Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns

Wang Peng; Yuan Xing; Wang Kehan; Xu Shiji; Xue Jiaxing; Wang Huan; Wu Xiuhua; Zhao Hongkang; Li Qunsheng

doi:null

Your Location：

Home >

Browse articles >

Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns

Updated：2026-09-17

- Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns
- Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns
- 中国化学工程学报（英文） 2026年95卷第7期页码：10-22
- Affiliations：
  
  State Key Laboratory of Chemical Resource Engineering, Beijing University of Chemical Technology, Beijing 100029, China
  Engineering Research Center of Preparation Technology of Ultra-Pure Chemicals for Integrated Circuits, Ministry of Education, Beijing University of Chemical Technology, Beijing 100029, China
  No.7 Research & Design Institute Co., Ltd., China National Nuclear Corporation, Taiyuan 030032, China
  Uranium Purification and Conversion Engineering and Technology Research Center, China National Nuclear Corporation, Taiyuan 030032, China
- Author bio：
  
  *Corresponding authors. State Key Laboratory of Chemical Resource Engineering, Beijing University of Chemical Technology, Beijing 100029, China.E-mail addresses:zhaohk@mail.buct.edu.cn(H. Zhao)
  *Corresponding authors. State Key Laboratory of Chemical Resource Engineering, Beijing University of Chemical Technology, Beijing 100029, China.E-mail addresses:liqs@mail.buct.edu.cn(Q. Li).
- Funds：
  
  the National Natural Science Foundation of China(U2267226)
- DOI：
  中图分类号：
- 收稿：2025-11-30，
  
  修回：2026-01-11，
  
  录用：2026-01-16，
  
  网络首发：2026-04-08，
  
  纸质出版：2026-07
- Accepted：
Scan QR Code
Wang Peng, Yuan Xing, Wang Kehan, 等. Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns[J]. 中国化学工程学报（英文）, 2026,95(7):10-22.

Wang Peng, Yuan Xing, Wang Kehan, et al. Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns[J]. Chinese Journal of Chemical Engineering, 2026, 95(7): 10-22.
Wang Peng, Yuan Xing, Wang Kehan, 等. Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns[J]. 中国化学工程学报（英文）, 2026,95(7):10-22. DOI：

Wang Peng, Yuan Xing, Wang Kehan, et al. Interpretable machine learning-based prediction of hydrodynamic performance of divided fixed-valve tray in distillation columns[J]. Chinese Journal of Chemical Engineering, 2026, 95(7): 10-22. DOI：

摘要

Abstract

Accurate prediction of tray hydrodynamics is essential for the design and optimization of modern distillation equipment. Conventional empirical correlations often show limited generalizability across diverse operating conditions

restricting their practical applicability. In this study

a data-driven modeling (DDM) framework integrated with Interpretable machine learning (ML) was developed to predict the hydrodynamic characteristics of a divide

d fixed-valve tray

including wet pressure drop

clear liquid height

weeping rate

and entrainment rate. A total of 760 experimental data points were obtained from cold-model experiments. Four machine learning algorithms―Random Forest

Extreme Gradient Boosting

Support Vector Regression

and a shallow Multilayer Perceptron―were trained and compared. Model performance was evaluated using the coefficient of determination (

)

root mean square error (RMSE)

and a composite

-based index (

com

). Among these

the SVR model achieved the highest predictive accuracy

with

com

values of 0.9750 and 0.9834 for the test and extension sets

respectively. Building upon the best-performing SVR model

an expanded feature set was constructed using physically informed transformations of the orifice kinetic energy factor and overflow strength. Pearson correlation and SHAP analyses were applied to quantify each feature's contribution

revealing the dominant hydrodynamic drivers and clarifying their positive or negative influences on tray behavior. The integrated modeling and interpretability framework not only enhances predictive reliability but also provides actionable insight for guiding tray design and operational optimization.

关键词

Keywords

references

H.K. Zhao, Q.S. Li, G.Q. Yu, C.N. Dai, Z.G. Lei, Performance analysis and quantitative design of a flow-guiding sieve tray by computational fluid dynamics, AIChE J. 65 (5) (2019) e16563.

