Machine learning approaches for permittivity prediction and rational design of microwave dielectric ceramics
Machine learning approaches for permittivity prediction and rational design of microwave dielectric ceramics
复制标题
用于微波介电陶瓷介电常数预测和合理设计的机器学习方法
DOI：
10.1016/j.jmat.2021.02.012
复制
发表时间：
2021-10-15
影响因子：
9.4
通讯作者：
Li, Yongxiang
中科院分区：
文献类型：
--
作者：
Qin, Jincheng;Liu, Zhifu;Li, Yongxiang
低介电常数微波介质陶瓷（MWDC）由于其在5G和物联网新时代的应用前景而引起了人们的极大兴趣。虽然理论规则和计算方法是实际使用的介电常数预测，不令人满意的可预测性和普适性阻碍了新的高性能材料的合理设计。在这项工作中，基于254个单相微波介电陶瓷（MWDC）的数据集，机器学习（ML）方法建立了一个高精度的介电常数预测模型，并给出了定量化学/结构性质关系的见解。我们采用了五种常用的算法，并介绍了32个内在的化学，结构和热力学特征，与介电常数的建模。机器学习结果有助于确定介电常数的决定性因素，包括单位体积的极化率、平均键长和每个原子的平均单元体积。讨论了特征与性质的关系。通过验证数据验证了径向基函数核支持向量回归机构建的最优模型具有良好的上级预测性和泛化能力。低介电常数材料系统筛选从数据集相似的3300材料没有报道的微波介电常数高通量预测使用最佳模型。合成了几种预测的低介电常数陶瓷，实验结果与ML预测结果吻合较好，验证了预测模型的可靠性。(C)2021中国陶瓷学会制作和主办：Elsevier B. V.
Low permittivity microwave dielectric ceramics (MWDCs) are attracting great interest because of their promising applications in the new era of 5G and IoT. Although theoretical rules and computational methods are of practical use for permittivity prediction, unsatisfactory predictability and universality impede rational design of new high-performance materials. In this work, based on a dataset of 254 single-phase microwave dielectric ceramics (MWDCs), machine learning (ML) methods established a high accuracy model for permittivity prediction and gave insights of quantitative chemistry/structureproperty relationships. We employed five commonly-used algorithms, and introduced 32 intrinsic chemical, structural and thermodynamic features which have correlations with permittivity for modeling. Machine learning results help identify the permittivity decisive factors, including polarizability per unit volume, average bond length, and average cell volume per atom. The feature-property relationships were discussed. The optimal model constructed by support vector regression with radial basis function kernel was validated its superior predictability and generalization by verification dataset. Low permittivity material systems were screened from a dataset of similar to 3300 materials without reported microwave permittivity by high-throughput prediction using optimal model. Several predicted low permittivity ceramics were synthesized, and the experimental results agree well with ML prediction, which confirmed the reliability of the prediction model. (C) 2021 The Chinese Ceramic Society. Production and hosting by Elsevier B.V.