| 683 | 4 | 791 |
| 下载次数 | 被引频次 | 阅读次数 |
在“双碳”战略与“中国制造2025”深度融合的大背景下，铝电解作为能耗密集型基础工业过程，其智能化转型是推动铝工业高质量发展和实现绿色高效生产的重要途径。近年来，随着人工智能、大数据及数字孪生技术的发展，其在铝电解领域的应用也逐渐兴起，有机结合数字孪生和铝电解技术，是推动铝电解智能制造发展的关键技术路径。系统综述了铝电解过程核心机理，指出了传统工艺控制方法中的局限性，探讨构建铝电解数字孪生体的必要性和可行性，挖掘数字孪生体在工业过程仿真、智能决策和自主优化的潜力，总结当前研究面临的三大挑战，构建面向“双碳”目标的铝电解智能柔性制造系统、铝电解数字孪生体原型系统，指出铝电解数字孪生体前景目标，并提出未来铝电解智能制造中的研究挑战和发展方向。本文提出铝电解结合数字孪生推动铝电解智能制造，旨在为铝工业构建可持续、柔性及智能制造新范式提供理论基础，扩大我国有色金属产业在全球第一轮科技革命中的战略竞争优势。
Abstract：Against the backdrop of the deep integration of the "Dual Carbon" strategy and the "Made in China 2025" initiative, aluminum electrolysis, as an energy-intensive fundamental industrial process, is undergoing an intelligent transformation that serves as a key pathway to promote high-quality development in the aluminum industry and achieve green and efficient production. In recent years, with the development of artificial intelligence, big data and digital twin technology, their applications in the field of aluminum electrolysis have gradually emerged. The organic integration of digital twin and aluminum electrolysis technologies represents a critical technical route for advancing intelligent manufacturing in this domain. This paper systematically reviews the core mechanisms of the aluminum electrolysis process, identifies the limitations of traditional process control methods, explores the necessity and feasibility of constructing a digital twin for aluminum electrolysis, and investigates the potential of digital twins in industrial process simulation, intelligent decision-making, and self-optimization. It summarizes the three major challenges currently facing research in this area, proposes the construction of a flexible intelligent manufacturing system for aluminum electrolysis oriented toward the goals of the "Dual Carbon" strategy, and outlines the development of a prototype digital twin system. Furthermore, the paper defines the future objectives of aluminum electrolysis digital twins and presents research challenges and directions for intelligent manufacturing. By integrating digital twin technology with aluminum electrolysis, this work aims to provide a theoretical foundation for establishing a sustainable, flexible, and intelligent manufacturing paradigm for the aluminum industry, thereby enhancing China's strategic competitiveness in the first round of the global technological revolution.
[1]刘业翔,李劼.现代铝电解[M].北京:冶金工业出版社,2008.LIU Y X, LI J. Modern aluminum electrolysis[M]. Beijing:Metallurgical Industry Press, 2008.
[2]张红亮,李劼,徐宇杰,等.工业铝电解直流电耗与电流效率的经济关系研究[J].轻金属, 2014(12):1-3, 28.ZHANG H L, LI J, XU Y J, et al. The economic relationship between DC power consumption and current efficiency in aluminum reduction[J]. Light Metals, 2014(12):1-3, 28.
[3]卢浩洁,王婉君,代敏,等.中国铝生命周期能耗与碳排放的情景分析及减排对策[J].中国环境科学, 2021, 41(1):451-462.LU H H, WANG W J, DAI M, et al. Scenario analysis of energy consumption and carbon emissions in Chinese aluminum life cycle and emissions reduction measures[J].China Environmental Science, 2021, 41(1):451-462.
[4]桂卫华,曾朝晖,陈晓方,等.知识驱动的流程工业智能制造[J].中国科学:信息科学, 2020, 50(9):1345-1360.GUI W H, ZENG C H, CHEN X F, et al. Knowledge-driven smart manufacturing for process industries[J]. Scientia Sinica Informations, 2020, 50(9):1345-1360.
[5]LI J, XU Y J, ZHANG H L, et al. An inhomogeneous threephase model for the flow in aluminium reduction cells[J].International Journal of Multiphase Flow, 2011, 37(1):46-54.
[6]吕晓军,孙启东,陈昌,等.铝电解阴极燕尾槽内炭块-糊料-钢棒界面接触状态仿真优化[J].中南大学学报(自然科学版), 2020, 51(12):3331-3340.LV X J, SUN Q D, CHEN C, et al. Numerical simulation and optimization of contact state for cathode slot of aluminum electrolytic cell[J]. Journal of Central South University(Science and Technology), 2020, 51(12):3331-3340.
