化工科研范式智能化转型的思考与展望

doi:10.16085/j.issn.1000-6613.2023-0530

摘要/Abstract

摘要：

化工行业作为国家的支柱性产业，不断地积极响应国家号召，推动行业数字化、智能化发展。实验室和研究院作为化学工程核心技术支撑，是化工行业智能化转型中必不可少的一部分。站在智能化变革的起点，本文调研归纳了目前国内外化工实验室的智能化转型最新进展，围绕科研创新展望了化工实验室的智能化转型蓝图，提出了从信息化、数字化到智能化过渡，涵盖不同发展层级的智能研究院建设大纲，为规划智能研究院建设的具体方案提供指导，并展望了人工智能全面赋能的化工科研范式变革。

关键词: 人工智能, 系统工程, 计算机模拟, 实验验证, 优化设计, 自动化

Abstract:

As a pillar industry, the chemical industry is actively responding to the national call to promote the digital and intelligent development. As an essential part of the intelligent transformation of the chemical industry, it is necessary to conduct in-depth research and propose an implementable overall technical solution to lay a solid foundation for the subsequent intelligent transformation. This paper summarizes the latest progress of the intelligent transformation of chemical laboratories in China and abroad, outlines the blueprint of the intelligent transformation of chemical laboratories around scientific research and innovation, and proposes an outline of building intelligent research institutes covering different levels of development from informationization, digitalization and transition to intelligence, so as to provide a guidance for the specific plan of intelligent research institutes. An outlook of research paradigm change empowered by artificial intelligence (AI) is also provided.

Key words: artificial intelligence, systems engineering, computer simulation, experimental validation, optimal design, automation

中图分类号:

TQ016

李蓝宇, 黄新烨, 王笑楠, 邱彤. 化工科研范式智能化转型的思考与展望[J]. 化工进展, 2023, 42(7): 3325-3330.

LI Lanyu, HUANG Xinye, WANG Xiaonan, QIU Tong. Reflection and prospects on the intelligent transformation of chemical engineering research[J]. Chemical Industry and Engineering Progress, 2023, 42(7): 3325-3330.