M. Tang, S.F. Zhang, D.W. Wang, Y. Liu, L.S. Wang, C. Liu, Experimental study and modeling development of pressure drop in concurrent gas-liquid columns with a tridimensional rotational flow sieve tray, Chem. Eng. Sci. 191 (2018) 383—397.

F. Yan, D.W. Wang, Y. Liu, R.J. Wang, B.S. Hu, S.F. Zhang, W. Zhang, M. Tang, Experimental and simulated studies on the distribution law of rotational—perforated fluid in tridimensional rotational flow sieve tray, Chem. Eng. Sci. 286 (2024) 119658.

M. Tang, S.F. Zhang, D.W. Wang, Y. Liu, Y.S. zhang, L.S. Wang, C. Liu, CFD simulation of gas flow field distribution and design optimization of the tridimensional rotational flow sieve tray with different structural parameters, Chem. Eng. Sci. 201 (2019) 34—49.

L.H. Zhang, Z.J. Li, N. Yang, B. Jiang, H.F. Cong, Z.H. Zhang, Hydrodynamics and mass transfer performance of vapor—liquid flow of orthogonal wave tray column, J. Taiwan Inst. Chem. Eng. 63 (2016) 6—16.

X. Gao, X.G. Li, X. Liu, H. Li, Z.M. Yang, J.S. Zhang, A novel potential application of SiC ceramic foam material to distillation: foam monolithic tray, Chem. Eng. Sci. 135 (2015) 489—500.

J. Na, H. Li, X. Liu, X.X. Ou, X.L. Fan, X. Gao, Hydrodynamic and mass transfer correlations for SiC ceramic foam monolithic trays used in distillation column, J. Chem. Technol. Biotechnol. 98 (11) (2023) 2754—2762.

S. Abbasnia, Z. Nasri, V. Shafieyoun, M. Golzarijalal, Nye tray vs sieve tray: a comparison based on computational fluid dynamics and tray efficiency, Can. J. Chem. Eng. 99 (S1) (2021) S681—S692.

S. Abbasnia, Q.J. Yu, Z. Nasri, A. Khojasteh, Nye tray versus sieve tray:experimental study on hydrodynamic parameters, Chem. Eng. Technol. 45 (1) (2022) 110—118.

H.F. Cong, X.G. Li, Z.J. Li, H. Li, X. Gao, Combination of spiral nozzle and column tray leading to a new direction on the distillation equipment innovation, Sep. Purif. Technol. 158 (2016) 293—301.

N.V. Deryagina, N.A. Voinov, D.A. Zemtsov, A.V. Bogatkova, Hydrodynamics of the vortex tray, Therm. Sci. Eng. Prog. 18 (2020) 100524.

N.A. Voinov, D.A. Zemtsov, A.V. Bogatkova, N.V. Deryagina, Vortex tray for adiabatic and nonadiabatic fractionation, Chem. Petrol. Eng. 57 (3) (2021) 220—226.

R. Wang, J.L. Tao, Y.L. Ling, F. Wei, J.D. Liu, Total spray tray (TST) for distillation columns: a new generation tray with lower pressure drop, Chem. Ind. Chem. Eng. Q. 23 (4) (2017) 523—527.

N.A. Kotschering, W.M. Oleski, W.W. Dilman, Investigation of dualflow tray behavior under distillation conditions, Khim. Prom-st. (St. Petersburg, Russ. Fed.) 7 (1960) 591—593.

Z.P. Xu, A. Afacan, K.T. Chuang, Efficiency of dualflow tray s in distillation, Can. J. Chem. Eng. 72 (4) (1994) 607—613.

J.J. Zhang, Y.F. Wang, G.S. Yu, X.J. Mao, F.C. Wang, Experimental study of two phase flow characteristics on the dual-flow tray, Chem. Eng. Res. Des. 102 (2015) 90—99.

H.Z. Kister, J.R. Haas, Entrainment from sieve trays in the froth regime, Ind. Eng. Chem. Res. 27 (12) (1988) 2331—2341.

D.L. Bennett, A.S. Kao, L.W. Wong, A mechanistic analysis of sieve tray froth height and entrainment, AIChE. J. 41 (9) (1995) 2067—2082.

