arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02475cond-mat.mtrl-sciphysics.data-an
收藏

高性能永磁体矫顽力的精确机器学习预测

Accurate Machine Learning Predictions of Coercivity in High-Performance Permanent Magnets

Churna Bhandari, Gavin N. Nop, Jonathan D. H. Smith, Durga Paudyal

AI总结:

针对永磁体矫顽力难以精确预测的问题,该研究结合实验数据、DFT计算与微磁学建模,利用机器学习方法实现了对Ce掺杂Nd2Fe14B等材料矫顽力的快速准确预测,并揭示了单轴磁晶各向异性的关键作用。

摘要:

电动汽车和风力涡轮机行业对高性能永磁体日益增长的需求,促使人们寻找具有成本效益的替代品。由于稀土元素的全球供应、材料稳定性和较低的最大磁能积 BH$_{max}$ 等问题,发现具有理想内禀和外禀永磁性能的新型磁性材料对研究人员提出了重大挑战。虽然第一性原理密度泛函理论(DFT)能够预测材料的磁矩、磁晶各向异性常数和交换相互作用,但它无法计算矫顽力($H_c$)。尽管理论上可以通过微磁学模拟计算 $H_c$,但由于 Brown 佯谬,预测值比实验值大近一个数量级。为规避这些问题,我们在从实验、DFT 计算和微磁学建模获得的广泛数据库上采用机器学习(ML)方法。大型数据集的使用使得对 Ce 掺杂 Nd$_2$Fe$_{14}$B 等材料的 $H_c$ 预测更为真实,且与微磁学模拟的矫顽力相比表现更佳。值得注意的是,我们的 ML 模型准确识别出单轴磁晶各向异性是 $H_c$ 的主要贡献因素。通过 DFT 计算,我们预测了 Nd$_2$Fe$_{14}$B 中依赖于 Nd 位的磁各向异性行为,证实 Nd $4g$ 位主要贡献于单轴磁晶各向异性,并计算了 Curie 温度(T$_{C}$)。两项计算结果均与实验吻合良好。耦合的实验数据集与包含 DFT 输入的 ML 建模,在预测 $H_c$ 时比以往使用微磁学建模具有更高的准确度和速度。此外,我们利用 ML 预测,通过微磁学模拟对晶粒间交换耦合进行了逆向工程。

英文摘要:

Increased demand for high-performance permanent magnets in the electric vehicle and wind turbine industries has prompted the search for cost-effective alternatives.Discovering new magnetic materials with the desired intrinsic and extrinsic permanent magnet properties presents a significant challenge to researchers because of issues with the global supply of rare-earth elements, material stability, and a low maximum magnetic energy product BH$_{max}$.While first-principle density functional theory (DFT) predicts materials' magnetic moments, magneto-crystalline anisotropy constants, and exchange interactions, it cannot compute coercivity ($H_c$).Although it is possible to calculate $H_c$ theoretically with micromagnetic simulations, the predicted value is larger than the experiment by almost an order of magnitude, due to the Brown paradox.To circumvent these, we employ machine learning (ML) methods on an extensive database obtained from experiments, DFT calculations, and micromagnetic modeling.The use of a large dataset enables realistic $H_c$ predictions for materials such as Ce-doped Nd$_2$Fe$_{14}$B, comparing favorably against micromagnetically simulated coercivities.Remarkably, our ML model accurately identifies uniaxial magneto-crystalline anisotropy as the primary contributor to $H_c$. With DFT calculations, we predict the Nd-site dependent magnetic anisotropy behavior in Nd$_2$Fe$_{14}$B, confirming that Nd $4g$-sites mainly contribute to uniaxial magneto-crystalline anisotropy, and also calculate Curie temperature (T$_{C}$).Both calculated results are in good agreement with experiment.The coupled experimental dataset and ML modeling with DFT input predict $H_c$ with far greater accuracy and speed than was previously possible using micromagnetic modeling.Further, we reverse-engineer the inter-grain exchange coupling with micromagnetic simulations by employing the ML predictions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