Integrated High-Frequency Coaxial Transformer Design Platform Using Artificial Neural Network Optimization and FEM Simulation

Li, Jeffrey; Water, Wayne; Zhu, Boyuan; Lu, Junwei

doi:10.1109/tmag.2014.2368123

Cited by 23 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Overall, there is more research carried out on machine learning for improving the runtime of the optimization of electromagnetic devices, as was also shown in Table 2. Different machine learning algorithms, such as SVM, multi-layer perceptron (MLP), Knearest neighbor (KNN), and CNN have been investigated to optimize transformers, antennas, and motors (motors are the majority applications) [135][136][137][138][139][140][141][142][146][147][148][149][150]. It is noted that deep learning follows promising results when applied for topology optimization of electromagnetic devices, and this topic has attracted much attention recently [143][144][145].…”

Section: Machine Learning For Optimization Of Electromagnetic Devicesmentioning

confidence: 99%

Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

Lei

Bramerdorfer

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

This paper reviews the recent developments of design optimization methods for electromagnetic devices, with a focus on machine learning methods. First, the recent advances in multi-objective, multidisciplinary, multilevel, topology, fuzzy, and robust design optimization of electromagnetic devices are overviewed. Second, a review is presented to the performance prediction and design optimization of electromagnetic devices based on the machine learning algorithms, including artificial neural network, support vector machine, extreme learning machine, random forest, and deep learning. Last, to meet modern requirements of high manufacturing/production quality and lifetime reliability, several promising topics, including the application of cloud services and digital twin, are discussed as future directions for design optimization of electromagnetic devices.

show abstract

Section: Machine Learning For Optimization Of Electromagnetic Devicesmentioning

confidence: 99%

Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

Lei

Bramerdorfer

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The selected model represents a pragmatic approach with regression ANNs, which is robust and easy to extend [15], [36], [40], [41]. Since the model uses ANNs at the sub-component level, internal variables are accessible for inspection.…”

Section: A Working Principlementioning

confidence: 99%

Artificial Neural Network (ANN) Based Fast and Accurate Inductor Modeling and Design

Guillod

Papamanolis

Kolar

2020

IEEE Open J. Power Electron.

151

View full text Add to dashboard Cite

This paper analyzes the potential of Artificial Neural Networks (ANNs) for the modeling and optimization of magnetic components and, specifically, inductors. After reviewing the basic properties of ANNs, several potential modeling and design workflows are presented. A hybrid method, which combines the accuracy of 3D Finite Element Method (FEM) and the low computational cost of ANNs, is selected and implemented. All relevant effects are considered (3D magnetic and thermal field patterns, detailed core loss data, winding proximity losses, coupled loss-thermal model, etc.) and the implemented model is extremely versatile (30 input and 40 output variables). The proposed ANN-based model can compute 50 000 designs per second with less than 3 % deviation with respect to 3D FEM simulations. Finally, the inductor of a 2 kW DC-DC buck converter is optimized with the ANN-based workflow. From the Pareto fronts, a design is selected, measured, and successfully compared with the results obtained with the ANNs. The implementation (source code and data) of the proposed workflow is available under an open-source license.

show abstract

“…On the other hand, the magnetic link is one of the lossy, heavy, and bulky components in a high-frequency and very-high-frequency power supplies or converters. The recently developed amorphous and nanocrystalline magnetic alloy shows significantly lower core loss and a higher maximum flux density, which could lead to a possible route to design an efficient, compact, and lightweight magnetic core [27][28][29]. Fig.…”

Section: Grid Integration Of Direct Drive Wave Energy Generators (Ddwmentioning

confidence: 99%

Design and characterisation of advanced magnetic material‐based core for isolated power converters used in wave energy generation systems

Islam

Farrok²,

Rahman

et al. 2020

IET Electric Power Applications

View full text Add to dashboard Cite

The oceanic wave energy generation has been drawn significant attention in the field of power engineering recently. These generation systems are basically direct drive electrical power generators connected to the wave energy devices with the variable frequency drives (VFDs). This study proposes an application of high-frequency transformers at the output stages of VFDs for the galvanic isolation purpose among multiple output ports of VFDs in a wave farm. The design process of a highfrequency magnetic link involves multiphysics problems that entail complex tradeoffs between electrical and magnetic properties including efficiency. Moreover, the performance of the magnetic link depends on the switching characteristics of the power switching devices and various excitation signals. Therefore, extensive multiphysics research in the field of design and optimisation of magnetic links is needed to develop next-generation technologies. In this study, a finite-element method-based systematic process is presented for the design of amorphous alloy-based core of the high-frequency magnetic link. Two cores are developed and characterised in the laboratory. The characterised data obtained from the experiment can be used in the future design optimisation of other high-frequency magnetic links.

show abstract

Integrated High-Frequency Coaxial Transformer Design Platform Using Artificial Neural Network Optimization and FEM Simulation

Cited by 23 publications

References 11 publications

Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

Artificial Neural Network (ANN) Based Fast and Accurate Inductor Modeling and Design

Design and characterisation of advanced magnetic material‐based core for isolated power converters used in wave energy generation systems

Contact Info

Product

Resources

About