Parallel EM optimization approach to microwave filter design using feature assisted neuro-transfer functions

Feng, Feng; Zhang, Chao; Zhang, Shunlu; Gongal-Reddy, Venu-Madhav-Reddy; Zhang, Qi‐Jun

doi:10.1109/mwsym.2016.7539963

Cited by 15 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Handling massive EM analyses in reasonable timeframes requires efficient numerical routines and many of these have been developed over the last two decades or so. [21][22][23][24][25][26][27] Some of available methods include surrogate-assisted routines (space mapping, 21 response correction, 22 feature-based optimization [23][24][25] ), adjointbased gradient algorithms, 26,27 or machine learning procedures. 28,29 High-frequency design, just like almost any other task, is an inherently multiobjective endeavor.…”

Section: Introductionmentioning

confidence: 99%

“…This leads to practical problems when performing simulation‐driven design tasks such as parametric optimization or investigating the effects of manufacturing tolerances (eg, statistical design). Handling massive EM analyses in reasonable timeframes requires efficient numerical routines and many of these have been developed over the last two decades or so . Some of available methods include surrogate‐assisted routines (space mapping, response correction, feature‐based optimization), adjoint‐based gradient algorithms, or machine learning procedures …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accelerated multiobjective design of miniaturized microwave components by means of nested kriging surrogates

Pietrenko‐Dabrowska

Koziel

2020

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

Design of microwave components is an inherently multiobjective task. Often, the objectives are at least partially conflicting and the designer has to work out a suitable compromise. In practice, generating the best possible trade‐off designs requires multiobjective optimization, which is a computationally demanding task. If the structure of interest is evaluated through full‐wave electromagnetic (EM) analysis, the employment of widely used population‐based metaheuristics algorithms may become prohibitive in computational terms. This is a common situation for miniaturized components, where considerable cross‐coupling effects make traditional representations (eg, network equivalents) grossly inaccurate. This article presents a framework for accelerated EM‐driven multiobjective design of compact microwave devices. It adopts a recently reported nested kriging methodology to identify the parameter space region containing the Pareto front and to render a fast surrogate, subsequently used to find the first approximation of the Pareto set. The final trade‐off designs are produced in a separate, surrogate‐assisted refinement process. Our approach is demonstrated using a three‐section impedance matching transformer designed for the best matching and the minimum footprint area. The Pareto set is generated at the cost of only a few hundred of high‐fidelity EM simulations of the transformer circuit despite a large number of geometry parameters involved.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Accelerated multiobjective design of miniaturized microwave components by means of nested kriging surrogates

Pietrenko‐Dabrowska

Koziel

2020

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

show abstract

“…In some practical cases, the EM response does not have explicitly identifiable feature information. More recently, researchers have investigated the use of transfer function-based features to assist the surrogate-based EM optimization [80], [81].…”

Section: Feature-assisted Neuro-tf Surrogate-based Em Optimizationmentioning

confidence: 99%

“…They can address the challenge when the feature parameters cannot be effectively extracted from the EM responses. In [80], feature zeros of the neuro-TF are used as feature parameters to assist the neuro-TF surrogate-based optimization. As a further advance over the work of [80], the research work in [81] introduced a multifeature-assisted neuro-TF surrogatebased EM optimization method.…”

Section: Feature-assisted Neuro-tf Surrogate-based Em Optimizationmentioning

confidence: 99%

“…To further address a situation where the features cannot be clearly and explicitly identified from the filter response, features extracted from transfer function response (transfer function-based features) are used to assist the surrogate to perform the EM optimization [80], [81]. Considering that the transfer function-based features can address the situation where the features cannot be clearly and explicitly identified from the filter response, it is of great interest to investigate the use of the transfer function-based features to perform cognition-driven optimizations.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Advanced Neural Network Modeling and Electromagnetic Optimization Approaches for Microwave Passive Components

