1.交通运输部天津水运工程科学研究所,天津 300456
2.中国地质大学 数理学院,北京 100080
3.北京邮电大学 集成电路学院,北京 100080
李顺(1997—),助理研究员,博士,主要从事高性能热电转换材料与器件研究,(电子信箱)lis@tiwte.ac.cn。
收稿:2026-01-10,
网络首发:2026-04-22,
移动端阅览
李顺,彭浩然,符秀丽.数据驱动的高熵碲化物组分高通量理论设计与性能预测[J].宁夏大学学报(自然科学版中英文),XXXX,XX(XX):1-10.
Li Shun,Peng Haoran,Fu Xiuli.Research on Composition Design and Phase Stability of High Entropy Telluride Driven by Data[J].Journal of Ningxia University (Natural Science Edition in Chinese and English),XXXX,XX(XX):1-9.
李顺,彭浩然,符秀丽.数据驱动的高熵碲化物组分高通量理论设计与性能预测[J].宁夏大学学报(自然科学版中英文),XXXX,XX(XX):1-10. DOI: 10.20176/j.cnki.nxdz.20260404.
Li Shun,Peng Haoran,Fu Xiuli.Research on Composition Design and Phase Stability of High Entropy Telluride Driven by Data[J].Journal of Ningxia University (Natural Science Edition in Chinese and English),XXXX,XX(XX):1-9. DOI: 10.20176/j.cnki.nxdz.20260404.
针对高熵碲化物热电材料组分的空间庞大、传统“试错法”研发模式效率低的难题,从理论层面建立一套结合机器学习与第一性原理计算的数据驱动设计框架。通过构建包含混合焓、原子尺寸差异等物理特征的高维描述符空间,训练梯度提升回归模型,实现对多主元体系形成能的精准预测。采用沙普利加性解释(SHapley additive explanations,SHAP)方法,揭示热力学参数与几何参数间的竞争机制,确定定量的相形成判据。利用该判据对 PbTe
-
SnTe
-
GeTe三元体系进行全组分高通量筛选,成功获得一种兼具高热力学稳定性(-46.31 kJ/mol)与超低晶格热导率(0.85 W/mK)的高熵组分。电子结构计算结果显示,引入过渡金属Mn,诱导了导带底能带收敛与p
-
d轨道强杂化,有效解耦了电、热输运参数。理论评估结果显示,该高熵组分在850 K时的热电优值达1.60,较PbTe基体提升67%。初步验证了数据驱动策略在理论设计中的可行性,为后续的实验合成与验证提供了明确的组分指引。
To address the vast compositional space and the inefficiency of traditional “trial-and-error” methods in the development of high-entropy telluride thermoelectric materials, this study establishes a theoretical data-driven design framework that integrates machine learning with first-principles calculations. By constructing a high-dimensional descriptor space that encompasses physical features such as mixing enthalpy and atomic size difference, a gradient boosting regression model was trained to accurately predict the
formation energy of multiprincipal-element systems. SHAP (SHapley Additive exPlanations) interpretability analysis elucidated the competitive mechanisms between thermodynamic and geometric parameters, leading to the formulation of a quantitative criterion for phase formation. Using this criterion, a high-throughput theoretical screening of the entire PbTe-SnTe-GeTe ternary space was conducted. An optimal high-entropy composition featuring both high thermodynamic stability (-46.31 kJ/mol) and ultra-low lattice thermal conductivity (0. 85 W/mK) was theoretically identified. Electronic structure calculations further demonstrated that the introduction of the transition metal Mn induces convergence of the conduction band and strong hybridization of p-d orbitals, which effectively decouples the electrical and thermal transport parameters. Theoretical evaluations suggest that this high-entropy composition could achieve a thermoelectric figure of merit (
z
T) of 1.60 at 850 K, representing an approximate 67% improvement over the PbTe matrix. This work preliminarily verifies the feasibility of data-driven strategies for rational theoretical design of complex thermoelectric materials and provides a clear framework for future experimental synthesis and validation. It is important to note that all results herein are theoretical predictions, and subsequent experimental synthesis and performance evaluations are ongoing.
