Artificial intelligence–based design optimization of nonuniform microstrip line band pass filter

Abstract

Design optimization of many electromagnetic and multiphysics problems have multiscale issues that require a fast, efficient, and accurate surrogate‐based model to be used. Recently, in microwave engineering field, artificial intelligence–based models are being used for modeling of complex microwave stages. In all the studies, the main aim is to form models inner structure parameters, by using the given data to predict the linear/nonlinear relationships between given inputs and outputs. Herein, a surrogate‐based model of a nonuniform microstrip transmission line (NTL) with a typical application of design optimization of a band‐pass filter for ISM band application using deep learning (DL) and meta‐heuristic optimization has been presented. In order to have a computationally efficient and accurate optimization process, firstly a 3D EM unit element model of NTL has been designed. The training and test data sets are created based on different sampling methods. A DL regression model modified multilayer perceptron M2LP have been used for prediction of scattering parameters (S) of the NTL, with respect to the variation of geometrical design parameters. The proposed S‐parameters will then be used to calculate the equivalent S‐parameters of the cascading NTL to be used to calculate the NTL‐based microstrip band‐pass filter S‐parameter response. The optimal design parameters of each line used in the filter design have been determined using a fast and powerful optimization algorithm differential evolutionary algorithm.

Surrogate‐assisted optimization of 3D printed ceramic nonuniform nonplanar microstrip filter

“…Here by using basic circuit theory, 1,41 and the scattering parameters of unit element predicted by the surrogate model, the S-matrix of the M element NUNPMF is obtained from the transmission matrix obtained via cascaded T matrices of the M unit cells. For the optimization process, the following equations have been used as the cost function.…”

“…surrogate-assisted optimization is one of the efficient methods for design optimization of microwave components which have multiscale issues that need a solution method with fast response, high efficiency, and high accuracy. 1 With respect to the ever-increasing performance criteria's such as size reduction, wide operation band, being low cost and so forth, the design and optimization process of the components become harder and more complex, where this force the designers to face a challenging problem. Either designer has to use a coarse model to achieve computationally efficiency in its design optimization process at the expanse of low accuracy, or has to use a fine model with high accuracy at the expanse of very low or even infeasible computation efficient.…”

“…Then, by using the basic circuit theory, scattering parameters predicted by data-driven model and a metaheuristic optimization algorithm Grey Wolf (GW) 24,25 the equivalent scattering response of cascaded unit elements can be obtained to determine the optimal design variable value sets to form the desired filter characteristics. 1 Furthermore, to have a low-cost manufacturing process 3D printing technology had been used to create nonuniform substrate structures with a ceramic material substrate of the design. In the next section, the details of the proposed ceramic-based NUNPMF transmission line unit element and the proposed filter design is presented alongside of the generated data set for the training process.…”

“…surrogate‐assisted optimization is one of the efficient methods for design optimization of microwave components which have multiscale issues that need a solution method with fast response, high efficiency, and high accuracy 1 . With respect to the ever‐increasing performance criteria's such as size reduction, wide operation band, being low cost and so forth, the design and optimization process of the components become harder and more complex, where this force the designers to face a challenging problem.…”

“…Here the data‐driven surrogate modeling technique had been used for predicting the scattering [S] parameters of proposed filter, where for avoid both dimensionality and efficient sample gathering problems, a unit element design for the proposed NUNPMF design had been modeled in 3D EM full‐wave simulator. Then, by using the basic circuit theory, scattering parameters predicted by data‐driven model and a metaheuristic optimization algorithm Grey Wolf (GW) 24,25 the equivalent scattering response of cascaded unit elements can be obtained to determine the optimal design variable value sets to form the desired filter characteristics 1 . Furthermore, to have a low‐cost manufacturing process 3D printing technology had been used to create nonuniform substrate structures with a ceramic material substrate of the design.…”