PDF(581 KB)
PDF(581 KB)
PDF(581 KB)
新材料研发智能化技术发展研究
Development of Key Technologies for Intelligent Research and Development of New Materials
新材料研发智能化技术发展迅速，显著增强材料研发效率及工程化应用水平，获得国际性的高度关注；我国在此领域发展相对滞后，基础设施条件面临缺口，制约着新材料原始创新及产业发展质量。本文总结了新材料研发智能化涉及的关键技术，从技术角度梳理了国内外发展现状，分析了我国新材料研发智能化面临的挑战；阐述了新材料研发智能化技术体系框架，包括材料智能计算设计技术与核心软件、材料自主 / 智能实验技术与高端装置、材料人工智能基础算法及关键技术、材料数字孪生、材料智能化研发平台与协同创新网络等。提出了创新生态构建及保障、产业化发展环境、数据底座与标准体系、人才培养与国际合作方面的举措建议，以期推动新材料研发智能化技术体系的发展与应用。
The rapid development of key technologies for the intelligent research and development (R&D) of new materials has significantly promoted the R&D efficiency and industrialization of materials and attracted global attention. China’s development in this field lags behind the advanced international level in terms of key technologies and infrastructures, which has restricted the original innovation and industrial development of the material sector. This study summarizes the key technologies involving the intelligent R&D of new materials, explores the developing status of these key technologies in China and abroad, and analyzes the challenges faced by China. Moreover, the intelligent R&D technology system is summarized including intelligent computing and design technologies and software, autonomous/intelligent experiment technologies and equipment, artificial-intelligence-driven basic algorithms and technologies, digital twins, intelligent R&D platforms and collaborative innovation networks. Furthermore,countermeasures are proposed from the aspects of innovative ecology construction, industrial environment improvement, standards system establishment, talent training, and international cooperation.
新材料 / 人工智能 / 自主实验 / 智能计算 / 材料大数据
new materials / artificial intelligence / autonomous experimentation / intelligent computing / big data of materials
| [1] |
Materials genome initiative for global competitiveness [EB/OL].(2011-06-15)[2023-04-15]. https://www.mgi.gov/sites/default/files/documents/materials_genome_initiative-final.pdf#: ~: text=This%20Materials%20Genome%20Initiative%20for%20Global%20Competitiveness%20aims, materials%20in%20a%20more%20expeditious%20and%20economical%20way.
|
| [2] |
Materials genome initiative strategic plan [EB/OL]. (2014-12-15)[2023-04-15]. https://www.nist.gov/system/files/documents/2018/06/26/mgi_strategic_plan_-_dec_2014.pdf#: ~: text=The%20Subcommittee%20on%20the%20Materials%20Genome%20Initiative%20%28SMGI%29, the%20goals%20of%20the%20Materials%20Genome%20Initiative%20%28MGI%29.
|
| [3] |
Materials genome initiative strategic plan [EB/OL]. (2021-11-15)[2023-04-15]. https://www.mgi.gov/sites/default/files/documents/MGI-2021-Strategic-Plan.pdf.
|
| [4] |
Horizon 2020: Details of the EU funding programme which ended in 2020 and links to further information [EB/OL]. [2023-04-15]. https: //research-and-innovation.ec.europa.eu/funding/funding-opportunities/funding-programmes-and-open-calls/horizon-2020_en#Article.
|
| [5] |
Horizon Europe: Research and innovation funding programme until 2027 [EB/OL]. [2023-04-15]. https://research-and-innovation.ec.europa.eu/funding/funding-opportunities/funding-programmes-and-open-calls/horizon-europe_en.
|
| [6] |
The future of manufacturing: A new era of opportunity and challenge for the UK [EB/OL]. [2023-04-15]. https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/255922/13-809-future-manufacturing-project-report.pdf.
|
| [7] |
谢建新 , 宿彦京 , 薛德桢 , 等 . 机器学习在材料研发中的应用 [J]. 金属学报 , 2021 , 57 11 : 1343 ‒ 1361 .
|
| [8] |
Friederich P, Häse F, Proppe J, al et. Machine-learned potentials for next-generation matter simulations [J]. Nature Materials, 2021, 20(6): 750‒761.
|
| [9] |
Srinivasan S, Batra R, Luo D, al et. Machine learning the metastable phase diagram of covalently bonded carbon [J]. Nature Communications, 2022, 13(1): 3251.
|
| [10] |
Fish J, Wagner G J, Keten S. Mesoscopic and multiscale modelling in materials [J]. Nature Materials, 2021, 20(6): 774‒786.
|
| [11] |
Yuan X Z, Zhou Y W, Peng Q, al et. Active learning to overcome exponential-wall problem for effective structure prediction of chemical-disordered materials [J]. NPJ Computational Materials, 2023, 9(1): 12.
|
| [12] |
Park J H, Min K M, Kim H K, al et. Integrated computational materials engineering for advanced automotive technology: With focus on life cycle of automotive body structure [J]. Advanced Materials Technologies, 2022, 10: 2201057.
|
| [13] |
Nikolaev P, Hooper D, Perea-Lopez N, al et. Discovery of wall-selective carbon nanotube growth conditions via automated experimentation [J]. ACS Nano, 2014, 8(10): 10214‒10222.
|
| [14] |
Deneault J R, Chang J, Myung J, al et. Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer [J]. MRS Bulletin, 2021, 46: 566‒575.
