矿浆电解槽固液悬浮过程流场和浓度场的快速预测

卢婷婷; 李康; 赵洪亮; 王维; 周振昊; 蔡笑怡; 刘风琴

doi:10.1007/s12613-024-2826-7

Volume 31 Issue 9

Sep. 2024

Turn off MathJax

图(9) / 表(6)

数据统计

计量

文章访问数: 396
HTML全文浏览量: 186
PDF下载量: 31
被引次数: 0

文章导航 > 矿物冶金与材料学报（英文） > 2024 > 31(9): 2006-2016

Tingting Lu, Kang Li, Hongliang Zhao, Wei Wang, Zhenhao Zhou, Xiaoyi Cai, and Fengqin Liu, Rapid prediction of flow and concentration fields in solid–liquid suspensions of slurry electrolysis tanks, Int. J. Miner. Metall. Mater., 31(2024), No. 9, pp. 2006-2016. https://doi.org/10.1007/s12613-024-2826-7

Cite this article as:

Tingting Lu, Kang Li, Hongliang Zhao, Wei Wang, Zhenhao Zhou, Xiaoyi Cai, and Fengqin Liu, Rapid prediction of flow and concentration fields in solid–liquid suspensions of slurry electrolysis tanks, Int. J. Miner. Metall. Mater., 31(2024), No. 9, pp. 2006-2016. https://doi.org/10.1007/s12613-024-2826-7

Citation:

PDF( 3137 KB)

引用本文 PDF XML SpringerLink

研究论文

矿浆电解槽固液悬浮过程流场和浓度场的快速预测

1)
绿色低碳钢铁冶金全国重点实验室, 北京 100083, 中国
2)
矿冶过程智能优化制造全国重点实验室, 北京 102628, 中国
3)
兰州理工大学材料科学与工程学院, 兰州 730050, 中国
4)
北京科技大学冶金与生态工程学院, 北京 100083, 中国

通讯作者:
赵洪亮 E-mail: zhaohl@ustb.edu.cn

文章亮点

(1) 基于CFD结合机器学习方法建立了固液流动的快速预测模型。

(2) 提出了利用正交试验科学地选取仿真工况的方法。

(3) 构建的模型极大地缩短了矿浆电解槽内场信息的响应时间。

中文摘要

矿浆电解作为一种湿法冶金工艺，具有流程短、能耗低、过程环保等优点。然而，多槽串联的特点导致槽内工况多变、工艺参数调控复杂，已有的搅拌经验公式和颗粒悬浮特性无法满足矿浆电解生产需求。基于此，本文提出利用计算流体动力学(CFD)与机器学习相结合的方法，构建了矿浆电解槽固液悬浮过程流场和浓度场的快速预测模型。通过正交试验科学地选取计算点，在有效减少仿真工况数量的情况下建立了覆盖较为全面的训练数据集，同时也为预测模型提供合理的权重；最后结合K-最近邻算法构建了矿浆电解槽场信息预测模型。结果表明：随着正交试验中水平个数的增加，模型的预测精度显著提高。采用4因素9水平所建立的模型能够准确地预测槽内流场和浓度场信息，其中平均速度和平均固体浓度的预测回归系数分别为0.926和0.937。相较于传统CFD计算，预测流场和浓度场的响应时间从75 h缩短至20 s，解决了数值模拟应用于实际生产时存在严重滞后性的问题，从而满足实时生产调控需求。

关键词:

Research Article

Rapid prediction of flow and concentration fields in solid–liquid suspensions of slurry electrolysis tanks

+ Author Affiliations

1)
State Key Laboratory of Advanced Metallurgy, University of Science and Technology Beijing, Beijing 100083, China
2)
State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process, Beijing 102628, China
3)
School of Materials Science and Engineering, Lanzhou University of Technology, Lanzhou 730050, China
4)
School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China

Fengqin Liu is an editorial board member for this journal and was not involved in the editorial review or the decision to publish this article. The authors declare no potential conflict of interest, and the manuscript is approved by all authors for publication.

