|
|
Material Sciences 2025
数值化与智能化技术在材料科学中的应用与发展综述
|
Abstract:
数值化和智能化技术正在推动材料科学的发展，尤其是在材料设计、优化和制造方面。有限元分析、分子动力学、第一性原理计算和多尺度建模等数值化技术，能够有效预测材料性能并优化设计。同时，人工智能和大数据分析通过机器学习，促进了新材料的发现和逆向设计。智能制造结合自适应控制系统，实现了生产过程的自动化和实时优化，进而提高制造效率和精度。尽管面临数据不足和计算成本的挑战，随着技术的进步，材料科学正朝着更加精准和自动化的方向发展。
Numerical and intelligent technologies are advancing materials science, especially in materials design, optimization and manufacturing. Numerical techniques such as finite element analysis, molecular dynamics, first-principles calculations, and multiscale modeling can effectively predict material properties and optimize design. Meanwhile, artificial intelligence and big data analytics facilitate the discovery of new materials and reverse design through machine learning. Intelligent manufacturing combined with adaptive control systems enables automation and real-time optimization of the production process, which in turn improves manufacturing efficiency and precision. Despite the challenges of insufficient data and computational costs, materials science is moving towards greater precision and automation as technology advances.
| [1] | Schleder, G.R., Padilha, A.C.M., Acosta, C.M., Costa, M. and Fazzio, A. (2019) From DFT to Machine Learning: Recent Approaches to Materials Science—A Review. Journal of Physics: Materials, 2, Article 032001. https://doi.org/10.1088/2515-7639/ab084b |
| [2] | 余海山. 结合第一性原理计算和机器学习的材料理论研究[D]: [博士学位论文]. 合肥: 中国科学技术大学, 2020. |
| [3] | Deringer, V.L., Caro, M.A. and Csányi, G. (2019) Machine Learning Interatomic Potentials as Emerging Tools for Materials Science. Advanced Materials, 31, Article 1902765. https://doi.org/10.1002/adma.201902765 |
| [4] | 牛程程, 李少波, 胡建军, 等. 机器学习在材料信息学中的应用综述[J]. 材料导报, 2020, 34(23): 23100-23108. |
| [5] | 米晓希, 汤爱涛, 朱雨晨, 等. 机器学习技术在材料科学领域中的应用进展[J]. 材料导报, 2021, 35(15): 15115-15124. |
| [6] | Gomes, C.P., Selman, B. and Gregoire, J.M. (2019) Artificial Intelligence for Materials Discovery. MRS Bulletin, 44, 538-544. https://doi.org/10.1557/mrs.2019.158 |
| [7] | Konstantopoulos, G., Koumoulos, E.P. and Charitidis, C.A. (2022) Digital Innovation Enabled Nanomaterial Manufacturing: Machine Learning Strategies and Green Perspectives. Nanomaterials, 12, Article 2646. https://doi.org/10.3390/nano12152646 |
| [8] | Skylaris, C. (2016) A Benchmark for Materials Simulation. Science, 351, 1394-1395. https://doi.org/10.1126/science.aaf3412 |
| [9] | 高军, 朱新宇, 姚晨光, 等. 有限元在开关面板用新型聚酯工程塑料开发中的应用研究[J]. 塑料工业, 2015, 43(10): 123-126. |
| [10] | 章凌, 赵优存, 李祎, 等. 基于FEA的复合材料结构极限承载失效预测[J]. 宇航总体技术, 2023, 7(5): 29-37. |
| [11] | 赵宇, 彭珍瑞. 基于SGMD及LWOA-ELM的有限元模型修正[J]. 计算力学学报, 2023, 40(2): 255-263. |
| [12] | 赵宇, 彭珍瑞. 基于MWOA-ELM代理模型的有限元模型修正[J]. 传感器与微系统, 2022, 41(1): 127-130. |
| [13] | Zhang, L., Han, J., Wang, H., Car, R. and E, W. (2018) Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics. Physical Review Letters, 120, Article 143001. https://doi.org/10.1103/physrevlett.120.143001. |
| [14] | Schütt, K., Kindermans, P.J., Sauceda Felix, H.E., et al. (2017) SCHNET: A Continuous-Filter Convolutional Neural Network for Modeling Quantum Interactions. Advances in Neural Information Processing Systems, 30. |
| [15] | 邓斌, 华海明, 张与之, 等. 深度势能方法及其在电化学储能材料中的应用[J]. 储能科学与技术, 2024, 13(9): 2884-2906. |
