化工领域中的人工智能：人工神经网络技术的应用与前景

doi:10.16085/j.issn.1000-6613.2025-0517

化工进展 ›› 2025, Vol. 44 ›› Issue (8): 4808-4820.DOI: 10.16085/j.issn.1000-6613.2025-0517

• 过程模拟与仿真前沿与趋势 • 上一篇

化工领域中的人工智能：人工神经网络技术的应用与前景

鹿兰停¹^,²(), 康胜¹(), 许文轲¹, 蒋子强¹, 王德民¹, 刘东阳¹^,², 赵亮¹^,²(), 徐春明¹^,²

^1.中国石油大学（北京）化学工程与环境学院，北京 102249
^2.中国石油大学（北京）重质油全国重点实验室，北京 102249

收稿日期:2025-04-08 修回日期:2025-06-02 出版日期:2025-08-25 发布日期:2025-09-08
通讯作者: 赵亮
作者简介:鹿兰停(2001—)，女，硕士研究生，研究方向为人工神经网络优化下“数据+机理”模型在催化裂解反应中的开发。E-mail：lulanting2023@163.com
康胜（2003—），男，本科生，研究方向为人工神经网络技术在化工中的应用。E-mail：2022010452@student.cup.edu.cn。
基金资助:
中国博士后科学基金(BX20240424);国家自然科学基金(22325808);国家自然科学基金(U22B20140);国家自然科学基金(22021004);国家自然科学基金(L2324201);NSFC-CAS联合项目(XK2023HXC001)

Artificial intelligence in the chemical industry: Applications and prospects of artificial neural network technology

LU Lanting¹^,²(), KANG Sheng¹(), XU Wenke¹, JIANG Ziqiang¹, WANG Demin¹, LIU Dongyang¹^,², ZHAO Liang¹^,²(), XU Chunming¹^,²

^1.College of Chemical Engineering and Environment, China University of Petroleum (Beijing), Beijing 102249, China
^2.State Key Laboratory of Heavy Oil Processing, China University of Petroleum (Beijing), Beijing 102249, China

Received:2025-04-08 Revised:2025-06-02 Online:2025-08-25 Published:2025-09-08
Contact: ZHAO Liang

摘要/Abstract

摘要：

伴随着人工智能技术的快速发展以及应用成本的降低，人工智能已经渗透于众多传统行业，推动产业格局变革。化工行业作为全球经济的重要组成部分之一，长期受到高能耗和环境污染等挑战，并面临工艺优化和系统调度复杂、催化剂研发效率低、故障诊断困难以及产物预测不准等一系列“卡脖子”难题，而人工神经网络（artificial neural network，ANN）技术凭借强大的非线性映射、自组织自适应学习及大数据驱动特性，已经逐步融入到化工基础研究和生产过程，为解决这些难题带来了新契机。本文综述了ANN催化剂设计与选用、反应条件优化、化工产品分析预测、过程系统优化以及环境监测与治理等化工领域的应用现状，探讨了ANN驱动化工核心难题解决的突破路径及具体案例，并分析了现有ANN在化工中应用的不足与挑战，最后提出了ANN未来在化工领域中应用的发展方向。

关键词: 人工神经网络, 化工智能化, 过程优化, 数据驱动

Abstract:

With rapid development of artificial intelligence (AI) technology and the reduction in application costs, AI has penetrated many traditional industries, driving changes in the industrial landscape. The chemical industry, an important part of the global economy, has long faced challenges such as high energy consumption and environmental pollution. It is confronted with a series of "neck-breaking" problems, including complex process optimization and system scheduling, low catalyst R&D efficiency, difficulty in fault diagnosis and inaccurate product prediction. Artificial neural network (ANN), with its powerful nonlinear mapping, self-organization and adaptive learning and big data-driven characteristics, has been gradually integrated into basic chemical research and production processes, providing new opportunities to solve these problems. This paper reviewed the current status of ANN applications in the chemical industry, including catalyst design and selection, reaction condition optimization, chemical product analysis and prediction, process system optimization, and environmental monitoring and management. It discussed breakthrough paths and specific cases of ANN-driven chemical industries, analyzed the shortcomings and challenges of existing ANN applications in the chemical industry, and finally proposed directions for future applications in the chemical industry.

Key words: artificial neural networks, chemical intelligence, process optimisation, data-driven

中图分类号:

TQ-9

鹿兰停, 康胜, 许文轲, 蒋子强, 王德民, 刘东阳, 赵亮, 徐春明. 化工领域中的人工智能：人工神经网络技术的应用与前景[J]. 化工进展, 2025, 44(8): 4808-4820.

