Design optimization of a pattern reconfigurable microstrip antenna using differential evolution and 3D EM simulation‐based neural network model

Abstract

In this work, design optimization of a varicap diode loaded antenna consisting of four identical rectangular microstrips is presented as a pattern reconfigurable antenna at 5.2 GHz. The microstrips are printed on the front of a FR4 substrate with the dimensions of 40 mm × 25 mm and ε r = 4.6, h = 1.58 mm and probe‐fed via a coupling using a rectangular microstrip line symmetrically placed between them. In first stage, S11 of the antenna are obtained as its real and imaginary parts as continuous functions of geometry of the microstrip components within 3 to 7 GHz using multi‐layer perceptron (MLP) trained and validated by 3D EM simulated data. In order to determine the most suitable (MLP) architecture and training algorithm, 20 different MLP architectures are tested. Then, S11 are optimized with respect to the geometry parameters using differential evolution algorithm and MLP based model. The antenna is prototyped with the optimally selected parameters and measured. From the comparison of simulation and measurement results, it can be observed that the measurement results agree with the simulation results, thus it can be concluded that the proposed antenna is a simple and successful design subject to the design purposes with together its design methodology.

Low-Cost Multi-Objective Optimization of Multiparameter Antenna Structures Based on the l1 Optimization BPNN Surrogate Model

“…Therefore, it is worthwhile improving the optimization speed at the cost of small degradation of the calculation accuracy. Fortunately, surrogate model techniques [28][29][30][31][32][33][34][35][36][37][38][39][40][41] have been proven to effectively avoid the huge computational cost of the EM-driven process. The use of surrogate models has been a recurrent approach adopted by the evolutionary computational community to reduce the fitness function evaluations required to produce acceptable results.…”

Deep learning base modified MLP model for precise scattering parameter prediction of capacitive feed antenna

“…In such a case, the designer should either use a low accurate coarse model for computationally efficient optimization process or a highly accurate fine design model with the low computational efficient optimization process. For the last decades, many studies have been done on creating numerical or analytical methods for accurate models for the design of microwave stages, one of the most commonly used numerical methods is artificial neural network (ANN) models . Commonly, either measured or simulated results of microwave designs are being used for creating ANN‐based circuit models.…”

“…For the last decades, many studies have been done on creating numerical or analytical methods for accurate models for the design of microwave stages, one of the most commonly used numerical methods is artificial neural network (ANN) models. [7][8][9][10] Commonly, either measured or simulated results of microwave designs are being used for creating ANN-based circuit models. Even though the gathering of training and test data might become a considerable effort, once the ANN model is created the overall computation duration of estimation can be overlooked, most especially during a design optimization process.…”

Application of artificial intelligence algorithms on modeling of reflection phase characteristics of a nonuniform reflectarray element

“…The optimization of a large‐scaled RA design is not computationally efficient, or in most cases, it is not feasible due to the high mesh size that might take days of simulations even for a few iterations. Thus, during the design optimization process of an RA, the designer should choose either a coarse model design for a computationally efficient optimization at the expanse of realization error or a fine design model with high accuracy at the expanse of extremely high or infeasible computational time for design optimization process . A feasible solution is to use a fast and accurate unit element model of RA design, where the reflection phase characteristic of each element is predicted concerning the variation of geometrical design parameters of the unit element …”

“…Thus, during the design optimization process of an RA, the designer should choose either a coarse model design for a computationally efficient optimization at the expanse of realization error or a fine design model with high accuracy at the expanse of extremely high or infeasible computational time for design optimization process. 24 A feasible solution is to use a fast and accurate unit element model of RA design, where the reflection phase characteristic of each element is predicted concerning the variation of geometrical design parameters of the unit element. [25][26][27][28] There are many studies for creating artificial intelligence (AI)-based regression methods for fast and high-accurate electromagnetic models for the design of microwave devices, such as using artificial neural networks (ANNs), genetic programming (GP), symbolic regression (SR), and machine learning algorithms.…”