人工智能辅助微流控技术的研究进展

Research progress of artificial intelligence-assisted microfluidics technology

摘要

在工业 4.0 的驱动下，智能化在各行各业中均发挥着重要作用，人工智能技术与微流控技术结合是微流控领域发展的一个必然趋势，人工智能强大的数据处理能力辅助集成式微流控技术的设计，赋予其高效高通量生成、高精度可控性的生产能力，可以为材料合成、化学反应和生物医学等领域提供强大工具. 相较于传统人工分析方法，人工智能辅助的微流控技术具有更高的处理速率、更少的人为干预，有效缓解传统微流控依赖研究人员经验、实验重复性差、优化过程耗时耗力等问题. 此外，人工智能模型有望进一步实现对液滴生成、反应条件优化等的深入探究. 鉴于此，该交叉领域无疑具有广阔的发展前景，而目前系统性的总结和阐述却相对缺乏. 本文旨在系统性地梳理人工智能辅助微流控技术的研究进展. 首先介绍了微流控领域常用的人工智能模型，然后分别从微流控液滴生成、微反应器优化设计、功能微纳材料合成、微流控化学反应和生物医学技术五个方面详细阐述了人工智能辅助微流控技术的应用，最后对这一交叉领域未来的发展方向进行了总结和展望，为相关领域的研究者提供研究新思路.

Abstract

In recent years, artificial intelligence (AI) has witnessed tremendous progress, particularly in the field of engineering applications. From simple machine learning (ML) models and deep learning (DL) models equipped with complex image processing capabilities to the rapidly advancing large language models, these have demonstrated formidable capabilities in engineering applications. Microfluidics, a crucial technology in chemical synthesis and life sciences, integrated with AI has emerged as a significant trend in the field of microfluidics. The combination of AI’s powerful data processing capabilities with the high-throughput generation, high-precision controllability, and rapid reaction analysis capabilities of microfluidics provides a powerful toolkit for fields such as materials science, chemical reaction, and biomedicine. Compared to traditional manual analysis methods, AI-assisted microfluidic technology provides faster processing speeds and reduced human intervention to address the challenges in conventional microfluidics, such as reliance on researcher experience, poor experimental repeatability, and time-consuming optimization processes. Simultaneously, AI models can facilitate investigations into fundamental microfluidic principles. This represents a highly promising direction, yet literature that systematically summarizes and elaborates on this emerging interdisciplinary field remains scarce. This paper systematically reviews the research progress of AI-assisted microfluidic technology. We start by introducing the AI models, which are employed in the microfluidics domain, including four common ML models: tree-based models, support vector machines (SVM), DL, and reinforcement learning (RL). Tree models typically possess strong interpretability. SVM is a common classification model suitable for complex data. DL models are frequently used image processing models that achieve functions such as object detection and image classification by simulating the human brain via neural networks. RL is a distinct trial-and-error AI algorithm that continuously enhances its own performance through interaction with the environment. Next, we discuss the applications of AI-assisted microfluidic technology from several aspects: microfluidic droplet generation, microreactor optimization design, micro/nanomaterial synthesis, catalytic reactions, and biomedical detection. Regarding droplet microfluidics, we examine how AI models predict the generation performance and employ explainable frameworks to investigate the underlying factors governing these processes. We showcase the use of DL for flow pattern recognition and the real-time tracking of droplets and bubbles. Turning to microreactors, we analyze the integration of ML for structural design and performance optimization. In the realm of micro/nanomaterial synthesis, we explore AI-driven approaches for performance prediction and the construction of autonomous synthesis platforms. In the field of chemical reactions, we discuss the application of AI to identify optimal reaction conditions and enhance substance detection. Finally, we discuss the advancement of AI in cell sorting, high-precision detection, and the forecasting of cellular changes within the biomedical field. In conclusion, this review provides an outlook on the future development of this interdisciplinary field. We propose four perspectives: the expand of standardized protocols and highly versatile interfaces, the development of efficient label-free, semi-supervised models and high-precision models suitable for small datasets; the creation of end-to-end AI models that bypass complex feature extraction steps; and the integration of AI models with integrated microfluidic chips to develop automated platforms and realize innovative microfluidic application modes.