LU Lanting, KANG Sheng, XU Wenke, JIANG Ziqiang, WANG Demin, LIU Dongyang, ZHAO Liang, XU Chunming. Artificial intelligence in the chemical industry: Applications and prospects of artificial neural network technology[J]. Chemical Industry and Engineering Progress, 2025, 44(8): 4808-4820.

图/表 8

参考文献 77

[1]	宋泓阳, 孙晓岩, 项曙光. 人工神经网络在化工过程中的应用进展[J]. 化工进展, 2016, 35(12): 3755-3762.
	SONG Hongyang, SUN Xiaoyan, XIANG Shuguang. Progress on the application of artificial neural network in chemical industry[J]. Chemical Industry and Engineering Progress, 2016, 35(12): 3755-3762.
[2]	ILIYASU Abdullah M, DAOUD Mohammad Sh, SALAMA Ahmed Sayed, et al. Towards an intelligent integrated methodology for accurate determination of volume percentages in three-phase flow systems[J]. Scientific Reports, 2025, 15: 8407.
[3]	刘方, 徐龙, 马晓迅. BP神经网络的发展及其在化学化工中的应用[J]. 化工进展, 2019, 38(6): 2559-2573.
	LIU Fang, XU Long, MA Xiaoxun. Development of BP neural network and its application in chemistry and chemical engineering[J]. Chemical Industry and Engineering Progress, 2019, 38(6): 2559-2573.
[4]	韩玉. 人工智能在化工行业的应用[J]. 橡塑资源利用, 2019(2): 25-28.
	HAN Yu. Application of artificial intelligence in chemical industry[J]. Rubber & Plastics Resources Utilization, 2019(2): 25-28.
[5]	张卫华, 吴重光, 王春利, 等. 基于神经网络的化工过程故障诊断[J]. 计算机与应用化学, 2010, 27(7): 987-991.
	ZHANG Weihua, WU Chongguang, WANG Chunli, et al. The artificial neural network based fault diagnosis of chemical process[J]. Computers and Applied Chemistry, 2010, 27(7): 987-991.
[6]	赵晓弘, 胡西娅, 纪博睿, 等. 人工神经网络在石油化工中的应用研究进展[J]. 当代化工, 2024, 53(5): 1228-1232.
	ZHAO Xiaohong, HU Xiya, JI Borui, et al. Research progress in application of artificial neural network in petrochemical industry[J]. Contemporary Chemical Industry, 2024, 53(5): 1228-1232.
[7]	ROSENBLATT F. The perceptron: A probabilistic model for information storage and organization in the brain[J]. Psychological Review, 1958, 65(6): 386-408.
[8]	ARBIB M. Review of ‘perceptrons: An introduction to computational geometry’ (MINSKY M and PAPERT S， 1969)[J]. IEEE Transactions on Information Theory, 1969, 15(6): 738-739.
[9]	HOPFIELD J J. Neurons with graded response have collective computational properties like those of two-state neurons[J]. Proceedings of the National Academy of Sciences of the United States of America, 1984, 81(10): 3088-3092.
[10]	RUMELHART David E, HINTON Geoffrey E, WILLIAMS Ronald J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.
[11]	罗祉婧, 韦振宇, 郑荻凡, 等. 卷积神经网络在化工领域的应用综述[J]. 云南化工, 2023, 50(2): 21-23.
	LUO Zhijing, WEI Zhenyu, ZHENG Difan, et al. Review of the application of CNN in the field of chemical engineering[J]. Yunnan Chemical Technology, 2023, 50(2): 21-23.
[12]	张硕羲, 姚涵文, 曹存盼, 等. 基于深度学习算法的化工园区火灾检测方法[J]. 信息技术与信息化, 2025(2): 117-120.
	ZHANG Shuoxi, YAO Hanwen, CAO Cunpan, et al. Fire detection method in chemical industry park based on deep learning algorithm[J]. Information Technology and Informatization, 2025(2): 117-120.
[13]	于志省, 李应成, 王宇遥, 等. 人工神经网络在材料开发中的应用研究进展[J]. 工程塑料应用, 2023, 51(2): 158-164.
	YU Zhixing, LI Yingcheng, WANG Yuyao, et al. Research progress on application of artificial neural network in material development[J]. Engineering Plastics Application, 2023, 51(2): 158-164.
[14]	吴步军. 催化剂计算机辅助设计与优化[J]. 化学工程与装备, 2015(3): 4-7.
	WU Bujun. Catalyst for computer aided design and optimization[J]. Chemical Engineering & Equipment, 2015(3): 4-7.
[15]	韩晓霞, 赵超凡. 神经网络及遗传算法在催化剂设计中的应用[J]. 现代化工, 2018, 38(8): 213-216.
	HAN Xiaoxia, ZHAO Chaofan. Application of artificial neural network and genetic algorithm in catalyst design[J]. Modern Chemical Industry, 2018, 38(8): 213-216.
[16]	DE SOUZA Paulo A L, AFZAL Raja Muhammad, CAMACHO Felipe Gomes, et al. Catalyst development for the tri-reforming of methane (TRM) process by integrated singular machine learning models[J]. The Canadian Journal of Chemical Engineering, 2025, 103(2): 758-770.
[17]	RAJAPAKSE Dinuka, MECKSTROTH Josh, JANTZ Dylan T, et al. Deconvoluting kinetic rate constants of catalytic substrates from scanning electrochemical approach curves with artificial neural networks[J]. ACS Measurement Science Au, 2022, 3(2): 103-112.
[18]	ALTIKAT Aysun, CEYLAN Zeynep, GULBE Alper. Forecasting of chlorophenols removing with advanced oxidation processes: An artificial neural networks application[J]. Environmental Engineering and Management Journal, 2020, 19(8): 1275-1287.
[19]	马善为, 曲艳超, 刘吉, 等. 基于样本优化的BP神经网络SCR脱硝催化剂体积设计[J]. 节能, 2021, 40(2): 24-28.
	MA Shanwei, QU Yanchao, LIU Ji, et al. Design of SCR catalyst volume based on BP neural network with optimized net training[J]. Energy Conservation, 2021, 40(2): 24-28.
