Volume 8,Issue 8
Digital‑Fluid Intelligent Learning: AI‑Driven Visualization for Dynamic Demonstration in Fluid Mechanics Classes
Aiming at common pain points in current fluid‑mechanics classes, including invisible flow phenomena, insufficient physical experiment supplies, high‑threshold conventional CFD tools, and poor interactivity of digital resources, this paper takes the “Digital‑Fluid Intelligent Learning” AI visualization demonstration system as the carrier to explore innovative paths for empowering dynamic demonstrations in fluid‑mechanics classes with AI technology. From four dimensions: flow‑field visualization, virtual‑experiment library, real‑time solving engine, and inquiry‑based ecosystem, this study puts forward implementation strategies. It breaks the disconnection between theories and phenomena in traditional teaching, realizes real‑time interactive generation of dynamic flow‑field effects in class, effectively lowers the cognitive threshold for core knowledge points, and provides referable practical solutions for the digital transformation of engineering fluid‑related courses.
[1] Zhou L, Liang Y, Yuan A, et al., 2025, Research on Teaching Innovation of Industry-Education Integration for the Course “Fundamentals of Thermal Engineering and Fluid Mechanics” Under the Background of Emerging Engineering Education. Guizhou Agricultural Mechanization, 2025(4): 56–60.
[2] Jin X, Lai M, Li H, 2021, Physics-Informed Deep-Learning Modeling and Simulation Method for Flow Fields. Acta Mechanica Sinica, 53(10): 2616–2629.
[3] Brunton SL, Noack BR, Koumoutsakos P, 2020, Machine Learning for Fluid Mechanics. Annual Review of Fluid Mechanics, 52: 477–508.
[4] Jia Y, Zhang J, Wu C, et al., 2024, Development and Teaching Application of Virtual-Reality Technology for Three-Dimensional Flow-Fields. Mechanics in Engineering, 46(3): 643–648.
[5] De Jong T, Linn MC, Zacharia ZC, 2013, Physical and Virtual Laboratories in Science and Engineering Education. Science, 340(6130): 305–308.
[6] Brinson JR, 2015, Learning Outcome Achievement in Non-Traditional (Virtual and Remote) Versus Traditional (Hands-On) Laboratories: A Review of the Empirical Research. Computers & Education, 87: 218–237.
[7] Shi P, Fu X, Yang J, et al., 2024, Development and Evaluation of a Virtual Simulation Experiment System for the Course of Fluid Mechanics. International Journal of Mechanical Engineering Education, 52(2): 109–125.
[8] Sun M, Wang W, Chai H, et al., 2025, Research on Problem-Oriented Practical Teaching Strategy for Fluid Mechanics and Hydraulic Transmission Based on ANSYS Simulation Technology. Internal Combustion Engine & Parts, 2025(14): 143–145.
[9] Zhu Y, Sun Z, Hu Y, 2025, Curriculum-System-Construction Practice of Promoting Teaching via Scientific Research and Integrating Research With Teaching — Taking the Course “Computational Fluid Mechanics” as the Research Object. Education and Teaching Forum, 2025(1): 101–104.
[10] Pope SB, 2000, Turbulent Flows. Cambridge University Press, 2000.
[11] Thuerey N, Weissenow K, Prantl L, et al., 2020, Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows. AIAA Journal, 58(1): 25–36.
