Application of artificial intelligence (AI) in the design of complex chemical engineering processes: Status, challenges and prospects

doi:10.16085/j.issn.1000-6613.2025-0549

Abstract

Abstract:

Artificial intelligence has driven rapid advancements in the design of complex chemical engineering processes with a new data-driven model, serving as a powerful force behind transformative developments in the chemical industry and holding significant implications for the evolution of research paradigms, new technologies, and industrial processes. This paper focuses on the progress of intelligent algorithms in the design of complex chemical processes, and systematically outlines the applications in molecular structure and property prediction, recommendation of reaction and separation pathways, and intelligent optimization of process parameters. The paper also summarizes the performance of intelligent algorithms in big datasets collection and cleaning, pattern recognition, and trend prediction. It provides an in-depth analysis of the challenges faced by intelligent algorithms in chemical process design, including issues related to the lack of professional feature data quality and the insufficient interpretability of models. The paper proposes the practical need for the development of comprehensive multi-level chemical big datasets, the continuous exploration of the relationship between intelligent algorithm structures and chemical process node information, and further improvements in the interpretability and structural stability of intelligent models. These efforts aim to construct a large-scale model framework for intelligent chemical process design, from molecular structure recognition to process design, and ultimately realize intelligent design in the chemical industry.

Key words: artificial intelligence, molecular fingerprint, thermodynamic properties, multiscale prediction, optimal design

摘要：

基于人工智能的数据驱动复杂化工过程设计新模式发展迅速，成为推动化工行业变革性发展的强大动力，对引领研究范式变革、新技术开发及流程再造具有重要理论指导与实践意义。本文聚焦人工智能在复杂化工过程设计中的研究进展，系统阐述其在分子结构物性预测、热/动力学预测、反应分离路径推荐、工艺过程优化四个核心环节的作用及应用成效，总结分析了在数据收集与清洗、模式识别与趋势预测的表现，深入剖析了当前面临的专业特征数据质量不稳定、模型可解释性不足等挑战，并提出了未来应构建全要素、多层级化工大数据库，持续探究智能算法与化工流程结构信息关联机制，着力提升模型的可解释和架构稳定性，为构建从分子识别到过程设计的智能模型框架、实现化工过程智能设计提供新思路。

关键词: 人工智能, 分子指纹, 热力学性质, 多尺度预测, 优化设计

CLC Number:

TP181

CHEN Songsong, BAO Aili, HUO Feng, HOU Yahui, CUI Gaijing, ZHANG Junping. Application of artificial intelligence (AI) in the design of complex chemical engineering processes: Status, challenges and prospects[J]. Chemical Industry and Engineering Progress, 2025, 44(8): 4821-4837.

陈嵩嵩, 鲍艾丽, 霍锋, 侯亚慧, 崔改静, 张军平. 人工智能（AI）在复杂化工过程设计中的应用：现状、挑战与展望[J]. 化工进展, 2025, 44(8): 4821-4837.

