高通量自动流程集成计算与数据管理智能平台及其在合金设计中的应用
收稿日期: 2021-01-21
修回日期: 2021-03-30
网络出版日期: 2021-06-11
基金资助
国家重点研发计划项目(2017YFB0701700);国家自然科学基金项目(51872017);北航高性能计算平台项目
High-Throughput Automatic Integrated Material Calculations and Data Management Intelligent Platform and the Application in Novel Alloys
Received date: 2021-01-21
Revised date: 2021-03-30
Online published: 2021-06-11
Supported by
National Key Research and Development Program of China(2017YFB0701700);National Natural Science Foundation of China(51872017);the High-Performance Computing (HPC) Resources at Beihang University
材料研发模式经历了经验主导的第一范式、理论模型主导的第二范式和计算模拟主导的第三范式，如今正处于数据驱动的第四范式。为加速新材料的设计与研发，发展基于材料数据库和人工智能算法的高通量自动集成计算和数据挖掘算法变得至关重要。本文介绍了作者团队自主开发的分布式高通量自动流程集成计算和数据管理智能平台ALKEMIE2.0 (Artificial Learning and Knowledge Enhanced Materials Informatics Engineering 2.0)，该平台基于AMDIV设计理念，包含了自动化、模块化、数据库、人工智能和可视化流程等5个适用于数据驱动的材料研发模式核心要素。概括来说，ALKEMIE2.0以模块化的方式集成了多个不同尺度的计算模拟软件；其高通量自动纠错流程可实现从建模、运行到数据分析，全程自动无人工干预；支持单用户不低于104量级的并发高通量自动计算模拟。进一步而言，ALKEMIE2.0具有强大的可移植性和可扩展性，目前已部署在国家超算天津中心，基于多类型材料数据库结合超算强大的计算能力使得人工智能算法在新材料设计与研发中得以快速的应用和实践。更重要的是，ALKEMIE2.0设计了用户友好的可视化操作界面，使得结构建模、工作流计算逻辑、数据分析和机器学习模型具有更高的透明性和更强的可操作性，且适用于对材料计算模拟掌握程度从初级到专业的所有材料研究人员。最后，通过多平台部署和高通量筛选二元铝合金2个算例详细展示了ALKEMIE2.0的主要特色及功能。
王冠杰 , 李开旗 , 彭力宇 , 张壹铭 , 周健 , 孙志梅 . 高通量自动流程集成计算与数据管理智能平台及其在合金设计中的应用[J]. 金属学报, 2022 , 58(1) : 75 -88 . DOI: 10.11900/0412.1961.2021.00041
The development of novel materials has experienced three paradigms: purely empirical, theoretical models, and computational materials science. Currently, the huge amount of data generated by experiments and simulations has facilitated a shift in materials science to a data-driven fourth paradigm. Therefore, the development of high-throughput automatic integrated computations and data mining algorithms based on material databases and artificial intelligence algorithms is critical for accelerating the design of novel materials. This paper presents an open-source distributed computational platform called Artificial Learning and Knowledge Enhanced Materials Informatics Engineering 2.0 (ALKEMIE2.0) based on the AMDIV (automation-modular-database-intelligence-visualization) design concepts. The ALKEMIE2.0 platform includes five core components of automation, modular, materials database, artificial intelligence, and visualization, which are suitable for the computational design of novel materials. The overall characteristics of ALKEMIE2.0 are divided into five pillars. ALKEMIE-Core integrates multiscale calculations and simulation software using the ALKEMIE-Plugin application programming interface. Its high-throughput calculation workflows that support 104 magnitude concurrencies are implemented by integrating the automatic frameworks of model constructions, calculation workflows, and data analyses. Furthermore, the platform is based on the ALKEMIE-Server, which can easily and automatically open daemon services and realize information interactions in distributed supercomputers. With its strong portability and scalability, ALKEMIE has been deployed in the National Supercomputing Tianjin Center. In addition, the multitype materials database called the ALKEMIE-Data Vault contains structure, task, workflow, and material property databases, which combined with the power of supercomputing, enables the rapid application of artificial intelligence algorithms in the design of new materials. In particular, the many user-friendly interfaces, which were elaborately designed using the ALKEMIE-GUI and are suitable for scientists with broad backgrounds, make structural building, work flowcharts, data analysis, and machine learning models more transparent and maneuverable. Finally, the main features of ALKEMIE2.0 are demonstrated using two examples of multiplatform deployment and high-throughput screening of binary aluminum alloys.
