Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing

Abstract

The macroscopic properties of permanent magnets and the resultant performance required for real implementations are determined by the magnets’ microscopic features. However, earlier micromagnetic simulations and experimental studies required relatively a lot of work to gain any complete and comprehensive understanding of the relationships between magnets’ macroscopic properties and their microstructures. Here, by means of supervised learning, we predict reliable values of coercivity (μ0Hc) and maximum magnetic energy product (BHmax) of granular NdFeB magnets according to their microstructural attributes (e.g. inter-grain decoupling, average grain size, and misalignment of easy axes) based on numerical datasets obtained from micromagnetic simulations. We conducted several tests of a variety of supervised machine learning (ML) models including kernel ridge regression (KRR), support vector regression (SVR), and artificial neural network (ANN) regression. The hyper-parameters of these models were optimized by a very fast simulated annealing (VFSA) algorithm with an adaptive cooling schedule. In our datasets of randomly generated 1,000 polycrystalline NdFeB cuboids with different microstructural attributes, all of the models yielded similar results in predicting both μ0Hc and BHmax. Furthermore, some outliers, which deteriorated the normality of residuals in the prediction of BHmax, were detected and further analyzed. Based on all of our results, we can conclude that our ML approach combined with micromagnetic simulations provides a robust framework for optimal design of microstructures for high-performance NdFeB magnets.

Optimizing the Structures of Transformer Neural Networks Using Parallel Simulated Annealing

“…The use of SA was estimated to improve the prediction time in the problem analyzed by around 15% in most cases. In another example, robust networks aimed at optimizing structures of high-performance magnets were decided using the Very Fast Simulated Annealing Algorithm [62,63].…”

Recent Unrevealing on Magnetic Hysteresis of Permanent Magnets

“…解析などの巨視的な解析手法に加え [20][21][22] ，最近では磁気トモ グラフィー測定による微視的な解析手法も整備されつつあ る [23][24][25] ．また，Micromagnetic (MM) シミュレーションも大き な進展を見せており [26][27][28][29][30][31] ，計算機や計算アルゴリズムの進化 に加えて機械学習を導入した高速化，大規模化 [32][33][34] や電子顕 微鏡で得た実際の微細組織構造をモデリングする手法の開 発 [35][36][37] なども進められている． ÁEðM; HÞ ¼ EðM [20][21][22]62)…”

Artificial Intelligence—Engineering Magnetic Materials: Current Status and a Brief Perspective

“…Thermodynamic stability, combined with magnetic performance, also constitutes examples of typical information able to be acquired. The (material) characterization context currently brings interesting opportunities for enhancing quality control: training algorithms with microstructures representing materials with different features, as in the case of magnetic losses for electrical steels, but potentially applicable to others as intrinsic coercivity of permanent magnets (as exemplified in [30]) has the potential to support industry in further refinements of process control. Lastly, in the space of applications, there is apparently a limited implementation of AI linked to magnetic materials per se, although it is already possible to confirm its value in predicting results in both individual components, as inductors, and (sub)systems such as industrial motors.…”