Figures/Tables 14

References 113

[1]	CHIANG Leo H, BRAUN Birgit, WANG Zhenyu, et al. Towards artificial intelligence at scale in the chemical industry[J]. AIChE Journal, 2022, 68 (6), e17644.
[2]	HE Gaoqi, LIU Shun, LIU Zhuoran, et al. Prototype-based contrastive substructure identification for molecular property prediction[J]. Briefings in Bioinformatics, 2024, 25 (6), 565.
[3]	GERASIMOV Michail, SOTO Fernando A, WAGNER Janika, et al. Species distribution during solid electrolyte interphase formation on lithium using MD/DFT-parameterized kinetic Monte Carlo simulations[J]. Journal of Physical Chemistry C, 2023, 127 (10):4872-4886.
[4]	JALILI Seifollah, TAFAZZOLI Mohsen, Mehdi JALALI-HERAVI. Comparison of multiple linear regression and artificial neural networks in predicting octanol/water partition coefficient of a variety of organic molecules[J]. Journal of Theoretical & Computational Chemistry, 2003, 2 (3):335-344.
[5]	SAQIB Muhammad, RANI Mashal, MUBASHIR Tayyaba, et al. Designing of low band gap organic semiconductors through data mining from multiple databases and machine learning assisted property prediction[J]. Optical Materials, 2024, 150: 115295.
[6]	LI Miao, LI Jian, LU Yuchen, et al. Developing the QSPR model for predicting the storage lipid/water distribution coefficient of organic compounds[J]. Frontiers of Environmental Science & Engineering, 2020, 15 (2): 24.
[7]	FEI Jiangchi, MAO Qiming, PENG Lu, et al. The internal relation between quantum chemical descriptors and empirical constants of polychlorinated compounds[J]. Molecules, 2018, 23 (11):2935.
[8]	BOUNACEUR Roda, Nicolas BARTHéLEMY, DELORT Nicolas, et al. A multimodal learning model based on a QSPR approach for the estimation of RON, MON and CN, for any C, H, O hydrocarbons[J]. Fuel, 2025, 381:133438.
[9]	LI Ruichen, YE Haotian, JIANG Du, et al. A computational framework for neural network-based variational Monte Carlo with Forward Laplacian[J]. Nature Machine Intelligence, 2024, 6 (2):209-219.
[10]	YIN WanJian. Density functional theory-free descriptor for the practical discovery of perovskite catalysts[J]. Computational Materials Science, 2021, 193: 110342.
[11]	XIAO Y, SHEN C, ZHANG W B. Screening and prediction of metal-doped α-borophene monolayer for nitric oxide elimination[J]. Materials Today Chemistry, 2022, 25:100958.
[12]	KOHN W, BECKE A D, PARR R G. Density functional theory of electronic structure[J]. The Journal of Physical Chemistry, 1996, 100 (31): 12974-12980.
[13]	SCHERBAKOV K A, KONDRATIEV M S, SAMCHENKO A A, et al. The electronic structure properties of 20L-amino acids in neutral and zwitterion forms: Quantum-chemical calculations[J]. Biophysics, 2016, 61 (3):361-372.
[14]	沈良骏, 叶世勇, 李前树. AM1半经验方法研究苯环在PEEK模型分子内的运动[J]. 高等学校化学学报,1994, 15 (7):1050-1054.
	SHEN Liangjun, YE Shiyong, LI Qianshu. AM1 scmiempirical method for study the motion of phenyl rings in model compounds of PEEK[J]. Chemical Journal of Chinese Universities, 1994, 15(7): 1050-1054.
[15]	BREGANTE Daniel T, CHAN Matthew C, TAN Jun Zhi, et al. The shape of water in zeolites and its impact on epoxidation catalysis[J]. Nature Catalysis, 2021, 4 (9): 797-808.
[16]	YAFFE Denise, COHEN Yoram, ESPINOSA Gabriela, et al. Fuzzy ARTMAP and back-propagation neural networks based quantitative structure-property relationships (QSPRs) for octanol-water partition coefficient of organic compounds[J]. Journal of Chemical Information and Computer Sciences, 2002, 42 (2):162-183.
[17]	WAN Zhongyu, WANG Quande, LIANG Jinhu. Accurate prediction of standard enthalpy of formation based on semiempirical quantum chemistry methods with artificial neural network and molecular descriptors[J]. International Journal of Quantum Chemistry, 2020, 121 (2):e26441.
[18]	任嘉辉, 刘豫, 刘朝, 等. 基于分子指纹和拓扑指数的工质临界温度理论预测[J]. 化工学报, 2022, 73 (04):1493-1500.
	REN Jiahui, LIU Yu, LIU Chao, et al. Critical temperature prediction of working fluids using molecular fingerprints and topological indices[J]. CIESC Journal, 2022, 73(4): 1493-1500.
[19]	LEE Hao-Yeh, YANG Tsung-Hua, Lung CHIEN I,et al. Grade transition using dynamic neural networks for an industrial high-pressure ethylene-vinyl acetate (EVA) copolymerization process[J]. Computers & Chemical Engineering, 2009, 33 (8): 1371-1378.
[20]	SUCH Felipe Petroski, Shagan SAH, DOMINGUEZ Miguel Alexander, et al. Robust spatial filtering with graph convolutional neural networks[J]. IEEE Journal of Selected Topics in Signal Processing, 2017, 11(6): 884-896.
[21]	COLEY Connor W, BARZILAY Regina, GREEN William H, et al. Convolutional embedding of attributed molecular graphs for physical property prediction[J]. Journal of Chemical Information and Modeling, 2017, 57(8): 1757-1772.
[22]	LUSCI Alessandro, POLLASTRI Gianluca, BALDI Pierre. Deep architectures and deep learning in chemoinformatics: The prediction of aqueous solubility for drug-like molecules[J]. Journal of Chemical Information and Modeling, 2013, 53(7): 1563-1575.
[23]	MAZHEIKA Aliaksei, WANG Yanggang, VALERO Rosendo, et al. Artificial-intelligence-driven discovery of catalyst genes with application to CO₂ activation on semiconductor oxides[J]. Nature Communications, 2022, 13(1): 419.
[24]	ZHENG Anhui, WANG Yuxuan, ZHANG Fangfei, et al. Data-driven design and controllable synthesis of Pt/carbon electrocatalysts for H₂ evolution[J]. iScience, 2021, 24(12): 103430.
[25]	CHENG Lei, TANG Yawen, OSTRIKOV Kostya, et al. Single-atom heterogeneous catalysts: Human- and AI-driven platform for augmented designs, analytics and reality-enabled manufacturing[J]. Angewandte Chemie, 2024, 136(5): e202313599.
[26]	MACE Samuel, XU Yingjian, NGUYEN Bao N. Automated transition metal catalysts discovery and optimisation with AI and machine learning[J]. ChemCatChem, 2024, 16(10): e202301475.
[27]	Jorge BENAVIDES-HERNÁNDEZ, DUMEIGNIL Franck. From characterization to discovery: Artificial intelligence, machine learning and high-throughput experiments for heterogeneous catalyst design[J]. ACS Catalysis, 2024, 14(15): 11749-11779.