| 1 | Agrawal A , Choudhary A . Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science [J]. APL Mater., 2016, 4: 053208 |
| 2 | Holdren J P . Materials genome initiative for global competitiveness [R]. Washington, DC: Executive Office of the President of the United States, National Science and Technology Council, 2011 |
| 3 | Lin L C , Berger A H , Martin R L , et al . In silico screening of carbon-capture materials [J]. Nat. Mater., 2012, 11: 633 |
| 4 | Su Y J , Fu H D , Bai Y , et al . Progress in materials genome engineering in China [J]. Acta Metall. Sin., 2020, 56: 1313 |
| 4 | 宿彦京, 付华栋, 白 洋 等 . 中国材料基因工程研究进展 [J]. 金属学报, 2020, 56: 1313 |
| 5 | Yang K S , Setyawan W , Wang S D , et al . A search model for topological insulators with high-throughput robustness descriptors [J]. Nat. Mater., 2012, 11: 614 |
| 6 | Jain A , Ong S P , Hautier G , et al . Commentary: The Materials Project: A materials genome approach to accelerating materials innovation [J]. APL Mater., 2013, 1: 011002 |
| 7 | Ong S P , Richards W D , Jain A , et al . Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis [J]. Comput. Mater. Sci., 2013, 68: 314 |
| 8 | Jain A , Ong S P , Chen W , et al . FireWorks: A dynamic workflow system designed for high-throughput applications [J]. Concurr. Comput., 2015, 27: 5037 |
| 9 | Mathew K , Montoya J H , Faghaninia A , et al . Atomate: A high-level interface to generate, execute, and analyze computational materials science workflows [J]. Comput. Mater. Sci., 2017, 139: 140 |
| 10 | Supka A R , Lyons T E , Liyanage L , et al . AFLOWπ: A minimalist approach to high-throughput ab initio calculations including the generation of tight-binding hamiltonians [J]. Comput. Mater. Sci., 2017, 136: 76 |
| 11 | Pizzi G , Cepellotti A , Sabatini R , et al . AiiDA: Automated interactive infrastructure and database for computational science [J]. Comput. Mater. Sci., 2016, 111: 218 |
| 12 | Larsen A H , Mortensen J J , Blomqvist J , et al . The atomic simulation environment—A Python library for working with atoms [J]. J. Phys.: Condens. Matter, 2017, 29: 273002 |
| 13 | Belsky A , Hellenbrandt M , Karen V L , et al . New developments in the Inorganic Crystal Structure Database (ICSD): Accessibility in support of materials research and design [J]. Acta Cryst., 2002, 58B: 364 |
| 14 | Quirós M , Gra?ulis S , Girdzijauskait? S , et al . Using SMILES strings for the description of chemical connectivity in the Crystallography Open Database [J]. J. Cheminform., 2018, 10: 23 |
| 15 | Curtarolo S , Setyawan W , Wang S D , et al . AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations [J]. Comput. Mater. Sci., 2012, 58: 227 |
| 16 | Kirklin S , Saal J E , Meredig B , et al . The Open Quantum Materials Database (OQMD): Assessing the accuracy of DFT formation energies [J]. npj Comput. Mater., 2015, 1: 15010 |
| 17 | Draxl C , Scheffler M . The NOMAD laboratory: From data sharing to artificial intelligence [J]. J. Phys. Mater., 2019, 2: 036001 |
| 18 | Pedregosa F , Varoquaux G , Gramfort A , et al . Scikit-learn: Machine learning in Python [J]. J. Mach. Learn. Res., 2011, 12: 2825 |