关键词

人工智能 / 微流控 / 神经网络 / 微反应器 / 功能微纳材料 / 化学反应 / 生物检测

Key words

artificial intelligence / microfluidics / neural networks / microreactor / functional micro/nanomaterials / chemical reaction / biological detection

参考文献

[1] Shukr R F, Qader H A, Qader I B, et al. Pharm—lab—on—a—chip: Advancements in pharmaceutical and pharmacological analysis through microfluidic chip technology: A comprehensive review[J]. Chem Pap, 2025, 79(11): 7247

[2] Zheng J H, Cole T, Zhang Y X, et al. Exploiting machine learning for bestowing intelligence to microfluidics[J]. Biosens Bioelectron, 2021, 194: 113666

[3] Liu H, Nan L, Chen F, et al. Functions and applications of artificial intelligence in droplet microfluidics[J]. Lab Chip, 2023, 23(11): 2497

[4] Zheng J H, Niu Y F, Li N, et al. Microfluidic technology for cleaner production in microchemical engineering: Design, fabrication and application panorama[J]. Chem Eng Sci, 2025, 317: 122120

[5] Gelin P, Bihi I, Ziemecka I, et al. Microfluidic device for high—throughput production of monodisperse droplets[J]. Ind Eng Chem Res, 2020, 59(28): 12784

[6] Wu Z, Li Q A, Chen X Y, et al. Applications of machine learning on magnesium alloys[J]. Chin J Eng, 2024, 46(10): 1797

[7] （吴铮, 李全安, 陈晓亚, 等. 机器学习在镁合金应用中的研究进展[J]. 工程科学学报, 2024, 46(10)： 1797）

[8] Ma H Z, Liu Y C, Zhao J H, et al. Advances in machine learning applications to resource technology for organic solid waste[J]. Chin J Eng, 2025, 47(3): 550

[9] （马鸿志, 刘忆婵, 赵继华, 等. 机器学习在有机固体废物资源化的应用进展[J]. 工程科学学报, 2025, 47(3)： 550）

[10] Das S. Synergizing microfluidics and machine learning for next generation intelligent Lab—on—a—Chip devices[J]. Microchem J, 2025, 218: 114862

[11] Zhou S Z, Chen B B, Fu E S, et al. Computer vision meets microfluidics: A label—free method for high—throughput cell analysis[J]. Microsyst Nanoeng, 2023, 9: 116

[12] Wang Y, Fang Q. Application of artificial intelligence in microfluidic systems[J]. Chin J Anal Chem, 2020, 48(4): 439

[13] （王宇, 方群. 人工智能在微流控系统中的应用[J]. 分析化学, 2020, 48(4)： 439）

[14] Tao H C, Wu T Y, Kheiri S, et al. Self—driving platform for metal nanoparticle synthesis: Combining microfluidics and machine learning[J]. Adv Funct Mater, 2021, 31(51): 2106725

[15] Rizkin B A, Shkolnik A S, Ferraro N J, et al. Combining automated microfluidic experimentation with machine learning for efficient polymerization design[J]. Nat Mach Intell, 2020, 2(4): 200

[16] Mohammed B, Hamza C. A robust estimation of blasting—induced flyrock using machine learning decision tree algorithms: Random forest, gradient boosting machine, and XGBoost[J]. Min Metall Explor, 2025, 42(3): 1609

[17] Esmaeili—Jaghdan Z, Tatar A, Shokrollahi A, et al. Machine learning modelling of dew point pressure in gas condensate reservoirs: Application of decision tree—based models[J]. Neural Comput Appl, 2023, 36(4): 1973

[18] Liu M Q, Hu H Y, Cui Y J, et al. Modeling and analysis of droplet generation in microchannels using interpretable machine learning methods[J]. Chem Eng J, 2025, 511: 161972

[19] Dubey S, Vishwakarma P, Ramarao T, et al. Artificial intelligence—based droplet size prediction for microfluidic system[J]. Int J Numer Methods Heat Fluid Flow, 2024, 34(8): 3045

[20] Lim K, Ardekani A. Hyperspectral enhanced imaging analysis of nanoparticles using machine learning methods[J]. Nanoscale Adv, 2024, 6(20): 5171

[21] Riti J, Sutra G, Naas T, et al. Combining deep learning and droplet microfluidics for rapid and label—free antimicrobial susceptibility testing of colistin[J]. Biosens Bioelectron, 2024, 257: 116301

[22] Wang Z L, Gu C, Wang M, et al. Research progress and application status of deep learning in steelmaking process[J]. Chin J Eng, 2022, 44(7): 1171

[23] （王仲亮, 顾超, 王敏, 等. 深度学习在炼钢过程中的研究进展及应用现状[J]. 工程科学学报, 2022, 44(7)： 1171）

[24] Shi J B, You L J, Wang Y J, et al. Deep learning based method for dynamic tracking of bubbles in microfluidic gas—driven water experiments[J]. Geoenergy Sci Eng, 2024, 243: 213391