[28]	NIU Zhiqiang, ZHAO Wanhui, DENG Hao, et al. Generative artificial intelligence for designing multi-scale hydrogen fuel cell catalyst layer nanostructures[J]. ACS Nano,2024, 18 (31): 20504-20517.
[29]	GAO Yuchen, YUAN Yuhang, HUANG Suozhi, et al. A knowledge-data dual-driven framework for predicting the molecular properties of rechargeable battery electrolytes[J]. Angewandte Chemie International Edition, 2025, 64(4): e202416506.
[30]	ROOSTA Ahmadreza, HAGHBAKHSH Reza, DUARTE Ana Rita C, et al. Machine learning coupled with group contribution for predicting the density of deep eutectic solvents[J]. Fluid Phase Equilibria, 2023, 565: 113672.
[31]	Ziyu LYU, GU Chao, Ziyang LYU, et al. Composition engineering on the local structure and viscosity of the CaO-SiO₂-Al₂O₃-P₂O₅-FeO slag by machine learning methods[J]. Crystals, 2022, 12(10): 1338.
[32]	LIANG Tao, LIU Wei, TAN Kai, et al. Advancing ionic liquid research with pSCNN: A novel approach for accurate normal melting temperature predictions[J]. ACS Omega, 2024, 9(29): 31694-31702.
[33]	GAO Tianyu, JI Yujin, LIU Cheng, et al. Molecular descriptor-enhanced graph neural network for energetic molecular property prediction[J]. Science China Materials, 2024, 67(4): 1243-1252.
[34]	CAO Xinyu, GONG Ming, TULA Anjan, et al. An improved machine learning model for pure component property estimation[J]. Engineering, 2024, 39: 61-73.
[35]	LI Chunyan, FENG Jihua, LIU Shihu, et al. A novel molecular representation learning for molecular property prediction with a multiple SMILES-based augmentation[J]. Computational Intelligence and Neuroscience, 2022, 2022(1): 8464452.
[36]	WEN Huaqiang, SU Yang, WANG Zihao, et al. A systematic modeling methodology of deep neural network-based structure-property relationship for rapid and reliable prediction on flashpoints[J]. AIChE Journal, 2022, 68(1): e17402.
[37]	SHARMA Anshu, LI Li, GARG Aman, et al. Probe into the volumetric properties of binary mixtures: Essence of regression-based machine learning algorithms[J]. Journal of Molecular Liquids, 2024, 399: 124498.
[38]	DHAKAL Pratik, SHAH Jindal K. Developing machine learning models for ionic conductivity of imidazolium-based ionic liquids[J]. Fluid Phase Equilibria, 2021, 549: 113208.
[39]	ZHANG Biao, SUDRE Guillaume, QUINTARD Guilhem, et al. Imidazolium-based poly(ionic liquid)/ionic liquid solutions: Rheology, structuration and ionic transport properties[J]. Polymer, 2021, 237: 124305.
[40]	张娜娜, 李圆圆, 贾文, 等. 几种离子液体的制备及性能表征[J]. 辽宁化工, 2021, 50 (12):1781-1784.
	ZHANG Nana, LI Yuanyuan, JIA Wen, et al. Preparation and characterization of several ionic liquids[J]. Liaoning Chemical Industry. 2021, 50 (12), 1781-1784.
[41]	ZHAO Nan, JACQUEMIN Johan. The development of the UNIFAC-CONDUCT model as a novel approach for the estimation of the conductivity of pure ionic liquids[J]. Fluid Phase Equilibria, 2017, 449: 60-67.
[42]	LAZZÚS Juan A. A group contribution method to predict the thermal decomposition temperature of ionic liquids[J]. Journal of Molecular Liquids, 2012, 168: 87-93.
[43]	WANG Chenyang, SONG Cancan, ZHOU Guobing, et al. Developing machine learning models for predicting multiple physical properties of ionic liquids through a combined constitution-structure-interaction descriptor[J]. Journal of Chemical & Engineering Data, 2024, 69(12): 4350-4361.
[44]	LING Yulong, LI Kun, WANG Mi, et al. Revisiting the structure, interaction, and dynamical property of ionic liquid from the deep learning force field[J]. Journal of Power Sources, 2023, 555: 232350.
[45]	Dorota WILEŃSKA, ANUSIEWICZ Iwona, FREZA Sylwia, et al. Predicting the viscosity and electrical conductivity of ionic liquids on the basis of theoretically calculated ionic volumes[J]. Molecular Physics, 2015, 113(6): 630-639.
[46]	Jonathan NILSSON-HALLÉN, Bodil AHLSTRÖM, MARCZEWSKI Maciej, et al. Ionic liquids: A simple model to predict ion conductivity based on DFT derived physical parameters[J]. Frontiers in Chemistry, 2019, 7: 126.
[47]	KUMAR Ashwani, KUMAR Parvin. Quantitative structure toxicity analysis of ionic liquids toward acetylcholinesterase enzyme using novel QSTR models with index of ideality of correlation and correlation contradiction index[J]. Journal of Molecular Liquids, 2020, 318: 114055.
[48]	ZHANG Lei, YE Lili, WANG Fan, et al. Prediction of hydrogen abstraction rate constants at the allylic site between alkenes and OH with multiple machine learning models[J]. The Journal of Physical Chemistry A, 2024, 128(4): 761-772.
[49]	YU Jinhui, SHAN Dezun, SONG Hongwei, et al. A novel hybrid machine learning model for predicting rate constants of the reactions between alkane and CH₃ radical[J]. Fuel, 2022, 322: 124150.
[50]	YU Jinhui, RUAN Shanshan, SONG Hongwei, et al. Machine learning rate constants of hydrogen abstraction reactions between ester and H atom[J]. Combustion and Flame, 2023, 255: 112901.
[51]	ZHANG Yu, XIA Min, SONG Hongwei, et al. Predicting rate constants of alkane cracking reactions using machine learning[J]. The Journal of Physical Chemistry A, 2024, 128(12): 2383-2392.
[52]	HOUSTON Paul L, NANDI Apurba, BOWMAN Joel M. A Machine learning approach for prediction of rate constants[J]. Journal of Physical Chemistry Letters 2019, 10 (17), 5250-5258.
[53]	HOUSTON Paul L, NANDI Apurba, BOWMAN Joel M. A machine learning approach for rate constants. Ⅲ. Application to the Cl(²P)+CH₄ → CH₃+HCl reaction[J]. The Journal of Physical Chemistry A, 2022, 126(33): 5672-5679.
[54]	PAUL Shyeni, ZHU Yunqing, ROMAIN Charles, et al. Ring-opening copolymerization (ROCOP): Synthesis and properties of polyesters and polycarbonates[J]. Chemical Communications, 2015, 51(30): 6459-6479.
[55]	LU Junhui, ZHANG Huimin, YU Jinhui, et al. Predicting rate constants of hydroxyl radical reactions with alkanes using machine learning[J]. Journal of Chemical Information and Modeling, 2021, 61(9): 4259-4265.
[56]	CHUNG Yunsie, GREEN William H. Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates[J]. Chemical Science, 2024, 15(7): 2410-2424.
