Multivalued Neural Network Inverse Modeling and Applications to Microwave Filters

Zhang, Chao; Jin, Jing; Na, Weicong; Zhang, Qi‐Jun; Yu, Ming

doi:10.1109/tmtt.2018.2841889

Cited by 153 publications

(122 citation statements)

References 29 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…In another work, a multivalued neural network was used to satisfy the tuning requirements of high-order filters, a method that significantly improved the convergence speed of the algorithm. 3 Similarly, ref. [4] proposed a method based on least squares support vector regression, but the coupling matrix (M) extraction from scattering parameters (S-parameters) was completed in an ideal state, so it was difficult to adopt the method in actual filter tuning.…”

Section: Introductionmentioning

confidence: 95%

See 1 more Smart Citation

Tuning model for microwave filter by using improved back‐propagation neural network based on gauss kernel clustering

Cao

2019

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

Given the difficulty of a single model in dealing with complex systems. In this study, we propose a tuning model that uses a probabilistic fusion of sub‐optimal back‐propagation neural network based on the Gauss kernel clustering. This study focused mainly three aspects of work compared with the traditional tuning model. First, the calculation of the coupling matrix of scattering parameters is achieved by solving polynomial coefficients after eliminating the inconsistent phase shift and resonant cavity loss. Second, the best clustering center and a number were obtained by mapping the scattered data to high‐dimensional space, and the prediction of multi‐output variables were realized by sub‐model probability fusion. Third, an improved shuffled frog leaping algorithm was introduced to optimize the initial weights of the back‐propagation neural network, and a differential operation significantly improved the diversity of the population and the searchability of the algorithm. Finally, the experiment of nine‐order cross‐coupled filters shows that the proposed method has a better capability to train the weights and thresholds, which improves the generalization performance of the system.

show abstract

Section: Introductionmentioning

confidence: 95%

“…[] proposed a data‐driven model for tuning microwave filters, which pointed out the direction of tuning for low‐order filters. In another work, a multivalued neural network was used to satisfy the tuning requirements of high‐order filters, a method that significantly improved the convergence speed of the algorithm . Similarly, ref.…”

Section: Introductionmentioning

confidence: 99%

Tuning model for microwave filter by using improved back‐propagation neural network based on gauss kernel clustering

Cao

2019

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

show abstract

“…Applications to Microwave Filters [18] In the second part of the thesis, the following significant contributions were made for inverse modeling of microwave filters:…”

Section: Multivalued Neural Network Inverse Modeling Andmentioning

confidence: 99%

“…One of the techniques is through optimization [2], [92], [93]. Another technique is the inverse modeling technique [1], [17], [18].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Advances in Optimization and Inverse Modeling Techniques for Microwave Filters

Zhang¹

Self Cite

View full text Add to dashboard Cite

Optimization and modeling techniques are the essential part of design process of microwave filters. Space mapping is a recognized method for speeding up electromagnetic (EM) optimization, and has been applied to microwave filter design.In the first part of this thesis, a cognition-driven formulation of space mapping method is proposed and applied to EM-based filter optimization to increase optimization efficiency and the ability to avoid being trapped in local minima. This new technique utilizes two sets of intermediate feature space parameters, including feature frequency parameters and ripple height parameters. The design variables are mapped to the feature frequency parameters, which are further mapped to the ripple height parameters. By formulating the cognition-driven optimization directly in the feature space, our method increases optimization efficiency and the ability to avoid being trapped in local minima. In the second part of this thesis, a multivalued neural network is proposed to solve the non-uniqueness (multivalued) problem in inverse modeling. Our proposed technique can be effectively applied to parameter extraction of microwave filters. We propose a multivalued neural network inverse modeling technique to associate a single set of electrical parameters with multiple sets of geometrical or physical parameters. One set of geometrical or physical parameters is called one value of our proposed inverse model. Our proposed multivalued neural network is structured to accommodate multiple values for the model output.We also propose a new training error function to focus on matching each training sample using only one value of our proposed inverse model, while other values are ii free and can be trained to match other contradictory samples. In this way, our pro-

show abstract

Neural Networks for Microwave Circuits

Feng,

Na,

Jin

et al. 2024

Encyclopedia of RF and Microwave Engineering

View full text Add to dashboard Cite

Neural networks, also called artificial neural networks (ANNs), are important techniques for performing forward/inverse modeling for microwave 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 could be otherwise computationally expensive or for which efficient analytical formulas are not available. By training an ANN using data from electromagnetic (EM)/physics simulations, one can use the trained ANN as models for microwave circuits to replace the EM/physics models, which are typically CPU intensive, to significantly accelerate circuit design with EM/physics‐level accuracies. Fundamental concepts of the ANN structure and training, knowledge‐based neural networks, automated model generation, neuro‐transfer function modeling, deep neural network modeling, neural network‐based inverse modeling, and the use for EM/multiphysics design optimizations are described here.

show abstract

Multivalued Neural Network Inverse Modeling and Applications to Microwave Filters

Cited by 153 publications

References 29 publications

Tuning model for microwave filter by using improved back‐propagation neural network based on gauss kernel clustering

Tuning model for microwave filter by using improved back‐propagation neural network based on gauss kernel clustering

Advances in Optimization and Inverse Modeling Techniques for Microwave Filters

Neural Networks for Microwave Circuits

Contact Info

Product

Resources

About