肖颖 , 梁耕源 , 雷博文 , 等 . 用于能量收集的离子热电材料研究进展 [J]. 材料导报 , 2023 , 37 ( 4 ): 22020174 . DOI: 10.11896/cldb.22020174 http://dx.doi.org/10.11896/cldb.22020174 .
陈群 , 郝俊红 , 陈磊 , 等 . 电-热综合能源系统中能量的整体输运模型 [J]. 电力系统自动化 , 2017 , 41 ( 13 ): 7 - 13 .
宋鑫芳 , 张勇 . 高熵合金研究进展 [J]. 粉末冶金技术 , 2022 , 40 ( 5 ): 451 - 457 .
FAN Zhao , WANG Hui , WU Yuan , et al . Thermoelectric performance of PbSnTeSe high-entropy alloys [J]. Materials Research Letters , 2017 , 5 ( 3 ): 187 - 194 .
JIANG Jian , CHENG Ruiqing , YIN Lei , et al . Van der Waals epitaxial growth of two-dimensional PbSe and its high-performance heterostructure devices [J]. Science Bulletin , 2022 , 67 ( 16 ): 1659 - 1668 .
JIANG Binbin , WANG Wu , LIU Shixuan , et al . High figure-of-merit and power generation in high-entropy GeTe-based thermoelectrics [J]. Science , 2022 , 377 ( 6602 ): 208 - 213 .
ZHANG Qian , LIAO Bolin , LAN Yucheng , et al . High thermoelectric performance by resonant dopant indium in nanostructured SnTe [J]. Proceedings of the National Academy of Sciences , 2013 , 110 ( 33 ): 13261 - 13266 .
SU Meini , YOUNG Ben , GARDNER L . Flexural response of aluminium alloy SHS and RHS with internal stiffeners [J]. Engineering Structures , 2016 , 121 : 170 - 180 .
LI Kai , SUN Liang , BAI Wei , et al . High-entropy strategy to achieve electronic band convergence for high-performance thermoelectrics [J]. Journal of the American Chemical Society , 2024 , 146 ( 20 ): 14318 - 14327 .
王钰莹 , 于海峰 , 黎兵 , 等 . 如何利用开源工具分析 fMRI 数据:基于多体素模式的有监督机器学习算法介绍 [J]. 心理科学 , 2022 , 45 ( 3 ): 718 - 724 .
MANGALATHU S , HWANG S H , JEON J S . Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach [J]. Engineering Structures , 2020 , 219 : 110927 . DOI: 10.1016/j.engstruct.2020.110927 http://dx.doi.org/10.1016/j.engstruct.2020.110927 .
张聪 , 刘杰 , 解树一 , 等 . 高通量计算与机器学习驱动高熵合金的研究进展 [J]. 材料工程 , 2023 , 51 ( 3 ): 1 - 16 .
杨婉茹 , 贾宏伟 , 刘卓 , 等 . CdMnO 4 光催化材料的电子结构和光学性质的第一性原理计算 [J]. 宁夏大学学报(自然科学版) , 2021 , 42 ( 1 ): 34 - 38 .
李景学 , 于跃 , 徐斯然 , 等 . 电子自旋效应在电催化剂中的作用 [J]. 物理化学学报 , 2023 , 39 ( 12 ): 2302049 . DOI: 10.3866/PKU.WHXB202302049 http://dx.doi.org/10.3866/PKU.WHXB202302049 .
王娟 , 杨小渝 , 王宗国 , 等 . SQS 二元合金设计的高通量方法和技术研究 [J]. 计算机工程与科学 , 2016 , 38 ( 3 ): 401 - 410 .
EVANS J . Straightforward statistics for the behavioral sciences [M]. Pacific Grove : Thomson Brooks/Cole Publishing Co , 1996 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号