[57]	LI Minghan, ZHAO Lingling, JIN Shuo, et al. Process schemes of ethanol coupling to C₄ olefins based on a genetic algorithm for back propagation neural network optimization[J]. Heliyon, 2022, 8(12): e12301.
[58]	NASR Noha, HAFEZ Hisham, NAGGAR M Hesham EL, et al. Application of artificial neural networks for modeling of biohydrogen production[J]. International Journal of Hydrogen Energy, 2013, 38(8): 3189-3195.
[59]	ZAMANIYAN Akbar, JODA Fatemeh, BEHROOZSARAND Alireza, et al. Application of artificial neural networks (ANN) for modeling of industrial hydrogen plant[J]. International Journal of Hydrogen Energy, 2013, 38(15): 6289-6297.
[60]	GHASEMZADEH Kamran, Abbas AGHAEINEJAD-MEYBODI, BASILE Angelo. Hydrogen production as a green fuel in silica membrane reactor: Experimental analysis and artificial neural network modeling[J]. Fuel, 2018, 222: 114-124.
[61]	GHASEMZADEH Kamran, AHMADNEJAD Farzad, Abbas AGHAEINEJAD-MEYBODI, et al. Hydrogen production by a PdAg membrane reactor during glycerol steam reforming: ANN modeling study[J]. International Journal of Hydrogen Energy, 2018, 43(15): 7722-7730.
[62]	Stefan SIMIĆ, Erna ZUKIĆ, SCHMERMUND Luca, et al. Shortening synthetic routes to small molecule active pharmaceutical ingredients employing biocatalytic methods[J]. Chemical Reviews, 2022, 122(1): 1052-1126.
[63]	WIRNSBERGER Peter, IBARZ Borja, PAPAMAKARIOS George. Estimating Gibbs free energies via isobaric-isothermal flows[J]. Machine Learning: Science and Technology, 2023, 4(3): 035039.
[64]	CHEN Guzhong, SONG Zhen, QI Zhiwen, et al. Neural recommender system for the activity coefficient prediction and UNIFAC model extension of ionic liquid-solute systems[J]. AIChE Journal, 2021, 67(4): e17171.
[65]	ABRANCHES Dinis O, MAGINN Edward J, COLÓN Yamil J. Activity coefficient acquisition with thermodynamics-informed active learning for phase diagram construction[J]. AIChE Journal, 2023, 69(8): e18141.
[66]	FELTON Kobi C, Hashem BEN-SAFAR, LAPKIN A.Lapkin DeepGamma: A deep learning model for activity coefficient prediction[C]//1st Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE), 2022.
[67]	WINTER Benedikt, WINTER Clemens, SCHILLING Johannes, et al. A smile is all you need: Predicting limiting activity coefficients from SMILES with natural language processing[J]. Digital Discovery, 2022, 1(6): 859-869.
[68]	WINTER Benedikt, WINTER Clemens, ESPER Timm, et al. SPT-NRTL: A physics-guided machine learning model to predict thermodynamically consistent activity coefficients[J]. Fluid Phase Equilibria, 2023, 568: 113731.
[69]	HU Zehua, LI Peilong, LIU Yefei. Enhancing the performance of evolutionary algorithm by differential evolution for optimizing distillation sequence[J]. Molecules, 2022, 27(12): 3802.
[70]	MAYEVSKIY Mark, FROLKOVA Anastasia, FROLKOVA Alla. Separation and purification of methyl isobutyl ketone from acetone+isopropanol+water+methyl isobutyl ketone+methyl isobutyl carbinol+diisobutyl ketone mixture[J]. ACS Omega, 2020, 5(39): 25365-25370.
[71]	BALHORN Lukas Schulze, CABALLERO Marc, SCHWEIDTMANN Artur M. Toward autocorrection of chemical process flowsheets using large language models[J]. Computer Aided Chemical Engineering, 2024, 53: 3109-3114.
[72]	VOGEL Gabriel, SCHULZE BALHORN Lukas, SCHWEIDTMANN Artur M. Learning from flowsheets: A generative transformer model for autocompletion of flowsheets[J]. Computers & Chemical Engineering, 2023, 171: 108162.
[73]	HIRTREITER Edwin, BALHORN Lukas Schulze, SCHWEIDTMANN Artur M. Toward automatic generation of control structures for process flow diagrams with large language models[J]. AIChE Journal, 2024, 70(1): e18259.
[74]	BALHORN Lukas Schulze, HIRTREITER Edwin, LUDERER Lynn, et al. Data augmentation for machine learning of chemical process flowsheets[J]. Computer Aided Chemical Engineering, 2023, 52: 2011-2016.
[75]	VOGEL Gabriel, HIRTREITER Edwin, SCHULZE BALHORN Lukas, et al. SFILES 2.0: An extended text-based flowsheet representation[J]. Optimization and Engineering, 2023, 24(4): 2911-2933.
[76]	BOIKO Daniil A, MACKNIGHT Robert, KLINE Ben, et al. Autonomous chemical research with large language models[J]. Nature, 2023, 624(7992): 570-578.
[77]	ZHANG Wei, WANG Qinggong, KONG Xiangtai, et al. Fine-tuning large language models for chemical text mining[J]. Chemical Science, 2024, 15(27): 10600-10611.
[78]	BUBEL Martin, LUDL Patrick Otto, SEIDEL Tobias, et al. A modular approach for surrogate modeling of flowsheets[J]. Chemie Ingenieur Technik, 2021, 93(12): 1987-1997.
[79]	DUTTA Debaprasad, UPRETI Simant R. Artificial intelligence-based process control in chemical, biochemical, and biomedical engineering[J]. The Canadian Journal of Chemical Engineering, 2021, 99(11): 2467-2504.
[80]	BEHROOZSARAND Alireza, SHAFIEI Sirous. Control of TAME reactive distillation using non-dominated sorting genetic algorithm-Ⅱ[J]. Journal of Loss Prevention in the Process Industries, 2012, 25(1): 192-201.
[81]	BEHROOZSARAND Alireza, WOOD David A. Evolutionary algorithms for controller tuning of tert-amyl-methyl-ether reactive distillation[J]. Journal of Systems Science and Systems Engineering, 2020, 29(3): 325-343.
[82]	EL-GENDY Eman M, SAAFAN Mahmoud M, ELKSAS Mohamed S, et al. Applying hybrid genetic-PSO technique for tuning an adaptive PID controller used in a chemical process[J]. Soft Computing, 2020, 24(5): 3455-3474.
[83]	LIU Jingwei, LI Tianyue, CHEN Jiaming, et al. Research on improved intelligent control processes based on three kinds of artificial intelligence[J]. Processes, 2020, 8(9): 1042.
[84]	MAZINAN A H. A new algorithm to AI-based predictive control scheme for a distillation column system[J]. The International Journal of Advanced Manufacturing Technology, 2013, 66(9): 1379-1388.
[85]	FREUDENMANN Thomas, GEHRMANN Hans-Joachim, ALEKSANDROV Krasimir, et al. Hybrid models for efficient control, optimization, and monitoring of thermo-chemical processes and plants[J]. Processes, 2021, 9(3): 515.
[86]	MA Yan, ZHU Wenbo, BENTON Michael G, et al. Continuous control of a polymerization system with deep reinforcement learning[J]. Journal of Process Control, 2019, 75: 40-47.