[25] Yatawatta S. Reinforcement learning[J]. Astron Comput, 2024, 48: 100833

[26] Zhang Y C, Duan H B, Wei C. Digital twin—based obstacle avoidance method for unmanned aerial vehicle formation control using deep reinforcement learning[J]. Chin J Eng, 2024, 46(7): 1187

[27] （张宇宸, 段海滨, 魏晨. 基于深度强化学习的无人机集群数字孪生编队避障[J]. 工程科学学报, 2024, 46(7)： 1187）

[28] Chen Y W, Sun T T, Liu Z Y, et al. Towards design automation of microfluidic mixers: Leveraging reinforcement learning and artificial neural networks[J]. Micromachines, 2024, 15(7): 901

[29] Liu L B, Bi M C, Wang Y H, et al. Artificial intelligence—powered microfluidics for nanomedicine and materials synthesis[J]. Nanoscale, 2021, 13(46): 19352

[30] Yang B, Zhu X, Wei B A, et al. Computer vision and machine learning methods for heat transfer and fluid flow in complex structural microchannels: A review[J]. Energies, 2023, 16(3): 1500

[31] Ma L, Zhao X, Hou J S, et al. Droplet microfluidic devices: Working principles, fabrication methods, and scale—up applications[J]. Small Methods, 2024, 8(8): e2301406

[32] Barnes C, Sonwane A R, Sonnenschein E C, et al. Machine learning enhanced droplet microfluidics[J]. Phys Fluids, 2023, 35(9): 092003

[33] Lashkaripour A, McIntyre D P, Calhoun S G K, et al. Design automation of microfluidic single and double emulsion droplets with machine learning[J]. Nat Commun, 2024, 15(1): 83

[34] Roy P, House M L, Dutcher C S. A microfluidic device for automated high throughput detection of ice nucleation of snomax^® [J]. Micromachines, 2021, 12(3): 296

[35] Lashkaripour A, Rodriguez C, Mehdipour N, et al. Machine learning enables design automation of microfluidic flow—focusing droplet generation[J]. Nat Commun, 2021, 12(1): 25

[36] Samari A, Jannati K, Jafari A. A data driven framework for optimizing droplet microfluidics with residual block and Fourier enhanced networks[J]. Sci Rep, 2025, 15: 29077

[37] Lou P W, Huang Y T, Zeng H, et al. Predictive diagnosis of papillary thyroid carcinoma using interpretable machine learning[J]. Chin J Eng, 2025, 47(9): 1896

[38] （娄鹏威, 黄玉婷, 曾辉, 等. 基于可解释机器学习模型的甲状腺乳头状癌诊断预测[J]. 工程科学学报, 2025, 47(9)： 1896）

[39] Shen C, Zheng Q B, Shang M J, et al. Using deep learning to recognize liquid—liquid flow patterns in microchannels[J]. AlChE J, 2020, 66(8): e16260

[40] Zhang S Y, Li H R, Wang K, et al. Accelerating intelligent microfluidic image processing with transfer deep learning: A microchannel droplet/bubble breakup case study[J]. Sep Purif Technol, 2023, 315: 123703

[41] Yang Y L, Qian J H, Fang G P, et al. Research progress on the process analysis technology for microreactors[J]. Microchem J, 2025, 212: 113373

[42] Zhao X L, Jiang H Y, Wang S, et al. Microreactors in chemical process intensification: Chemical reactions, crystallizations, extractions and emulsifications[J]. Chem Eng J, 2025, 519: 165223

[43] Suryawanshi P L, Gumfekar S P, Bhanvase B A, et al. A review on microreactors: Reactor fabrication, design, and cutting—edge applications[J]. Chem Eng Sci, 2018, 189: 431

[44] Naseri Karimvand A, Amirmahani M, Sadeghinasab R, et al. Machine learning and genetic algorithms in the microfluidic design of highly efficient micromixers[J]. Ind Eng Chem Res, 2024, 63(43): 18626

[45] Kumar S, Kumar P, Grewal K S. Machine learning—driven multi—objective optimization of microchannel reactors for CO₂ conversion[J]. Adv Sustainable Syst, 2025, 9(6): 2500064

[46] Kundacina I, Kundacina O, Miskovic D, et al. Advancing microfluidic design with machine learning: A Bayesian optimization approach[J]. Lab Chip, 2025, 25(4): 657

[47] Pan Y Q, Xiao Q F, Zhao F Y, et al. Chat—microreactor: A large—language—model—based assistant for designing continuous flow systems[J]. Chem Eng Sci, 2025, 311: 121567

[48] Chen X Y, Lv H L. Intelligent control of nanoparticle synthesis on microfluidic chips with machine learning[J]. NPG Asia Mater, 2022, 14: 69

