数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (4): 18-29.

doi: 10.11871/jfdc.issn.2096-742X.2021.04.002

• 可视化与可视分析专题 • 上一篇    下一篇

基于可视化的固态电解质材料机器学习筛选与预测

蒲剑苏1,*(),朱正国1(),邵慧1(),高博洋1(),朱焱麟2(),闫宗楷3(),向勇3()   

  1. 1.电子科技大学,计算机学院,大数据可视分析实验室,四川 成都 610000
    2.深圳市清洁能源研究院,深圳 518048
    3.电子科技大学,材料与能源学院,材料基因工程研究中心,四川 成都 610000
  • 收稿日期:2021-06-10 出版日期:2021-08-20 发布日期:2021-08-30
  • 通讯作者: 蒲剑苏
  • 作者简介:蒲剑苏,电子科技大学,计算机学院,副教授,研究方向为数据分析与可视化、可视分析、时空数据分析、智慧城市相关方面的研究。主持了国家自然基金项目3项,省重点研发项目1项,省部级项目4项,横向3项;承担了国家重点研发计划、国家科技重大专项、教育部联合基金、总装预研有关课题(含子课题)的主要研究工作;参与了国家安全重大基础研究(国防973)在内的多个重大项目的研究。在SCI期刊/国际会议上发表论文24篇;受邀担任了Vis, VAST, EuroVis, PacificVis, SECON,VLDB等国际一流会议与期刊的审稿人;中国图象图形学学会下属可视化与可视分析专委会常任委员, ChinaVis 2018的组织委员会主席。与华为、29所等多家企业与研究所开展了合作。针对目前“互联网+”与中国制造2025的大背景,以云计算大数据等关键技术作为基础与框架,建设特种数据的集中共享与研究平台,比如材料高通量实验数据、微波实验分析数据等,提供对数据分析与可视化方面的支撑。
    本文中负责总体统稿,总结对应的科学问题,修改论文。
    PU Jiansu is currently an Associate Professor with the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China. And he is honored as the special expert of Sichuan Thousand Talents Program. His research interests include information visuali-zation, visual analysis in spatiotemporal data, time series, and social networks.
    In this paper, he is responsible for the overall draft, the corre-sponding scientific issues summary, the research on the conce-ptual framework, and the paper revision.
    E-mail: jiansu.pu@foxmail.com|朱正国,电子科技大学,计算机学院,大数据可视分析实验室,硕士研究生(中电第十研究所联合培养项目),研究方向为数据分析与可视化、材料数据可视化、特种数据分析。
    本文中负责论文撰写,部分系统设计与实现,论文修改。
    ZHU Zhengguo received the B.S. degree from the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China, in 2020, where he is currently pursuing the master's degree majoring in computer science. His research interests include visual analysis, visualization of materials screening, and special data visualization.
    In this paper, he is responsible for the paper writing, the part of the system design and implementation, and the paper revision.
    E-mail: 202022080208@std.uestc.edu.cn|邵慧,电子科技大学,计算机学院,大数据可视分析实验室,硕士研究生,研究方向为数据分析与可视化,可视分析,材料数据可视化。
    本文中负责总体系统设计与实现。
    SHAO Hui received the B.S. degree from the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China, in 2019, where she is currently pursuing the master's degree majoring in computer science. Her research interests include information visualization, visual analysis, and visualization of materials screening.
    In this paper, she is responsible for the overall system design and implementation.
    E-mail: sophyond@163.com|高博洋,电子科技大学,计算机学院,大数据可视分析实验室,硕士研究生,研究方向为数据分析与可视化,材料数据可视化,社交媒体分析。
    本文中负责机器学习算法实现与分析,部分系统设计与实现,论文修改。
    GAO Boyang received the B.S. degree from the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China, in 2020, where he is currently pursuing the master's degree majoring in computer science. His research interests include visual analysis, visualization of materials screening, and social network analysis.
    In this paper, he is responsible for the machine learning algo-rithm implementation and analysis, the part of the system design and implementation, and the paper revision.
    E-mail: 202052080209@std.uestc.edu.cn|朱焱麟,深圳市清洁能源研究院,高级研究员,博士,主要研究方向为固态电解质,基于数据的新材料设计以及高通量实验方法学等。
    本文中负责专业数据解析,案例分析,论文修改。
    ZHU Yanlin is a senior researcher at Shenzhen Clean Energy Research Institute, received his Ph.D. degree in Materials Science and Engineering from the University of Electronic Science and Technology of China in 2020. His research interests cover solid-state electrolytes, new materials discovery based on data-driven method, and high-throughput experimental methodology.
