This paper motivates the development of sophisticated data–driven models for power magnetic material characteristics.Core losses and hysteresis loops are critical information in the design process of power magnetics, yet the physics behind them is not fully understood or directly applicable. Both losses and hysteresis loops change for each magnetic material and depend heavily on electrical operating conditions (e.g., waveform, frequency, amplitude, dc bias), mechanical properties (e.g., pressure,vibration), temperature, and geometry of the magnetic components,and in a nonlinear and coupled fashion. Understanding the complex and intertwined relationship these factors have on core loss is important for the development of accurate models and their applicability and limitations. Existing studies on power magnetics are usually developed based on a small amount of data and do not reveal the full magnetic behavior across a wide range of operating conditions. In this paper, based on a recently dev loped large-scale open-source database– <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MagNet –the core losses and hysteresis loops of Mn–Zn ferrites are analyzed over a wide range of amplitudes, frequencies, waveform shapes, dc bias levels, and temperatures, to quantify the complexity of modeling magnetic core losses, amplitude permeability, and hysteresis loops and provide guidelines for modeling power magnetics with datadriven methods.

/pdf/why-magnet-quantifying-the-complexity-of-modeling-power-26frum9c.pdf

Why MagNet: Quantifying the Complexity of Modeling Power Magnetic Material Characteristics

This article applies machine learning to power magnetics modeling. We first introduce an open-source database—MagNet—which hosts a large amount of experimentally measured excitation data for many materials across a variety of operating conditions, consisting of more than 500 000 data points in its current state. The processes for data acquisition and data quality control are explained. We then demonstrate a few neural network-based power magnetics modeling tools for modeling the core losses and <inline-formula><tex-math notation="LaTeX">$B$</tex-math></inline-formula>–<inline-formula><tex-math notation="LaTeX">$H$</tex-math></inline-formula> loops. The neural network allows multiple factors that may influence the magnetic characteristics to be modeled in a unified framework, where the nonlinear behaviors are captured with high accuracy and high generality. Neural network models are found to be effective in compressing the measurement data and predicting the material characteristics, paving the way for “neural networks as datasheets” to assist power magnetics design. Transfer learning is applied to the training of neural network models to further reduce the data size requirement while maintaining sufficient model accuracy.

How MagNet: Machine Learning Framework for Modeling Power Magnetic Material Characteristics

This article presents the MagNet-AI platform as an online platform to demonstrate the “neural network as datasheet” concept for <inline-formula><tex-math notation="LaTeX">$B$</tex-math></inline-formula>–<inline-formula><tex-math notation="LaTeX">$H$</tex-math></inline-formula> loop modeling and material recommendation of power magnetics across wide operation range. Instead of directly presenting the measured characteristics of magnetic core materials as time sequences, we employ a neural network to capture the <inline-formula><tex-math notation="LaTeX">$B$</tex-math></inline-formula>–<inline-formula><tex-math notation="LaTeX">$H$</tex-math></inline-formula> loop mapping relationships of magnetic materials under different excitation waveforms at different temperatures and dc bias. Long short-term memory and transformer-based neural network models are developed, verified, and compared. The neural network can be used to rapidly predict hysteresis loops and core losses under different operating conditions, compare materials, and recommend materials for design. The neural network model is also proved effective in reconstructing the raw measurement while accurately maintaining the magnetic characteristics, enabling rapid material evaluation and comparison.

MagNet-AI: Neural Network as Datasheet for Magnetics Modeling and Material Recommendation

Predicting core losses is a difficult task for designing magnetic components. Under triangular current waveforms the classical approaches work with duty cycles close to 0.5 but are inaccurate for high and low duty cycles. In this work the composite waveform hypothesis is tested, using data from the MagNet database for N87 material at 25 ºC (3312 data points). Limitations of the composite waveform hypothesis are discussed and a technique to expand the loss space is presented. The new approach based in an extended loss space is validated against the classical improved Generalized Steinmetz Equation, reducing the root mean square and 95 percentile errors by 5.85 and 6.96 times, allowing to predict core losses accurately even at high and low duty cycles. A direct correlation between the expanded loss space and the Steinmetz parameters from the improved Generalized Steinmetz Equation is proven, allowing to represent the core losses as functions of these parameters and generating the composite improved Generalized Steinmetz Equation. The proposed methodology for core loss prediction is validated making use of all data available from the MagNet database (10 materials, 4 temperatures, 59423 data points), achieving better results than the commonly used improved Generalized Steinmetz Equation. 

The Composite Improved Generalized Steinmetz Equation (ciGSE): an Accurate Model Combining the Composite Waveform Hypothesis with Classical Approaches

A precise evaluation of power converter losses is essential for accurately predicting power loss and optimizing control parameters to enhance efficiency across various scenarios and applications. Conventional power loss evaluation methods separate the theoretical analysis and experimental verification stages. Consequently, these methods often suffer from irreconcilable disparities between the analytical predictions and measurement outcomes. This article introduces a transfer learning (TL)-based refinement approach for power loss evaluation, which can be iteratively improved with ongoing experimental data. Our method entails the creation of an extensive source domain dataset for training a source domain model, followed by fine-tuning in the target domain. Consequently, a self-adaptive and refined power loss evaluation model is established with a small amount of experimental data. We conducted a case study featuring a 6.6 kW synchronous boost converter, considering six degrees of freedom for operational conditions. Leveraging a dataset of 2 33 280 simulation samples and 45 experimental samples, our refined power loss evaluation model achieved a remarkable 50% reduction in average power loss error compared with conventional methodologies. Guided by the TL refined power loss model, the peak efficiency and corresponding optimal control parameters can be obtained.

Refining Power Converter Loss Evaluation: A Transfer Learning Approach

This paper presents a transformer-based encoder-projector-decoder neural network architecture for modeling power magnetics B-H hysteresis loops. The transformer-based encoder-decoder network architecture maps a flux density excitation waveform (B) into the corresponding magnetic field strength (H) waveform. The predicted B-H loop can be used to estimate the core loss and support magnetics-in-circuit simulations. A projector is added between the transformer encoder and decoder to capture the impact of other inputs such as frequency, temperature, and dc bias. An example transformer neural network is designed, trained, and tested to prove the effectiveness of the proposed architecture.

Predicting the B-H Loops of Power Magnetics with Transformer-based Encoder-Projector-Decoder Neural Network Architecture

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of {limit} columns in the table. Remove at least 1 column to add or create another one.

Min Luo

Author Tools

Chat about Author

Papers

Why MagNet: Quantifying the Complexity of Modeling Power Magnetic Material Characteristics

How MagNet: Machine Learning Framework for Modeling Power Magnetic Material Characteristics

Predicting the B-H Loops of Power Magnetics with Transformer-based Encoder-Projector-Decoder Neural Network Architecture