Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation

doi:10.1016/j.cjche.2025.05.015

中国化学工程学报 ›› 2025, Vol. 84 ›› Issue (8): 244-253.DOI: 10.1016/j.cjche.2025.05.015

• Full Length Article • 上一篇下一篇

Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation

Zifeng Li^1,2, Xiaoping Guan^1,2, Jingchang Zhang^1,2, Qiang Guo^1,2, Qiushi Xu^1,2, Ning Yang^1,2

1. State Key Laboratory of Mesoscience and Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China;
2. School of Chemical Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

收稿日期:2025-02-27 修回日期:2025-04-28 接受日期:2025-05-28 出版日期:2025-08-28 发布日期:2025-06-11
通讯作者: Ning Yang,E-mail:nyang@ipe.ac.cn
基金资助:
The authors acknowledge the support from National Key Research and Development Program of China(2023YFC3905400), the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA0490102) and National Natural Science Foundation of China (22178354, 2242100322408374).

Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation

Zifeng Li^1,2, Xiaoping Guan^1,2, Jingchang Zhang^1,2, Qiang Guo^1,2, Qiushi Xu^1,2, Ning Yang^1,2

1. State Key Laboratory of Mesoscience and Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China;
2. School of Chemical Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2025-02-27 Revised:2025-04-28 Accepted:2025-05-28 Online:2025-08-28 Published:2025-06-11
Contact: Ning Yang,E-mail:nyang@ipe.ac.cn
Supported by:
The authors acknowledge the support from National Key Research and Development Program of China(2023YFC3905400), the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA0490102) and National Natural Science Foundation of China (22178354, 2242100322408374).

摘要/Abstract

摘要： Integrating Bayesian Optimization with Volume of Fluid (VOF) simulations, this work aims to optimize the operational conditions and geometric parameters of T-junction microchannels for target droplet sizes. Bayesian Optimization utilizes Gaussian Process (GP) as its core model and employs an adaptive search strategy to efficiently explore and identify optimal combinations of operational parameters within a limited parameter space, thereby enabling rapid optimization of the required parameters to achieve the target droplet size. Traditional methods typically rely on manually selecting a series of operational parameters and conducting multiple simulations to gradually approach the target droplet size. This process is time-consuming and prone to getting trapped in local optima. In contrast, Bayesian Optimization adaptively adjusts its search strategy, significantly reducing computational costs and effectively exploring global optima, thus greatly improving optimization efficiency. Additionally, the study investigates the impact of rectangular rib structures within the T-junction microchannel on droplet generation, revealing how the channel geometry influences droplet formation and size. After determining the target droplet size, we further applied Bayesian Optimization to refine the rib geometry. The integration of Bayesian Optimization with computational fluid dynamics (CFD) offers a promising tool and provides new insights into the optimal design of microfluidic devices.

关键词: Bayesian optimization, VOF, Microchannels, CFD, Rib structure, Optimal design

Abstract: Integrating Bayesian Optimization with Volume of Fluid (VOF) simulations, this work aims to optimize the operational conditions and geometric parameters of T-junction microchannels for target droplet sizes. Bayesian Optimization utilizes Gaussian Process (GP) as its core model and employs an adaptive search strategy to efficiently explore and identify optimal combinations of operational parameters within a limited parameter space, thereby enabling rapid optimization of the required parameters to achieve the target droplet size. Traditional methods typically rely on manually selecting a series of operational parameters and conducting multiple simulations to gradually approach the target droplet size. This process is time-consuming and prone to getting trapped in local optima. In contrast, Bayesian Optimization adaptively adjusts its search strategy, significantly reducing computational costs and effectively exploring global optima, thus greatly improving optimization efficiency. Additionally, the study investigates the impact of rectangular rib structures within the T-junction microchannel on droplet generation, revealing how the channel geometry influences droplet formation and size. After determining the target droplet size, we further applied Bayesian Optimization to refine the rib geometry. The integration of Bayesian Optimization with computational fluid dynamics (CFD) offers a promising tool and provides new insights into the optimal design of microfluidic devices.

Key words: Bayesian optimization, VOF, Microchannels, CFD, Rib structure, Optimal design

Zifeng Li, Xiaoping Guan, Jingchang Zhang, Qiang Guo, Qiushi Xu, Ning Yang. Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation[J]. 中国化学工程学报, 2025, 84(8): 244-253.