[20]	HAN Peilun, SHEN Xiaoqian, SHEN Boxiong. A simulation study on NO _x reduction efficiency in SCR catalysts utilizing a modern C3-CNN algorithm[J]. Fuel, 2024, 363: 130985.
[21]	TARJOMANNEJAD Ali, NAKHOSTIN PANAHI Parvaneh, FARZI Ali, et al. Design of an intelligent system for modeling and optimization of perovskite-type catalysts for catalytic reduction of NO with CO[J]. Chemical Engineering Research and Design, 2025, 214: 54-64.
[22]	ISHIKAWA Atsushi. Heterogeneous catalyst design by generative adversarial network and first-principles based microkinetics[J]. Scientific Reports, 2022, 12(1): 11657.
[23]	HISAMA Kaoru, ISHIKAWA Atsushi, ASPERA Susan Menez, et al. Theoretical catalyst screening of multielement alloy catalysts for ammonia synthesis using machine learning potential and generative artificial intelligence[J]. The Journal of Physical Chemistry C, 2024, 128(44): 18750-18758.
[24]	ASIF Muhammad, YAO Chengxi, ZUO Zitu, et al. Machine learning-driven catalyst design, synthesis and performance prediction for CO₂ hydrogenation[J]. Journal of Industrial and Engineering Chemistry, 2025, 144: 32-47.
[25]	QIU Qianhong, DU Changming. An application of graph neural network in pollution abatement: Acceleration heterogeneous catalyst design[J]. Materials Today Communications, 2024, 40: 109916.
[26]	BLAKEMORE David C, CASTRO Luis, CHURCHER Ian, et al. Organic synthesis provides opportunities to transform drug discovery[J]. Nature Chemistry, 2018, 10(4): 383-394.
[27]	杨婷, 董亚超, 都健. 基于卷积神经网络的偶联反应催化剂及速率常数预测方法[J]. 过程工程学报, 2024, 24(7): 833-842.
	YANG Ting, DONG Yachao, DU Jian. Catalyst and reaction rate constant prediction methods of coupling reaction based on convolutional neural network[J]. The Chinese Journal of Process Engineering, 2024, 24(7): 833-842.
[28]	吕翠英, 华贲. 乙烯生产装置优化人工神经网络模型的建立[J]. 石油炼制与化工, 1997, 28(1): 48-51.
	LU Cuiying, HUA Ben. Establishment of a neural network model for ethylene plant optimization[J]. Petroleum Processing and Petrochemicals, 1997, 28(1): 48-51.
[29]	莫裕俊. 基于BP神经网络的乙醇制备烯烃反应条件最优化设计[J]. 江西化工, 2023, 39(2): 88-91.
	MO Yujun. Optimization design of olefin reaction conditions for ethanol preparation based on BP neural network[J]. Jiangxi Chemical Industry, 2023, 39(2): 88-91.
[30]	薄翠梅, 张湜, 林锦国, 等. 径向基函数神经网络在精馏塔软测量中的应用[J]. 南京工业大学学报(自然科学版), 2002, 24(3): 82-86.
	BO Cuimei, ZHANG Shi, LIN Jinguo, et al. RBF neural networks applied in soft-measuring of distillation columns[J]. Journal of Nanjing University (Natural Science Edition), 2002, 24(3): 82-86.
[31]	顾恒昌, 牟鹏, 李建伟. 基于交叉迭代BLSTM网络的乙烯裂解炉建模[J]. 化工学报, 2019, 70(2): 548-555.
	GU Hengchang, MU Peng, LI Jianwei. Modeling and application of ethylene cracking furnace based on cross-iterative BLSTM network[J]. CIESC Journal, 2019, 70(2): 548-555.
[32]	洪娟, 田文德. 基于群智能算法优化LSTM的催化裂化预测研究[J]. 山东化工, 2023, 52(18): 92-96.
	HONG Juan, TIAN Wende. Prediction of catalytic cracking based on swarm intelligence algorithm optimization of LSTM[J]. Shandong Chemical Industry, 2023, 52(18): 92-96.
[33]	WANG Zhiwen, YANG Bolun, CHEN Chun, et al. Modeling and optimization for the secondary reaction of FCC gasoline based on the fuzzy neural network and genetic algorithm[J]. Chemical Engineering and Processing: Process Intensification, 2007, 46(3): 175-180.
[34]	SELVAMURUGAN Aishwarya, GANESAN Parthiban Kunnathur, NAYAK Shashank S, et al. CNN-LSTM-based nonlinear model predictive controller for temperature trajectory tracking in a batch reactor[J]. ACS Omega, 2024, 9(47): 47203-47212.
[35]	HONG Juan, TIAN Wende. Prediction in catalytic cracking process based on swarm intelligence algorithm optimization of LSTM[J]. Processes, 2023, 11(5): 1454.
[36]	TANG Xiaowei, XU Bing, XU Zichen. Reactor temperature prediction method based on CPSO-RBF-BP neural network[J]. Applied Sciences, 2023, 13(5): 3230.
[37]	霍学松, 陈瀑, 戴嘉伟, 等. 微小型近红外光谱仪的应用进展与展望[J]. 分析测试学报, 2022, 41(9): 1301-1313.
	HUO Xuesong, CHEN Pu, DAI Jiawei, et al. Progress and prospect of application of miniatured near infrared spectrometers[J]. Journal of Instrumental Analysis, 2022, 41(9): 1301-1313.
[38]	陈笑, 宦克为, 赵环, 等. 基于变量频次加权自助采样法的近红外光谱变量选择方法研究[J]. 分析化学, 2021, 49(10): 1743-1749.
	CHEN Xiao, HUAN Kewei, ZHAO Huan, et al. Variable selection of near infrared spectroscopy based on variable frequency weighted bootstrap sampling[J]. Chinese Journal of Analytical Chemistry, 2021, 49(10): 1743-1749.
[39]	CHEN Hui, LIN Zan, TAN Chao. Application of near-infrared spectroscopy and class-modeling to antibiotic authentication[J]. Analytical Biochemistry, 2020, 590: 113514.
[40]	宦克为, 刘小溪, 郑峰, 等. 基于蒙特卡罗特征投影法的小麦蛋白质近红外光谱测量变量选择[J]. 农业工程学报, 2013, 29(4): 266-271.