[49] Wu X J, Chen A, Yu X D, et al. Microfluidic synthesis of multifunctional micro—/ nanomaterials from process intensification: Structural engineering to high electrochemical energy storage[J]. ACS Nano, 2024, 18(32): 20957

[50] Lu J M, Wang H F, Pan J Z, et al. Research progress of microfluidic technique in synthesis of micro/nano materials[J]. Acta Chim Sin, 2021, 79(7): 809

[51] Xi M M, Zhang P S, Dai J Y, et al. Synergy of robotics and microfluidics for intelligent micro— and nanomanipulation[J]. Biomicrofluidics, 2025, 19(5): 051301

[52] Mekki—Berrada F, Ren Z K, Huang T, et al. Two—step machine learning enables optimized nanoparticle synthesis[J]. npj Comput Mater, 2021, 7: 55

[53] Nathanael K, Cheng S B, Kovalchuk N M, et al. Optimization of microfluidic synthesis of silver nanoparticles: A generic approach using machine learning[J]. Chem Eng Res Des, 2023, 193: 65

[54] Hanari N, Mihandoost S, Rezvantalab S. Intelligence prediction of microfluidically prepared nanoparticles[J]. Sci Rep, 2025, 15(1): 37512

[55] Mihandoost S, Rezvantalab S, M Pallares R, et al. A generative adversarial network approach to predict nanoparticle size in microfluidics[J]. ACS Biomater Sci Eng, 2025, 11(1): 268

[56] Gong Z Y, Zhang C W, Song D Y, et al. ChemReactSeek: An artificial intelligence—guided chemical reaction protocol design using retrieval—augmented large language models[J]. Chem Commun, 2025, 61(70): 13137

[57] Lu J M, Wang H F, Guo Q H, et al. Roboticized AI—assisted microfluidic photocatalytic synthesis and screening up to 10, 000 reactions per day[J]. Nat Commun, 2024, 15: 8826

[58] Ahmadi F, Simchi M, Perry J M, et al. Integrating machine learning and digital microfluidics for screening experimental conditions[J]. Lab Chip, 2023, 23(1): 81

[59] Zhou Z P, Li X C, Zare R N. Optimizing chemical reactions with deep reinforcement learning[J]. ACS Cent Sci, 2017, 3(12): 1337

[60] Jia Y J, Liang X, Zhang L, et al. Machine learning—assisted microfluidic approach for broad—spectrum liposome size control[J]. J Pharm Anal, 2025, 15(6): 101221

[61] Fan D, Liu Y, Liu Y L. The latest advances in microfluidic DLD cell sorting technology: The optimization of channel design[J]. Biosensors, 2025, 15(2): 126

[62] Yuan H L, Song G T, Qi X N, et al. Microfluidics—driven synthetic biology and biomanufacturing: Research progress in methods and applications and future perspectives[J]. Chin J Biotechnol, 2025, 41(11): 4004

[63] （袁会领, 宋国田, 齐显尼, 等. 微流控技术驱动的合成生物学与生物制造：方法与应用的研究进展及展望[J]. 生物工程学报, 2025, 41(11)： 4004）

[64] Saffari H, Fathi D, Palay P, et al. Machine learning and microfluidic integration for oocyte quality prediction[J]. Sci Rep, 2025, 15(1): 26532

[65] Asadian E, Bahramian F, Siavashy S, et al. A review on recent advances of AI—integrated microfluidics for analytical and bioanalytical applications[J]. TrAC Trends Anal Chem, 2024, 181: 118004

[66] Cheng Z, Wu W F, Zhou X, et al. Microfluidic fluorescence—activated cell sorting of convolutional neural network—designed synthetic yeast promoter[J]. ACS Synth Biol, 2025, 14(6): 2105

[67] Rejuan R, Aulisa E, Li W, et al. Validation of a microfluidic device prototype for cancer detection and identification: Circulating tumor cells classification based on cell trajectory analysis leveraging cell—based modeling and machine learning[J]. Int J Numer Methods Biomed Eng, 2025, 41(4): e70037

[68] Chen K, Tang J Y, Wen L, et al. Machine learning for image—based cell classification, detection, and segmentation in microfluidic biosensors: A computer vision perspective[J]. Microchem J, 2025, 215: 114357

[69] Juberi H, Zia A B, Farrell J, et al. Deep learning and hybrid deep neural network to quantify agglutination in dual—phase lab—in—tubing microfluidics[J]. IEEE Sens Lett, 2024, 8(8): 7003704

[70] Cheng J X, Anne R, Chen Y C. Transforming microfluidics for single—cell analysis with robotics and artificial intelligence[J]. Lab Chip, 2025, 25(23): 6100

基金资助

“小米青年学者”资助项目()