A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

doi:10.1016/j.cjche.2023.11.001

中国化学工程学报 ›› 2024, Vol. 66 ›› Issue (2): 71-83.DOI: 10.1016/j.cjche.2023.11.001

• Full Length Article • 上一篇下一篇

A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

Bo Wang¹, Han Zhou¹, Shan Jing¹, Qiang Zheng¹, Wenjie Lan², Shaowei Li^1,3

1. Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China;
2. State Key Laboratory of Heavy Oil Processing, China University of Petroleum (Beijing), Beijing 102249, China;
3. State Key Laboratory of Chemical Engineering, Tsinghua University, Beijing 100084, China

收稿日期:2023-05-09 修回日期:2023-10-30 出版日期:2024-02-28 发布日期:2024-04-20
通讯作者: Shaowei Li,E-mail:lsw@tsinghua.edu.cn
基金资助:
We gratefully acknowledge the support of the National Natural Science Foundation of China (22278234, 21776151).

A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

Bo Wang¹, Han Zhou¹, Shan Jing¹, Qiang Zheng¹, Wenjie Lan², Shaowei Li^1,3

1. Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China;
2. State Key Laboratory of Heavy Oil Processing, China University of Petroleum (Beijing), Beijing 102249, China;
3. State Key Laboratory of Chemical Engineering, Tsinghua University, Beijing 100084, China

Received:2023-05-09 Revised:2023-10-30 Online:2024-02-28 Published:2024-04-20
Contact: Shaowei Li,E-mail:lsw@tsinghua.edu.cn
Supported by:
We gratefully acknowledge the support of the National Natural Science Foundation of China (22278234, 21776151).

摘要/Abstract

摘要： An artificial neural network (ANN) method is introduced to predict drop size in two kinds of pulsed columns with small-scale data sets. After training, the deviation between calculate and experimental results are 3.8 % and 9.3 %, respectively. Through ANN model, the influence of interfacial tension and pulsation intensity on the droplet diameter has been developed. Droplet size gradually increases with the increase of interfacial tension, and decreases with the increase of pulse intensity. It can be seen that the accuracy of ANN model in predicting droplet size outside the training set range is reach the same level as the accuracy of correlation obtained based on experiments within this range. For two kinds of columns, the drop size prediction deviations of ANN model are 9.6 % and 18.5 % and the deviations in correlations are 11 % and 15 %.

关键词: Artificial neural network, Drop size, Solvent extraction, Pulsed column, Two-phase flow, Hydrodynamics

Abstract: An artificial neural network (ANN) method is introduced to predict drop size in two kinds of pulsed columns with small-scale data sets. After training, the deviation between calculate and experimental results are 3.8 % and 9.3 %, respectively. Through ANN model, the influence of interfacial tension and pulsation intensity on the droplet diameter has been developed. Droplet size gradually increases with the increase of interfacial tension, and decreases with the increase of pulse intensity. It can be seen that the accuracy of ANN model in predicting droplet size outside the training set range is reach the same level as the accuracy of correlation obtained based on experiments within this range. For two kinds of columns, the drop size prediction deviations of ANN model are 9.6 % and 18.5 % and the deviations in correlations are 11 % and 15 %.

Key words: Artificial neural network, Drop size, Solvent extraction, Pulsed column, Two-phase flow, Hydrodynamics

Bo Wang, Han Zhou, Shan Jing, Qiang Zheng, Wenjie Lan, Shaowei Li. A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets[J]. 中国化学工程学报, 2024, 66(2): 71-83.