	HUAN Kewei, LIU Xiaoxi, ZHENG Feng, et al. Variable selection of near-infrared spectroscopy for measuring wheat protein based on MC-LPG[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(4): 266-271.
[41]	LIU Taiang, ZHANG Qing, CHANG Dongping, et al. Characterization of tobacco leaves by near-infrared reflectance spectroscopy and electronic nose with support vector machine[J]. Analytical Letters, 2018, 51(12): 1935-1943.
[42]	郑运, 杨思雨, 王涛, 等. 基于数据增强策略和卷积神经网络的近红外光谱分析研究[J]. 分析化学, 2024, 52(9): 1266-1276.
	ZHENG Yun, YANG Siyu, WANG Tao, et al. Near infrared spectral analysis based on data augmentation strategy and convolutional neural network[J]. Chinese Journal of Analytical Chemistry, 2024, 52(9): 1266-1276.
[43]	于水, 宦克为, 刘小溪, 等. 并联卷积神经网络的近红外光谱定量分析模型[J]. 光谱学与光谱分析, 2024, 44(6): 1627-1635.
	YU Shui, HUAN Kewei, LIU Xiaoxi, et al. Quantitative analysis modeling of near infrared spectroscopy with parallel convolution neural network[J]. Spectroscopy and Spectral Analysis, 2024, 44(6): 1627-1635.
[44]	王妞, 宦克为, 傅钲淇, 等. 高效通道注意力结合卷积神经网络的近红外光谱分析模型研究[J]. 长春理工大学学报(自然科学版), 2024, 47(1): 16-22.
	WANG Niu, HUAN Kewei, FU Zhengqi, et al. Research on the near-infrared spectral analysis model based on efficient channel attention and convolutional neural networks[J]. Journal of Changchun University of Science and Technology (Natural Science Edition), 2024, 47(1): 16-22.
[45]	CHE Jikai, LIANG Qing, XIA Yifan, et al. The study on nondestructive detection methods for internal quality of Korla fragrant pears based on near-infrared spectroscopy and machine learning[J]. Foods, 2024, 13(21): 3522.
[46]	ZHU Yaolin, ZHANG Yong, CHEN Xin, et al. Non-destructive identification of virgin Cashmere and chemically modified wool fibers based on fractional order derivative and improved wavelength extraction algorithm using NIR spectroscopy and chemometrics[J]. Journal of Natural Fibers, 2024, 21(1): 2409901.
[47]	LU Xinyu, WU Haoping, MA Hao, et al. Deep learning-assisted spectrum-structure correlation: State-of-the-art and perspectives[J]. Analytical Chemistry, 2024, 96(20): 7959-7975.
[48]	李爱民, 王志, 魏砾宏, 等. 固体废弃物热解产物的神经网络预测模型[J]. 沈阳航空工业学院学报, 2002, 19(1): 5-9.
	LI Aimin, WANG Zhi, WEI Lihong, et al. The prediction mode of neural net on pyrolysis product of solid waste[J]. Journal of Shenyang Institute of Aeronautcal Engineering, 2002, 19(1): 5-9.
[49]	HE Chasheng, ZHANG Chengwei, BIAN Tengfei, et al. A review on artificial intelligence enabled design, synthesis, and process optimization of chemical products for industry 4.0[J]. Processes, 2023, 11(2): 330.
[50]	WEI Jennifer N, DUVENAUD David, Al􀅡n ASPURU-GUZIK. Neural networks for the prediction of organic chemistry reactions[J]. ACS Central Science, 2016, 2(10): 725-732.
[51]	王国清, 杜志国, 张利军, 等. 应用BP神经网络预测石脑油热裂解产物收率[J]. 石油化工, 2007, 36(7): 699-704.
	WANG Guoqing, DU Zhiguo, ZHANG Lijun, et al. Applying BP neural networks to predict product-yields of naphtha steam cracking[J]. Petrochemical Technology, 2007, 36(7): 699-704.
[52]	邓志平, 任少君, 翁琪航, 等. 基于物理信息神经网络的生物质气化产物分布预测方法[J]. 动力工程学报, 2024, 44(5): 719-726.
	DENG Zhiping, REN Shaojun, WENG Qihang, et al. Prediction method for biomass gasification product distribution based on physics-informed neural network[J]. Journal of Chinese Society of Power Engineering, 2024, 44(5): 719-726.
[53]	CONDE-GUTIÉRREZ R A, MÁRQUEZ-NOLASCO A, CRUZ-JACOBO U, et al. Simultaneous increase of parameters of an experimental absorption system: Neural network inverse optimization methodology with multi-inputs[J]. Applied Soft Computing, 2024, 159: 111606.
[54]	ALSAYAH Ahmed Mohsin, ALSHUKRI Mohammed J, Samer ALI, et al. Prediction of overall heat transfer coefficient in concentric tube heat exchangers using artificial neural networks: A comparative study with empirical correlations[J]. International Communications in Heat and Mass Transfer, 2025, 163: 108723.
[55]	JIN Qi, CHEN Xuemei, YANG Chaolei, et al. ANN-based optimization of disk-shaped microchannel heat exchanger for thermal and hydraulic performance improvement[J]. International Journal of Thermal Sciences, 2025, 213: 109805.
[56]	HAMEDI Homa, KARIMI Iftekhar A, GUNDERSEN Truls. Simulation-based approach for integrating work within heat exchange networks for sub-ambient processes[J]. Energy Conversion and Management, 2020, 203: 112276.
[57]	MIRANDA C B, COSTA C B B, CABALLERO J A, et al. Optimal synthesis of multiperiod heat exchanger networks: A sequential approach[J]. Applied Thermal Engineering, 2017, 115: 1187-1202.
[58]	鄢烈祥, 麻德贤. 全局优化搜索新算法——列队竞争算法(Ⅰ) 解非线性和混合整数非线性规划问题[J]. 化工学报, 1999, 50(5): 663-670.