|
| [15] |
Azoulay P, Graff-Zivin J, Uzzi B, al et. Toward a more scientific science [J]. Science, 2018, 361(6408): 1194‒1197.
|
| [16] |
Burger B, Maffettone P M, Gusev V V, al et. A mobile robotic chemist [J]. Nature, 2020, 583(7815): 237‒241.
|
| [17] |
Han G Q, Li G D, Huang J, al et. Two-photon-absorbing ruthenium complexes enable near infrared light-driven photocatalysis [J]. Nature Communications, 2022, 13(1): 2288.
|
| [18] |
Tabor D P, Roch L M, Saikin S K, al et. Accelerating the discovery of materials for clean energy in the era of smart automation [J]. Nature Reviews Materials, 2018, 3(5): 5‒20.
|
| [19] |
Kaufman J, Begley E. MatML: A data interchange markup language [J]. Advanced Materials and Processes, 2003, 161(11): 35‒37.
|
| [20] |
Jain A, Ong S P, Hautier G, al et. Commentary: The materials project: A materials genome approach to accelerating materials innovation [J]. APL Materials, 2013, 1(1): 011002.
|
| [21] |
Tshitoyan V, Dagdelen J, Weston L, al et. Unsupervised word embeddings capture latent knowledge from materials science literature [J]. Nature, 2019, 571(7763): 95‒98.
|
| [22] |
Rao Z Y, Tung P Y, Xie R W, al et. Machine learning-enabled high-entropy alloy discovery [J]. Science, 2022, 378(6615): 78‒85.
|
| [23] |
Xie T, C Grossman J. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties [J]. Physical Review Letters, 2018, 120(14): 145301.
|
| [24] |
Segler M H, Preuss M, P Waller M. Planning chemical syntheses with deep neural networks and symbolic AI [J]. Nature, 2018, 555(7698): 604‒610.
|
| [25] |
Lori A W, R Gopal R. Frontiers of materials research: A decadal survey [J]. MRS Bulletin, 2017, 42(7): 537.
|
| [26] |
Rapp K. Artificial intelligence in manufacturing: Real world success stories and lessons learned [EB/OL]. (2022-01-07)[2023-04-15]. https://www.nist.gov/blogs/manufacturing-innovation-blog/artificial-intelligence-manufacturing-real-world-success-stories.
|
| [27] |
Flores-Leonar M M, Mejía-Mendoza L M, Aguilar-Granda A, al et. Materials acceleration platforms: On the way to autonomous experimentation [J]. Current Opinion in Green and Sustainable Chemistry, 2020, 25: 100370.
|
| [28] |
Peterson E, Lavin A. Physical computing for materials acceleration platforms [J]. Matter, 2022, 5(11): 3586‒3596.
|
| [29] |
Aspuru-Guzik A, Persson K. Materials acceleration platform: Accelerating advanced energy materials discovery by integrating high-throughput methods and artificial intelligence [EB/OL]. (2018-01-15)[2023-04-15]. https://dash.harvard.edu/handle/1/35164974?show=full.
|
| [30] |
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 10 : 1313 ‒ 1323 .
|
| [31] |
Xie J X, Su Y J, Zhang D W, al et. A vision of materials genome engineering in China [J]. Engineering, 2022, 10(3): 10‒12.
|
| [32] |
Zhang H T, Fu H D, He X D, al et. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening [J]. Acta Materialia, 2020, 200: 803‒810.
|
| [33] |
Zhang H T, Fu H D, Zhu S C, al et. Machine learning assisted composition effective design for precipitation strengthened copper alloys [J]. Acta Materialia, 2021, 215: 117118.
|
| [34] |
Wang C S, Fu H D, Jiang L, al et. A property-oriented design strategy for high performance copper alloys via machine learning [J]. NPJ Computational Materials, 2019, 5(1): 87.
|
| [35] |
Wen C, Zhang Y, Wang C X, al et. Machine learning assisted design of high entropy alloys with desired property [J]. Acta Materialia, 2019, 170: 109‒117.
|
| [36] |
Zhang Y, Wen C, Wang C X, al et. Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models [J]. Acta Materialia, 2020, 185: 528‒539.
|
| [37] |
Wen C, Wang C, Zhang Y, al et. Modeling solid solution strengthening in high entropy alloys using machine learning [J]. Acta Materialia, 2021, 212: 116917.
|
| [38] |
Liu P, Huang H, Jiang X, al et. Evolution analysis of γ´precipitate coarsening in Co-based superalloys using kinetic theory and machine learning [J]. Acta Materialia, 2022, 235: 118101.
|
| [39] |
Wang W, Jiang X, Tian S, al et. Automated pipeline for superalloy data by text mining [J]. NPJ Computational Materials, 2022, 8(1): 9.
|
| [40] |
Zhang T, Jiang Y, Song Z, al et. Catalogue of topological electronic materials [J]. Nature, 2019, 566(7745): 475‒479.
|
| [41] |
Tang F, Po H C, Vishwanath A, al et. Comprehensive search for topological materials using symmetry indicators [J]. Nature, 2019, 566(7745): 486‒489.
|
| [42] |
Yang Q, Yang S, Qiu P, al et. Flexible thermoelectrics based on ductile semiconductors [J]. Science, 2022, 377(6608): 854‒858.
|
| [43] |
Li M X, Zhao S F, Lu Z, al et. High-temperature bulk metallic glasses developed by combinatorial methods [J]. Nature, 2019, 569(7754): 99‒103.
|
/
| 〈 |
|
〉 |