[87]	DUTTA Debaprasad, UPRETI Simant R. A reinforcement learning-based transformed inverse model strategy for nonlinear process control[J]. Computers & Chemical Engineering, 2023, 178: 108386.
[88]	LIU Jingjun, DAOUTIDIS Prodromos, YANG Bolun. Process design and optimization for etherification of glycerol with isobutene[J]. Chemical Engineering Science, 2016, 144: 326-335.
[89]	ZHANG Ruihang, WANG Zexin, WEI Xiaoming, et al. Modelling and optimization of ethane recovery process from natural gas via ZIF-8/water-glycol slurry with low energy consumption[J]. Energy, 2023, 263: 125645.
[90]	THAKUR Amit K, GUPTA Santosh K, KUMAR Rahul, et al. Multi-objective optimization of an industrial slurry phase ethylene polymerization reactor[J]. International Journal of Chemical Reactor Engineering, 2022, 20(6): 649-659.
[91]	YOU Xinqiang, GU Jinglian, GERBAUD Vincent, et al. Optimization of pre-concentration, entrainer recycle and pressure selection for the extractive distillation of acetonitrile-water with ethylene glycol[J]. Chemical Engineering Science, 2018, 177: 354-368.
[92]	CUI Yue, ZHANG Zhishan, SHI Xiaojing, et al. Triple-column side-stream extractive distillation optimization via simulated annealing for the benzene/isopropanol/water separation[J]. Separation and Purification Technology, 2020, 236: 116303.
[93]	TARAFDER Abhijit, LEE Bennett C S, Ajay K RAY, et al. Multiobjective optimization of an industrial ethylene reactor using a nondominated sorting genetic algorithm[J]. Industrial & Engineering Chemistry Research, 2005, 44(1): 124-141.
[94]	郭艳东, 苏航, 陈嵩嵩, 等. 煤基甲醇芳构化分离过程多目标优化[J]. 过程工程学报, 2021, 21(1): 71-82.
	GUO Yandong, SU Hang, CHEN Songsong, et al. Multi-objective optimization of separation unit for coal-based methanol aromatization[J]. Chinese Journal of Process Engineering, 2021, 21 (1): 71-82.
[95]	ZHAO Fei, XU Zaifeng, ZHAO Jiangang, et al. Process design and multi-objective optimization for separation of ternary mixtures with double azeotropes via integrated quasi-continuous pressure-swing batch distillation[J]. Separation and Purification Technology, 2021, 276: 119288.
[96]	HEIDARI Ali Asghar, PAHLAVANI Parham. An efficient modified grey wolf optimizer with Lévy flight for optimization tasks[J]. Applied Soft Computing, 2017, 60: 115-134.
[97]	RAMIREZ ATENCIA Cristian, Javier DEL SER, CAMACHO David. Weighted strategies to guide a multi-objective evolutionary algorithm for multi-UAV mission planning[J]. Swarm and Evolutionary Computation, 2019, 44: 480-495.
[98]	LIN Qiuzhen, MA Yueping, CHEN Jianyong, et al. An adaptive immune-inspired multi-objective algorithm with multiple differential evolution strategies[J]. Information Sciences, 2018, 430: 46-64.
[99]	KASHAN Ali Husseinzadeh, KESHMIRY Marziehsadat, DAHOOIE Jalil Heidary, et al. A simple yet effective grouping evolutionary strategy (GES) algorithm for scheduling parallel machines[J]. Neural Computing and Applications, 2018, 30(6): 1925-1938.
[100]	GOEL Rajeev, MAINI Raman. A hybrid of ant colony and firefly algorithms (HAFA) for solving vehicle routing problems[J]. Journal of Computational Science, 2018, 25: 28-37.
[101]	YILDIZ Ali R. A new hybrid differential evolution algorithm for the selection of optimal machining parameters in milling operations[J]. Applied Soft Computing, 2013, 13(3): 1561-1566.
[102]	YANG Ao, KONG ZONG yang, SUNARSO Jaka. Design and optimisation of novel hybrid side-stream reactive-extractive distillation for recovery of isopropyl alcohol and ethyl acetate from wastewater[J]. Chemical Engineering Journal, 2023, 451: 138563.
[103]	MIAO Guang, ZHUO Kaisheng, LI Guoqing, et al. An advanced optimization strategy for enhancing the performance of a hybrid pressure-swing distillation process in effective binary-azeotrope separation[J]. Separation and Purification Technology, 2022, 282: 120130.
[104]	ZHOU Zixiang, GUO Yandong, CHEN Songsong, et al. A new multi-objective optimization algorithm for separation processes[J]. Chemical Engineering Research and Design, 2025, 213: 159-171.
[105]	SAFFARI Peyman Roudgar, SALARIAN Hesamoddin, LOHRASBI Ali, et al. Optimization of a thermal cracking reactor using genetic algorithm and water cycle algorithm[J]. ACS Omega, 2022, 7(15): 12493-12508.
[106]	ZHOU Xin, LI Zhiyang, FENG Xiang, et al. A hybrid deep learning framework driven by data and reaction mechanism for predicting sustainable glycolic acid production performance[J]. AIChE Journal, 2023, 69(7): e18083.
[107]	XU Wei, WANG Yuan, ZHANG Dongrui, et al. Transparent AI-assisted chemical engineering process: Machine learning modeling and multi-objective optimization for integrating process data and molecular-level reaction mechanisms[J]. Journal of Cleaner Production, 2024, 448: 141412.
[108]	SONG Shuang, XU Xinyao, LAN Haoxiang, et al. Design of co-cured multi-component thermosets with enhanced heat resistance, toughness, and processability via a machine learning approach[J]. Macromolecular Rapid Communications, 2024, 45(19): 2400337.
[109]	何林, 贺常晴, 隋红. 人工智能驱动新型界面分离材料的创制[J]. 化工进展, 2024, 43(4): 1649-1654.
	HE Lin, HE Changqing, SUI Hong. Prospects for the creation of novel interfacial separation materials driven by artificial intelligence[J]. Chemical Industry and Engineering Progress, 2024, 43(4): 1649-1654.
[110]	WANG Shifa, MO Peilin, LI Dengfeng, et al. Intelligent algorithms enable photocatalyst design and performance prediction[J]. Catalysts, 2024, 14(4): 217.
[111]	GENG Zhiqiang, WANG Zun, ZHU Qunxiong, et al. Multi-objective operation optimization of ethylene cracking furnace based on AMOPSO algorithm[J]. Chemical Engineering Science, 2016, 153: 21-33.
[112]	RAHIMI Mohammad, MOOSAVI Seyed Mohamad, SMIT Berend, et al. Toward smart carbon capture with machine learning[J]. Cell Reports Physical Science, 2021, 2(4): 100396.
[113]	DE Riju, BHARTIYA Sharad, SHASTRI Yogendra. Multi-objective optimization of integrated biodiesel production and separation system[J]. Fuel, 2019, 243: 519-532.

