☆ 4.7 Article

Grain size analysis in permanent magnets from Kerr microscopy images using machine learning techniques

MATERIALS CHARACTERIZATION (2022)

Journal

MATERIALS CHARACTERIZATION

Volume 186, Issue -, Pages -

Publisher

ELSEVIER SCIENCE INC

DOI: 10.1016/j.matchar.2022.111790

Keywords

Machine learning; Kerr microscopy; Permanent magnets; Grain analysis; Semantic segmentation; Micromagnetic domains; Quantitative microstructure analysis

Funding

German Federal Ministry for Education and Research (BMBF) [13FH255PA6]

Ask authors/readers for more resources

Protocol

Community support

Reagent

Community support

Automated Summary New
Abstract

Understanding the relationships between composition, structure, processing and properties is important for developing improved materials. This paper introduces the use of machine learning and deep learning models to classify the microstructure of sintered NdFeB magnets and discusses the challenges faced by traditional machine learning models in this process.

Understanding the relationships between composition, structure, processing and properties helps in the development of improved materials for known applications as well as for new applications.Materials scientists, chemists and physicists have researched these relationships for many years, until the recent past, by characterizing the bulk properties of functional materials and describing them with theoretical models. Magnets are widly used in electric vehicles (EV), hybrid electric vehicles (HEV), data storage, power generation and transmission, sensors etc. The search for novel magnetic phases requires an efficient quantitative microstructure analysis of microstructural information like phases, grain distribution and micromagnetic structural information like domain patterns, and correlating the information with intrinsic magnetic parameters of magnet samples. The information out of micromagnetic domains helps in obtaining the optimized microstructures in magnets that have good intrinsic magnetic properties.This paper is aimed at introducing the use of a traditional machine learning (ML) model with a higher dimensional feature set and a deep learning (DL) model to classify various regions in sintered NdFeB magnets based on Kerr-microscopy images. The obtained results are compared against reference data, which is generated manually by subject experts. Additionally, the results were compared against the approach for grain analysis, which is based on the electron backscatter diffraction (EBSD) technique. Further, the challenges faced by the traditional machine learning model for classifying microstructures in Kerr micrographs are discussed.

Authors

I am an author on this paper

Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7

Not enough ratings

Secondary Ratings

Novelty

Significance

Scientific rigor

Rate this paper

Microstructure, coercivity and thermal stability of nanostructured (Nd,Ce)-(Fe,Co)-B hot-compacted permanent magnets

Yuye Wu, Konstantin P. Skokov, Lukas Schafer, Fernando Maccari, Alex Aubert, Hao Xu, Haichen Wu, Chengbao Jiang, Oliver Gutfleisch

Summary: We report on the microstructure, hard magnetic properties, and thermal stability of hot-compacted nanocrystalline (Nd0.85Ce0.15)15(Fe1-xCox)7(8)B(7) permanent magnets. The substitution of Fe by Co influences the grain boundary phase composition and degrades the coercivity at lower Co concentrations (x < 0.3). At higher Co concentrations (x >= 0.6), the absence of a grain boundary phase leads to strong magnetic coupling. Additional RE(Fe,Co)2, RE(Fe,Co)4B, and RECo5 phases gradually form with increasing Co concentration (x > 0.6). A new type of microstructure with nanograins and good thermal stability is observed at x = 0.4 and 0.6. In (Nd0.85Ce0.15)(15)(Fe0.4Co0.6)78B-7 magnets, the temperature coefficient of coercivity exceeds 0.3%/K within the temperature range of 300 K-500 K and 0.23%/K for the temperature range of 300 K-650 K, demonstrating the potential for designing highly thermal-stable permanent magnets.

ACTA MATERIALIA (2022)