This article presents an overview of artificial neural network (ANN) techniques for a microwave computer-aided design (CAD). ANN-based techniques are becoming useful for performing forward/inverse modeling for active/passive components to enhance a circuit design. With measured or simulated data of microwave devices, ANNs can be trained to learn relevant microwave relationships, which are, otherwise, computationally expensive or for which efficient analytical formulas are not available. Fundamental concepts of the ANN structure and training, such as feedforward neural networks (FFNNs), recurrent neural networks (RNNs)/dynamic neural networks (DNNs)/time-delay neural networks (TDNNs), deep neural networks, and neural network training and extrapolation, are described. Knowledge-based neural networks (KBNNs) are described for improving the accuracy and reliability of modeling and design optimization. Various advanced ANN techniques, such as neuro-transfer function (neuro-TF) modeling, neural network inverse modeling, and deep neural network modeling, are discussed. The existing and emerging applications of ANN in microwave CAD are identified, such as electromagnetic (EM)/multiphysics modeling, modeling of nonlinear circuits and transistors, filter design, very large-scale integration (VLSI) interconnects, oscillator, transmitter and receiver modeling, and CAD applications in such as gallium nitride (GaN) high electron-mobility transistor (HEMT), wireless power transfer (WPT), microelectromechanical system (MEMS), and substrate-integrated waveguide (SIW).

Yield-driven optimization is important in microwave design due to the uncertainties introduced in the manufacturing process. For the first time, we extend in this paper the use of polynomial chaos (PC) approach from electromagnetic (EM)-based yield estimation to EM-based yield optimization of microwave structures. We first formulate a novel objective function for yield-driven EM optimization. By incorporating the PC coefficients into the formulation, the objective function is analytically related to yield optimization variables, which are the nominal point. We then derive the sensitivity formulas of the PC coefficients with respect to the nominal point, following which we derive the sensitivities of the optimization objective function with respect to yield optimization variables. These sensitivities are then used in gradient-based optimization algorithms to find the optimal yield solution iteratively. The proposed objective function requires fewer EM simulations to provide reliable yield representation than that in the conventional Monte Carlo-based yield optimization approach. As a result, the number of EM simulations required to find the update direction and suitable step size for the change of the nominal point is reduced at each iteration of optimization. This allows the proposed approach to achieve similar yield increase using much fewer EM simulations or greater yield increase using similar number of EM simulations compared to the conventional yield optimization approach. The advantages of our proposed approach are demonstrated by yield-driven EM optimization of three waveguide filter examples.

This paper proposes a novel technique to develop a low-cost electromagnetic (EM) centric multiphysics parametric model for microwave components. In the proposed method, we use space mapping techniques to combine the computational efficiency of EM single physics (EM only) simulation with the accuracy of the multiphysics simulation. The EM responses with respect to different values of geometrical parameters in nondeformed structures without considering other physics domains are regarded as coarse model. The coarse model is developed using the parametric modeling methods such as artificial neural networks or neuro-transfer function techniques. The EM responses with geometrical and nongeometrical design parameters as variables in the practical deformed structures due to thermal and structural mechanical stress factors are regarded as fine model. The fine model represents the behavior of EM centric multiphysics responses. The proposed model includes the EM domain coarse model and two mapping neural networks to map the EM domain (single physics) to the multiphysics domain. Our proposed technique can achieve good accuracy for multiphysics parametric modeling with fewer multiphysics training data and less computational cost. After the modeling process, the proposed model can be used to provide accurate and fast prediction of EM centric multiphysics responses of microwave components with respect to the changes of design parameters within the training ranges. The proposed technique is illustrated by a tunable four-pole waveguide filter example at 10.5-11.5 GHz and an iris coupled microwave cavity filter example at 690-720 MHz.

Feature-based electromagnetic (EM) optimization techniques can help avoid local minima in microwave design. Zeros of the transfer functions are recently used to help extract the features when the features of filter responses are not explicitly identifiable. This letter proposes a feature zero-adaptation approach to enlarge the surrogate range by overcoming the problem of varying orders of the transfer function w.r.t. the changes in design variables. In this way, the proposed technique allows larger step sizes for optimization, therefore, speeding up the overall EM optimization process. During each optimization iteration, parallel techniques are proposed to be used to generate multiple EM geometrical samples simultaneously for creating the feature-based surrogate model. The proposed technique is demonstrated using two microwave filter examples.

Space mapping is a recognized surrogate-based optimization method to accelerate the electromagnetic (EM) design. In this article, for the first time, space mapping is elevated from solving the problem of EM optimization to solving the problem of multiphysics optimization for high power microwave filters. Multiphysics analysis, which involves the EM domain with other physics domains, is increasingly important for high-performance microwave components to obtain an accurate system design. To speed up the multiphysics design, a space-mapping-based surrogate model including a coarse model and two mapping functions is proposed in this article. We propose to use EM single physics responses as the coarse model to provide good approximations to fine model multiphysics responses. To avoid repetitive EM simulations during the surrogate model training and optimization process, the coarse model is developed using an artificial neural network (ANN). Frequency mapping and explicit input mapping are further performed to develop the proposed surrogate model. Multiple EM and multiphysics training samples are evaluated in parallel to develop the surrogate model. A trust-region algorithm, tailored to the space-mapping-based multiphysics optimization technique, is proposed to improve the convergence. By exploiting the knowledge of the coarse model established by relatively inexpensive EM data, the proposed technique can provide a larger and more efficient optimization update in each optimization iteration, consequently obtaining optimal solutions faster than the existing multiphysics optimization without space mapping. Two examples of multiphysics optimization of high-power microwave filters are used to validate the proposed technique.