参考文献

[1] H. Zhou, X. Yu, S. Jing, H. Zhou, W.J. Lan, S.W. Li, Measurement of droplet breakage in a pump-mixer, Chem. Eng. Sci. 195(2019)23-38.
[2] K. Gottliebsen, B. Grinbaum, D.H. Chen, G.W. Stevens, The use of pulsed perforated plate extraction column for recovery of sulphuric acid from copper tank house electrolyte bleeds, Hydrometallurgy 58(3)(2000)203-213.
[3] H.J. Bart, Extraction columns in hydrometallurgy, Hydrometallurgy 78(1-2)(2005)21-29.
[4] N.B. Wyatt, T.J. O'Hern, B. Shelden, Drop-size distributions and spatial distributions in an annular centrifugal contactor, AlChE. J. 59(6)(2013)2219-2226.
[5] S.H. Yin, K.H. Chen, C. Srinivasakannan, S.W. Li, J.W. Zhou, J.H. Peng, L.B. Zhang, Microfluidic solvent extraction of Ce (III) and Pr (III) from a chloride solution using EHEHPA (P507) in a serpentine microreactor, Hydrometallurgy 175(2018)266-272.
[6] R.L. Yadav, A.W. Patwardhan, Design aspects of pulsed sieve plate columns, Chem. Eng. J. 138(1-3)(2008)389-415.
[7] C. Korb, H.J. Bart, Solvent extraction in columns in a droplet breakage domain, Hydrometallurgy 173(2017)71-79.
[8] W. Li, Y. Wang, K.A. Mumford, K.H. Smith, G.W. Stevens, Prediction of holdup and drop size distribution in a disc-doughnut pulsed column with tenova kinetics internals for the water-Alamine 336 system, Hydrometallurgy 181(2018)82-90.
[9] A. Kumar, S. Hartland, Prediction of drop size in pulsed perforated-plate extraction columns, Chem. Eng. Commun. 44(1-6)(1986)163-182.
[10] H. Parmar, V. Pareek, C.M. Phan, G.M. Evans, Influence of jet-jet interaction on droplet size and jet instability in immiscible liquid-liquid system, Chem. Eng. Sci. 123(2015)247-254.
[11] J.Q. Liu, S.W. Li, S. Jing, Hydraulic performance of an annular pulsed disc-and-doughnut column, Solvent Extr. Ion Exch. 33(2015)385-406.
[12] D. Tsaoulidis, P. Angeli, Liquid-liquid dispersions in intensified impinging-jets cells, Chem. Eng. Sci. 171(2017)149-159.
[13] H. Yi, Y. Wang, K.H. Smith, W.Y. Fei, G.W. Stevens, Hydrodynamic performance of a pulsed solvent extraction column with novel ceramic internals:Holdup and drop size, Ind. Eng. Chem. Res. 56(4)(2017)999-1007.
[14] J.Q. Liu, S.W. Li, Y.Y. Wang, S. Jing, Extraction of uranium nitrate with 30%(v/v) tributyl phosphate in kerosene in an pilot annular pulsed disc-and-doughnut column-Part I:Hydraulic performance, Solvent Extr. Ion Exch. 35(1)(2017)19-34.
[15] A.B. Jahya, G.W. Stevens, H.R.C. Pratt, Pulsed disc-and-doughnut column performance, Solvent Extr. Ion Exch. 27(1)(2009)63-82.
[16] M. Torab-Mostaedi, A. Ghaemi, M. Asadollahzadeh, Flooding and drop size in a pulsed disc and doughnut extraction column, Chem. Eng. Res. Des. 89(12)(2011)2742-2751.
[17] R. Torkaman, J. Safdari, M. Torab-Mostaedi, M.A. Moosavian, M. Asadollahzadeh, Extraction of samarium and gadolinium from aqueous nitrate solution with D2EHPA in a pulsed disc and doughnut column, J. Taiwan Inst. Chem. Eng. 48(2015)18-25.
[18] Y. Wang, K.H. Smith, K.A. Mumford, H. Yi, L.N. Wang, G.W. Stevens, Prediction of drop size in a pulsed and non-pulsed disc and doughnut solvent extraction column, Chem. Eng. Res. Des. 109(2016)667-674.
[19] J.Q. Liu, S.W. Li, S. Jing, Scale-up study on the performance of annular pulsed disc-and-doughnut columns, Solvent Extr. Ion Exch. 34(5)(2016)485-501.
