CFD-ML integrated multi-objective optimization for n-butane partial oxidation reactor

doi:10.1016/j.cjche.2025.06.019

Chinese Journal of Chemical Engineering ›› 2025, Vol. 88 ›› Issue (12): 53-64.DOI: 10.1016/j.cjche.2025.06.019

Previous Articles Next Articles

CFD-ML integrated multi-objective optimization for n-butane partial oxidation reactor

Xiangkun Liu¹, Qihuan Qiu¹, Bingxu Chen², Yao Shi¹, Longqin Gu², Xinggui Zhou¹, Xuezhi Duan¹

1. State Key Laboratory of Chemical Engineering and Low-Carbon Technology, East China University of Science and Technology, Shanghai 200237, China;
2. State Key Laboratory of Green Chemical Engineering and Industrial Catalysis, Sinopec Shanghai Research Institute of Petrochemical Technology Co., Ltd., Shanghai 201208, China

Received:2025-04-30 Revised:2025-06-02 Accepted:2025-06-02 Online:2025-08-07 Published:2026-02-09
Contact: Yao Shi,E-mail:shiyao@ecust.edu.cn;Xuezhi Duan,E-mail:xzduan@ecust.edu.cn
Supported by:
This work was financially supported by the National Natural Science Foundation of China (22408098 and 22393952), the China Postdoctoral Science Foundation (2024M750908), and the National Key Research and Development Program of China (2024YFA1509903).

CFD-ML integrated multi-objective optimization for n-butane partial oxidation reactor

Xiangkun Liu¹, Qihuan Qiu¹, Bingxu Chen², Yao Shi¹, Longqin Gu², Xinggui Zhou¹, Xuezhi Duan¹

1. State Key Laboratory of Chemical Engineering and Low-Carbon Technology, East China University of Science and Technology, Shanghai 200237, China;
2. State Key Laboratory of Green Chemical Engineering and Industrial Catalysis, Sinopec Shanghai Research Institute of Petrochemical Technology Co., Ltd., Shanghai 201208, China

通讯作者: Yao Shi,E-mail:shiyao@ecust.edu.cn;Xuezhi Duan,E-mail:xzduan@ecust.edu.cn
基金资助:
This work was financially supported by the National Natural Science Foundation of China (22408098 and 22393952), the China Postdoctoral Science Foundation (2024M750908), and the National Key Research and Development Program of China (2024YFA1509903).

Abstract

Abstract: This study develops a CFD-ML integrated framework to achieve multi-objective optimization for the partial oxidation of n-butane to maleic anhydride (MA). A reactor-pellet coupled model was established to investigate the effects of four key operating parameters, revealing that inlet temperature dominates reactor performance by increasing MA yield from 35.0% to 37.6% while sharply raising hotspot temperatures by 42 K. The coupled model was then employed to generate 621 cases for training machine learning models, among which the Gaussian Process Regression (GPR) model exhibits superior accuracy. The GPR model was further integrated with the genetic algorithm to generate Pareto-optimal sets. The results indicate that a critical inflection point is identified on the Pareto front, and once this point is exceeded, even a slight increase in MA yield could lead to a sharp rise in the reactor hotspot temperature, thereby increasing the risk of thermal runaway.

Key words: n-Butane partial oxidation, Reactor operating conditions, Reactor simulation, Machine learning, Pareto optimization

摘要： This study develops a CFD-ML integrated framework to achieve multi-objective optimization for the partial oxidation of n-butane to maleic anhydride (MA). A reactor-pellet coupled model was established to investigate the effects of four key operating parameters, revealing that inlet temperature dominates reactor performance by increasing MA yield from 35.0% to 37.6% while sharply raising hotspot temperatures by 42 K. The coupled model was then employed to generate 621 cases for training machine learning models, among which the Gaussian Process Regression (GPR) model exhibits superior accuracy. The GPR model was further integrated with the genetic algorithm to generate Pareto-optimal sets. The results indicate that a critical inflection point is identified on the Pareto front, and once this point is exceeded, even a slight increase in MA yield could lead to a sharp rise in the reactor hotspot temperature, thereby increasing the risk of thermal runaway.

关键词: n-Butane partial oxidation, Reactor operating conditions, Reactor simulation, Machine learning, Pareto optimization

Xiangkun Liu, Qihuan Qiu, Bingxu Chen, Yao Shi, Longqin Gu, Xinggui Zhou, Xuezhi Duan. CFD-ML integrated multi-objective optimization for n-butane partial oxidation reactor[J]. Chinese Journal of Chemical Engineering, 2025, 88(12): 53-64.

