Abstract
The blast furnace is a highly energy-intensive, highly polluting, and extremely complex reactor in the ironmaking process. Soft sensors are a key technology for predicting molten iron quality indices reflecting blast furnace energy consumption and operation stability, and play an important role in saving energy, reducing emissions, improving product quality, and producing economic benefits. With the advancement of the Internet of Things, big data, and artificial intelligence, data-driven soft sensors in blast furnace ironmaking processes have attracted increasing attention from researchers, but there has been no systematic review of the data-driven soft sensors in the blast furnace ironmaking process. This review covers the state-of-the-art studies of data-driven soft sensors technologies in the blast furnace ironmaking process. Specifically, we first conduct a comprehensive overview of various data-driven soft sensor modeling methods (multiscale methods, adaptive methods, deep learning, etc.) used in blast furnace ironmaking. Second, the important applications of data-driven soft sensors in blast furnace ironmaking (silicon content, molten iron temperature, gas utilization rate, etc.) are classified. Finally, the potential challenges and future development trends of data-driven soft sensors in blast furnace ironmaking applications are discussed, including digital twin, multi-source data fusion, and carbon peaking and carbon neutrality.
摘要
在高能耗、高污染、极为复杂的冶炼过程中, 高炉是极为重要的反应器。软测量技术是在线实时预测反映高炉能耗和运行稳定性质量指标的关键技术, 在节能减排、提高产品质量和带来经济效益方面发挥着重要作用。随着物联网、大数据和人工智能的发展, 高炉炼铁过程中的数据驱动软测量技术受到越来越多关注, 但目前尚无关于高炉炼铁过程数据驱动软测量技术的系统性总结与评价。本文详细总结了高炉炼铁过程数据驱动软测量技术的最新研究成果与发展现状。具体而言, 首先对高炉炼铁中使用的各种数据驱动软测量建模方法(如多尺度方法、自适应方法、深度学习等)进行了全面分类总结与分析。其次, 对高炉炼铁中数据驱动软测量技术的应用现状(如硅含量、熔铁温度、气体利用率等)作对比分析。最后, 展望了数据驱动软测量技术在高炉数字孪生、多源信息融合、碳达峰与碳中和等方面的潜在挑战和未来发展趋势。
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Change history
23 November 2023
An Erratum to this paper has been published: https://doi.org/10.1631/FITEE.22e0366
22 November 2023
An Erratum to this paper has been published: https://doi.org/10.1631/FITEE.22e0366
References
An JQ, Wu M, He Y, 2013. A temperature field detection system for blast furnace based on multi-source information fusion. Intell Autom Soft Comput, 19(4):625–634. https://doi.org/10.1080/10798587.2013.869121
An JQ, Peng K, Cao WH, et al., 2016. A soft-sensing method for missing temperature information based on dynamic neural network on BF wall. J Chem Ind Eng, 67(3):903–911 (in Chinese). https://doi.org/10.11949/j.issn.0438-1157.20151941
An JQ, Shen XL, Wu M, et al., 2019. A multi-time-scale fusion prediction model for the gas utilization rate in a blast furnace. Contr Eng Pract, 92:104120. https://doi.org/10.1016/j.conengprac.2019.104120
Azadi P, Minaabad SA, Bartusch H, et al., 2020. Nonlinear prediction model of blast furnace operation status. Comput Aided Chem Eng, 48:217–222. https://doi.org/10.1016/B978-0-12-823377-1.50037-9
Azadi P, Winz J, Leo E, et al., 2022. A hybrid dynamic model for the prediction of molten iron and slag quality indices of a large-scale blast furnace. Comput Chem Eng, 156:107573. https://doi.org/10.1016/j.compchemeng.2021.107573
Azzedine A, Nouri F, Bouhouche S, 2021. Mathematical and numerical results for quality control of hot metal in blast furnace. J Math Comput Sci, 11(3):2914–2933.