| 19 | Abadi M, Agarwal A, Barham P, et al . TensorFlow: Large-scale machine learning on heterogeneous distributed systems [Z]. arXiv:1603.04467, 2016 |
| 20 | Paszke A , Gross S , Massa F , et al . PyTorch: An imperative style, high-performance deep learning library [A]. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) [C]. Vancouver, Canada: Curran Associates, 2019: 32 |
| 21 | Ouyang R H , Ahmetcik E , Carbogno C , et al . Simultaneous learning of several materials properties from incomplete databases with multi-task SISSO [J]. J. Phys. Mater., 2019, 2: 024002 |
| 22 | Gossett E , Toher C , Oses C , et al . AFLOW-ML: A RESTful API for machine-learning predictions of materials properties [J]. Comput. Mater. Sci., 2018, 152: 134 |
| 23 | Ward L , Dunn A , Faghaninia A , et al . Matminer: An open source toolkit for materials data mining [J]. Comput. Mater. Sci., 2018, 152: 60 |
| 24 | Wang G J , Peng L Y , Li K Q , et al . ALKEMIE: An intelligent computational platform for accelerating materials discovery and design [J]. Comput. Mater. Sci., 2021, 186: 110064 |
| 25 | Kingma D P, Ba J. Adam: A method for stochastic optimization [Z]. arXiv:1412.6980, 2014 |
| 26 | Zhang C Y, Bengio S, Hardt M, et al . Understanding deep learning requires rethinking generalization [Z]. arXiv:1611.03530, 2016 |
| 27 | Hunter J D . Matplotlib: A 2D graphics environment [J]. Comput. Sci. Eng., 2007, 9: 90 |
| 28 | Kresse G , Hafner J . Ab initio molecular dynamics for liquid metals [J]. Phys. Rev., 1993, 47B: 558 |
| 29 | Giannozzi P , Baroni S , Bonini N , et al . Quantum Espresso: A modular and open-source software project for quantum simulations of materials [J]. J. Phys.: Condens. Matter, 2009, 21: 395502 |
| 30 | Huang Y D , Zhou J , Wang G J , et al . Abnormally strong electron-phonon scattering induced unprecedented reduction in lattice thermal conductivity of two-dimensional Nb2C [J]. J. Am. Chem. Soc., 2019, 141: 8503 |
| 31 | Gonze X , Amadon B , Anglade P M , et al . ABINIT: First-principles approach to material and nanosystem properties [J]. Comput. Phys. Commun., 2009, 180: 2582 |
| 32 | Plimpton S . Fast parallel algorithms for short-range molecular dynamics [J]. J. Comput. Phys., 1995, 117: 1 |
| 33 | Tegeler M , Shchyglo O , Kamachali R D , et al . Parallel multiphase field simulations with OpenPhase [J]. Comput. Phys. Commun., 2017, 215: 173 |
| 34 | Lukas H L , Fries S G , Sundman B . Computational Thermodynamics: The Calphad Method [M]. Cambridge: Cambridge University Press, 2007: 265 |
| 35 | Otero-de-la-Roza A , Abbasi-Pérez D , Lua?a V . Gibbs2: A new version of the quasiharmonic model code. II. Models for solid-state thermodynamics, features and implementation [J]. Comput. Phys. Commun., 2011, 182: 2232 |
| 36 | Morgan B J . Lattice-geometry effects in garnet solid electrolytes: A lattice-gas Monte Carlo simulation study [J]. Roy. Soc. Open Sci., 2017, 4: 170824 |