E.C. Uys, C.E. Schwarz, A.J. Burger, J.H. Knoetze, New froth behaviour observations and comparison of experimental sieve tray entrainment data with existing correlations, Chem. Eng. Res. Des. 90 (12) (2012) 2072—2085.

W.X. Zhang, R.B.H. Tan, A model for bubble formation and weeping at a submerged orifice with liquid cross-flow, Chem. Eng. Sci. 58 (2) (2003) 287—295.

W.X. Zhang, R.B.H. Tan, A model for bubble formation and weeping at a submerged orifice, Chem. Eng. Sci. 55 (24) (2000) 6243—6250.

A.R.C. Souza, M.J. Bagajewicz, A.L.H. Costa, Globally optimal distillation tray design using a mathematical programming approach, Chem. Eng. Res. Des. 180 (2022) 1—12.

W.C. Chen, Y.W. Fan, L.L. Zhang, B.C. Sun, Y. Luo, H.K. Zou, G.W. Chu, J.F. Chen, Computational fluid dynamic simulation of gas-liquid flow in rotating packed bed: a review, Chin. J. Chem. Eng. 41 (2022) 85—108.

Z. Li, Y.C. Xia, J. Long, C.S. Liu, L.F. Zhang, Multi-scale feature fused stacked autoencoder and its application for soft sensor modeling, Chin. J. Chem. Eng. 81 (2025) 241—254.

T. Hu, L. Qin, L.Y. Zhou, X.F. Zheng, L.T. Zhu, Analysis and optimization of methanol production and temperature gradient in CO 2 hydrogenation fixed bed reactors using CFD and Bayesian optimization, Chem. Eng. Sci. 321 (2026) 123030.

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.

Z. Wang, R.C. He, J. Long, A systematic data-driven modelling framework for nonlinear distillation processes incorporating data intervals clustering and new integrated learning algorithm, Chin. J. Chem. Eng. 81 (2025) 182—199.

K.X. Bi, T. Qiu, An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method, Chin. J. Chem. Eng. 27 (8) (2019) 1888—1894.

E. Soroush, S. Shahsavari, M. Mesbah, M. Rezakazemi, Z.E. Zhang, A robust predictive tool for estimating CO 2 solubility in potassium based amino acid salt solutions, Chin. J. Chem. Eng. 26 (4) (2018) 740—746.

X.K. Liu, Q.H. Qiu, B.X. Chen, Y. Shi, L.Q. Gu, X.G. Zhou, X.Z. Duan, CFD-ML integrated multi-objective optimization for n -butane partial oxidation reactor, Chin. J. Chem. Eng. 88 (2025) 53—64.

X.P. Xu, T. Zhang, Z.M. Mu, Y.L. Ma, M.Y. Liu, Application of wavelet neural network with chaos theory for enhanced forecasting of pressure drop signals in vapor- liquid- solid fluidized bed evaporator, Chin. J. Chem. Eng. 78 (2025) 67—81.

X. Zhou, C. Liu, Z.B. Zhang, X.R. Song, H.Y. Luo, W.T. Zhang, L.Y. Wu, H. Zhao, Y. B. Liu, X.B. Chen, H. Yan, C.H. Yang, Hybrid modelling incorporating reaction and mechanistic data for accelerating the development of isooctanol oxidation, Chin. J. Chem. Eng. 80 (2025) 166—183.

S.K. Lahiri, K.C. Ghanta, Prediction of pressure drop of slurry flow in pipeline by hybrid support vector regression and genetic algorithm model, Chin. J. Chem. Eng. 16 (6) (2008) 841—848.

F.F. Chen, Z.Y. Xiao, Z.F. Luo, P. Jiang, J.J. Chen, Y.H. Ji, J.H. Zhu, X.H. Lu, L.W. Mu, Prediction of mass transfer performance in gas-liquid stirred bioreactor using machine learning, Chin. J. Chem. Eng. 84 (2025) 211—226.

Y.P. Luo, W.Y. Wang, Y.Y. Zhang, M.X. Chen, P. Shao, A transformer-based model for predicting and analyzing light olefin yields in methanol-to-olefins process, Chin. J. Chem. Eng. 83 (2025) 266—276.