References

[1] R. Cucciniello, D. Cespi, M. Riccardi, E. Neri, F. Passarini, F.M. Pulselli, Maleic anhydride from bio-based 1-butanol and furfural: a life cycle assessment at the pilot scale, Green Chem. 25 (15) (2023) 5922-5935.
[2] M. Muller, M. Kutscherauer, S. Bocklein, G.D. Wehinger, T. Turek, G. Mestl, Modeling the selective oxidation of n-butane to maleic anhydride: From active site to industrial reactor, Catal. Today 387 (2022) 82-106.
[3] F. Trifiro, R.K. Grasselli, How the yield of maleic anhydride in n-butane oxidation, using VPO catalysts, was improved over the years, Top. Catal. 57 (14) (2014) 1188-1195.
[4] N. Ballarini, F. Cavani, C. Cortelli, S. Ligi, F. Pierelli, F. Trifiro, C. Fumagalli, G. Mazzoni, T. Monti, VPO catalyst for n-butane oxidation to maleic anhydride: a goal achieved, or a still open challenge? Top. Catal. 38 (1) (2006) 147-156.
[5] G. Mestl, D. Lesser, T. Turek, Optimum performance of vanadyl pyrophosphate catalysts, Top. Catal. 59 (17) (2016) 1533-1544.
[6] Y. Dong, M. Geske, O. Korup, N. Ellenfeld, F. Rosowski, C. Dobner, R. Horn, What happens in a catalytic fixed-bed reactor for n-butane oxidation to maleic anhydride? Insights from spatial profile measurements and particle resolved CFD simulations, Chem. Eng. J. 350 (2018) 799-811.
[7] Y. Dong, F.J. Keil, O. Korup, F. Rosowski, R. Horn, Effect of the catalyst pore structure on fixed-bed reactor performance of partial oxidation of n-butane: a simulation study, Chem. Eng. Sci. 142 (2016) 299-309.
[8] S. Boecklein, G. Mestl, A. Adler, M. Kutscherauer, New catalyst system for producing maleic anhydride by means of the catalytic oxidation of n-butane: US₂0220266233.2022-08-25.
[9] M. J. Mummey, Process for the production of maleic anhydride: US4855459.1989-08-08.
[10] T.P. Wellauer, D.L. Cresswell, E.J. Newson, Optimal policies in maleic anhydride production through detailed reactor modelling, Chem. Eng. Sci. 41 (4) (1986) 765-772.
[11] J. Maussner, C. Dreiser, O. Wachsen, H. Freund, Systematic model-based design of tolerant chemical reactors, J. Adv. Manuf. Process. 1 (3) (2019) e10024.
[12] G. Maria, A.C. Dan, Setting optimal operating conditions for a catalytic reactor for butane oxidation using parametric sensitivity analysis and failure probability indices, J. Loss Prev. Process. Ind. 25 (6) (2012) 1033-1043.
[13] D.H. Oh, D. Adams, N.D. Vo, D.Q. Gbadago, C.H. Lee, M. Oh, Actor-critic reinforcement learning to estimate the optimal operating conditions of the hydrocracking process, Comput. Chem. Eng. 149 (2021) 107280.
[14] L.T. Zhu, E.Y. Kenig, A study of methanol-to-olefins packed bed reactor performance using particle-resolved CFD and machine learning, AlChE. J. 70 (10) (2024) e18520.
[15] H.L. Zhang, A.Q. Zhu, J. Xu, W. Ge, Gas-solid reactor optimization based on EMMS-DPM simulation and machine learning, Particuology 89 (2024) 131-143.
[16] Z. Wu, A. Tran, Y.M. Ren, C.S. Barnes, S. Chen, P.D. Christofides, Model predictive control of phthalic anhydride synthesis in a fixed-bed catalytic reactor via machine learning modeling, Chem. Eng. Res. Des. 145 (2019) 173-183.
[17] X.K. Liu, A.R. Khan, Y. Shi, W.Y. Chen, X.Z. Duan, Dependences of catalyst layer thickness and pellet grading mode on partial oxidation of n-butane, Chem. Eng. Sci. 296 (2024) 120235.
[18] D. Nemec, J. Levec, Flow through packed bed reactors: 1. single-phase flow, Chem. Eng. Sci. 60 (24) (2005) 6947-6957.
[19] C. Becker, Katalytische Wandreaktorkonzepte Für Msa-Synthese Und Methanol-Dampfreformierung, PhD Thesis, Institut fur¨ Chemische Verfahrenstechnik der Universitat¨ Stuttgart, 2002.
[20] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, G. Louppe, P. Prettenhofer, R. Weiss, R.J. Weiss, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay, Scikit-learn: machine learning in Python, Journal of Machine Learning Research, 12(10)(2011)2825.