	YAN Liexiang, MA Dexian. A new algorithm for global optimization search-line-up competition algorithm (Ⅰ) Solving nonlinear programming and mixed-integer nonlinear programming problems[J]. Journal of Chemical Industry and Engineering (China), 1999, 50(5): 663-670.
[59]	朱添宇, 孙琳, 任超, 等. 基于全周期持续节能的换热网络滑动窗口分析与裕量缓释优化控制[J]. 化工进展, 2023, 42(3): 1195-1205.
	ZHU Tianyu, SUN Lin, REN Chao, et al. Sliding window analysis and slow-release margin optimal control for heat exchanger networks based on full cycle sustainable energy saving[J]. Chemical Industry and Engineering Progress, 2023, 42(3): 1195-1205.
[60]	毕立群, 麻德贤. Hopfield神经网络与专家系统相结合的换热网络设计方法有效性分析[J]. 高校化学工程学报, 1998, 12(4): 361-367.
	BI Liqun, MA Dexian. Efficiency analysis of HNN/ES based system for heat exchanger network design[J]. Journal of Chemical Engineering of Chinese Universities, 1998, 12(4): 361-367.
[61]	FAWAZ Ahmad, HUA Yuchao, LE CORRE Steven, et al. Topology optimization of heat exchangers: A review[J]. Energy, 2022, 252: 124053.
[62]	DONG Yinghao, ZHANG Wenjie, TAO Yingjie. CTAB modified TiO₂ supported on HZSM-5 zeolite for enhanced photocatalytic degradation of azophloxine[J]. Journal of Materials Research and Technology, 2020, 9(4): 9403-9411.
[63]	阎文雯, 仇翔. 聚丙烯连续生产过程的短期调度和经济优化[J]. 石油化工自动化, 2008, 44(4): 30-33.
	YAN Wenwen, QIU Xiang. Short-term scheduling and economic optimization of continuous polypropylene production process[J]. Automation in Petro-Chemical Industry, 2008, 44(4): 30-33.
[64]	WANG Zhenjiang, CAO Zhengcai, HUANG Ran, et al. A study on attribute selection for job shop scheduling problem[C]//2017 13th IEEE Conference on Automation Science and Engineering (CASE). Xi’an, China： IEEE, 2017: 1032-1037.
[65]	HUBERT Stefan, MEINTSCHEL Jonas, BLEIDORN Dominik, et al. Production scheduling using deep reinforcement learning and discrete event simulation[J]. Chemie Ingenieur Technik, 2023, 95(7): 1003-1011.
[66]	张蕾, 吴重光. 基于神经网络的PID控制器在PCS7上的设计与应用[J]. 科技资讯, 2011, 9(20): 60-61.
	ZHANG Lei, WU Chongguang. Design and application of PID controller based on neural network in PCS7[J]. Science & Technology Information, 2011, 9(20): 60-61.
[67]	Daniel RANGEL-MARTINEZ, RICARDEZ-SANDOVAL Luis A. A recurrent reinforcement learning strategy for optimal scheduling of partially observable job-shop and flow-shop batch chemical plants under uncertainty[J]. Computers & Chemical Engineering, 2024, 188: 108748.
[68]	杨维, 李歧强. 粒子群优化算法综述[J]. 中国工程科学, 2004, 6(5): 87-94.
	YANG Wei, LI Qiqiang. Survey on particle swarm optimization algorithm[J]. Engineering Science, 2004, 6(5): 87-94.
[69]	IKONEN Teemu J, HELJANKO Keijo, HARJUNKOSKI Iiro. Reinforcement learning of adaptive online rescheduling timing and computing time allocation[J]. Computers & Chemical Engineering, 2020, 141: 106994.
[70]	LEE Chia-Yen, HUANG Yitao, CHEN Peng-Jen. Robust-optimization-guiding deep reinforcement learning for chemical material production scheduling[J]. Computers & Chemical Engineering, 2024, 187: 108745.
[71]	虞玮玮. 化工项目环境监理中污染防治与环境风险防范[J]. 化工管理, 2021(26): 27-28.
	YU Weiwei. Pollution prevention and environmental risks controlling in environmental supervision of chemical projects[J]. Chemical Enterprise Management, 2021(26): 27-28.
[72]	王旭坪, 于秀丽, 王天腾. 基于集成学习策略的化工园区大气污染影响预测[J]. 运筹与管理, 2021, 30(11): 127-134.
	WANG Xuping, YU Xiuli, WANG Tianteng. Air pollution impact prediction of chemical industry park based on ensemble learning strategy[J]. Operations Research and Management Science, 2021, 30(11): 127-134.
[73]	XIN Ruo bo, JIANG Zhi Fang, LI Ning, et al. An air quality predictive model of Licang of Qingdao City based on BP neural network[J]. Advanced Materials Research, 2013, 756/757/758/759: 3366-3371.
[74]	诸飞, 俞阿龙. 基于改进GA-BP神经网络的工厂污水监测系统研究[J]. 现代电子技术, 2018, 41(11): 133-138.
	ZHU Fei, YU Along. Research on factory sewage monitoring system based on improved GA-BP neural network[J]. Modern Electronics Technique, 2018, 41(11): 133-138.
[75]	ELZWAYIE Adnan, Ahmed EL-SHAFIE, YASEEN Zaher Mundher, et al. RBFNN-based model for heavy metal prediction for different climatic and pollution conditions[J]. Neural Computing and Applications, 2017, 28(8): 1991-2003.
[76]	DU Jiao, SHANG Xiaoxian, LI Tao, et al. Recycling and modeling of chromium from sludge produced from magnetic flocculation treatment of chromium-containing wastewater[J]. Process Safety and Environmental Protection, 2022, 157: 20-26.
[77]	陈洪刚, 董波, 唐相臣. 基于优化FCM算法的土壤污染监测点科学布设方法[J]. 粘接, 2024, 51(12): 189-192.
	CHEN Honggang, DONG Bo, TANG Xiangchen. A scientific method for laying out soil pollution monitoring points based on optimized FCM algorithm[J]. Adhesion, 2024, 51(12): 189-192.