[20] J.Q. Liu, S.W. Li, S. Jing, Axial mixing and mass transfer performance of an annular pulsed disc-and-doughnut column, Solvent Extr. Ion Exch. 33(2015)592-606.
[21] A. Kumar, S. Hartland, Gravity settling in liquid/liquid dispersions, Can. J. Chem. Eng. 63(3)(1985)368-376.
[22] M. Lorenz, H. Haverland, A. Vogelphol, Fluid dynamics of pulsed sieve plate extraction columns, Chem. Eng. Technol. 13(1)(1990)411-422.
[23] E. Aufderheide, A. Vogelpohl, A convective model to interpret dispersed-phase residence time measurements in pulsed liquid/liquid extractors, Chem. Eng. Sci. 41(7)(1986)1747-1757.
[24] V.G. Lade, A.D. Pakhare, V.K. Rathod, Mass transfer studies in pulsed sieve plate extraction column for the removal of tributyl phosphate from aqueous nitric acid, Ind. Eng. Chem. Res. 53(12)(2014)4812-4820.
[25] A.E. Ferreira, S. Agarwal, R.M. Machado, M.L.F. Gameiro, S.M.C. Santos, M.T.A. Reis, M.R.C. Ismael, M.J.N. Correia, J.M.R. Carvalho, Extraction of copper from acidic leach solution with Acorga M5640 using a pulsed sieve plate column, Hydrometallurgy 104(1)(2010)66-75.
[26] M.R. Usman, H. Sattar, S.N. Hussain, H. Muhammad, A. Asghar, W. Afzal, Drop size in a liquid pulsed sieve-plate extraction column, Braz. J. Chem. Eng. 26(4)(2009)677-683.
[27] A. Bahmanyar, N. Khoobi, M.R. Mozdianfard, H. Bahmanyar, The influence of nanoparticles on hydrodynamic characteristics and mass transfer performance in a pulsed liquid-liquid extraction column, Chem. Eng. Process. 50(11-12)(2011)1198-1206.
[28] K. Sreenivasulu, D. Venkatanarasaiah, Y.B.G. Varma, Drop size distributions in liquid pulsed columns, Bioprocess Eng. 17(3)(1997)189-195.
[29] M.H.S. Segler, M. Preuss, M.P. Waller, Planning chemical syntheses with deep neural networks and symbolic AI, Nature 555(7698)(2018)604-610.
[30] H. Xiao, J.L. Wu, J.X. Wang, R. Sun, C.J. Roy, Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations:A data-driven, physics-informed Bayesian approach, J. Comput. Phys. 324(2016)115-136.
[31] X. Li, L. Peng, Y. Hu, J. Shao, T.H. Chi, Deep learning architecture for air quality predictions, Environ. Sci. Pollut. Res. 23(22)(2016)22408-22417.
[32] P. Raccuglia, K.C. Elbert, P.D.F. Adler, C. Falk, M.B. Wenny, A. Mollo, M. Zeller, S.A. Friedler, J. Schrier, A.J. Norquist, Machine-learning-assisted materials discovery using failed experiments, Nature 533(7601)(2016)73-76.
[33] D.A.C. Beck, J.M. Carothers, V.R. Subramanian, J. Pfaendtner, Data science:Accelerating innovation and discovery in chemical engineering, AIChE. J. 62(5)(2016)1402-1416.
[34] L. Tian, Z.F. Xu, L.J. Chen, Y. Liu, T.A. Zhang, Study on oxygen gas holdup and kinetics using various types of paddles during marmatite leaching process, Hydrometallurgy 180(2018)158-171.
[35] S. Azizi, M.M. Awad, E. Ahmadloo, Prediction of water holdup in vertical and inclined oil-water two-phase flow using artificial neural network, Int. J. Multiph. Flow 80(2016)181-187.
[36] A. Behkish, R. Lemoine, L. Sehabiague, R. Oukaci, B.I. Morsi, Prediction of the gas holdup in industrial-scale bubble columns and slurry bubble column reactors using back-propagation neural networks, Int. J. Chem. React. Eng. 3(1)(2005) A53.