Cardoso W, di Felice R, 2021. Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning. Int J Adv Intell Inform, 7(3):268–281. https://doi.org/10.26555/ijain.v7i3.771
Chen K, Liu Y, 2017. Adaptive weighting just-in-time-learning quality prediction model for an industrial blast furnace. ISIJ Int, 57(1):107–113. https://doi.org/10.2355/isijinternational.ISIJINT-2016-292
Chen K, Liang Y, Gao Z, et al., 2017. Just-in-time correntropy soft sensor with noisy data for industrial silicon content prediction. Sensors, 17(8):1830. https://doi.org/10.3390/s17081830
Chen SH, Gao CH, 2020. Linear priors mined and integrated for transparency of blast furnace black-box SVM model. IEEE Trans Ind Inform, 16(6):3862–3870. https://doi.org/10.1109/TII.2019.2940475
Chu YX, Gao CH, 2014. Data-based multiscale modeling for blast furnace system. AIChE J, 60(6):2197–2210. https://doi.org/10.1002/aic.14426
Cui GM, Jiang ZG, Liu PL, et al., 2018. Prediction of blast furnace temperature based on multi-information fusion of image and data. Proc Chinese Automation Congress, p.2317–2322. https://doi.org/10.1109/CAC.2018.8623386
Ding ZY, Zhang J, Liu Y, 2017. Ensemble non-Gaussian local regression for industrial silicon content prediction. ISIJ Int, 57(11):2022–2027. https://doi.org/10.2355/isijinternational.ISIJINT-2017-251
Diniz APM, Côco KF, Gomes FSV, et al., 2021. Forecasting model of silicon content in molten iron using wavelet decomposition and artificial neural networks. Metals, 11(7):1001. https://doi.org/10.3390/met11071001
Du S, Wu M, Chen LF, et al., 2021. Prediction model of burn-through point with fuzzy time series for iron ore sintering process. Eng Appl Artif Intell, 102:104259. https://doi.org/10.1016/j.engappai.2021.104259
Fang YJ, Jiang ZH, 2020. Use of adaptive weighted echo state network ensemble for construction of prediction intervals and prediction reliability of silicon content in ironmaking process. Proc 2nd Int Conf on Industrial Artificial Intelligence, p.1–6. https://doi.org/10.1109/IAI50351.2020.9262187
Fang YJ, Jiang ZH, Pan D, et al., 2020. Soft sensors based on adaptive stacked polymorphic model for silicon content prediction in ironmaking process. IEEE Trans Instrum Meas, 70:2503412. https://doi.org/10.1109/TIM.2020.3038285
Fontes DOL, Vasconcelos LGS, Brito RP, 2020. Blast furnace hot metal temperature and silicon content prediction using soft sensor based on fuzzy C-means and exogenous nonlinear autoregressive models. Comput Chem Eng, 141:107028. https://doi.org/10.1016/j.compchemeng.2020.107028
Fortuna L, Graziani S, Rizzo A, et al., 2007. Soft Sensors for Monitoring and Control of Industrial Processes. Springer, London, UK. https://doi.org/10.1007/978-1-84628-480-9
Gao CH, Jian L, Liu XY, et al., 2011a. Data-driven modeling based on Volterra series for multidimensional blast furnace system. IEEE Trans Neur Netw, 22(12):2272–2283. https://doi.org/10.1109/TNN.2011.2175945
Gao CH, Zeng J, Zhou ZY, 2011b. Identification of multiscale nature and multiple dynamics of the blast furnace system from operating data. AIChE J, 57(12):3448–3458. https://doi.org/10.1002/aic.12554
Gao CH, Lin QQ, Ni JS, et al., 2021. A nonuniform delay-coordinate embedding-based multiscale predictor for blast furnace systems. IEEE Trans Contr Syst Technol, 29(5):2223–2230. https://doi.org/10.1109/TCST.2020.3023072
Gao S, Dai Y, Li YJ, et al., 2022. Augmented flame image soft sensor for combustion oxygen content prediction. Meas Sci Technol, 34(1):015401. https://doi.org/10.1088/1361-6501/ac95b5
Geerdes M, Chaigneau R, Lingiardi O, 2020. Modern Blast Furnace Ironmaking: an Introduction (4th Ed.). IOS Press, Amsterdam, the Netherlands.