Corresponding author:
Hongliang Zhao E-mail: zhaohl@ustb.edu.cn
Received: 8 December 2023; Revised: 9 January 2024; Accepted: 11 January 2024; Available online: 12 January 2024

Abstract

Abstract

Slurry electrolysis (SE), as a hydrometallurgical process, has the characteristic of a multitank series connection, which leads to various stirring conditions and a complex solid suspension state. The computational fluid dynamics (CFD), which requires high computing resources, and a combination with machine learning was proposed to construct a rapid prediction model for the liquid flow and solid concentration fields in a SE tank. Through scientific selection of calculation samples via orthogonal experiments, a comprehensive dataset covering a wide range of conditions was established while effectively reducing the number of simulations and providing reasonable weights for each factor. Then, a prediction model of the SE tank was constructed using the K-nearest neighbor algorithm. The results show that with the increase in levels of orthogonal experiments, the prediction accuracy of the model improved remarkably. The model established with four factors and nine levels can accurately predict the flow and concentration fields, and the regression coefficients of average velocity and solid concentration were 0.926 and 0.937, respectively. Compared with traditional CFD, the response time of field information prediction in this model was reduced from 75 h to 20 s, which solves the problem of serious lag in CFD applied alone to actual production and meets real-time production control requirements.
- slurry electrolysis;
- solid–liquid suspension;
- computational fluid dynamics;
- K-nearest neighbor algorithm;
- rapid prediction

FullText(HTML)

Supplements(0)

References(25)

