基于神经网络和CFD的规整填料塔流体力学计算

摘要提出一种结合计算流体力学(CFD)和BP (Back Propagation)人工神经网络的多尺度计算方法,计算规整填料塔上的流体力学行为。根据最小特征单元实际尺寸建立小尺度三维CFD模型,研究了填料塔单气相和气液两相流体流动分布方式,弥补了在研究塔壁单元和层间转换单元产生压降方面的缺陷。建立了结点网络模型,计算全塔的流体分布等宏观信息。以CFD计算收集到的数据集训练了2组神经网络模型,分别以结点流量为输入计算干塔压降和持液量。计算结果与相关实验数据比较,干塔压降计算模型的平均相对偏差为8.63%,最大相对偏差为14.02%。持液量计算模型的平均相对偏差约为9.63%,最大相对偏差为13.97%。这表明该训练好的人工神经网络模型具备较好的预测能力,结果较为可信。

	Service

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	Email Alert
	RSS
	作者相关文章
	李邢
	曾爱武

关键词：规整填料计算流体力学 BP神经网络干塔压降持液量

Abstract： A multi-scale calculation method combining computational fluid dynamics (CFD) and back propagation neural network (BPNN) was proposed to calculate the hydrodynamic behavior of structured packing column. According to the actual size of the representative elementary units, a small-scale 3D CFD model was established, and the flow distribution of single gas phase and gas-liquid two-phase fluid in the packing column was studied, which made up for the defects in the pressure drop of the column wall unit and the interlayer conversion unit. A node network model was established to calculate the macroscopic information such as the fluid distribution of the whole column. Two neural network models were trained with the data set collected by CFD calculation, and the dry pressure drop and liquid holdup were calculated respectively with the node flow as input neuron. Compared with the relevant experimental data, the average relative deviation of the prediction model for dry pressure drop was 8.63% and the maximum relative deviation was 14.2%. The average relative deviation and maximum relative deviation of the prediction model for liquid holdup were 9.63% and 13.97%, respectively. The trained artificial neural network model was proved to be prospective to determinate dry pressure drops and liquid holdup of structured packing columns.

Keywords： structured packing columns computational fluid dynamic back propagation neural network dry pressure drops liquid holdup

Received 2022-04-11;

Corresponding Authors: 曾爱武,副研究员,awzeng@tju.edu.cn Email: awzeng@tju.edu.cn

About author: 李邢(1996—),女,硕士研究生,现从事规整填料塔流体力学研究。

引用本文:

李邢, 曾爱武.基于神经网络和CFD的规整填料塔流体力学计算[J]. 化学工业与工程, 2025,42(1): 130-137

LI Xing, ZENG Aiwu.Hydrodynamic calculation of structured packing column based on neural network and CFD[J]. Chemcial Industry and Engineering, 2025,42(1): 130-137