Glaessgen E, Stargel D, 2012. The digital twin paradigm for future NASA and U.S. air force vehicles. Proc 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conf, p.1818. https://doi.org/10.2514/6.2012-1818
Hashimoto Y, Sawa Y, Kitamura Y, et al., 2018. Development and validation of kinematical blast furnace model with long-term operation data. ISIJ Int, 58(12):2210–2218. https://doi.org/10.2355/isijinternational.ISIJINT-2018-177
Hashimoto Y, Kitamura Y, Ohashi T, et al., 2019a. Transient model-based operation guidance on blast furnace. Contr Eng Pract, 82:130–141. https://doi.org/10.1016/j.conengprac.2018.10.009
Hashimoto Y, Okamoto Y, Kaise T, et al., 2019b. Practical operation guidance on thermal control of blast furnace. ISIJ Int, 59(9):1573–1581. https://doi.org/10.2355/isijinternational.ISIJINT-2019-119
He BC, Zhang QZ, Zhang XM, 2022. A faster dynamic feature extractor and its application to industrial quality prediction. IEEE Trans Ind Inform, p.1–11, early access. https://doi.org/10.1109/TII.2022.3205356
He X, Ji J, Liu KX, et al., 2019. Soft sensing of silicon content via bagging local semi-supervised models. Sensors, 19(17):3814. https://doi.org/10.3390/s19173814
Hu TH, Wang XP, Wang Y, et al., 2021. Prediction of blast furnace temperature based on evolutionary optimization. Proc 11th Int Conf on Evolutionary Multi-criterion Optimization, p.759–768. https://doi.org/10.1007/978-3-030-72062-9_60
Hu YF, Zhou H, Yao S, et al., 2022. Comprehensive evaluation of the blast furnace status based on data mining and mechanism analysis. Int J Chem React Eng, 20(2):225–235. https://doi.org/10.1515/ijcre-2021-0160
Jian L, Gao CH, 2013. Binary coding SVMs for the multiclass problem of blast furnace system. IEEE Trans Ind Electron, 60(9):3846–3856. https://doi.org/10.1109/TIE.2012.2206336
Jian L, Gao CH, Xia ZQ, 2011. A sliding-window smooth support vector regression model for nonlinear blast furnace system. Steel Res Int, 82(3):169–179. https://doi.org/10.1002/srin.201000082
Jian L, Gao CH, Xia ZH, 2012. Constructing multiple kernel learning framework for blast furnace automation. IEEE Trans Autom Sci Eng, 9(4):763–777. https://doi.org/10.1109/TASE.2012.2211100
Jiang K, Jiang ZH, Xie YF, et al., 2018. A trend prediction method based on fusion model and its application. Proc 13th World Congress on Intelligent Control and Automation, p.322–328. https://doi.org/10.1109/WCICA.2018.8630347
Jiang K, Jiang ZH, Xie YF, et al., 2020. Classification of silicon content variation trend based on fusion of multilevel features in blast furnace ironmaking. Inform Sci, 521:32–45. https://doi.org/10.1016/j.ins.2020.02.039
Jiang YC, Yin S, Dong JW, et al., 2021a. A review on soft sensors for monitoring, control, and optimization of industrial processes. IEEE Sens J, 21(11):12868–12881. https://doi.org/10.1109/JSEN.2020.3033153
Jiang YC, Yin S, Li K, et al., 2021b. Industrial applications of digital twins. Phil Trans R Soc A Math Phys Eng Sci, 379(2207):20200360. https://doi.org/10.1098/rsta.2020.0360
Jiang YS, Yang N, Yao QQ, et al., 2020. Real-time moisture control in sintering process using offline-online NARX neural networks. Neurocomputing, 396:209–215. https://doi.org/10.1016/j.neucom.2018.07.099
Jiang ZH, Pan D, Gui WH, et al., 2018. Temperature measurement of molten iron in taphole of blast furnace combined temperature drop model with heat transfer model. Ironmak Steelmak, 45(3):230–238. https://doi.org/10.1080/03019233.2016.1254423
Jiménez J, Mochón J, de Ayala JS, et al., 2004. Blast furnace hot metal temperature prediction through neural networks-based models. ISIJ Int, 44(3):573–580.