人工神经网络类型	主要特点	优势	局限性
前馈神经网络
MLP	含输入层、隐藏层、输出层，通过非线性激活函数实现复杂映射	通用性强，可解决分类、回归问题，适用于化工过程建模等场景	需大量数据支撑，易过拟合，对高维数据处理效率低
CNN	引入卷积层和池化层，提取数据局部空间特征	擅长处理图像、传感器阵列等具有空间相关性的数据，参数共享降低计算复杂度	对非空间结构数据（如文本）适用性差，需依赖大量标注图像数据
RBF	以径向基函数为激活函数，具备局部逼近能力	学习速度快，适合小样本数据建模，在快速响应场景中表现优异	全局逼近能力弱，隐藏层节点数需经验确定，泛化能力受限
反馈神经网络
RNN	隐藏层神经元环状连接，存储历史信息	对短序列数据（如简单时间序列）建模有效，结构简单易实现	长序列训练时梯度消失问题显著，难以捕捉长期依赖关系
LSTM	引入门控机制（输入门、遗忘门、输出门），选择性记忆信息	有效解决长序列梯度消失问题，擅长捕捉长期依赖，适用于语音识别、故障预测等场景	结构复杂、参数众多，训练耗时较长，对计算资源要求高
GRU	LSTM 简化版，合并遗忘门与输入门，参数更少	计算效率高，实时性强，适用于化工过程动态监控等对响应速度要求高的场景	长期依赖捕捉能力略弱于LSTM，复杂时序任务中表现受限

