Neural Network Inverse Modeling and Applications to Microwave Filter Design

By Humayun Kabir, Ying Wang, Ming Yu, Qi-jun Zhang. IEEE transactions on microwave theory and techniques, 2008

313 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/d14f25d539eb937e1e1e419315d9cb3e8ddcf1ca

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Slawomir Koziel
2. Yixuan Tan
3. Yongmin Liu
4. Zongfu Yu
5. Erfan Khoram
6. Dianjing Liu

In Electrical and Electronic Engineering

1. Slawomir Koziel
2. Tomislav Dragicevic
3. Mateja Novak
4. Zongfu Yu

Citations in the corpus

• Artificial Intelligence Aided Automated Design for Reliability of Power Electronic Systems (2019, unknown): “Forward ANNs are the most commonly used deep-learning algorithms and have been applied already to various electrical engineering problems, from predicting the voltage distortion in electrical distribution networks [28], to designing the microwave filters [29], [30].”
• Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures (2017, result): “[1] H.”
• Weighting Factor Design in Model Predictive Control of Power Electronic Converters: An Artificial Neural Network Approach (2019, background): “learning algorithms for various electrical engineering problems, from predicting the voltage distortion in electrical distribution networks [26], to designing the microwave filters [27], [28].”
• Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy (2019, methodology): “Neural networks have been used to solve the design, optimization and prediction problems of electromagnetism in some early works [45-47], but the model capability and performance were limited, largely due to the simple model structure and the lack of data.”
• Fast simulation‐driven antenna design using response‐feature surrogates (2015, background): “, kriging [19–21], neural networks [22, 23], or support vector regression [24]), and correction of an underlying low-fidelity model (socalled physics-based surrogates [25]), the latter approach seems to be more suitable for ad hoc optimization of a given antenna structure due to the high initial cos”