Kramer MA, 1991. Nonlinear principal component analysis using autoassociative neural networks. AIChE J, 37(2):233–243. https://doi.org/10.1002/aic.690370209
Lay-Ekuakille A, Ugwiri MA, Okitadiowo JD, et al., 2021. Computer vision for sensed images approach in extremely harsh environments: blast furnace chute wear characterization. IEEE Sens J, 21(10):11969–11976. https://doi.org/10.1109/JSEN.2021.3063264
Li HY, Bu XP, Liu XJ, et al., 2021. Evaluation and prediction of blast furnace status based on big data platform of ironmaking and data mining. ISIJ Int, 61(1):108–118. https://doi.org/10.2355/isijinternational.ISIJINT-2020-249
Li J, Gao CH, 2010. Multi-scale entropy analysis on the complexity of blast furnace ironmaking process. Proc 2nd Int Conf on Industrial Mechatronics and Automation, p.257–260. https://doi.org/10.1109/ICINDMA.2010.5538172
Li JL, Zhu RJ, Zhou P, et al., 2021. Prediction of the cohesive zone in a blast furnace by integrating CFD and SVM modelling. Ironmak Steelmak, 48(3):284–291. https://doi.org/10.1080/03019233.2020.1771893
Li JP, Hua CC, Yang YN, et al., 2018. Fuzzy classifier design for development tendency of hot metal silicon content in blast furnace. IEEE Trans Ind Inform, 14(3):1115–1123. https://doi.org/10.1109/TII.2017.2770177
Li JP, Hua CC, Yang YN, 2021a. A novel multiple-input-multiple-output random vector functional-link networks for predicting molten iron quality indexes in blast furnace. IEEE Trans Ind Electron, 68(11):11309–11317. https://doi.org/10.1109/TIE.2020.3031525
Li JP, Hua CC, Yang YN, et al., 2021b. A novel MIMO T-S fuzzy modeling for prediction of blast furnace molten iron quality with missing outputs. IEEE Trans Fuzzy Syst, 29(6):1654–1666. https://doi.org/10.1109/TFUZZ.2020.2983667
Li JP, Hua CC, Yang YN, et al., 2022. Data-driven Bayesian-based Takagi-Sugeno fuzzy modeling for dynamic prediction of hot metal silicon content in blast furnace. IEEE Trans Syst Man Cybern Syst, 52(2):1087–1099. https://doi.org/10.1109/TSMC.2020.3013972
Li S, Li WQ, Cook C, et al., 2018. Independently recurrent neural network (IndRNN): building a longer and deeper RNN. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.5457–5466. https://doi.org/10.1109/CVPR.2018.00572
Li S, Chang JC, Chu MS, et al., 2022. A blast furnace coke ratio prediction model based on fuzzy cluster and grid search optimized support vector regression. Appl Intell, 52(12):13533–13542. https://doi.org/10.1007/S10489-022-03234-8
Li WP, Zhou P, 2020. Robust regularized RVFLNs modeling of molten iron quality in blast furnace ironmaking. Acta Autom Sin, 46(4):721–733 (in Chinese). https://doi.org/10.16383/j.aas.2018.c170670
Li WY, Zhuo YT, Bao J, et al., 2021. A data-based soft-sensor approach to estimating raceway depth in iron-making blast furnaces. Powd Technol, 390:529–538. https://doi.org/10.1016/j.powtec.2021.05.072
Li YJ, Zhang S, Yin YX, et al., 2019. A soft sensing scheme of gas utilization ratio prediction for blast furnace via improved extreme learning machine. Neur Process Lett, 50(2):1191–1213. https://doi.org/10.1007/s11063-018-9888-3
Li YJ, Zhang S, Zhang J, et al., 2020. Data-driven multiobjective optimization for burden surface in blast furnace with feedback compensation. IEEE Trans Ind Inform, 16(4):2233–2244. https://doi.org/10.1109/tii.2019.2908989
Li YJ, Li HQ, Zhang J, et al., 2021. Data and knowledge driven approach for burden surface optimization in blast furnace. Comput Electr Eng, 92:107191. https://doi.org/10.1016/j.compeleceng.2021.107191
Li YJ, Zhang J, Zhang S, et al., 2022. Dual ensemble online modeling for dynamic estimation of hot metal silicon content in blast furnace system. ISA Trans, 128:686–697. https://doi.org/10.1016/j.isatra.2021.09.018
Li YQ, Cai D, Wang JL, et al., 2020. Recurrence behavior statistics of blast furnace gas sensor data in Industrial Internet of Things. IEEE Int Things J, 7(6):5666–5676. https://doi.org/10.1109/JIOT.2020.2980617