人工神经网络类型	主要特点	优势	局限性
前馈神经网络
MLP	含输入层、隐藏层、输出层，通过非线性激活函数实现复杂映射	通用性强，可解决分类、回归问题，适用于化工过程建模等场景	需大量数据支撑，易过拟合，对高维数据处理效率低
CNN	引入卷积层和池化层，提取数据局部空间特征	擅长处理图像、传感器阵列等具有空间相关性的数据，参数共享降低计算复杂度	对非空间结构数据（如文本）适用性差，需依赖大量标注图像数据
RBF	以径向基函数为激活函数，具备局部逼近能力	学习速度快，适合小样本数据建模，在快速响应场景中表现优异	全局逼近能力弱，隐藏层节点数需经验确定，泛化能力受限
反馈神经网络
RNN	隐藏层神经元环状连接，存储历史信息	对短序列数据（如简单时间序列）建模有效，结构简单易实现	长序列训练时梯度消失问题显著，难以捕捉长期依赖关系
LSTM	引入门控机制（输入门、遗忘门、输出门），选择性记忆信息	有效解决长序列梯度消失问题，擅长捕捉长期依赖，适用于语音识别、故障预测等场景	结构复杂、参数众多，训练耗时较长，对计算资源要求高
GRU	LSTM 简化版，合并遗忘门与输入门，参数更少	计算效率高，实时性强，适用于化工过程动态监控等对响应速度要求高的场景	长期依赖捕捉能力略弱于LSTM，复杂时序任务中表现受限

