MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling

Li, Haoran; Serrano, Diego; Guillod, Thomas; Dogariu, Evan; Nadler, Andrew B.; Wang, Shukai; Luo, Min; Bansal, Vineet; Chen, Yuxin; Sullivan, Charles R.; Chen, Minjie

doi:10.1109/apec43599.2022.9773372

“…One major obstacle for data-driven models of magnetic materials is that only a small amount of high-quality data is available, especially for new materials. A large-scale opensource power magnetics database -MagNet 1 -has been constructed recently to provide a common ground for big-data characterization for power magnetics [11]. Details about this database are provided in a separate paper [12].…”

Section: Data Preparationmentioning

confidence: 99%

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

Chen¹

2023

Preprint

0

View full text Add to dashboard Cite

Core losses and hysteresis loops are critical information in the design process of power magnetics, yet the physics behind core loss and hysteresis loops are not fully understood. Core losses and hysteresis loops change for each magnetic material, are highly nonlinear, and depend heavily on the electrical operating conditions (e.g., waveform, frequency, amplitude, dc bias) and the mechanical properties (e.g. pressure, vibration), as well as temperature, and geometry of the magnetic components. Understanding the complexity of these factors is important for the development of accurate models, in addition to addressing the applicability and limitations of each model. 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 developed large-scale open-source database - MagNet - the core losses and hysteresis loops of Mn-Zn ferrites are analyzed in a wide range of amplitudes, frequencies, waveform shapes, dc bias, and temperatures, to quantify the complexity of modeling magnetic core losses and hysteresis loops and provide guidelines for modeling power magnetics with data-driven methods.

show abstract

“…One major obstacle for data-driven models of magnetic materials is that only a small amount of high-quality data is available in the vendor's datasheets. A large-scale opensource power magnetics database -MagNet 1 -has been constructed recently to provide a common ground for datadriven characterization for power magnetics [14]. Details about this database are provided in a separate paper [12].…”

Section: Data Preparationmentioning

confidence: 99%

Quantifying the Complexity of Modeling Power Magnetic Material Characteristics

Chen¹

2022

Preprint

0

View full text Add to dashboard Cite

Core losses and hysteresis loops are critical information in the design process of power magnetics, yet the physics behind core loss and hysteresis loops are not fully understood. Core losses and hysteresis loops change for each magnetic material, are highly nonlinear, and depend heavily on the electrical operating conditions (e.g., waveform, frequency, amplitude, dc bias) and the mechanical properties (e.g. pressure, vibration), as well as temperature, and geometry of the magnetic components. Understanding the complexity of these factors is important for the development of accurate models, in addition to addressing the applicability and limitations of each model. 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 developed large-scale open-source database - MagNet - the core losses and hysteresis loops of Mn-Zn ferrites are analyzed in a wide range of amplitudes, frequencies, waveform shapes, dc bias, and temperatures, to quantify the complexity of modeling magnetic core losses and hysteresis loops and provide guidelines for modeling power magnetics with data-driven methods.

show abstract

“…These magnetic components are typically the largest in volume and have significant power loss, and therefore have an adverse impact on the system performance. While there have been major strides in the modeling and analysis of power This paper is a combination and extension of four previously published conference paper, "MagNet: a machine learning framework for magnetic core loss modeling" in IEEE COMPEL 2020 [1], "Transfer Learning Methods for Magnetic Core Loss Modeling" in IEEE COMPEL 2021 [2], "MagNet: an open-source database for data-driven magnetic core loss modeling" in IEEE APEC 2022 [3], and "Neural Network as Datasheet: Modeling B-H Loops of Power Magnetics with Sequence-to-Sequence LSTM Encoder-Decoder Architecture" in IEEE COMPEL 2022 [4]. This work was jointly supported by ARPA-E Differentiate Project and the Schmidt DataX Fund at Princeton University made possible through a major gift from the Schmidt Futures Foundation.…”

Section: Introductionmentioning

confidence: 99%

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

Chen¹

2023

Preprint

0

View full text Add to dashboard Cite

This paper applies machine learning to modeling power magnetics. 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. 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 core losses and B–H loops. Machine learning allows the many factors that may influence the magnetic characteristics being modeled in a unified framework, and provides insights to quantify the complexity of magnetic characteristics and reduce the size of the measurement data required to build a precise model. Neural network models are found effective in compressing the measurement data and predicting the behaviors of magnetic materials such as the core loss and the B–H loop. The behaviors of a typical power magnetic material (e.g., TDK N87) across a wide range of operating conditions (e.g., temperature, waveform, dc-bias) can be well described by a small-scale neural network (200 KB) which is 10,000 times smaller than the raw measured time-series data (2 GB), paving the way toward using neural networks as an interactive datasheet to assist magnetics design.

show abstract

MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling

Cited by 39 publications

References 25 publications

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

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

Quantifying the Complexity of Modeling Power Magnetic Material Characteristics

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

Contact Info

Product

Resources

About