参考文献

[1] T.S. Kaminski, P. Garstecki, Controlled droplet microfluidic systems for multistep chemical and biological assays, Chem. Soc. Rev. 46 (20) (2017) 6210-6226.
[2] H.N. Joensson, H. Andersson Svahn, Droplet microfluidics: a tool for single-cell analysis, Angew. Chem. Int. Ed 51 (49) (2012) 12176-12192.
[3] D. Dendukuri, P.S. Doyle, The synthesis and assembly of polymeric microparticles using microfluidics, Adv. Mater. 21 (41) (2009) 4071-4086.
[4] Q. Yu, X.Y. Chen, Insights into the breaking and dynamic mixing of microemulsion (W/O) in the T-junction microchannel, Chaos Solitons Fractals 155 (2022) 111774.
[5] J.C. Zhang, S.L. Shu, X.P. Guan, N. Yang, Lattice Boltzmann simulation of drop splitting in a fractal tree-like microchannel, Chem. Eng. Sci. 252 (2022) 117277.
[6] G.F. Christopher, N.N. Noharuddin, J.A. Taylor, S.L. Anna, Experimental observations of the squeezing-to-dripping transition in T-shaped microfluidic junctions, Phys. Rev. E 78 (3) (2008) 036317.
[7] D.A. Hoang, V. van Steijn, L.M. Portela, M.T. Kreutzer, C.R. Kleijn, Benchmark numerical simulations of segmented two-phase flows in microchannels using the Volume of Fluid method, Comput. Fluids 86 (2013) 28-36.
[8] G.Y. Soh, G.H. Yeoh, V. Timchenko, Numerical investigation on the velocity fields during droplet formation in a microfluidic T-junction, Chem. Eng. Sci. 139 (2016) 99-108.
[9] X.L. Li, L.Q. He, Y. He, H.L. Gu, M.H. Liu, Numerical study of droplet formation in the ordinary and modified T-junctions, 31 (8) (2019) 082101.
[10] P.I. Frazier, A tutorial on Bayesian optimization, (2018): 1807.02811.
[11] B. Shahriari, K. Swersky, Z.Y. Wang, R.P. Adams, N. de Freitas, Taking the human out of the loop: a review of Bayesian optimization, Proc. IEEE 104 (1) (2016) 148-175.
[12] Q. Yu, X.Y. Chen, X.Y. Li, D.Y. Zhang, Optimized design of droplet micro-mixer with sinusoidal structure based on Pareto genetic algorithm, Int. Commun. Heat Mass Transf. 135 (2022) 106124.
[13] I. Kundacina, O. Kundacina, D. Miskovic, V. Radonic, Advancing microfluidic design with machine learning: a Bayesian optimization approach, Lab Chip 25 (4) (2025) 657-672.
[14] C.W. Hirt, B.D. Nichols, Volume of fluid (VOF) method for the dynamics of free boundaries, J. Comput. Phys. 39 (1) (1981) 201-225.
[15] H.G. Weller, G. Tabor, H. Jasak, C. Fureby, A tensorial approach to computational continuum mechanics using object-oriented techniques, 12 (6) (1998) 620-631.
[16] J.U. Brackbill, D.B. Kothe, C. Zemach, A continuum method for modeling surface tension, J. Comput. Phys. 100 (2) (1992) 335-354.
[17] M. G. Genton, Classes of kernels for machine learning: a statistics perspective, J. Mach. Learn. Res. 2 (2001) 299-312.
[18] O. Kramer, Scikit-learn. Machine Learning for Evolution Strategies. Springer International Publishing, (2016), pp 5-53.
[19] P. Garstecki, M.J. Fuerstman, H.A. Stone, G.M. Whitesides, Formation of droplets and bubbles in a microfluidic T-junction-scaling and mechanism of break-up, Lab Chip 6 (3) (2006) 437-446.
[20] A. Choudhary, R. Thakur, Evaluation of connected component labeling algorithms on shared and distributed memory multiprocessors, Proceedings Sixth International Parallel Processing Symposium. March 23-26, 1992, Beverly Hills, CA, USA. IEEE, (1992) 362-365.
[21] P. Ngatchou, A. Zarei, A. El-Sharkawi, Pareto multi objective optimization, Proceedings of the 13th International Conference on, Intelligent Systems Application to Power Systems. November 6-10, 2005, Arlington, VA, USA. IEEE, (2006) 84-91.
[22] K.P. Schwarz, M.G. Sideris, R. Forsberg, The use of FFT techniques in physical geodesy, Geophys. J. Int. 100 (3) (1990) 485-514.
[23] W.W. Xu, S.J. Cui, X. Xu, S.B. Lu, Z.Z. Liu, Q. Li, Numerical simulation on the characteristics of droplet generation and the distribution of discrete-phase flow patterns in T-junction microchannels, Int. J. Heat Fluid Flow 110 (2024) 109626.

Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation

Bayesian optimization of operational and geometric parameters of microchannels for targeted droplet generation

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]	Yujing Zhao, Qilei Liu, Jian Du, Qingwei Meng, Liang Sun, Lei Zhang. High-throughput and intelligent design of potential GRK2 inhibitor candidates using deep learning and mathematical programming methods[J]. 中国化学工程学报, 2025, 84(8): 11-22.
[2]	Qingchun Yang, Dongwen Rong, Qiwen Guo, Runjie Bao, Dawei Zhang. Ensemble learning-driven multi-objective optimization of the co-pyrolysis process of biomass and coal for high economic and environmental performance[J]. 中国化学工程学报, 2025, 84(8): 23-34.
[3]	Yaohua Huang, Huatong Zhu, Heping Wu, Lele Zhang, Hao Lu, Qiang Yang. Combined micromixing and coalescence separation for improved oil desulfurization[J]. 中国化学工程学报, 2025, 83(7): 191-198.
[4]	Hewei Yang, Bowen Tang, Ye Tian, Wei Tan. Dynamic load characteristics and wake vortex structure of spiral finned cylinders in cross-flow[J]. 中国化学工程学报, 2025, 82(6): 105-115.
[5]	Yulan Zhao, Yifan Qin, Xiao Dong Chen, Jie Xiao. Acid-base regulation in duodenum by intestinal fluid secretion: A simulation study[J]. 中国化学工程学报, 2025, 81(5): 76-86.
[6]	Qinwen Liu, Guoqing Lian, Wenli Dong, Yu Su, Wei Quan Leong, Chi-Hwa Wang, Wenqi Zhong. A three-dimensional CFD numerical simulation study on pressurized oxy-fuel gasification of poultry manure in an industrial-scale gasifier[J]. 中国化学工程学报, 2025, 81(5): 115-127.
[7]	Zhaoyi Song, Yuanxi Zhang, Guangwen Chu, Lei Shao, Yang Xiang. Micromixing efficiency and enhancement methods for non-Newtonian fluids in millimeter channel reactors[J]. 中国化学工程学报, 2025, 78(2): 108-119.
[8]	Qingzhao Liu, Yang Qin, Guodong Zhu, Xubin Zhang, Fumin Wang, Guobing Li, Shuai Liu, Zhiwei Zhang, Bingxin Zhu, Zheng Wang. Numerical simulation of power and flow field characteristics of different spiral stirred reactors[J]. 中国化学工程学报, 2025, 78(2): 218-231.
[9]	Min An, Chengxiang Wang, Qing Liu, Mengya Wang, Zhirong Yang, Wenpeng Li, Guoli Zhou, Jingtao Wang, Jinli Zhang. Mixing behavior and mass transfer of liquid—liquid two-phase flow in an annular microchannel with helical wires[J]. 中国化学工程学报, 2025, 77(1): 42-56.
[10]	Hai Cao, Haibin Yang, Yanxiong Fang, Yuandi Zeng, Xiaolan Cai, Jingjing Ma. Study on trifluoromethanesulfonic acid-promoted synthesis of daidzein: Process optimization and reaction mechanism[J]. 中国化学工程学报, 2024, 71(7): 132-139.
[11]	Junhai Deng, Shilin Lan, Juchang Wu, Shenghua Du, Weidong Liu, Luchang Han, Yefeng Zhou. CFD-PBM coupled modeling of the liquid-liquid dispersion characteristics and structure optimization for Kenics static mixer[J]. 中国化学工程学报, 2024, 70(6): 173-188.
[12]	Kang Liu, You Fan, Juan Chen. A model free adaptive control method based on self-adjusting PID algorithm in pH neutralization process[J]. 中国化学工程学报, 2024, 76(12): 227-236.
[13]	Shuaishuai Zhang, Yuanbo Liu, Tong Zheng, Da Ruan, Zhong Lan, Tingting Hao, Xuehu Ma. Energy, exergy, economic, and environmental compromising performance of dual-stage evaporation-ammonia hybrid compression–absorption refrigeration system for the cooling supply of keto-benzene dewaxing process[J]. 中国化学工程学报, 2024, 75(11): 274-289.
[14]	Luhang Yang, Xixiang Zhang, Jingyi Lu, Zhou Tian, Wenli Du. A local space transfer learning-based parallel Bayesian optimization with its application[J]. 中国化学工程学报, 2024, 74(10): 227-237.
[15]	Yuan Yao, Peiqiao Liu, Qian Zhang, Zequan Li, Benjun Xi, Changyuan Tao, Yundong Wang, Zuohua Liu. Effect of aspect ratio of elliptical stirred vessel on mixing time and flow field characteristics in the absence of baffles[J]. 中国化学工程学报, 2024, 65(1): 63-74.