model microwave devices, the existing literature generally uses its size parameters as one-dimensional (1-D) input, which does not give full play to the image-processing ability of CNN. In order to make full use of the characteristics of CNN, this letter converts the 1-D input of microwave devices into the form of an image model, that is, the 1-D input is transformed into a two-dimensional (2-D) matrix composed of 0 and 1 as the input. The image model is combined with CNN, called image-based CNN (ICNN), which establishes a deep learning surrogate model between the physical parameters and electrical properties of microwave devices and improves the accuracy and generalization ability of the model. Taking the resonant frequency of the microstrip antenna as a simulation example, modelling was carried out by the proposed ICNN and compared with the mainstream machine learning methods. The results show that the proposed method has high convergence and fitting accuracy. [ABSTRACT FROM AUTHOR]

The design of electromagnetic components generally relies on simulation of full-wave electromagnetic field software exploiting global optimization methods. The main problem of the method is time consuming. Aiming at solving the problem, this study proposes a regression surrogate model based on AdaBoost Gaussian process (GP) ensemble (AGPE). In this method, the GP is used as the weak model, and the AdaBoost algorithm is introduced as the ensemble framework to integrate the weak models, and the strong learner will eventually be used as a surrogate model. Numerical simulation experiment is used to verify the effectiveness of the model, the mean relative error (MRE) of the three classical benchmark functions decreases, respectively, from 0.0585, 0.0528, 0.0241 to 0.0143, 0.0265, 0.0116, and then the method is used to model the resonance frequency of rectangular microstrip antenna (MSA) and coplanar waveguide butterfly MSA. The MRE of test samples based on the APGE are 0.0069, 0.0008 respectively, and the MRE of a single GP are 0.0191, 0.0023 respectively. The results show that, compared with a single GP regression model, the proposed AGPE method works better. In addition, in the modeling experiment of resonant frequency of rectangular MSA, the results obtained by AGPE are compared with those obtained by using neural network (NN). The results show that the proposed method is more effective. [ABSTRACT FROM AUTHOR]

Bayesian Optimization (BO) is an efficient global optimization algorithm, which is widely used in the field of engineering design. The probabilistic surrogate model and acquisition function are the two keys to the algorithm. Building an efficient probabilistic surrogate model and designing a collection function with excellent exploring capabilities can improve the performance of BO algorithm, allowing it to find the optimal value of the objective function with fewer iterations. Due to the characteristics of small samples and non-parametric derivation of the Gaussian Process (GP), traditional BO algorithms usually use the GP as a surrogate model. Compared with the GP, the Student's T Process (STP) retains the excellent properties of GP, and has more flexible posterior variance and stronger robustness. In this paper, STP is used as the surrogate model in BO algorithm, the hyperparameters of the model are optimized by STP, and the estimation strategy function (EST) is improved based on the posterior output of the optimized STP, thus realizing the improved BO algorithm based on the STP. To verify the performance of the proposed algorithm, numerical experiments are designed to compare the performances of the traditional BO algorithm, which includes the lower confidence bound function (LCB) and EST as acquisition function respectively and GP as the surrogate model, and the proposed BO algorithm with STP as the surrogate model and LCB, expected improvement function (EI), expected regret minimization function (ERM) as acquisition function respectively. The results show that the proposed algorithm in this paper performs well when finding the global minimum of multimodal functions. Based on the developed algorithm in this paper, the resonant frequency of printed dipole antenna and E-shaped antenna is modeled and optimized, which further confirms the good design ability and design accuracy of the BO algorithm proposed in this paper. [ABSTRACT FROM AUTHOR]

Bayesian Optimization (BO) is an efficient global optimization algorithm, which is widely used in the field of engineering design. The probabilistic surrogate model and acquisition function are the two keys to the algorithm. Building an efficient probabilistic surrogate model and designing a collection function with excellent exploring capabilities can improve the performance of BO algorithm, allowing it to find the optimal value of the objective function with fewer iterations. Due to the characteristics of small samples and non-parametric derivation of the Gaussian Process (GP), traditional BO algorithms usually use the GP as a surrogate model. Compared with the GP, the Student's T Process (STP) retains the excellent properties of GP, and has more flexible posterior variance and stronger robustness. In this paper, STP is used as the surrogate model in BO algorithm, the hyperparameters of the model are optimized by STP, and the estimation strategy function (EST) is improved based on the posterior output of the optimized STP, thus realizing the improved BO algorithm based on the STP. To verify the performance of the proposed algorithm, numerical experiments are designed to compare the performances of the traditional BO algorithm, which includes the lower confidence bound function (LCB) and EST as acquisition function respectively and GP as the surrogate model, and the proposed BO algorithm with STP as the surrogate model and LCB, expected improvement function (EI), expected regret minimization function (ERM) as acquisition function respectively. The results show that the proposed algorithm in this paper performs well when finding the global minimum of multimodal functions. Based on the developed algorithm in this paper, the resonant frequency of printed dipole antenna and E-shaped antenna is modeled and optimized, which further confirms the good design ability and design accuracy of the BO algorithm proposed in this paper. [ABSTRACT FROM AUTHOR]

The results of this reported work indicated that gold nanoparticle arrays self-assembled on indium tin oxide (ITO) glasses can obtain broader localized surface plasmon resonance (LSPR) wavelength range and higher sensitivity than the bare quartz. The results of surface electric field calculated using finite difference time domain showed that the electric field of nanoparticles on ITO glasses is enhanced and the repulsive forces within each particle is weakened. According to the dipolar interaction mechanism, a weakened repulsive forces within each particle lead to a lower resonance frequency and a strong redshift of the LSPR spectra. [ABSTRACT FROM AUTHOR]