[7]XU Y J, ZHANG H L, LI J, et al. A nonlinear shallow-water model combined with gas bubble effect for melt flows and interface instability in aluminum reduction cells[J]. JOM,2013, 65:1459-1466.
[8]LI J, WANG J J, CHEN C, et al. Design and optimization method of controlled heat exchange structure for aluminum electrolysis cell under current fluctuations[J]. MetaResource,2024, 1(1):23-46. DOI:10.23919/metar.2024.000004.
[9]YANG S, ZOU Z, LI J, et al. Online anode current signal in aluminum reduction cells:measurements and prospects[J].JOM, 2016, 68:623-634.
[10]邹忠,彭晨,李劼,等.基于分布式感知的铝电解智能识别系统及应用[J].中南大学学报(自然科学版), 2023, 54(2):732-743.ZOU Z, PENG C, LI J, et al. Intelligent identification system and application of aluminum electrolysis based on distributed perception[J]. Journal of Central South University(Science and Technology), 2023, 54(2):732-743.
[11]LEI Y X, KARIMI H R, CHEN X F. A novel self-supervised deep LSTM network for industrial temperature prediction in aluminum processes application[J]. Neurocomputing, 2022,502:177-185.
[12]GRIEVES M, VICKERS J. Digital twin:mitigating unpredictable, undesirable emergent behavior in complex systems[M]//KAHLEN F J, FLUMERFELT S, ALVES A. Transdisciplinary perspectives on complex systems:new findings and approaches.[S.l.]:Springer International Publishing Switzerland, 2017:85-113. DOI:10.1007/978-3-319-38756-7_4.
[13]JAFARI M, KAVOUSI-FARD A, CHEN T, et al. Review on digital twin technology in smart grid, transportation system and smart city:challenges and future[J]. IEEE Access, 2023,11:17471-17484.
[14]ABD ELAZIZ M, AL-QANESS M A A, DAHOU A, et al.Digital twins in healthcare:applications, technologies,simulations, and future trends[J]. Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery, 2024, 14(6):e1559. DOI:10.1002/widm.1559.
[15]桂卫华,岳伟超,谢永芳,等.铝电解生产智能优化制造研究综述[J].自动化学报, 2018, 44(11):1957-1970.GUI W H, YUE W C, XIE Y F, et al. A review of intelligent optimal manufacturing for aluminum reduction production[J].Acta Automatica Sinica, 2018, 44(11):1957-1970.
[16]沈宁.我国铝电解氧化铝浓度控制的进展[J].轻金属,1998(6):25-31.SHEN N. Progress of aluminum electrolysis alumina concentration control in China[J]. Light Metals, 1998(6):25-31.
[17]王迎春,耿长福,吴宏鑫.一种自适应模糊控制器及其在电解铝过程控制中的应用[J].航天控制, 2001(4):22-28.WANG Y C, GENG C F, WU H X. An adaptive fuzzy controller and its application in the process control of aluminum electrolysis[J]. Aerospace Control, 2001(4):22-28.
[18]周铁托,殷恩生,刘永刚,等.铝电解槽计算机控制技术综合评述:上[J].轻金属, 1998(4):35-38.ZHOU T T, YIN E S, LIU Y G, et al. A comprehensive review of aluminum electrolyzer computer control technology:Ⅰ[J].Light Metals, 1998(4):35-38.
[19]杜善周,黄涌波,鲁绍杰,等.基于分布式感知的氧化铝浓度动态仿真[J].有色金属(冶炼部分), 2023(11):26-32.DU S Z, HUANG Y B, LU S J, et al. Dynamic simulation of alumina concentration based on distributed sensing[J].Nonferrous Metals(Extractive Metallurgy), 2023(11):26-32.
[20]朱家华,徐杨,曹斌,等.面向铝工业基于PSO+LSTM的电解槽氧化铝浓度预测研究[J].轻金属, 2023(7):21-27.ZHU J H, XU Y, CAO B, et al. Prediction study of alumina concentration in electrolytic cell based on PSO+LSTM for aluminum industry[J]. Light Metals, 2023(7):21-27.
[21]朱家华.面向铝工业的电解槽氧化铝浓度预测研究[D].贵阳:贵州大学, 2024.ZHU J H. Prediction of alumina concentration in electrolyzer for aluminum industry[D]. Guiyang:Guizhou University, 2024.
[22]陈志洋.提高大型预焙铝电解槽氧化铝浓度控制准确性的方法[J].轻金属, 2023(8):30-35.CHEN Z Y. Methods to improve the accuracy of alumina concentration control in high-ampearge prebaked aluminum reduction pots[J]. Light Metals, 2023(8):30-35.