Li YR, Yang CJ, 2021. Domain knowledge based explainable feature construction method and its application in ironmaking process. Eng Appl Artif Intell, 100:104197. https://doi.org/10.1016/j.engappai.2021.104197
Liu C, Tang LX, Liu JY, 2020. A stacked autoencoder with sparse Bayesian regression for end-point prediction problems in steelmaking process. IEEE Trans Autom Sci Eng, 17(2):550–561. https://doi.org/10.1109/tase.2019.2935314
Liu Y, Gao Z, 2015. Enhanced just-in-time modelling for online quality prediction in BF ironmaking. Ironmak Steelmak, 42(5):321–330. https://doi.org/10.1179/1743281214Y.0000000229
Liu Y, Yu HQ, Gao ZL, et al., 2011. Improved online prediction of silicon content in ironmaking process using support vector regression with novel outlier detection. Adv Mater Res, 154–155:251–255. https://doi.org/10.4028/www.scientific.net/AMR.154-155.251
Liu Y, Fan Y, Chen JH, 2017. Flame images for oxygen content prediction of combustion systems using DBN. Energy Fuels, 31(8):8776–8783. https://doi.org/10.1021/acs.energyfuels.7b00576
Lughofer E, Pollak R, Feilmayr C, et al., 2021. Prediction and explanation models for hot metal temperature, silicon concentration, and cooling capacity in ironmaking blast furnaces. Steel Res Int, 92(9):2100078. https://doi.org/10.1002/srin.202100078
Luo SH, Chen TX, 2020. Two derivative algorithms of gradient boosting decision tree for silicon content in blast furnace system prediction. IEEE Access, 8:196112–196122. https://doi.org/10.1109/ACCESS.2020.3034566
Luo SH, Dai Z, Guo F, et al., 2019. Identification of extreme temperature fluctuation in blast furnace based on fractal time series analysis. Techn Gaz, 26(4):1098–1103. https://doi.org/10.17559/TV-20190607101917
Luo SH, Dai ZA, Chen TX, et al., 2020. A weighted SVM ensemble predictor based on AdaBoost for blast furnace ironmaking process. Appl Intell, 50(7):1997–2008. https://doi.org/10.1007/s10489-020-01662-y
Masson MH, Canu S, Grandvalet Y, et al., 1999. Software sensor design based on empirical data. Ecol Modell, 120(2–3):131–139. https://doi.org/10.1016/S0304-3800(99)00097-6
Pan D, Jiang ZH, Chen ZP, et al., 2018. Temperature measurement method for blast furnace molten iron based on infrared thermography and temperature reduction model. Sensors, 18(11):3792. https://doi.org/10.3390/s18113792
Papadopoulos G, Edwards PJ, Murray AF, 2001. Confidence estimation methods for neural networks: a practical comparison. IEEE Trans Neur Netw, 12(6):1278–1287. https://doi.org/10.1109/72.963764
Radhakrishnan V, Mohamed A, 2000. Neural networks for the identification and control of blast furnace hot metal quality. J Process Contr, 10(6):509–524. https://doi.org/10.1016/S0959-1524(99)00052-9
Rajesh N, Khare MR, Pabi SK, 2010. Application of ANN modelling techniques in blast furnace iron making. Int J Model Simul, 30(3):340–344. https://doi.org/10.1080/02286203.2010.11442589
Saxén H, Gao CH, Gao ZW, 2013. Data-driven time discrete models for dynamic prediction of the hot metal silicon content in the blast furnace—a review. IEEE Trans Ind Inform, 9(4):2213–2225. https://doi.org/10.1109/TII.2012.2226897
Saxén JE, Saxén H, Toivonen HT, 2016. Identification of switching linear systems using self-organizing models with application to silicon prediction in hot metal. Appl Soft Comput, 47:271–280. https://doi.org/10.1016/j.asoc.2016.05.048
Shen XL, An JQ, Wu M, et al., 2020. Burden control strategy based on reinforcement learning for gas utilization rate in blast furnace. IFAC-PapersOnLine, 53(2):11704–11709. https://doi.org/10.1016/j.ifacol.2020.12.667
Song HD, Zhou P, Wang H, et al., 2016. Nonlinear subspace modeling of multivariate molten iron quality in blast furnace ironmaking and its application. Acta Autom Sin, 42(11):1664–1679 (in Chinese). https://doi.org/10.16383/j.aas.2016.c150819
Su XL, Zhang S, Yin YX, et al., 2018. Prediction model of permeability index for blast furnace based on the improved multi-layer extreme learning machine and wavelet transform. J Franklin Inst, 355(4):1663–1691. https://doi.org/10.1016/j.jfranklin.2017.05.001