描述符	特征参量	优势	劣势
拓扑结构描述符	分子的拓扑连接结构	计算相对简单快速，能反映分子的整体形状和连接性	计算量大，无法准确捕捉分子的三维结构信息和电子性质，相似拓扑结构区分能力有限
几何构型描述符	分子的体积、表面积、形状因子	描述分子的大小和形状，与分子的物理性质如溶解性、渗透性等有一定关联	计算相对复杂，尤其是对于大分子或柔性分子
量子化学描述符	分子轨道能、电子亲和能、电离能等	与分子的化学活性、反应性密切相关	通常比较耗时，对于大规模分子体系的计算成本较高
物化性质描述符	熔点、沸点、溶解度、分配系数等	通常可以通过实验测量得到，具有较高的可靠性	实验测量可能需要耗费大量时间和资源

描述符	特征参量	优势	劣势
拓扑结构描述符	分子的拓扑连接结构	计算相对简单快速，能反映分子的整体形状和连接性	计算量大，无法准确捕捉分子的三维结构信息和电子性质，相似拓扑结构区分能力有限
几何构型描述符	分子的体积、表面积、形状因子	描述分子的大小和形状，与分子的物理性质如溶解性、渗透性等有一定关联	计算相对复杂，尤其是对于大分子或柔性分子
量子化学描述符	分子轨道能、电子亲和能、电离能等	与分子的化学活性、反应性密切相关	通常比较耗时，对于大规模分子体系的计算成本较高
物化性质描述符	熔点、沸点、溶解度、分配系数等	通常可以通过实验测量得到，具有较高的可靠性	实验测量可能需要耗费大量时间和资源