D.L. Bennett, R. Agrawal, P.J. Cook, New pressure drop correlation for sieve tray distillation columns, AIChE. J. 29 (3) (1983) 434—442.

P. Yan, X.G. Li, H. Li, X. Gao, Hydrodynamics and flow mechanism of foam column trays: contact angle effect, Chem. Eng. Sci. 176 (2018) 220—232.

H. Dhulesia, Clear liquid height on sieve and valve trays, Chem. Eng. Res. Des. 62 (1984) 321—326.

V. Vishwakarma, S.A. Haq, E. Schleicher, M. Schubert, U. Hampel, Experimental analysis of the hydrodynamic performance of an industrial-scale cross-flow sieve tray, Chem. Eng. Res. Des. 174 (2021) 294—306.

S. Marchini, V. Vishwakarma, M. Schubert, E. Brunazzi, U. Hampel, Effects of non-uniform weeping distributions on tray and point efficiencies, Results Eng. 19 (2023) 101238.

A. Zarei, S.H. Hosseini, R. Rahimi, CFD and experimental studies of liquid weeping in the circular sieve tray columns, Chem. Eng. Res. Des. 91 (12) (2013) 2333—2345.

R. Cao, Y. He, H.M. Guo, Y.S. Liu, Entrainment performance and model of multidowncomer sieve trays, Ind. Eng. Chem. Res. 56 (23) (2017) 6755—6763.

L.T. Zhu, B. Ouyang, H. Lei, Z.H. Luo, Conventional and data-driven modeling of filtered drag, heat transfer, and reaction rate in gas—particle flows, AIChE. J. 67 (8) (2021) e17299.

D.K. Le, J.Y. Yoon, A hybrid CFD—deep learning methodology for improving the accuracy of pressure drop prediction in cyclone separators, Chem. Eng. Res. Des. 190 (2023) 296—311.

Q.C. Yang, R.J. Bao, D.W. Rong, J.X. Xiao, J.L. Zhou, L. Zhao, D.W. Zhang, Interpretable machine learning for a ccelerating reverse design and optimizing CO 2 methanation catalysts with high activity at low temperatures, Ind. Eng. Chem. Res. 63 (33) (2024) 14727—14747.

T. Akiba, S. Sano, T. Yanase, T. Ohta, M. Koyama, Optuna: a next-generation hyperparameter optimization framework, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage AK USA. ACM, 2019, pp.2623—2631.

D.L. Bennett, R. Agrawal, P.J. Cook, New pressure drop correlation for sieve tray distillation columns, AIChE. J. 29 (3) (1983) 434—442.

C.J. Colwell, Clear liquid height and froth density on sieve trays, Ind. Eng. Chem. Process Des. Dev. 20 (2) (1981) 298—307.

J. Huang, J.H. Wu, P. Wang, Weeping rates and lower limits of the operation vapor velocity of trays, Chem. Eng. China 18 (3) (1990) 44—49.

V.E. Yashin, L.V. Ravichev, A.M. Trushin, Influence of entrainment on residual content of pollutants after absorber with sieve trays and wire demister, Ind. Process. Technol. 4 (1) (2024) 67—76, 11.

B.T. Ergan, O. Yucel, E. Gengec, E.S. Aydin, Integrating machine learning regression and classification for enhanced interpretability in optimizing the Fenton process for real wastewater treatment conditions, Sep. Purif. Technol. 363 (2025) 132182.

H.J. Feng, J.J. Li, Z. Jian, Prediction of ionic liquid toxicity by interpretable machine learning, Chin. J. Chem. Eng. 84 (2025) 201—210.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Toward the rational design for low-temperature hydrogenation of silicon tetrachloride: Mechanism and data-driven interpretable descriptor

Reaction process optimization based on interpretable machine learning and metaheuristic optimization algorithms

CFD analysis of particle deposition characteristics in the human upper respiratory tract: A study on multifactorial regulation laws under steady-state/cyclic breathing conditions

Oil hydrogenation in a HiGee-aided fixed bed reactor: Process intensification and macro-kinetic model

Comparative techno—economic and environmental assessment of hydrogen—to—carbon ratio adjustment strategies in biogas to methanol processes