Jin¹

View full text Add to dashboard Cite

Microwave modeling and optimization techniques play important roles in electromagnetic (EM)-based microwave component design. The purpose of this thesis is to propose advanced neural network modeling and EM optimization approaches for microwave passive components. This thesis first proposes a new deep neural network technique to solve high-dimensional microwave modeling problems which are more challenging than those solved by previous shallow neural networks. A smooth rectified linear unit (ReLU) is proposed for the new deep neural network. The proposed deep neural network employs both the sigmoid function and the smooth ReLU as activation functions. An advanced three-stage deep learning algorithm is proposed to train the new deep neural network model. This algorithm can determine the number of hidden layers with sigmoid functions and those with smooth ReLUs in the training process. It can also overcome the vanishing gradient problem for training the deep neural network. The proposed deep neural network technique can solve microwave modeling problems in higher dimension than the previous neural network method, i.e., shallow neural network method. Compared to the standard deep neural network using only ReLUs, the proposed deep neural network can achieve higher accuracy with fewer number of hidden neurons. The proposed deep neural network technique is a useful surrogate modeling technique for microwave components. Based on the investigation of the surrogate modeling technique, this thesis further studies the efficient surrogate-based EM optimization method and proposes an advanced cognition-driven EM optimization incorporating transfer function-based feature surrogate for EM geometry optimization of microwave filters. The proposed i optimization technique addresses the situations where the response at the starting point for the design optimization is substantially misaligned with the design specifications. We propose to extract transfer function-based feature parameters for optimization to address the challenge that the features cannot be clearly and explicitly identified from the filter response. Multiple transfer function-based feature parameters are extracted and used to develop the feature surrogate model for the proposed cognition-driven optimization. Furthermore, we derive new objective functions for the cognition-driven optimization directly in the feature space. The proposed cognition-driven optimization incorporating transfer function-based feature surrogate can achieve faster convergence than the existing feature-assisted EM optimization methods.Moreover, to address the EM topology optimization that our proposed cognitiondriven optimization method is not applicable, this thesis further proposes an efficient EM topology optimization technique for microwave component design. In the proposed technique, the finite element method (FEM) is used for EM simulation. We propose a new method to integrate Matrix Padé via Lanczos (MPVL) and Householder formula. The proposed method combines the advantages of MPVL and H...

show abstract

Parallel EM optimization using improved pole‐residue‐based neuro‐TF surrogate and isomorphic orthogonal DOE sampling for microwave components design

Liu

et al. 2023

Int J Numerical Modelling

Self Cite

View full text Add to dashboard Cite

Direct electromagnetic (EM) optimization for microwave components design is usually a time‐consuming process. To improve the optimization efficiency, this paper proposes a novel parallel EM optimization technique exploiting improved pole‐residue‐based neuro‐transfer function (neuro‐TF) surrogate and isomorphic orthogonal design of experiment (DOE) sampling strategy. We propose a new sampling method combining isomorphic orthogonal DOE and parallel EM simulations to generate training data for developing the neuro‐TF surrogate. This proposed sampling method can ensure the scattered distribution of data samples in the overall optimization process, thus effectively improving the surrogate accuracy and increasing the optimization speed. We also propose a new pole‐residue tracking technique for order‐changing to solve the discontinuity problem of pole/residues during the neuro‐TF surrogate development. Different from the fixed split ratio in existing pole‐residue tracking technique, the split ratio of poles and residues in the proposed technique is adaptive and determined according to the information of neighboring samples. Therefore, the continuity and smoothness of pole/residues after the splitting are improved, so as the neuro‐TF surrogate accuracy. In addition, the trust region algorithm is exploited during EM optimization to improve the convergence speed. In this way, the proposed EM optimization technique obtains the optimal solution in a shorter time with fewer iterations than the existing techniques. Two examples of EM optimizations of microwave components are used to illustrate the proposed technique.

show abstract

Parallel EM optimization approach to microwave filter design using feature assisted neuro-transfer functions

Cited by 15 publications

References 8 publications

Accelerated multiobjective design of miniaturized microwave components by means of nested kriging surrogates

Accelerated multiobjective design of miniaturized microwave components by means of nested kriging surrogates

Advanced Neural Network Modeling and Electromagnetic Optimization Approaches for Microwave Passive Components

Parallel EM optimization using improved pole‐residue‐based neuro‐TF surrogate and isomorphic orthogonal DOE sampling for microwave components design

Contact Info

Product

Resources

About