图/表 4

参考文献 36

1	GRAY Jim. Talk given by Jim Gray to the NRC-CSTB in Mountain View[R/OL]. , 2007.
2	OLIVETTI Elsa A, COLE Jacqueline M, KIM Edward, et al. Data-driven materials research enabled by natural language processing and information extraction[J]. Applied Physics Reviews, 2020, 7(4): 041317.
3	FRIEDERICH Pascal, KRENN Mario, TAMBLYN Isaac, et al. Scientific intuition inspired by machine learning-generated hypotheses[J]. Machine Learning: Science and Technology, 2021, 2(2): 025027.
4	ZHANG Linfeng, LIN Deye, WANG Han, et al. Active learning of uniformly accurate interatomic potentials for materials simulation[J]. Physical Review Materials, 2019, 3(2): 023804.
5	MRDJENOVICH David, HORTON Matthew K, MONTOYA Joseph H, et al. Propnet: A knowledge graph for materials science[J]. Matter, 2020, 2(2): 464-480.
6	DE PABLO Juan J, JACKSON Nicholas E, WEBB Michael A, et al. New frontiers for the materials genome initiative[J]. NPJ Computational Materials, 2019, 5: 41.
7	Unlocking the “Chemome” with DNA-Encoded Chemistry and Machine Learning [EB/OL]//Google AI Blog. [2021-11-19]. .
8	Homepage[EB/OL]. [2021-11-19]. .
9	REIZMAN Brandon J, WANG Yiming, BUCHWALD Stephen L, et al. Suzuki-Miyaura cross-coupling optimization enabled by automated feedback[J]. Reaction Chemistry & Engineering, 2016, 1(6): 658-666.
10	KNOWLES J. ParEGO: A hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(1): 50-66.
11	BAUMGARTNER Lorenz M, COLEY Connor W, REIZMAN Brandon J, et al. Optimum catalyst selection over continuous and discrete process variables with a single droplet microfluidic reaction platform[J]. Reaction Chemistry & Engineering, 2018, 3(3): 301-311.
12	EYKE Natalie S, GREEN William H, JENSEN Klavs F. Iterative experimental design based on active machine learning reduces the experimental burden associated with reaction screening[J]. Reaction Chemistry & Engineering, 2020, 5(10): 1963-1972.
13	COLEY C W, THOMAS D A, LUMMISS J A M, et al. A robotic platform for flow synthesis of organic compounds informed by AI planning[J]. Science, 2019, 365(6453): eaax1566.
14	YAN Chong, LI Haoran, CHEN Xiang, et al. Regulating the inner Helmholtz plane for stable solid electrolyte interphase on lithium metal anodes[J]. Journal of the American Chemical Society, 2019, 141(23): 9422-9429.
15	WILLIAMSON M J, TROMP R M, VEREECKEN P M, et al. Dynamic microscopy of nanoscale cluster growth at the solid-liquid interface[J]. Nature Materials, 2003, 2(8): 532-536.
16	GROMSKI Piotr S, HENSON Alon B, GRANDA Jarosław M, et al. How to explore chemical space using algorithms and automation[J]. Nature Reviews Chemistry, 2019, 3(2): 119-128.
17	CAO Liwei, RUSSO Danilo, FELTON Kobi, et al. Optimization of formulations using robotic experiments driven by machine learning DoE[J]. Cell Reports Physical Science, 2021, 2(1): 100295.
18	LI Junqi, BALLMER Steven G, GILLIS Eric P, et al. Synthesis of many different types of organic small molecules using one automated process[J]. Science, 2015, 347(6227): 1221-1226.
19	LI Jun, EASTGATE Martin D. Making better decisions during synthetic route design: Leveraging prediction to achieve greenness-by-design[J]. Reaction Chemistry & Engineering, 2019, 4(9): 1595-1607.
20	WANG Zheng, ZHAO Wei, HAO Gefei, et al. Mapping the resources and approaches facilitating computer-aided synthesis planning[J]. Organic Chemistry Frontiers, 2021, 8(4): 812-824.
21	AYRES Lucas B, GOMEZ F, Linton Jeb, et al. Taking the leap between analytical chemistry and artificial intelligence: A tutorial review[J]. Analytica Chimica Acta, 2021, 1161: 338403.
22	This is the kiwi-biolab, a BMBF KI Future Lab![EB/OL]. [2021-11-18]. .
23	Home-Data Analytics and Process Modeling-Datahow Zürich[EB/OL]. [2021-11-18]. .
24	Inauguration of a research consortium for the automated and digitalized chemical synthesis with the University of Cambridge and AstraZeneca.[EB/OL]. [2021-11-19]. .
25	“机器化学家”带来科研新范式——中国科学技术大学科研人员深耕精准智能化学领域[N]. 人民日报, 2023-04-24(19). .
26	YUAN Xiangzhou, SUVARNA Manu, Sean LOW, et al. Applied machine learning for prediction of CO₂ adsorption on biomass waste-derived porous carbons[J]. Environmental Science & Technology, 2021, 55(17): 11925-11936.
27	GUAN Jian, HUANG Tan, LIU Wei, et al. Design and prediction of metal organic framework-based mixed matrix membranes for CO₂ capture via machine learning[J]. Cell Reports Physical Science, 2022, 3(5): 100864.
28	XU Shidang, LI Jiali, CAI Pengfei, et al. Self-improving photosensitizer discovery system via Bayesian search with first-principle simulations[J]. Journal of the American Chemical Society, 2021, 143(47): 19769-19777.
29	Flore MEKKI-BERRADA, REN Zekun, HUANG Tan, et al. Two-step machine learning enables optimized nanoparticle synthesis[J]. NPJ Computational Materials, 2021, 7: 55.
30	YANG Haitao, LI Jiali, Kai Zhuo LIM, et al. Automatic strain sensor design via active learning and data augmentation for soft machines[J]. Nature Machine Intelligence, 2022, 4(1): 84-94.
31	LI Jiali, TELYCHKO Mykola, YIN Jun, et al. Machine vision automated chiral molecule detection and classification in molecular imaging[J]. Journal of the American Chemical Society, 2021, 143(27): 10177-10188.
32	ZHANG Shuyuan, LIANG Xiao, HUANG Xinye, et al. Precise and fast microdroplet size distribution measurement using deep learning[J]. Chemical Engineering Science, 2022, 247: 116926.
33	ZHANG Shuyuan, QIN Kang, HUANG Xinye, et al. Insight into microdispersion flows with a novel video deep learning method[J]. Advanced Intelligent Systems, 2022, 4(11): 2200098.
34	BI Kexin, BEYKAL Burcu, AVRAAMIDOU Styliani, et al. Integrated modeling of transfer learning and intelligent heuristic optimization for a steam cracking process[J]. Industrial & Engineering Chemistry Research, 2020, 59(37): 16357-16367.
35	BI Kexin, QIU Tong. Novel naphtha molecular reconstruction process using a self-adaptive cloud model and hybrid genetic algorithm-particle swarm optimization algorithm[J]. Industrial & Engineering Chemistry Research, 2019, 58(36): 16753-16760.
36	HUANG Xinye, ZHANG Shuyuan, LI Haoran, et al. An integrated method of Bayesian optimization and D-optimal design for chemical experiment optimization[J]. Processes, 2022, 11(1): 87.