应用领域	AI模型架构	研究内容	相关文献
分子识别	ANN/BPNN/GCN/G-CNNs/UG-RNN/SVR/RT/MLP/VMC	分子数据集构建、分子功能识别、同质/异质分子分类、结构与物化性质关联	[9,16-17,20-22]
分子设计	ANN/GNN/GCN/RF/SVM	分子间相互作用、催化剂结构设计与优化	[23-26, 108-110]
物性预测	ANN/GNN/pS-CNN/DL/MLP/RF/SVM/GAGBM/SE/RF/XRT	密度、黏度、熔点、电导率、临界性质等热物性预测	[30-33, 35,37,41-42,44]
反应过程	ANN/FNN/BPNN/SVR/GPR/GA/MLP	反应网络、反应速率、条件优化	[49-56,28-62]
分离过程	ANN/D-MPNN/AL/MLP/GPR/SPT	相平衡、热力学函数、活度系数、交互参数	[56,63-68]
流程设计	ANN/DE/GA/MOEA/NSGA-Ⅱ/LLM	分离序列、制备过程、PFD图绘制	[69-75,77-78]
过程控制	NN/BPNN/RBFNN/WNN/GA/NSGA-Ⅱ/RL/DRL/PSO/FGS	PID控制、精馏控制、反应控制、锅炉燃烧、PID图	[80-87]
过程优化	ANN/DNN/DBN/GA/NSGA-Ⅱ/GAGA/GP/MOWCA/MOGA/PSO/DL/NLP/FC-ResNet	反应分离过程、精馏过程、氧气脱硫、碳捕集	[70, 89-95,102-107, 111-113]