[37] A. Shaikh, M. Al-Dahhan, Development of an artificial neural network correlation for prediction of overall gas holdup in bubble column reactors, Chem. Eng. Process. 42(8-9)(2003)599-610.
[38] A.B. Gandhi, J.B. Joshi, Unified correlation for overall gas hold-up in bubble column reactors for various gas-liquid systems using hybrid genetic algorithm-support vector regression technique, Can. J. Chem. Eng. 88(5)(2010)758-776.
[39] A.B. Gandhi, J.B. Joshi, V.K. Jayaraman, B.D. Kulkarni, Development of support vector regression (SVR)-based correlation for prediction of overall gas hold-up in bubble column reactors for various gas-liquid systems, Chem. Eng. Sci. 62(24)(2007)7078-7089.
[40] R. Lemoine, B.I. Morsi, An algorithm for predicting the hydrodynamic and mass transfer parameters in agitated reactors, Chem. Eng. J. 114(1-3)(2005)9-31.
[41] S. Bansal, S. Roy, F. Larachi, Support vector regression models for trickle bed reactors, Chem. Eng. J. 207-208(2012)822-831.
[42] A.B. Gandhi, P.P. Gupta, J.B. Joshi, V.K. Jayaraman, B.D. Kulkarni, Development of unified correlations for volumetric mass-transfer coefficient and effective interfacial area in bubble column reactors for various gas-liquid systems using support vector regression, Ind. Eng. Chem. Res. 48(9)(2009)4216-4236.
[43] A.B. Gandhi, J.B. Joshi, Estimation of heat transfer coefficient in bubble column reactors using support vector regression, Chem. Eng. J. 160(1)(2010)302-310.
[44] K. Sivaramakrishnan, J.J. Nie, A. de Klerk, V. Prasad, Least squares-support vector regression for determining product concentrations in acid-catalyzed propylene oligomerization, Ind. Eng. Chem. Res. 57(39)(2018)13156-13176.
[45] S. Zaidi, Development of support vector regression (SVR)-based model for prediction of circulation rate in a vertical tube thermosiphon reboiler, Chem. Eng. Sci. 69(1)(2012)514-521.
[46] M. Izadi, M. Rahimi, R. Beigzadeh, Evaluation of micromixing in helically coiled microreactors using artificial intelligence approaches, Chem. Eng. J. 356(2019)570-579.
[47] K. Korkerd, C Soanuch, D. Gidaspow, P. Piumsomboon, B. Chalermsinsuwan, Artificial neural network model for predicting minimum fluidization velocity and maximum pressure drop of gas fluidized bed with different particle size distributions, S. Afr. J. Chem. Eng. 37(2021)61-73.
[48] N. Bar, M.N. Biswas, S.K. Das, Prediction of pressure drop using artificial neural network for gas non-Newtonian liquid flow through piping components, Ind. Eng. Chem. Res. 49(19)(2010)9423-9429.
[49] S.K. Jana, A.B. Biswas, S.K. Das, Pressure drop in tapered bubble columns using non-Newtonian pseudoplastic liquid-Experimental and ANN prediction, Can. J. Chem. Eng. 92(3)(2014)578-584.
[50] H. Sharma, G. Das, A.N. Samanta, ANN-based prediction of two-phase gas-liquid flow patterns in a circular conduit, AIChE. J. 52(9)(2006)3018-3028.
[51] A. Dasari, A.B. Desamala, A.K. Dasmahapatra, T.K. Mandal, Experimental studies and probabilistic neural network prediction on flow pattern of viscous oil-water flow through a circular horizontal pipe, Ind. Eng. Chem. Res. 52(23)(2013)7975-7985.
[52] J. Brockkotter, M. Cielanga, B. Weber, A. Jupke, Prediction and characterization of flooding in pulsed sieve plate extraction columns using data-driven models, Ind. Eng. Chem. Res. 59(44)(2020)19726-19735.