    In this paper, he is responsible for professional data analysis, case analysis, and the paper revision.
    E-mail: zhuyanlin@uceri.com|闫宗楷,电子科技大学材料与能源学院,讲师,作为主研承担国家重点研发计划课题、国家“863”计划课题等国家级科研项目10余项。过去5年在ACS Applied Materials & Interfaces、Applied Surface Science、Thin Solid Film等期刊发表论文10篇,申请国家发明专利25项,受邀在国际会议分论坛作报告2次。
    本文中负责专业数据解析,案例分析。
    YAN Zongkai is currently working as an assistant professor in the School of Materials and Energy, University of Electronic Science and Technology of China. He has undertaken more than 10 national-level scientific research projects such as the national key research and development plan and the national “863” plan. In the past 5 years, he has published 10 papers in ACS Applied Materials & Interfaces, Applied Surface Science, Thin Solid Film, and other journals; applied for 25 national invention patents, and was invited to give two presentations in international conference sub-forums.
    In this paper, he is responsible for professional data analysis, case analysis.
    E-mail: yanzongkai@uestc.edu.cn|向勇,电子科技大学,教授,博士生导师,中国材料学会材料基因组分委会副秘书长。中国科学技术大学本科(1995-2000),美国哈佛大学硕士、博士(2000-2005)。曾任硅谷英特尔公司总部高级工程师/项目经理(2005-2009)、电子科技大学微电子与固体电子学院院长助理(2009-2011)、能源科学与工程学院副院长(2011-2015)材料与能源学院院长(2018.1-2018.12)、电子薄膜与集成器件国家重点实验室珠海分室副主任(2010-),曾任“中国材料基因组计划”咨询专家组成员和“重点新材料研发及应用”重大项目材料基因工程方向论证专家。目前主要从事材料基因工程、全固态锂电池、电池智能管理等研究,承担了自然科学基金、863计划、工信部工业强基、科技部重点专项等项目,累计经费5000多万元,发表论文150多篇,申报发明专利200多项。
    在本文中承担基于数据的新材料设计以及高通量实验方法学的概念框架研究。
    XIANG Yong is a professor in the School of Materials and Energy, University of Electronic Science and Technology of China. And he is also the deputy secretary-general of the Material Gene Composition Committee of the Chinese Society for Materials Science. Bachelor of Science and Technology of China (1995-2000), Master and Ph.D. of Harvard University (2000-2005). Served as a senior engineer/project manager at the headquarters of Intel Corporation in Silicon Valley (2005-2009), assistant to the dean of the School of Microelectronics and Solid State Electronics at the University of Electronic Science and Technology of China (2009-2011), and deputy dean of the School of Energy Science and Engineering (2011-2015) Dean of the School of Energy (2018.1-2018.12), Deputy Director of the Zhuhai Branch of the State Key Laboratory of Electronic Thin Films and Integrated Devices (2010-), former member of the “China Material Genome Project” consulting expert group and major “Key New Material Research and Development and Application” Demonstration expert for the direction of genetic engineering of project materials. At present, he is mainly engaged in the research of material genetic engineering, all-solid-state lithium battery, battery intelligent management, etc., and has undertaken the Natural Science Foundation, 863 Program, the Ministry of Industry and Information Technology, the Ministry of Science and Technology Key Special Projects, etc., with a cumulative funding of more than 50 million yuan, and more than 150 papers published Article, more than 200 invention patents have been declared.
    In this paper, he is responsible for the research on the conce-ptual framework of the new materials discovery based on the data-driven method.
    E-mail: xyg@uestc.edu.cn
  • 基金资助:
    国家自然基金面上项目“时空大数据可视分析中信息混淆问题研究”(61872066);国家自然基金联合基金重点支持项目“可解释小样本深度学习与非完备信息博弈及其在电磁对抗中的应用”(U19A2078);四川省科技计划项目“基于时空大数据的信息混淆模型研究”(2020YFG0056)