层级	建设发展指标体系
0级（传统科研）	完全依靠科研人员进行科研探索和决策
1级（信息化）	利用计算机实现数据的采集和信息的记录查询
2级（数字化）	数据治理、数据共享和数字化平台的建设
3级（局部智能化）	纵向实现对智能化建设内容的试点建设
4级（全面智能化）	横向实现各个部门与模块的一体化协同和智能化全覆盖

层级	建设发展指标体系
0级（传统科研）	完全依靠科研人员进行科研探索和决策
1级（信息化）	利用计算机实现数据的采集和信息的记录查询
2级（数字化）	数据治理、数据共享和数字化平台的建设
3级（局部智能化）	纵向实现对智能化建设内容的试点建设
4级（全面智能化）	横向实现各个部门与模块的一体化协同和智能化全覆盖

[1]	杨建平. 降低HPPO装置反应系统原料消耗的PSE[J]. 化工进展, 2023, 42(S1): 21-32.
[2]	陈匡胤, 李蕊兰, 童杨, 沈建华. 质子交换膜燃料电池气体扩散层结构与设计研究进展[J]. 化工进展, 2023, 42(S1): 246-259.
[3]	张凤岐, 崔成东, 鲍学伟, 朱炜玄, 董宏光. 胺液吸收-分步解吸脱硫工艺的设计与评价[J]. 化工进展, 2023, 42(S1): 518-528.
[4]	孙玉玉, 蔡鑫磊, 汤吉海, 黄晶晶, 黄益平, 刘杰. 反应精馏合成甲基丙烯酸甲酯工艺优化及节能[J]. 化工进展, 2023, 42(S1): 56-63.
[5]	刘炫麟, 王驿凯, 戴苏洲, 殷勇高. 热泵中氨基甲酸铵分解反应特性及反应器结构优化[J]. 化工进展, 2023, 42(9): 4522-4530.
[6]	王晨, 白浩良, 康雪. 大功率UV-LED散热与纳米TiO₂光催化酸性红26耦合系统性能[J]. 化工进展, 2023, 42(9): 4905-4916.
[7]	吴正浩, 周天航, 蓝兴英, 徐春明. 人工智能驱动化学品创新设计的实践与展望[J]. 化工进展, 2023, 42(8): 3910-3916.
[8]	王俊杰, 潘艳秋, 牛亚宾, 俞路. 分子水平催化重整装置模型构建及应用[J]. 化工进展, 2023, 42(7): 3404-3412.
[9]	周龙大, 赵立新, 徐保蕊, 张爽, 刘琳. 电场-旋流耦合强化多相介质分离研究进展[J]. 化工进展, 2023, 42(7): 3443-3456.
[10]	薛凯, 王帅, 马金鹏, 胡晓阳, 种道彤, 王进仕, 严俊杰. 工业园区分布式综合能源系统的规划与调度[J]. 化工进展, 2023, 42(7): 3510-3519.
[11]	陈森, 殷鹏远, 杨证禄, 莫一鸣, 崔希利, 锁显, 邢华斌. 功能固体材料智能合成研究进展[J]. 化工进展, 2023, 42(7): 3340-3348.
[12]	顾诗亚, 董亚超, 刘琳琳, 张磊, 庄钰, 都健. 考虑中间节点的碳捕集管路系统设计与优化[J]. 化工进展, 2023, 42(6): 2799-2808.
[13]	李雪, 王艳君, 王玉超, 陶胜洋. 仿生表面用于雾水收集的最新研究进展[J]. 化工进展, 2023, 42(5): 2486-2503.
[14]	邹银才, 李清国, 吴辉, 钟小兵, 陈咸志. 弹载相变热沉传热仿真与优化[J]. 化工进展, 2023, 42(3): 1248-1256.
[15]	孙潇, 朱光涛, 裴爱国. 氢液化装置产业化与研究进展[J]. 化工进展, 2023, 42(3): 1103-1117.