References

[1]	C.Y. Wang, D.F. Qiu, F. Yin, H.Y. Wang, and Y.Q. Chen, Slurry electrolysis of ocean polymetallic nodule, Trans. Nonferrous Met. Soc. China, 20(2010), No.Supplement 1, p. s60.
[2]	Y.L. Zhang, C.Y. Wang, B.Z. Ma, X.W. Jie, and P. Xing, Extracting antimony from high arsenic and gold-containing stibnite ore using slurry electrolysis, Hydrometallurgy, 186(2019), p. 284. doi: 10.1016/j.hydromet.2019.04.026
[3]	Y.J. Zhang, X.W. Yang, L.H. Deng, and G. Yao, Leaching mechanism of sulfide ores in slurry electrolysis, Trans. Nonferrous Met. Soc. China, 10(2000), No. 1, . 105.
[4]	Y.L. Zhang, D.F. Qiu, C.Y. Wang, et al., Anodic process of stibnite in slurry electrolysis: The direct collision oxidation, Chin. J. Chem. Eng., 41(2022), p. 466. doi: 10.1016/j.cjche.2021.12.011
[5]	Y.L. Zhang, Z.C. Yao, X.W. Jie, B.Z. Ma, C.Y. Wang, and Y.Q. Chen, Anodic process of stibnite in slurry electrolysis: Indirect electro-oxidation, JOM, 75(2023), No. 5, p. 1551. doi: 10.1007/s11837-022-05563-y
[6]	T.T. Lu, H. Shen, G.Y. Na, et al., CFD simulation of suspension characteristics in a stirred tank for slurry electrolysis, Metall. Mater. Trans. B, 53(2022), No. 3, p. 1747. doi: 10.1007/s11663-022-02484-8
[7]	T.T. Lu, K. Li, F.Q. Liu, et al., Numerical simulation of solid-liquid suspension in a slurry electrolysis stirred tank, Chem. Eng. Res. Des., 189(2023), p. 371. doi: 10.1016/j.cherd.2022.11.046
[8]	F.Q. Liu, T. Lu, K. Li, C.M. Xie, and H.L. Zhao, Computational fluid dynamics study on the effect of stirring parameters on solid–liquid suspension in the slurry electrolysis square tank, Adv. Powder Technol., 34(2023), No. 5, art. No. 104016. doi: 10.1016/j.apt.2023.104016
[9]	M.Q. Gu, A.J. Xu, F. Yuan, X.M. He, and Z.F. Cui, An improved CBR model using time-series data for predicting the end-point of a converter, ISIJ Int., 61(2021), No. 10, p. 2564. doi: 10.2355/isijinternational.ISIJINT-2020-687
[10]	F. He and L.Y. Zhang, Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network, J. Process. Control, 66(2018), p. 51. doi: 10.1016/j.jprocont.2018.03.005
[11]	K. Feng, A.J. Xu, D.F. He, and H.B. Wang, An improved CBR model based on mechanistic model similarity for predicting end phosphorus content in dephosphorization converter, Steel Res. Int., 89(2018), No. 6, art. No. 1800063. doi: 10.1002/srin.201800063
[12]	R.H. Zhang and J. Yang, State of the art in applications of machine learning in steelmaking process modeling, Int. J. Miner. Metall. Mater., 30(2023), No. 11, p. 2055. doi: 10.1007/s12613-023-2646-1
[13]	G.F. Pan, F.Y. Wang, C.L. Shang, et al., Advances in machine learning- and artificial intelligence-assisted material design of steels, Int. J. Miner. Metall. Mater., 30(2023), No. 6, p. 1003. doi: 10.1007/s12613-022-2595-0
[14]	Z.J. Qin, Z. Wang, Y.Q. Wang, et al., Phase prediction of Ni-base superalloys via high-throughput experiments and machine learning, Mater. Res. Lett., 9(2021), No. 1, p. 32. doi: 10.1080/21663831.2020.1815093
[15]	Z. Xia, F. Zhao, X.H. Liu, and J.X. Xie, Prediction of interface structure and properties of Cu–Al composites assisted by machine learning, Chin. J. Nonferrous Met., 33(2023), No. 1, p. 88.
[16]	C. Gebhardt, T. Trimborn, F. Weber, A. Bezold, C. Broeckmann, and M. Herty, Simplified ResNet approach for data driven prediction of microstructure-fatigue relationship, Mech. Mater., 151(2020), art. No. 103625. doi: 10.1016/j.mechmat.2020.103625
[17]	A. Marcato, G. Boccardo, and D. Marchisio, From computational fluid dynamics to structure interpretation via neural networks: An application to flow and transport in porous media, Ind. Eng. Chem. Res., 61(2022), No. 24, p. 8530. doi: 10.1021/acs.iecr.1c04760
[18]	T. Yasuda, S. Ookawara, S. Yoshikawa, and H. Matsumoto, Materials processing model-driven discovery framework for porous materials using machine learning and genetic algorithm: A focus on optimization of permeability and filtration efficiency, Chem. Eng. J., 453(2023), art. No. 139540. doi: 10.1016/j.cej.2022.139540
[19]	F. Modaresi, S. Araghinejad, and K. Ebrahimi, A comparative assessment of artificial neural network, generalized regression neural network, least-square support vector regression, and K-nearest neighbor regression for monthly streamflow forecasting in linear and nonlinear conditions, Water Resour. Manage., 32(2018), No. 1, p. 243. doi: 10.1007/s11269-017-1807-2
[20]	N.S. Altman, An introduction to kernel and nearest-neighbor nonparametric regression, Am. Stat., 46(1992), No. 3, art. No. 175. doi: 10.1080/00031305.1992.10475879
[21]	D. Panchigar, K. Kar, S. Shukla, R.M. Mathew, U. Chadha, and S.K. Selvaraj, Machine learning-based CFD simulations: A review, models, open threats, and future tactics, Neural Comput. Appl., 34(2022), No. 24, p. 21677. doi: 10.1007/s00521-022-07838-6
[22]	Y.L. Gao and F. Gao, Edited AdaBoost by weighted kNN, Neurocomputing, 73(2010), No. 16-18, p. 3079. doi: 10.1016/j.neucom.2010.06.024
[23]	S.K.A. Kamarol, M.H. Jaward, H. Kälviäinen, J. Parkkinen, and R. Parthiban, Joint facial expression recognition and intensity estimation based on weighted votes of image sequences, Pattern Recognit. Lett., 92(2017), p. 25. doi: 10.1016/j.patrec.2017.04.003
[24]	J. Mohammadpour, S. Husain, F. Salehi, and A. Lee, Machine learning regression-CFD models for the nanofluid heat transfer of a microchannel heat sink with double synthetic jets, Int. Commun. Heat Mass Transf., 130(2022), art. No. 105808. doi: 10.1016/j.icheatmasstransfer.2021.105808
[25]	X.L. Wei, B.J. Xue, and Q. Zhao, Optimization design of the stability for the plunger assembly of oil pumps based on multi-target orthogonal test design, J. Hebei Univ. Eng. Nat. Sci. Ed., 27(2010), No. 3, p. 95.