应用领域	AI模型架构	研究内容	相关文献
分子识别	ANN/BPNN/GCN/G-CNNs/UG-RNN/SVR/RT/MLP/VMC	分子数据集构建、分子功能识别、同质/异质分子分类、结构与物化性质关联	[9,16-17,20-22]
分子设计	ANN/GNN/GCN/RF/SVM	分子间相互作用、催化剂结构设计与优化	[23-26, 108-110]
物性预测	ANN/GNN/pS-CNN/DL/MLP/RF/SVM/GAGBM/SE/RF/XRT	密度、黏度、熔点、电导率、临界性质等热物性预测	[30-33, 35,37,41-42,44]
反应过程	ANN/FNN/BPNN/SVR/GPR/GA/MLP	反应网络、反应速率、条件优化	[49-56,28-62]
分离过程	ANN/D-MPNN/AL/MLP/GPR/SPT	相平衡、热力学函数、活度系数、交互参数	[56,63-68]
流程设计	ANN/DE/GA/MOEA/NSGA-Ⅱ/LLM	分离序列、制备过程、PFD图绘制	[69-75,77-78]
过程控制	NN/BPNN/RBFNN/WNN/GA/NSGA-Ⅱ/RL/DRL/PSO/FGS	PID控制、精馏控制、反应控制、锅炉燃烧、PID图	[80-87]
过程优化	ANN/DNN/DBN/GA/NSGA-Ⅱ/GAGA/GP/MOWCA/MOGA/PSO/DL/NLP/FC-ResNet	反应分离过程、精馏过程、氧气脱硫、碳捕集	[70, 89-95,102-107, 111-113]