神经网络模型	应用场景	性能指标	参考文献
ANN	TRM	R²=0.97（DRM），R²=0.98（SRM/POX）	[16]
MLP+CNN	SECM approach 曲线动力学分析	MAE=0.14	[17]
迁移学习+ANN	芬顿氧化工艺	R²>0.95	[18]
MIV+BP	SCR脱硝系统	R²=0.9941	[19]
C3-CNN	SCR脱硝系统	R²=0.96788	[20]
GA-ANN	La_1-_x Sr _x (Cu_1-_x Mn _x )_1-_y Pd _y O₃体系	R²=0.9967	[21]
DFT+GAN	Rh-Ru合金表面合成氨反应	TOF=1.1×10^-3	[22]
DFT+LGBM+NSGA-Ⅲ	CO₂甲烷化	R²>0.90，RMSE<0.31	[24]
GNN+DFT	DACs设计	R²=0.985(训练集)，R²=0.952(测试集)	[25]

神经网络模型	应用场景	性能指标	参考文献
ANN	TRM	R²=0.97（DRM），R²=0.98（SRM/POX）	[16]
MLP+CNN	SECM approach 曲线动力学分析	MAE=0.14	[17]
迁移学习+ANN	芬顿氧化工艺	R²>0.95	[18]
MIV+BP	SCR脱硝系统	R²=0.9941	[19]
C3-CNN	SCR脱硝系统	R²=0.96788	[20]
GA-ANN	La_1-_x Sr _x (Cu_1-_x Mn _x )_1-_y Pd _y O₃体系	R²=0.9967	[21]
DFT+GAN	Rh-Ru合金表面合成氨反应	TOF=1.1×10^-3	[22]
DFT+LGBM+NSGA-Ⅲ	CO₂甲烷化	R²>0.90，RMSE<0.31	[24]
GNN+DFT	DACs设计	R²=0.985(训练集)，R²=0.952(测试集)	[25]

神经网络	应用场景	平均绝对误差	均方根误差	参考文献
LSTM
CNN-LSTM	预测BR反应器温度	0.9798	1.0019	[34]
PSO-LSTM	预测催化裂化反应温度和分馏塔塔底液位	0.0081（液位），0.0087（温度）	0.0104（液位），0.1220（温度）	[35]
CS-LSTM	预测催化裂化反应温度和分馏塔塔底液位	0.1386（液位），0.2533（温度）	0.0110（液位），0.3115（温度）	[35]
ICBL-LSTM	预测乙烯裂解炉丙烯收率	0.0290	0.0456	[31]
BP
BP	预测反应釜温度	0.268	2.391	[36]
RBF-BP		0.433	0.507
CPSO-RBF-BP		0.114	0.263

化工领域中的人工智能：人工神经网络技术的应用与前景

Artificial intelligence in the chemical industry: Applications and prospects of artificial neural network technology

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 77

相关文章 12

编辑推荐

Metrics

本文评价

对比项目	优点	缺点	适用场景
静态调度	能预先安排好调度，减少任务调度开销，适合长期规划，易于实施	缺乏灵活性，无法根据系统资源和任务执行情况进行及时调整	适用于生产条件稳定、变化少的场景，如炼油、化肥生产等较稳定的连续生产过程
动态调度	能灵活应对化工生产中实时变化，可及时处理突发事件，提高生产效率	需实时数据支持，算法复杂，依赖于先进计算工具	适用于生产条件多变、不确定性较高的场景，如精细化工、制药等多品种的间歇生产过程

[1]	杨证禄, 杨立峰, 路晓飞, 锁显, 张安运, 崔希利, 邢华斌. 机器学习加速多孔吸附剂筛选发现的研究进展[J]. 化工进展, 2025, 44(8): 4288-4301.
[2]	戴征舒, 左元浩, 陈孝罗, 张犁, 赵根, 张学军, 张华. 机器学习在喷射器研究中的应用进展[J]. 化工进展, 2024, 43(S1): 1-12.
[3]	焦竞, 刘琳琳, 都健. 基于代理模型的碳捕集与电厂集成调度优化[J]. 化工进展, 2024, 43(11): 6059-6067.
[4]	王雄, 杨振宁, 李越, 申威峰. 基于化工机理与工业数据孪生建模的甲醇精馏过程优化[J]. 化工进展, 2024, 43(1): 310-319.
[5]	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.
[6]	李乔, 田思琪, 冯泽民, 董立春. 甲醇和三甲氧基硅烷共沸物分离过程模拟和优化[J]. 化工进展, 2021, 40(5): 2431-2439.
[7]	姚羽曼, 罗文嘉, 戴一阳. 数据驱动方法在化工过程故障诊断中的研究进展[J]. 化工进展, 2021, 40(4): 1755-1764.
[8]	刘方, 徐龙, 马晓迅. BP神经网络的发展及其在化学化工中的应用[J]. 化工进展, 2019, 38(06): 2559-2573.
[9]	贺凯迅, 曹鹏飞. 基于智能优化算法的软测量模型建模样本优选及应用[J]. 化工进展, 2018, 37(07): 2516-2523.
[10]	王海宁，夏陆岳，周猛飞，朱鹏飞，潘海天. 过程工业软测量中的多模型融合建模方法[J]. 化工进展, 2014, 33(12): 3157-3163.
[11]	杜雨静1，2，范英芳1. 人工神经网络用于三苯基丙烯腈衍生物的定量结构-活性关系模型 [J]. 化工进展, 2010, 29(1): 25-.
[12]	刘建新. 基于神经网络模型的对二甲苯氧化过程优化 [J]. 化工进展, 2006, 25(6): 708-.