Su XL, Sun SL, Zhang S, et al., 2020. Improved multilayer online sequential extreme learning machine and its application for hot metal silicon content. J Franklin Inst, 357(17):12588–12608. https://doi.org/10.1016/j.jfranklin.2020.05.031
Sun QQ, Ge ZQ, 2021. A survey on deep learning for data-driven soft sensors. IEEE Trans Ind Inform, 17(9):5853–5866. https://doi.org/10.1109/TII.2021.3053128
Waller M, Saxén H, 2003. Time-varying event-internal trends in predictive modeling—methods with applications to ladlewise analyses of hot metal silicon content. Ind Eng Chem Res, 42(1):85–90. https://doi.org/10.1021/ie0201718
Wang GP, Yan ZY, Zhai HP, et al., 2021. Silicon content prediction of hot metal in blast furnace based on attention mechanism and CNN-IndRNN model. E3S Web Conf, 252:02025. https://doi.org/10.1051/e3sconf/202125202025
Wang P, Hu TH, Tang LX, 2022. A multiobjective evolutionary nonlinear ensemble learning with evolutionary feature selection for silicon prediction in blast furnace. IEEE Trans Neur Netw Learn Syst, 33(5):2080–2093. https://doi.org/10.1109/TNNLS.2021.3059784
Wang ZY, Gao CH, Liu XG, 2011. Using LSSVM model to predict the silicon content in hot metal based on KPCA feature extraction. Proc Chinese Control and Decision Conf, p.1967–1971. https://doi.org/10.1109/CCDC.2011.5968523
Wang ZY, Jiang DW, Wang XD, et al., 2021. Prediction of blast furnace hot metal temperature based on support vector regression and extreme learning machine. Chin J Eng, 43(4):569–576 (in Chinese). https://doi.org/10.13374/j.issn2095-9389.2020.05.28.001
Warne K, Prasad G, Rezvani S, et al., 2004. Statistical and computational intelligence techniques for inferential model development: a comparative evaluation and a novel proposition for fusion. Eng Appl Artif Intell, 17(8):871–885. https://doi.org/10.1016/j.engappai.2004.08.020
Wen L, Zhou P, Wang H, et al., 2018. Model free adaptive predictive control of multivariate molten iron quality in blast furnace ironmaking. Proc IEEE Conf on Decision and Control, p.2617–2622. https://doi.org/10.1109/CDC.2018.8619757
Wu M, Zhang KX, An JQ, et al., 2018. An energy efficient decision-making strategy of burden distribution for blast furnace. Contr Eng Pract, 78:186–195. https://doi.org/10.1016/j.conengprac.2018.06.019
Xie J, Zhou P, 2020. Robust stochastic configuration network multi-output modeling of molten iron quality in blast furnace ironmaking. Neurocomputing, 387:139–149. https://doi.org/10.1016/j.neucom.2020.01.030
Xu X, Hua CC, Tang YG, et al., 2016. Modeling of the hot metal silicon content in blast furnace using support vector machine optimized by an improved particle swarm optimizer. Neur Comput Appl, 27(6):1451–1461. https://doi.org/10.1007/s00521-015-1951-7
Yan F, Zhang XM, Yang CJ, et al., 2022. Data-driven modelling methods in sintering process: current research status and perspectives. Can J Chem Eng, early access. https://doi.org/10.1002/cjce.24790
Yang YL, Zhang S, Yin YX, 2016. A modified ELM algorithm for the prediction of silicon content in hot metal. Neur Comput Appl, 27(1):241–247. https://doi.org/10.1007/s00521-014-1775-x
Yin F, An JQ, Shen XL, et al., 2020. Interval prediction model of blast furnace gas utilization rate based on multi-time-scale. Proc 39th Chinese Control Conf, p.2300–2305. https://doi.org/10.23919/CCC50068.2020.9188400
Yu X, Tan C, 2022. China’s pathway to carbon neutrality for the iron and steel industry. Glob Environ Change, 76:102574. https://doi.org/10.1016/j.gloenvcha.2022.102574
Yuan M, Zhou P, Li ML, et al., 2015. Intelligent multivariable modeling of blast furnace molten iron quality based on dynamic AGA-ANN and PCA. J Iron Steel Res Int, 22(6):487–495. https://doi.org/10.1016/S1006-706X(15)30031-5
Zeng JS, Gao CH, Pan W, 2010a. Modeling of high dimensional blast furnace system by manifold learning. Proc 29th Chinese Control Conf, p.3157–3161.