[23]邓紫晴.基于阳极电流字典对学习的铝电解分布式槽况监测方法[D].长沙:中南大学, 2022.DENG Z Q. A distributed tank condition monitoring method for aluminum electrolysis based on anode current dictionary pair learning[D]. Changsha:Central South University, 2022.
[24]周九良.基于特征解释卷积神经网络的阳极效应识别和定位方法[D].长沙:中南大学, 2023.ZHOU J L. Anode effect recognition and localization method based on feature explanation convolutional neural network[D].Changsha:Central South University, 2023.
[25]WAN X X, CEN L H, CHEN X F, et al. Multi-generator adversarial dynamic spatial–temporal shapelet network for anode effect prediction in aluminum electrolysis process[J].Advanced Engineering Informatics, 2024, 62:102609. DOI:10.1016/j.aei.2024.102609.
[26]WAN X X, CEN L H, CHEN X F, et al. A novel multiple temporal-spatial convolution network for anode current signals classification[J]. International Journal of Machine Learning and Cybernetics 2022, 13(11):3299-3310.
[27]王一帆.铝电解槽数字孪生:阳极电流测量与分析[D].北京:北方工业大学, 2023.WANG Y F. Digital twin of aluminum electrolysis cell:measurement and analysis of anode current[D]. Beijing:North China University of Technology, 2023.
[28]罗唯杰.基于深度学习的铝电解过热度状态识别方法研究[D].长沙:中南大学, 2023.LUO W J. Research on recognition method of aluminum electrolysis superheat state based on deep learning[D].Changsha:Central South University, 2023.
[29]刘斌,韦业辉,徐辰华,等.基于特征融合和ILSTSVM的铝电解过热度识别[J].广西大学学报(自然科学版), 2022,47(4):998-1007.LIU B, WEI Y H, XU C H, et al. Identification of superheat degree of aluminum electrolysis based on feature fusion and ILSTSVM[J]. Journal of Guangxi University(Natural Science Edition), 2022, 47(4):998-1007.
[30]林清扬.基于多源数据深度特征融合的铝电解过热度识别方法[D].长沙:中南大学, 2022.LIN Q Y. A recognition method of superheat in aluminum electrolysis based on multi-source data deep feature fusion[D].Changsha:Central South University, 2022.
[31]王冬雷.基于知识引导深度网络的铝电解槽温估计与槽况识别[D].长沙:中南大学, 2023.WANG D L. Temperature estimation and condition recognition of aluminum electrolysis cells based on knowledge-guided deep networks[D]. Changsha:Central South University, 2023.
[32]赵博轩.基于深度学习的电解槽分子比趋势预测研究[D].北京:北方工业大学, 2023.ZHAO B X. Research on molecular ratio trend prediction of electrolytic tank based on deep learning[D]. Beijing:North China University of Technology, 2023.
[33]WANG J, XIE Y F, XIE S W, et al. Optimization of aluminum fluoride addition in aluminum electrolysis process based on pruned sparse fuzzy neural network[J]. ISA Transactions,2023, 133:285-301.
[34]YUE W C, GUI W H, CHEN X F, et al. A data and knowledge collaboration strategy for decision-making on the amount of aluminum fluoride addition based on augmented fuzzy cognitive maps[J]. Engineering, 2019, 5(6):1060-1076.
[35]杨玲,王智堂.铝电解阳极效应的分析及控制[J].有色金属(冶炼部分), 2007(3):28-30.YANG L, WANG Z T. Analyzing and controlling of anode effect in aluminium electrolysis[J]. Nonferrous Metals(Extractive Metallurgy), 2007(3):28-30.
[36]陈曦.基于时空图卷积神经网络的铝电解阳极效应预测[D].长沙:中南大学, 2023.CHEN X. Anode effect prediction based on spatialtemporal graph convolutional neural network in aluminum electrolysis[D]. Changsha:Central South University, 2023.
[37]陈晓冉.基于实例迁移学习的铝电解阳极效应预测[D].武汉:华中科技大学, 2020.CHEN X R. Research on anode effect prediction of aluminum electrolysis based on instance transfer learning[D]. Wuhan:Huazhong University of Science and Technology, 2020.
[38]GAO B L, NIU H K, GUAN Y C. Visualization of anode effect in aluminum electrolysis[J]. Journal of the Electrochemical Society, 2022, 169(1):013505. DOI:10.1149/1945-7111/ac4bf5.
[39]WANG X, LIU H, LIU W, et al. Correlation between chemical composition, wettability and carbon anode performance:exploration of high quality carbon anode preparation for aluminum electrolysis[J]. Fuel, 2024, 357(Part B):129823.DOI:10.1016/j.fuel.2023.129823.