CFD-ML integrated multi-objective optimization for n-butane partial oxidation reactor

CFD-ML integrated multi-objective optimization for n-butane partial oxidation reactor

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Zhi Ma, Peng Cui, Xu Wang, Lanyu Li, Haoxiang Xu, Adrian Fisher, Daojian Cheng. The integration of artificial intelligence and high-throughput experiments: An innovative driving force in catalyst design [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 117-132.
[2]	Dian Zhang, Bo Ouyang, Zheng-Hong Luo. Reaction process optimization based on interpretable machine learning and metaheuristic optimization algorithms [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 77-85.
[3]	Ali Tarik Karagoz, Omar Alqusair, Chao Liu, Jie Li. Advances in conceptual process design: From conventional strategies to AI-assisted methods [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 60-76.
[4]	Jianfeng Jiao, Xi Gao, Jie Li. Pure component property estimation framework using explainable machine learning methods [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 158-178.
[5]	Haijun Feng, Li Jiajia, Zhou Jian. Prediction of ionic liquid toxicity by interpretable machine learning [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 201-210.
[6]	Feifei Chen, Zhenyuan Xiao, Zhongfan Luo, Peng Jiang, Jingjing Chen, Yuanhui Ji, Jiahua Zhu, Xiaohua Lu, Liwen Mu. Prediction of mass transfer performance in gas-liquid stirred bioreactor using machine learning [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 211-226.
[7]	Yuan Tian, Honghua Zhang, Yueyang Qiao, Han Yang, Yanrong Liu, Xiaoyan Ji. Intelligent prediction of ionic liquids and deep eutectic solvents by machine learning [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 227-243.
[8]	Yongqi Pan, Yazi Yu, Lijie Wang, Guogang Hu, Yujun Wang, Guangsheng Luo. Intelligent chemical synthesis based on microchemical engineering technology [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 274-288.
[9]	Zhe Ding, Li Guo, Fang Bai, Chao Hua, Ping Lu, Jinyi Chen. Toward the rational design for low-temperature hydrogenation of silicon tetrachloride: Mechanism and data-driven interpretable descriptor [J]. Chinese Journal of Chemical Engineering, 2025, 79(3): 172-184.
[10]	Mingqi Jiang, Zhuo Wang, Zhijian Sun, Jian Wang. A parallel chemical reaction optimization method based on preference-based multi-objective expected improvement [J]. Chinese Journal of Chemical Engineering, 2025, 78(2): 82-92.
[11]	Yixin Wei, Leyu Shan, Tong Qiu, Diannan Lu, Zheng Liu. Machine learning-assisted retrosynthesis planning: Current status and future prospects [J]. Chinese Journal of Chemical Engineering, 2025, 77(1): 273-292.
[12]	Yingxue Fu, Xinyan Liu, Jingzi Gao, Yang Lei, Yuqiu Chen, Xiangping Zhang. Machine learning models for the density and heat capacity of ionic liquid-water binary mixtures [J]. Chinese Journal of Chemical Engineering, 2024, 73(9): 244-255.
[13]	Kai Ge, Yiping Huang, Yuanhui Ji. Machine learning with active pharmaceutical ingredient/polymer interaction mechanism: Prediction for complex phase behaviors of pharmaceuticals and formulations [J]. Chinese Journal of Chemical Engineering, 2024, 66(2): 263-272.
[14]	Denglong Ma, Ruitao Wu, Zekang Li, Kang Cen, Jianmin Gao, Zaoxiao Zhang. A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model [J]. Chinese Journal of Chemical Engineering, 2022, 48(8): 166-175.
[15]	Tong Qin, Zhenhao Xi, Ling Zhao, Weikang Yuan. Monte Carlo simulation of sequential structure control of AN-MA-IA aqueous copolymerization by different operation modes [J]. Chinese Journal of Chemical Engineering, 2022, 46(6): 231-242.