Zeng JS, Gao CH, Su HY, 2010b. Data-driven predictive control for blast furnace ironmaking process. Comput Chem Eng, 34(11):1854–1862. https://doi.org/10.1016/j.compchemeng.2010.01.005
Zhai XY, Chen MT, Lu WC, 2020. Fuel ratio optimization of blast furnace based on data mining. ISIJ Int, 60(11):2471–2476. https://doi.org/10.2355/isijinternational.ISIJINT-2020-238
Zhang HG, Yin YX, Zhang S, 2016. An improved ELM algorithm for the measurement of hot metal temperature in blast furnace. Neurocomputing, 174:232–237. https://doi.org/10.1016/j.neucom.2015.04.106
Zhang HG, Zhang S, Yin YX, et al., 2018. Prediction of the hot metal silicon content in blast furnace based on extreme learning machine. Int J Mach Learn Cyber, 9(10):1697–1706. https://doi.org/10.1007/s13042-017-0674-8
Zhang WL, Lin Q, Zhao J, et al., 2016. Soft computing for blast furnace gas system pressure based on an improved fuzzy model. Proc 12th World Congress on Intelligent Control and Automation, p.2400–2406. https://doi.org/10.1109/WCICA.2016.7578494
Zhang XM, Kano M, Matsuzaki S, 2019a. A comparative study of deep and shallow predictive techniques for hot metal temperature prediction in blast furnace ironmaking. Comput Chem Eng, 130:106575. https://doi.org/10.1016/j.compchemeng.2019.106575
Zhang XM, Kano M, Matsuzaki S, 2019b. Ensemble pattern trees for predicting hot metal temperature in blast furnace. Comput Chem Eng, 121:442–449. https://doi.org/10.1016/j.compchemeng.2018.10.022
Zhang XM, Kano M, Tani M, et al., 2020a. Prediction and causal analysis of defects in steel products: handling nonnegative and highly overdispersed count data. Contr Eng Pract, 95:104258. https://doi.org/10.1016/j.conengprac.2019.104258
Zhang XM, Wei CH, Song ZH, 2020b. Fast locally weighted PLS modeling for large-scale industrial processes. Ind Eng Chem Res, 59(47):20779–20786. https://doi.org/10.1021/acs.iecr.0c03932
Zhang ZY, Lu YF, Wang XJ, et al., 2022. A data-based compact high-order Volterra model for complex blast furnace system. IEEE Trans Ind Inform, 18(9):5827–5837. https://doi.org/10.1109/TII.2021.3131604
Zhao J, Wang W, Liu Y, et al., 2011. A two-stage online prediction method for a blast furnace gas system and its application. IEEE Trans Contr Syst Technol, 19(3):507–520. https://doi.org/10.1109/TCST.2010.2051545
Zhao XD, Fang YM, Liu L, et al., 2020. Ameliorated moth-flame algorithm and its application for modeling of silicon content in liquid iron of blast furnace based fast learning network. Appl Soft Comput, 94:106418. https://doi.org/10.1016/j.asoc.2020.106418
Zhou B, Ye H, Zhang HF, et al., 2016. Process monitoring of iron-making process in a blast furnace with PCA-based methods. Contr Eng Pract, 47:1–14. https://doi.org/10.1016/j.conengprac.2015.11.006
Zhou L, Gao CH, Zeng JS, et al., 2011. The fractal multiscale trend decomposition of silicon content in blast furnace hot metal. ISIJ Int, 51(4):588–592. https://doi.org/10.2355/isijinternational.51.588
Zhou P, Yuan M, Wang H, et al., 2015a. Data-driven dynamic modeling for prediction of molten iron silicon content using ELM with self-feedback. Math Probl Eng, 2015:326160. https://doi.org/10.1155/2015/326160
Zhou P, Yuan M, Wang H, et al., 2015b. Multivariable dynamic modeling for molten iron quality using online sequential random vector functional-link networks with self-feedback connections. Inform Sci, 325:237–255. https://doi.org/10.1016/j.ins.2015.07.002
Zhou P, Zhang L, Li WP, et al., 2018a. Autoencoder and PCA based RVFLNs modeling for multivariate molten iron quality in blast furnace ironmaking. Acta Autom Sin, 44(10):1799–1811 (in Chinese). https://doi.org/10.16383/j.aas.2018.c170299
Zhou P, Guo DW, Chai TY, 2018b. Data-driven predictive control of molten iron quality in blast furnace ironmaking using multi-output LS-SVR based inverse system identification. Neurocomputing, 308:101–110. https://doi.org/10.1016/j.neucom.2018.04.060
Zhou P, Guo DW, Wang H, et al., 2018c. Data-driven robust M-LS-SVR-based NARX modeling for estimation and control of molten iron quality indices in blast furnace ironmaking. IEEE Trans Neur Netw Learn Syst, 29(9):4007–4021. https://doi.org/10.1109/TNNLS.2017.2749412
Zhou P, Wang CY, Li MJ, et al., 2018d. Modeling error PDF optimization based wavelet neural network modeling of dynamic system and its application in blast furnace ironmaking. Neurocomputing, 285:167–175. https://doi.org/10.1016/j.neucom.2018.01.040
Zhou P, LI JL, Wen QQ, et al., 2018e. Soft-sensing method of cohesive zone shape and position in blast furnace shaft. IFAC-PapersOnLine, 51(21):48–52. https://doi.org/10.1016/j.ifacol.2018.09.391
Zhou P, Jiang Y, Wen CY, et al., 2019. Data modeling for quality prediction using improved orthogonal incremental random vector functional-link networks. Neurocomputing, 365:1–9. https://doi.org/10.1016/j.neucom.2019.06.062