| [16] | Wang, Z., Su, M., Duan, X., Yao, X., Han, X., Song, J., et al. (2022) Molecular Dynamics Simulation of the Thermomechanical and Tribological Properties of Graphene-Reinforced Natural Rubber Nanocomposites. Polymers, 14, Article 5056. https://doi.org/10.3390/polym14235056 |
| [17] | Teng, F., Wu, J., Su, B. and Wang, Y. (2022) High-Speed Tribological Properties of Eucommia Ulmoides Gum/Natural Rubber Blends: Experimental and Molecular Dynamics Simulation Study. Tribology International, 171, Article 107542. https://doi.org/10.1016/j.triboint.2022.107542 |
| [18] | Gao, Y., Xie, Y., Liao, M., Li, Y., Zhu, J. and Tian, W. (2023) Study on the Mechanism of the Effect of Graphene on the Rheological Properties of Rubber-Modified Asphalt Based on Size Effect. Construction and Building Materials, 364, Article 129815. https://doi.org/10.1016/j.conbuildmat.2022.129815 |
| [19] | Joseph, E., Swaminathan, N. and Kannan, K. (2020) Material Identification for Improving the Strength of Silica/SBR Interface Using MD Simulations. Journal of Molecular Modeling, 26, Article No. 234. https://doi.org/10.1007/s00894-020-04489-z |
| [20] | Sattar, M.A., Nair, A.S., Xavier, P.J. and Patnaik, A. (2019) Natural Rubber-SiO2 Nanohybrids: Interface Structures and Dynamics. Soft Matter, 15, 2826-2837. https://doi.org/10.1039/c9sm00254e |
| [21] | 张旭敏. 新型纳米填料/橡胶复合材料结构和性能的分子动力学模拟与实验研究[D]: [博士学位论文]. 南京: 南京理工大学, 2023. |
| [22] | 郭伟, 孙斌, 任继江, 等. 尼龙66/氧化石墨烯纳米复合材料力学性能的分子动力学模拟[J]. 中原工学院学报, 2018, 29(3): 27-33. |
| [23] | 唐黎明, 王新楠, 纪平, 等. 碳纳米管/丁腈橡胶复合材料力学及摩擦性能的分子动力学模拟[J]. 润滑与密封, 2022, 47(8): 21-26. |
| [24] | 熊敏. Al/Cu界面Ni中间层作用的第一性原理与分子动力学研究[D]: [硕士学位论文]. 成都: 西南交通大学, 2022. |
| [25] | 郝泽文. 卟啉基低维材料电子性质及其自旋输运性质的理论研究[D]: [硕士学位论文]. 济南: 山东师范大学, 2022. |
| [26] | 齐学强. 燃料电池电催化剂催化机理与可控制备[D]: [博士学位论文]. 重庆: 重庆大学, 2012. |
| [27] | 孙超. 基于密度泛函理论的材料设计: VO2相变温度的调控和LiFePO4电导率的提高[D]: [博士学位论文]. 上海: 上海大学, 2015. |
| [28] | 杨小渝, 郝德博, 舒城, 等. MatCloud-QE: 基于云原生理念的高通量第一性原理计算程序包[J]. 中国材料进展, 2024, 43(11): 1007-1015. |
| [29] | 陆文聪, 吴炎淼, 刘太昂, 等. 基于机器学习的材料设计[J]. 河南师范大学学报(自然科学版), 2024, 52(4): 120-131. |
| [30] | 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. |
| [31] | 李一航, 肖斌, 唐宇超, 等. 尖晶石氧化物能量和结构的第一性原理计算和机器学习[J]. 上海大学学报(自然科学版), 2021, 27(4): 635-649. |
| [32] | 王园园, 武川, 彭志伟, 等. 基于机器学习的钛合金弹性模量预测方法研究[J]. 精密成形工程, 2024, 16(1): 33-42. |
| [33] | 肖斌, 吴雨沁, 刘轶. 基于第一性原理计算的镍基单晶高温合金掺杂的机器学习研究[J]. 上海金属, 2020, 42(3): 97-104+110. |
| [34] | 李妮. 铝合金中化合物微电偶效应的第一性原理计算与腐蚀行为预测研究[D]: [博士学位论文]. 北京: 北京科技大学, 2021. |
| [35] | 康靓, 米晓希, 王海莲, 等. 人工神经网络在材料科学中的研究进展[J]. 材料导报, 2020, 34(21): 21172-21179. |
| [36] | Wang, A., Liang, H., McDannald, A., Takeuchi, I. and Kusne, A.G. (2022) Benchmarking Active Learning Strategies for Materials Optimization and Discovery. Oxford Open Materials Science, 2, itac006. https://doi.org/10.1093/oxfmat/itac006 |
| [37] | Huang, G., Guo, Y., Chen, Y. and Nie, Z. (2023) Application of Machine Learning in Material Synthesis and Property Prediction. Materials, 16, Article 5977. https://doi.org/10.3390/ma16175977 |
| [38] | 李宏伟, 高佳, 孙新新, 等. 面向高性能塑性成形的多尺度建模仿真研究进展[J]. 机械工程学报, 2024, 60(1): 27-43. |
| [39] | 张慧敏, 王京, 王一博, 等. 锂离子电池SEI多尺度建模研究展望[J]. 储能科学与技术, 2023, 12(2): 366-382. |