[53] H.B. Zhong, Z.N. Sun, J. Zhu, C. Zhang, Prediction of solid holdup in a gas-solid circulating fluidized bed riser by artificial neural networks, Ind. Eng. Chem. Res. 60(8)(2021)3452-3462.
[54] L. Xie, G.M. Zhou, D.D. Wang, H.F. Wang, C.W. Jiang, Machine learning and data-driven modeling to discover the bed expansion ratio correlation for gas-liquid-solid three-phase flows, Ind. Eng. Chem. Res. 62(1)(2023)789-800.
[55] L.Q. Lu, X. Gao, J.F. Dietiker, M. Shahnam, W.A. Rogers, Development of a filtered CFD-DEM drag model with multiscale markers using an artificial neural network and nonlinear regression, Ind. Eng. Chem. Res. 61(1)(2022)882-893.
[56] C.Z. Du, C.X. Han, Z. Yang, H. Wu, H. Luo, L. Niedzwiecki, B.N. Lu, W. Wang, Multiscale CFD simulation of an industrial diameter-transformed fluidized bed reactor with artificial neural network analysis of EMMS drag markers, Ind. Eng. Chem. Res. 61(24)(2022)8566-8580.
[57] L.T. Zhu, X.Z. Chen, B. Ouyang, W.C. Yan, H. Lei, Z. Chen, Z.H. Luo, Review of machine learning for hydrodynamics, transport, and reactions in multiphase flows and reactors, Ind. Eng. Chem. Res. 61(28)(2022)9901-9949.
[58] S.S. Joshi, V.H. Dalvi, V.S. Vitankar, A.J. Joshi, J.B. Joshi, Novel correlation for critical speed for solid suspension in stirred tanks developed using machine learning models trained on literature data, Ind. Eng. Chem. Res. 62(22)(2023)8954-8971.
[59] S.R. Hazare, S.V. Vala, C.S. Patil, A.J. Joshi, J.B. Joshi, V.S. Vitankar, A.W. Patwardhan, Correlating interfacial area and volumetric mass transfer coefficient in bubble column with the help of machine learning methods, Ind. Eng. Chem. Res. 62(5)(2023)2104-2123.
[60] S. Saraswathi K, H. Bhosale, P. Ovhal, N. Parlikkad Rajan, J.K. Valadi, Random forest and autoencoder data-driven models for prediction of dispersed-phase holdup and drop size in rotating disc contactors, Ind. Eng. Chem. Res. 60(1)(2021)425-435.
[61] Z.N. Su, Y. Wang, B.R. Tan, Q.Z. Cheng, X.F. Duan, D.B. Xu, L.L. Tian, T. Qi, Performance prediction of disc and doughnut extraction columns using Bayes optimization algorithm-based machine learning models, Chem. Eng. Process. Process. Intensif. 183(2023)109248.
[62] Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521(7553)(2015)436-444.
[63] R.E. Fan, P.H. Chen, C.J. Lin, Working set selection using second order information for training support vector machines, J Mach Learn. Res 6(2005)1889-1918.
[64] M. Arabloo, H. Ziaee, M. Lee, A. Bahadori, Prediction of the properties of brines using least squares support vector machine (LS-SVM) computational strategy, J. Taiwan Inst. Chem. Eng. 50(2015)123-130.
[65] L.T. Zhu, J.X. Tang, Z.H. Luo, Machine learning to assist filtered two-fluid model development for dense gas-particle flows, AlChE. J. 66(6)(2020) e16973.
[66] H. Zhou, J.J. Yang, S. Jing, W.J. Lan, Q.A. Zheng, S.W. Li, Influence of dispersed-phase viscosity on droplet breakup in a continuous pump-mixer, Ind. Eng. Chem. Res. 58(51)(2019)23458-23467.
[67] A. Kumar, S. Hartland, Unified correlations for the prediction of drop size in liquid-liquid extraction columns, Ind. Eng. Chem. Res. 35(8)(1996)2682-2695.
[68] A. Kumar, S. Hartland, A unified correlation for the prediction of dispersed-phase hold-up in liquid-liquid extraction columns, Ind. Eng. Chem. Res. 34(11)(1995)3925-3940.