Zhou P, Li WP, Wang H, et al., 2020. Robust online sequential RVFLNs for data modeling of dynamic time-varying systems with application of an ironmaking blast furnace. IEEE Trans Cybern, 50(11):4783–4795. https://doi.org/10.1109/TCYB.2019.2920483
Zhou P, Chen WQ, Yi CM, et al., 2021a. Fast just-in-time-learning recursive multi-output LSSVR for quality prediction and control of multivariable dynamic systems. Eng Appl Artif Intell, 100:104168. https://doi.org/10.1016/j.engappai.2021.104168
Zhou P, Jiang Y, Wen CY, et al., 2021b. Improved incremental RVFL with compact structure and its application in quality prediction of blast furnace. IEEE Trans Ind Inform, 17(12):8324–8334. https://doi.org/10.1109/TII.2021.3069869
Zhu HY, He BC, Zhang XM, 2022. Multi-gate mixture-of-experts stacked autoencoders for quality prediction in blast furnace ironmaking. ACS Omega, 7(45):41296–41303. https://doi.org/10.1021/acsomega.2c05029
Author information
Authors and Affiliations
Contributions
Yueyang LUO and Xinmin ZHANG drafted the paper. Long DENG, Chunjie YANG, and Zhihuan SONG helped organize the paper. Xinmin ZHANG and Manabu KANO revised and finalized the paper.
Corresponding author
Ethics declarations
Yueyang LUO, Xinmin ZHANG, Manabu KANO, Long DENG, Chunjie YANG, and Zhihuan SONG declare that they have no conflict of interest.
Additional information
Project supported by the National Natural Science Foundation of China (Nos. 62003301, 61933013, and 61833014), the Natural Science Foundation of Zhejiang Province, China (No. LQ21F030018), and the Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China (Nos. ICT2022B30 and ICT2022B08)
Yueyang LUO received his BE degree in automation from School of Mechanical Engineering and Automation, Beihang University, Beijing, China in 2021. He is currently working toward his ME degree in electronic information engineering in College of Control Science and Engineering, Zhejiang University, China. His research interests include time-series prediction, deep learning, and soft sensor.
Xinmin ZHANG, corresponding author of this invited paper, received his PhD degree in systems science from Kyoto University, Japan in 2019. From April to December 2019, he was a postdoctoral research fellow in Department of Systems Science, Kyoto University, Japan. Currently, he is an associate professor with the State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, China. His research interests include industrial big data modeling and analysis, process control, fault diagnosis, soft-sensor, and machine learning and deep learning with applications to industrial processes.
Manabu KANO received his BS, MS, and PhD degrees from Department of Chemical Engineering at Kyoto University in 1992, 1994, and 1999, respectively. He has been an instructor at Kyoto University since 1994. From 1999 to 2000, he was a visiting scholar at Ohio State University, USA. Since 2012, he has been a professor of systems science, Kyoto University. He has conducted research in collaboration with various industries, such as semiconductor, chemical, steel, and pharmaceutical. His research interests focus on process data analysis for quality improvement, process monitoring, and process control.
Long DENG is a senior engineer with the Central Research Institute of Baoshan Iron & Steel Co., Ltd., Shanghai, China. His research interests include automation and intelligent control of key processes, such as steelmaking, continuous casting, heating, and heat treatment.
Chunjie YANG received his BS degree in machine design, MS degree in fluid transmission and control, and PhD degree in industrial automation from Zhejiang University, China in 1992, 1995, and 1998, respectively. In 2009, he was a visiting scholar at Florida State University, USA. He is currently a professor in College of Control Science and Engineering, and a Qiushi Distinguished Professor of Zhejiang University, China. His current research interests include industrial big data, process monitoring, soft-sensor, and fault diagnosis.
Zhihuan SONG received his BE and ME degrees in industrial automation from Hefei University of Technology, China in 1983 and 1986, respectively, and his PhD degree in industrial automation from Zhejiang University, China in 1997. Since 1997, he has been in College of Control Science and Engineering, Zhejiang University, where he was first a postdoctoral research fellow, then an associate professor, and is currently a full professor. His research interests include modeling and fault diagnosis of industrial processes, analytics and applications of industrial big data, and advanced process control technologies.
Rights and permissions
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which permits any non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc/4.0/.
About this article
Cite this article
Luo, Y., Zhang, X., Kano, M. et al. Data-driven soft sensors in blast furnace ironmaking: a survey. Front Inform Technol Electron Eng 24, 327–354 (2023). https://doi.org/10.1631/FITEE.2200366
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2200366