Transforming Computational Fluid Dynamics: A Narrative Review of AI-Driven Methods and Applications
Keywords:
Computational Fluid Dynamics, Artificial Intelligence, Machine Learning, Simulation Modeling, CFD Validation, Engineering Innovation, High-Performance ComputingAbstract
Computational Fluid Dynamics (CFD) plays an essential role in modern engineering and scientific research, especially in modeling complex fluid behaviors across various industries. This narrative review aims to analyze recent advancements in CFD methods and applications, with a focus on the integration of Artificial Intelligence (AI), machine learning, and advanced numerical models. Literature was gathered from databases including Scopus, Web of Science, and Google Scholar using a set of comprehensive keywords, and studies were selected based on methodological quality, relevance, and recency. The review synthesizes evidence across multiple sectors, including aerospace, biomedical engineering, and renewable energy. Key findings show that AI-based approaches significantly enhance CFD by improving simulation efficiency and accuracy, particularly through surrogate models and reinforcement learning strategies. Applications of CFD in industrial design, emission control, and cardiovascular modeling were examined, with validation through experimental data ensuring reliability. However, challenges remain in accessing computational resources, validating models, and achieving methodological standardization. Systemic barriers—such as the need for high-performance computing, skilled personnel, and standardized protocols—were identified as primary constraints. The study concludes by emphasizing the critical role of AI integration and interdisciplinary collaboration in advancing CFD practices. It advocates for increased investment in infrastructure, policy-driven support, and further research into hybrid and real-time simulation models to enhance the robustness and scalability of CFD applications.
References
Ahmed, S., Kamal, K., Ratlamwala, T., Mathavan, S., Hussain, G., Alkahtani, M., … & Alsultan, M. (2022). Aerodynamic analyses of airfoils using machine learning as an alternative to RANS simulation. Applied Sciences, 12(10), 5194. https://doi.org/10.3390/app12105194
Alzhanov, N., Ng, E., & Zhao, Y. (2024). Hybrid CFD PINN FSI simulation in coronary artery trees. Fluids, 9(12), 280. https://doi.org/10.3390/fluids9120280
Bijjala, S. (2024). AIML enabled rapid vehicle aerodynamics design improvements. SAE Technical Paper, 1. https://doi.org/10.4271/2024-28-0007
Colombo, A., Chiastra, C., Gallo, D., Loh, P., Dokos, S., Zhang, M., … & Beier, S. (2025). Advancements in coronary bifurcation stenting techniques: Insights from computational and bench testing studies. International Journal for Numerical Methods in Biomedical Engineering, 41(3). https://doi.org/10.1002/cnm.70000
Crespo, A., Tagliafierro, B., Martínez-Estévez, I., Domínguez, J., deCastro, M., Gómez‐Gesteira, M., … & Stasnby, P. (2023). On the state-of-the-art of CFD simulations for wave energy converters within the open-source numerical framework of DualSPHysics. Proc. EWTEC, 15. https://doi.org/10.36688/ewtec-2023-145
Efthimiou, G. (2024). Application of an empirical model to improve maximum value predictions in CFD-RANS: Insights from four scientific domains. Atmosphere, 15(9), 1124. https://doi.org/10.3390/atmos15091124
Gupta, B., Yoshida, T., Ogawa, S., Danmoto, Y., & Yoshimoto, T. (2021). Improving vibration response of radial turbine in variable geometry turbochargers with CFD analysis. https://doi.org/10.1115/gt2021-59139
Harvill, R., Lane, J., & George, T. (2021). Hybrid system level and coarse grid CFD tool for three-dimensional natural circulation, mixing, and stratification modeling. Nuclear Technology, 208(1), 1–26. https://doi.org/10.1080/00295450.2020.1870371
Jackson, R., & Amano, R. (2017). Experimental study and simulation of a small-scale horizontal-axis wind turbine. Journal of Energy Resources Technology, 139(5). https://doi.org/10.1115/1.4036051
Jan, J., & Mackenzie, D. (2023). Challenges and solutions to visualize and study the oil flow pattern inside gear quenching tank using CFD methods. https://doi.org/10.31399/asm.cp.ht2023p0127
Kieckhefen, P., Pietsch, S., Dosta, M., & Heinrich, S. (2020). Possibilities and limits of computational fluid dynamics–discrete element method simulations in process engineering: A review of recent advancements and future trends. Annual Review of Chemical and Biomolecular Engineering, 11(1), 397–422. https://doi.org/10.1146/annurev-chembioeng-110519-075414