A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Wenbin Li, Feng Wu, Liuyun Xu, Jipeng Sun, Xiaoxun Ma. Numerical and experimental study on the particle erosion and gas–particle hydrodynamics in an integral multi-jet swirling spout-fluidized bed[J]. 中国化学工程学报, 2023, 61(9): 90-101.
[2]	Xuejing He, Zhenlin Li, Ji Wang, Hai Yu. Effects of tube cross-sectional shapes on flow pattern, liquid film and heat transfer of n-pentane across tube bundles[J]. 中国化学工程学报, 2023, 60(8): 16-25.
[3]	Yunchang Fan, Chunyan Zhu, Sheli Zhang, Lei Zhang, Qiang Wang, Feng Wang. Efficient and selective extraction of sinomenine by deep eutectic solvents[J]. 中国化学工程学报, 2023, 57(5): 109-117.
[4]	Ming Chen, Huiyan Jiao, Jun Li, Zhibin Wang, Feng He, Yang Jin. Liquid–liquid two-phase flow in a wire-embedded concentric microchannel: Flow pattern and mass transfer performance[J]. 中国化学工程学报, 2023, 56(4): 281-289.
[5]	Tian Zhang, Qingshan Huang, Shujun Geng, Aqiang Chen, Yan Liu, Haidong Zhang. Impacts of solid physical properties on the performances of a slurry external airlift loop reactor integrating mixing and separation[J]. 中国化学工程学报, 2023, 55(3): 1-12.
[6]	Chunxin Fan, Zini Guo, Jianhong Luo. Study on an improved rotating microchannel separator in the intensification for demulsification and separation process[J]. 中国化学工程学报, 2023, 55(3): 181-191.
[7]	Kun Wang, Guoquan Zhang, Linye Li, Yuzhang Li, Xiangxin Liao, Pu Cheng, Mingzhi Luo. Separation of lithium and nickel using ionic liquids and tributyl phosphate[J]. 中国化学工程学报, 2023, 63(11): 63-70.
[8]	Mohammad Amin Moradkhani, Seyyed Hossein Hosseini, Mengjie Song. Comprehensive modeling of frictional pressure drop during carbon dioxide two-phase flow inside channels using intelligent and conventional methods[J]. 中国化学工程学报, 2023, 63(11): 108-119.
[9]	Zewen Chen, Yongjun Wu, Jian Wang, Peicheng Luo. Study on the solid–liquid suspension behavior in a tank stirred by the long-short blades impeller[J]. 中国化学工程学报, 2022, 47(7): 79-88.
[10]	Dengke Pang, Zhihong Zhang, Yongquan Zhou, Zhenhai Fu, Quan Li, Yongming Zhang, Guangguo Wang, Zhuanfang Jing. The process and mechanism for cesium and rubidium extraction with saponified 4-tert-butyl-2-(α-methylbenzyl) phenol[J]. 中国化学工程学报, 2022, 46(6): 31-39.
[11]	Youfang Ma, Youfu Ma, Junfu Lyu, Weiye Liu. Experimental study on prediction model of wet gas pressure drop across single-orifice plate in horizontal pipes in the low gas phase Froude number region[J]. 中国化学工程学报, 2022, 46(6): 63-72.
[12]	Shenglin Yan, Yan Zhang, Chong Peng, Xiaoyong Yang, Yuan Huang, Zhishan Bai, Xiao Xu. Oil droplet movement and micro-flow characteristics during interaction process between gas bubble and oil droplet in flotation[J]. 中国化学工程学报, 2022, 45(5): 229-237.
[13]	Shabnam Ghahremanian, Abbas Abbassi, Zohreh Mansoori, Davood Toghraie. Effect of copper nanoparticles on thermal behavior of two-phase argon-copper nanofluid flow in rough nanochannels with focusing on the interface properties and heat transfer using molecular dynamics simulation[J]. 中国化学工程学报, 2022, 42(2): 344-350.
[14]	Xiaoyi Chen, Danyang Song, Dong Zhang, Xiaogang Jin, Xiang Ling, Dongren Liu. Flow characteristics simulation of spiral coil reactor used in the thermochemical energy storage system[J]. 中国化学工程学报, 2022, 42(2): 364-379.
[15]	Wen-Cong Chen, Ya-Wei Fan, Liang-Liang Zhang, Bao-Chang Sun, Yong Luo, Hai-Kui Zou, Guang-Wen Chu, Jian-Feng Chen. Computational fluid dynamic simulation of gas-liquid flow in rotating packed bed: A review[J]. 中国化学工程学报, 2022, 41(1): 85-108.