| [40] | 沈雪阳, 褚瑞轩, 蒋宜辉, 等. 相变存储新材料设计与多尺度模拟的研究进展[J]. 金属学报, 2024, 60(10): 1362-1378. |
| [41] | 陶梦琴, 蔡振飞, 吴慧敏, 等. 基于第一性原理计算的Li7La3Zr2O12固态电解质的研究进展[J]. 功能材料, 2022, 53(8): 8067-8077. |
| [42] | Badini, S., Regondi, S. and Pugliese, R. (2023) Unleashing the Power of Artificial Intelligence in Materials Design. Materials, 16, Article 5927. https://doi.org/10.3390/ma16175927 |
| [43] | Goswami, L., Deka, M.K. and Roy, M. (2023) Artificial Intelligence in Material Engineering: A Review on Applications of Artificial Intelligence in Material Engineering. Advanced Engineering Materials, 25, Article 2300104. https://doi.org/10.1002/adem.202300104 |
| [44] | López, C. (2023) Artificial Intelligence and Advanced Materials. Advanced Materials, 35, Article 2208683. https://doi.org/10.1002/adma.202208683 |
| [45] | 谢建新, 宿彦京, 薛德祯, 等. 机器学习在材料研发中的应用[J]. 金属学报, 2021, 57(11): 1343-1361. |
| [46] | 伍侃. 机器学习预测三元无机光伏材料[D]: [硕士学位论文]. 西安: 西北大学, 2022. |
| [47] | Zuccarini, C., Ramachandran, K. and Jayaseelan, D.D. (2024) Material Discovery and Modeling Acceleration via Machine Learning. APL Materials, 12, Article 090601. https://doi.org/10.1063/5.0230677 |
| [48] | Wang, T., Shao, M., Guo, R., Tao, F., Zhang, G., Snoussi, H., et al. (2020) Surrogate Model via Artificial Intelligence Method for Accelerating Screening Materials and Performance Prediction. Advanced Functional Materials, 31, Article 2006425. https://doi.org/10.1002/adfm.202006245 |
| [49] | Agrawal, A. and Choudhary, A. (2019) Deep Materials Informatics: Applications of Deep Learning in Materials Science. MRS Communications, 9, 779-792. https://doi.org/10.1557/mrc.2019.73 |
| [50] | 吕蔚. 基于数据挖掘的材料性能优化及分子筛选[D]: [博士学位论文]. 上海: 上海大学, 2019. |
| [51] | 万新阳. 基于机器学习算法的钙钛矿氧化物全解水光催化剂的高效筛选[D]: [硕士学位论文]. 南京: 东南大学, 2022. |
| [52] | Yuan, J., Li, Z., Yang, Y., Yin, A., Li, W., Sun, D., et al. (2024) Applications of Machine Learning Method in High-Performance Materials Design: A Review. Journal of Materials Informatics, 4, Article No. 14. https://doi.org/10.20517/jmi.2024.15 |
| [53] | Johnson, N.S., Vulimiri, P.S., To, A.C., Zhang, X., Brice, C.A., Kappes, B.B., et al. (2020) Invited Review: Machine Learning for Materials Developments in Metals Additive Manufacturing. Additive Manufacturing, 36, Article 101641. https://doi.org/10.1016/j.addma.2020.101641 |
| [54] | 刘春太. 基于数值模拟的注塑成型工艺优化和制品性能研究[D]: [博士学位论文]. 河南: 郑州大学, 2003. |
| [55] | Wang, J. and Zhang, D. (2021) Research on Application of Machine Learning Technology in New Material System. Journal of Physics: Conference Series, 1865, Article 032009. https://doi.org/10.1088/1742-6596/1865/3/032009 |
| [56] | 许家忠, 郑学海, 周洵. 复合材料打磨机器人的主动柔顺控制[J]. 电机与控制学报, 2019, 23(12): 151-158. |
| [57] | 马旭东, 王朝, 孙理. 基于蚁群算法塑模孔群加工路径优化[J]. 制造技术与机床, 2020(10): 97-101. |
| [58] | 侯腾跃, 孙炎辉, 孙舒鹏, 等. 机器学习在材料结构与性能预测中的应用综述[J]. 材料导报, 2022, 36(6): 161-172. |
| [59] | 吴炜, 孙强. 应用机器学习加速新材料的研发[J]. 中国科学(物理学 力学 天文学), 2018(10): 58-70. |
| [60] | Li, B., Cao, P., Saito, T. and Sokolov, A.P. (2022) Intrinsically Self-Healing Polymers: From Mechanistic Insight to Current Challenges. Chemical Reviews, 123, 701-735. https://doi.org/10.1021/acs.chemrev.2c00575 |
| [61] | 程强, 徐文祥, 刘志峰, 等. 面向智能绿色制造的机床装备研究综述[J]. 华中科技大学学报(自然科学版), 2022, 50(6): 31-38. |