Screening and Predication of Solid Electrolyte Based on Visualization

PU Jiansu1,*(),ZHU Zhengguo1(),SHAO Hui1(),GAO Boyang1(),ZHU Yanlin2(),YAN Zongkai3(),XIANG Yong3()   

  1. 1. Big Data Visual Analysis Lab, University of Electronic Science and Technology, Chengdu, Sichuan 610000, China
    2. Clean Energy Research Institute, Shenzhen 518048, China
    3. Material Genome Engineering Research Center, School of Materials and Energy, University of Electronic Science and Technology, Chengdu, Sichuan 610000, China
  • Received:2021-06-10 Online:2021-08-20 Published:2021-08-30
  • Contact: PU Jiansu

摘要:

【目的】随着“碳达峰”和“碳中和”目标的提出,能源消费领域电气化进程将进一步加快,其中在储能技术领域,锂电池是当前最具发展潜力的技术之一,已被广泛地应用在国民生活的方方面面。传统的锂电池所采用的液态电解质存在漏液、易燃和爆炸等多方面的潜在安全隐患,能量密度和安全性更高的固态电解质被认为是代替液态电解质的理想解决方案。当前,寻找具有高离子电导率等特性的固态电解质材料仍然是当前的研究热点。【应用背景】传统的材料研究采用“试错”模式,基于已知经验与材料物理化学特性进行假设,然后进行实验验证,通过对上述过程的反复迭代,最终找到目标材料。上述过程耗时费力,限制了相关材料的研发进程。近年来,机器学习等方法被广泛引入并用于新材料的研究中,但却缺少辅助工具帮助材料领域专家分析和理解机器学习模型,并实现对满足特定性能需求的材料预测。【方法】在这种背景下,我们基于可视化相关技术,建立了材料数据可视分析系统,期望促进材料科学家更高效地寻找高性能固体电解质材料。【结果】我们基于可视化技术对多种机器学习算法的结果进行重构和展示,并通过不同视图对材料之间的关系进行可视化对比和分析,结合我们实验分析得到的一些案例,最终给出了预测。【结论】最终,经过材料实验反馈,证实了部分预测材料的优良性能,验证了该系统的有效性。

关键词: 材料发掘, 固态电解质, 可视分析, 机器学习, 离子电导率, 材料发掘, 固态电解质

Abstract:

[Objective] It is a hot research topic to find the ideal solid electrolyte material with high ion conductivity, and replace the liquid electrolyte which has safety concerns as the electrolyte material of lithium batteries. [Context] In recent years, methods such as machine learning have been widely used in the prediction of new materials. However, there are few aids to help materials experts analyze and understand machine learning models to predict the composition of materials that meet performance requirements. [Methods] Under such background, we built a visual analysis system based on visualization technology, trying to help experts in the field of materials analyze the results of machine learning, predict and look for high-performance solid electrolyte materials. [Results] We compare the results of several machine learning algorithms and use visualization techniques to display the results. We visually analyze the relationship between materials through different views and finally give the prediction based on some cases we summarized. [Conclusions] Many material experiments have verified the excellent properties of some predicted materials and have confirmed the effectiveness of our system.

Key words: visual analysis system, machine learning, ionic conductivity, material discovery, solid electrolyte, visual analysis system, machine learning, ionic conductivity, material discovery, solid electrolyte