[1] SPIEGEL L, MEIER W. Distillation columns with structured packings in the next decade[J]. Chemical Engineering Research and Design, 2003, 81(1): 39-47
[2] OLUJI?, KAIBEL B, JANSEN H, et al. Fractionation research Inc. test data and modeling of a high-performance structured packing[J]. Industrial & Engineering Chemistry Research, 2013, 52(13): 4888-4894
[3] AMINI Y, KARIMI-SABET J, ESFAHANY M N. Experimental and numerical simulation of dry pressure drop in high-capacity structured packings[J]. Chemical Engineering & Technology, 2016, 39(6): 1161-1170
[4] WEN X, AKHTER S, AFACAN A, et al. CFD modeling of columns equipped with structured packings: I. Approach based on detailed packing geometry[J]. Asia-Pacific Journal of Chemical Engineering, 2007, 2(4): 336-344
[5] SAID W, NEMER M, CLODIC D. Modeling of dry pressure drop for fully developed gas flow in structured packing using CFD simulations[J]. Chemical Engineering Science, 2011, 66(10): 2107-2117
[6] SINGH R K, GALVIN J E, SUN X. Multiphase flow studies for microscale hydrodynamics in the structured packed column[J]. Chemical Engineering Journal, 2018, 353: 949-963
[7] LU X, XIE P, INGHAM D B, et al. A porous media model for CFD simulations of gas-liquid two-phase flow in rotating packed beds[J]. Chemical Engineering Science, 2018, 189: 123-134
[8] 徐崇嗣, 楼建中, 姜庆泉. 金属板波纹填料液流分布的研究[J]. 化工学报, 1986, 37(4): 402-411 XU Congsi, LOU Jianzhong, JIANG Qingquan. Liquid distribution for metallic corrugated plate packings[J]. Journal of Chemical Industry and Engineering, 1986, 37(4): 402-411(in Chinese)
[9] 裘俊红, 陈国标, 计建炳. 波纹板规整填料塔液体分布[J]. 化工学报, 2003, 54(5): 646-652 QIU Junhong, CHEN Guobiao, JI Jianbing. Liquid distribution in corrugated sheet structured packed column[J]. CIESC Journal, 2003, 54(5): 646-652(in Chinese)
[10] AROONWILAS A, CHAKMA A, TONTIWACHWUTHIKUL P, et al. Mathematical modelling of mass-transfer and hydrodynamics in CO₂ absorbers packed with structured packings[J]. Chemical Engineering Science, 2003, 58(17): 4037-4053
[11] AROONWILAS A, TONTIWACHWUTHIKUL P. Mechanistic model for prediction of structured packing mass transfer performance in CO₂ absorption with chemical reactions[J]. Chemical Engineering Science, 2000, 55(18): 3651-3663
[12] PETRE C F, LARACHI F, ILIUTA I, et al. Pressure drop through structured packings: Breakdown into the contributing mechanisms by CFD modeling[J]. Chemical Engineering Science, 2003, 58(1): 163-177
[13] LARACHI F, PETRE C F, ILIUTA I, et al. Tailoring the pressure drop of structured packings through CFD simulations[J]. Chemical Engineering and Processing: Process Intensification, 2003, 42(7): 535-541
[14] RAYNAL L, ROYON-LEBEAUD A. A multi-scale approach for CFD calculations of gas-liquid flow within large size column equipped with structured packing[J]. Chemical Engineering Science, 2007, 62(24): 7196-7204
[15] AMINI Y, NASR ESFAHANY M. CFD simulation of the structured packings: A review[J]. Separation Science and Technology, 2019, 54(15): 2536-2554
[16] CHOUDHURY D. Introduction to the renormalization group method and turbulence modeling[M]. Fluent Incorporated, 1973
[17] RAYNAL L, BOYER C, BALLAGUET J P. Liquid holdup and pressure drop determination in structured packing with CFD simulations[J]. The Canadian Journal of Chemical Engineering, 2004, 82(5): 871-879
[18] HIRT C W, NICHOLS B D. Volume of fluid (VOF) method for the dynamics of free boundaries[J]. Journal of Computational Physics, 1981, 39(1): 201-225
[19] BRACKBILL J U, KOTHE D B, ZEMACH C. A continuum method for modeling surface tension[J]. Journal of Computational Physics, 1992, 100(2): 335-354
[20] SHARMA R, SINGH K, SINGHAL D, et al. Neural network applications for detecting process faults in packed towers[J]. Chemical Engineering and Processing: Process Intensification, 2004, 43(7): 841-847
[21] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536
[22] KHOSRAVI NIKOU M R, EHSANI M R. Turbulence models application on CFD simulation of hydrodynamics, heat and mass transfer in a structured packing[J]. International Communications in Heat and Mass Transfer, 2008, 35(9): 1211-1219
[23] 谷芳, 刘春江, 袁希钢, 等. 板波纹规整填料液相分布模型[J]. 天津大学学报, 2005, 38(7): 586-591 GU Fang, LIU Chunjiang, YUAN Xigang, et al. Liquid distribution model for sheet corrugated structured packing[J]. Journal of Tianjin University, 2005, 38(7): 586-591(in Chinese)
[24] SUN B, HE L, LIU B, et al. A new multi-scale model based on CFD and macroscopic calculation for corrugated structured packing column[J]. AIChE Journal, 2013, 59(8): 3119-3130