| 37 | Sun Z M , Zhou J , Blomqvist A , et al . Formation of large voids in the amorphous phase-change memory Ge2Sb2Te5 alloy [J]. Phys. Rev. Lett., 2009, 102: 075504 |
| 38 | Cheng Y X , Zhu L G , Wang G J , et al . Vacancy formation energy and its connection with bonding environment in solid: A high-throughput calculation and machine learning study [J]. Comput. Mater. Sci., 2020, 183: 109803 |
| 39 | Peng Q , Zhou J , Chen J T , et al . Cu single atoms on Ti2CO2 as a highly efficient oxygen reduction catalyst in a proton exchange membrane fuel cell [J]. J. Mater. Chem., 2019, 7A: 26062 |
| 40 | Peng L Y , Li Z , Wang G J , et al . Reduction in thermal conductivity of Sb2Te phase-change material by scandium/yttrium doping [J]. J. Alloys Compd., 2020, 821: 153499 |
| 41 | Kalinin S V , Sumpter B G , Archibald R K . Big-deep-smart data in imaging for guiding materials design [J]. Nat. Mater., 2015, 14: 973 |
| 42 | Pan F S , Zhang D F , et al . Alumimum Alloy and Application [M]. Beijing: Chemical Industry Press, 2006: 155 |
| 42 | 潘复生, 张丁非 等 . 铝合金及应用 [M]. 北京: 化学工业出版社, 2006: 155 |
| 43 | Guan R G , Luo H F , Huang H , et al . Development of aluminum alloy materials: Current status, trend, and prospects [J]. Strateg. Stud. CAE, 2020, 22(5): 68 |
| 43 | 管仁国, 娄花芬, 黄 晖 等 . 铝合金材料发展现状、趋势及展望 [J]. 中国工程科学, 2020, 22(5): 68 |
| 44 | Madsen G K H , Singh D J . BoltzTraP. A code for calculating band-structure dependent quantities [J]. Comput. Phys. Commun., 2006, 175: 67 |
| 45 | Wang G J , Zhou J , Elliott S R , et al . Role of carbon-rings in polycrystalline GeSb2Te4 phase-change material [J]. J. Alloys Compd., 2019, 782: 852 |
| 46 | Wang G J , Zhou J , Sun Z M . First principles investigation on anomalous lattice shrinkage of W alloyed rock salt GeTe [J]. J. Phys. Chem. Solids, 2020, 137: 109220 |
| 47 | Mouhat F , Coudert F X . Necessary and sufficient elastic stability conditions in various crystal systems [J]. Phys. Rev., 2014, 90B: 224104 |
| 48 | Hill R . The elastic behaviour of a crystalline aggregate [J]. Proc. Phys. Soc., 1952, 65A: 349 |
| 49 | Voigt W . Lehrbuch der Kristallphysik [M]. Leipzig: B. G. Teubner, 1928: 1 |
| 50 | Guo X Q , Podloucky R , Freeman A J . First principles calculation of the elastic constants of intermetallic compounds: Metastable Al3Li [J]. J. Mater. Res., 1991, 6: 324 |
| 51 | Chinmulgund M , Inturi R B , Barnard J A . Effect of Ar gas pressure on growth, structure, and mechanical properties of sputtered Ti, Al, TiAl, and Ti3Al films [J]. Thin Solid Films, 1995, 270: 260 |
| 52 | Zhang D T , Li Y Y , Luo Z Q . A review on the progress of rapidly solidified hypereutectic Al-Si alloy materials [J]. Light Alloy Fabr. Technol., 2001, 29(2): 1 |
| 52 | 张大童, 李元元, 罗宗强 . 快速凝固过共晶铝硅合金材料的研究进展 [J]. 轻合金加工技术, 2001, 29(2): 1 |
| 53 | Xiang Q C , Wang J Y , Zhou Z P , et al . Survey on the development and application of Al-Fe alloys [J]. Foundry, 2006, 55: 875 |
| 53 | 向青春, 王静媛, 周振平 等 . 铝铁合金的研究进展与应用状况 [J]. 铸造, 2006, 55: 875 |
| 54 | Shackelford J F , Alexander W . CRC Materials Science and Engineering Handbook [M]. 3rd Ed., Boca Raton: CRC Press, 2000: 41 |
/
| 〈 |
|
〉 |