[40]SUN B, GUO T. Mechanism-driven and data-driven fusion prediction of seismic damage evolution of concrete structures based on cooperative multi-particle swarm optimization[J].Engineering Applications of Artificial Intelligence, 2024,133(Part F):108659. DOI:10.1016/j.engappai.2024.108659.
[41]LIN Y C, TANG J L, GUO J, et al. Advancing AI-enabled techniques in energy system modeling:a review of datadriven, mechanism-driven, and hybrid modeling approaches[J].Energies, 2025, 18(4):845. DOI:10.3390/en18040845.
[42]李鹏,黄文琦,王鑫,等.数据与知识联合驱动的人工智能方法在电力调度中的应用综述[J].电力系统自动化, 2024,48(1):160-175.LI P, HUANG W Q, WANG X, et al. Review on application of combined data-knowledge-driven artificial intelligence methods in power dispatching[J]. Automation of Electric Power Systems, 2024, 48(1):160-175.
[43]彭晨.知识-数据联合驱动的铝电解槽故障分析及寿命预测研究[D].长沙:中南大学, 2023.PENG C. Research on fault analysis and life prediction of aluminum electrolysis cells based on knowledge-data joint driven[D]. Changsha:Central South University, 2023.
[44]李劼,施辉洪,彭晨,等.铝电解槽寿命相关数据分析与可视化研究[J].有色金属(冶炼部分), 2024(11):138-149.LI J, SHI H H, PENG C, et al. Study on data analysis and visualization of lifespan of aluminum electrolysis cells[J].Nonferrous Metals(Extractive Metallurgy), 2024(11):138-149.
[45]向冬梅.基于数据驱动的铝电解槽安全健康状态诊断与剩余寿命预测研究[D].重庆:重庆大学, 2023.XIANG D M. Study on safety health state diagnosis and residual life prediction of aluminum electrolytic cell based on data drive[D]. Chongqing:Chongqing University, 2023
[46]何俊隆.基于数据驱动的铝电解过程关键参数优化方法研究[D].南宁:广西大学, 2022.HE J L. Research on key parameter optimization method of aluminum electrolysis process based on data drive[D].Nanning:Guangxi University, 2022.
[47]李浩然.基于数据驱动的铝电解槽况评判与故障诊断方法研究[D].南宁:广西大学, 2022.LI H R. Research on cell condition evaluation and fault diagnosis method of aluminum electrolysis based on data drive[D]. Nanning:Guangxi University, 2022.
[48]陶飞,刘蔚然,张萌,等.数字孪生五维模型及十大领域应用[J].计算机集成制造系统, 2019, 25(1):1-18.TAO F, LIU W R, ZHANG M, et al. Five-dimension digital twin model and its ten applications[J]. Computer Integrated Manufacturing Systems, 2019, 25(1):1-18.
[49]庄存波,刘检华,熊辉,等.产品数字孪生体的内涵、体系结构及其发展趋势[J].计算机集成制造系统, 2017, 23(4):753-768.ZHUANG C B, LIU J H, XIONG H, et al. Connotation,architecture and trends of product digital twin[J]. Computer Integrated Manufacturing Systems, 2017, 23(4):753-768.
[50]陶飞,刘蔚然,刘检华,等.数字孪生及其应用探索[J].计算机集成制造系统, 2018, 24(1):1-18.TAO F, LIU W R, LIU J H, et al. Digital twin and its potential application exploration[J]. Computer Integrated Manufacturing Systems, 2018, 24(1):1-18.
[51]罗若木.铝电解数字孪生体关键技术与原型系统研究[D].长沙:中南大学, 2023.LUO R M. Research on key technology and prototype system of aluminum electrolysis digital twin[D]. Changsha:Central South University, 2023.
基本信息:
DOI：10.20237/j.issn.1007-7545.2025.08.001
中图分类号:TP399;TF821
引用信息:
[1]李劼,施辉洪,张行涛,等.铝电解智能制造及数字孪生研究进展[J].有色金属(冶炼部分),2025(08):1-13.DOI:10.20237/j.issn.1007-7545.2025.08.001.
基金信息:
国家自然科学基金资助项目(U2202253);国家自然科学基金重点项目(62133016); 云南省科技计划项目(202202AB080017); 中南大学交叉前沿科学研究计划项目(2023QYJC007); 湖南省研究生创新基金资助项目(CX20230171); 重庆市自然科学基金资助项目(CSTB2022NSCQ-MSX1395)
2025-05-31
2025
2025-07-02
2025-07-03
2025
1
2025-08-08
2025-08-08