Knight, E., Rougier, E., Lei, Z., Euser, B., Chau, V., Boyce, S., … & Froment, M. (2020). HOSS: An implementation of the combined finite-discrete element method. Computational Particle Mechanics, 7(5), 765–787. https://doi.org/10.1007/s40571-020-00349-y
Koulali, A., Ziółkowski, P., Radomski, P., Sio, L., Zieliński, J., Martínez, M., … & Mikielewicz, D. (2024). Analysis of heat transfer and AuNPs-mediated photo-thermal inactivation of E. coli at varying laser powers using single-phase CFD modeling. International Journal of Numerical Methods for Heat & Fluid Flow, 35(1), 382–413. https://doi.org/10.1108/hff-04-2024-0252
Kurhade, A., Siraskar, G., Kondhalkar, G., Darade, M., Yadav, R., Biradar, R., … & Charwad, G. (2024). Optimizing aerofoil design: A comprehensive analysis of aerodynamic efficiency through CFD simulations and wind tunnel experiments. Journal of Mines Metals and Fuels, 713–724. https://doi.org/10.18311/jmmf/2024/45361
Küçüktopçu, E., Cemek, B., & Şimşek, H. (2024). Modeling environmental conditions in poultry production: Computational fluid dynamics approach. Animals, 14(3), 501. https://doi.org/10.3390/ani14030501
Łach, Ł., & Svyetlichnyy, D. (2025). Advances in numerical modeling for heat transfer and thermal management: A review of computational approaches and environmental impacts. Energies, 18(5), 1302. https://doi.org/10.3390/en18051302
Marfaing, O., Guingo, M., Laviéville, J., Mimouni, S., Baglietto, E., Lubchenko, N., … & Nadiga, B. (2018). Comparison and uncertainty quantification of two-fluid models for bubbly flows with NEPTUNE_CFD and STAR-CCM+. Nuclear Engineering and Design, 337, 1–16. https://doi.org/10.1016/j.nucengdes.2018.05.028
Mishra, A., Korba, D., Kaur, I., Singh, P., & Li, L. (2023). Prediction and validation of flow properties in porous lattice structures. Journal of Fluids Engineering, 145(4). https://doi.org/10.1115/1.4056524
Noordt, W., Ganju, S., & Brehm, C. (2021). Immersed-boundary wall-modeled large-eddy simulation of high Mach number boundary layer flows. https://doi.org/10.2514/6.2021-2751
Peng, X., Zhu, H., Xu, D., Hao, W., Wang, W., & Cai, G. (2024). Applying machine learning techniques: Uncertainty quantification in nonlinear dynamics character predictions via gated recurrent unit-based reduced-order models. International Journal of Pattern Recognition and Artificial Intelligence, 38(11). https://doi.org/10.1142/s0218001424510182
Phan, N., Ganachari, V., Shirguppikar, S., Gavali, P., Deshmukh, D., Jadhav, P., … & Pachore, M. (2024). A study on material removal rate in powder-mixed electro-discharge machining utilizing integrated experimental and computational fluid dynamics analysis. Tribology in Industry, 46(4), 549–559. https://doi.org/10.24874/ti.1660.04.24.05
Ranjbarzadeh, R., & Sappa, G. (2025). Numerical and experimental study of fluid flow and heat transfer in porous media: A review article. Energies, 18(4), 976. https://doi.org/10.3390/en18040976
Suárez, P., Alcántara-Ávila, F., Miró, A., Rabault, J., Font, B., Lehmkuhl, O., … & Vinuesa, R. (2025). Active flow control for drag reduction through multi-agent reinforcement learning on a turbulent cylinder at Red=3900Re_d=3900Red=3900. Flow Turbulence and Combustion. https://doi.org/10.1007/s10494-025-00642-x
Sundar, R., Majumdar, D., Shah, C., & Sarkar, S. (2024). Massive parallelisation and performance enhancement of an immersed boundary method-based unsteady flow solver. In Lecture Notes in Mechanical Engineering (pp. 459–472). https://doi.org/10.1007/978-981-97-1033-1_38
Tucker, M., Wilson, D., Bergstrom, D., & Carmalt, J. (2024). Comparison of treatments for equine laryngeal hemiplegia using computational fluid dynamic analysis in an equine head model. Frontiers in Veterinary Science, 11. https://doi.org/10.3389/fvets.2024.1478511
Wang, G., Shui, P., Yin, T., Cui, H., & Tian, Y. (2024). Optimizing nitrogen oxide emissions in industrial calcination through staged combustion: A CFD-, MP-PIC-, and RSM-based approach for enhanced process efficiency. Industrial & Engineering Chemistry Research, 63(33), 14541–14553. https://doi.org/10.1021/acs.iecr.4c01329
Yeo, H., & Ormiston, R. (2021). UH-60A Airloads Workshop - Setting the stage for the rotorcraft CFD/CSD revolution. https://doi.org/10.4050/f-0077-2021-16775
Yeo, H., & Ormiston, R. (2022). UH-60A Airloads Workshop—Setting the stage for the rotorcraft CFD/CSD revolution, Part II: Ongoing progress, impact, and lessons learned. Journal of the American Helicopter Society, 67(2), 1–16. https://doi.org/10.4050/jahs.67.022011
Zhang, J., Zhong, L., Su, B., Wan, M., Yap, J., Tham, J., … & Tan, R. (2014). Perspective on CFD studies of coronary artery disease lesions and hemodynamics: A review. International Journal for Numerical Methods in Biomedical Engineering, 30(6), 659–680. https://doi.org/10.1002/cnm.2625
