Journal of Engineering Research
Journal of Engineering Research. 2024; 3: (3) ; 10.12208/j.jer.20240034 .
总浏览量: 111
江西师范大学附属中学滨江校区 江西南昌
*通讯作者： 盛蔚彬,单位：江西师范大学附属中学滨江校区 江西南昌；
智能空气动力学作为空气动力学与人工智能技术的交叉研究领域，近年来取得了显著进展。传统空气动力学方法在复杂流场分析、湍流预测及气动优化中因计算成本高、实验周期长而面临挑战，而以机器学习和深度学习为代表的人工智能技术提供了数据驱动的新方案。本文系统梳理了智能空气动力学的研究背景与核心问题，详细探讨了机器学习、深度学习及强化学习在流体模拟、湍流控制、气动设计优化及飞行路径规划中的应用与发展。结合案例分析，研究展示了人工智能在流体力学非线性问题中预测精度与计算效率的显著提升。最后，本文展望了智能空气动力学在高效计算、复杂系统集成及跨学科协作中的未来发展方向。
Intelligent aerodynamics, as an interdisciplinary field combining aerodynamics and artificial intelligence (AI), has achieved remarkable progress in recent years. Traditional aerodynamic methods face challenges in analyzing complex flow fields, turbulence prediction, and aerodynamic optimization due to high computational costs and lengthy experimental cycles. In contrast, AI techniques, particularly machine learning and deep learning, offer data-driven solutions to these challenges. This paper systematically reviews the research background and core issues of intelligent aerodynamics, discussing the applications and advancements of machine learning, deep learning, and reinforcement learning in flow simulation, turbulence control, aerodynamic design optimization, and flight trajectory planning. Through case studies, the research demonstrates significant improvements in prediction accuracy and computational efficiency when addressing nonlinear problems in fluid mechanics using AI. Finally, this paper outlines future directions for intelligent aerodynamics, emphasizing efficient computation, integration of complex systems, and interdisciplinary collaboration.
[1] BRANLARD E. Wind turbine aerodynamics and vorticity-based methods: Fundamentals and recent applications [M]. Springer, 2017.
[2] KONAR A. Artificial intelligence and soft computing: behavioral and cognitive modeling of the human brain[M]. CRC press, 2018.
[3] WANG B, WANG J. Application of artificial intelligence in computational fluid dynamics[J]. Industrial & Engineering Chemistry Research, 2021, 60(7): 2772-2790.
[4] BOTTASSO C L, CAMPAGNOLO F, PETROVIĆ V. Wind tunnel testing of scaled wind turbine models: Beyond aerodynamics[J]. Journal of wind engineering and industrial aerodynamics, 2014, 127: 11-28.
[5] KOU J, ZHANG W. Data-driven modeling for unsteady aerodynamics and aeroelasticity[J]. Progress in Aerospace Sciences, 2021, 125: 100725.
[6] HU L, ZHANG J, XIANG Y, et al. Neural networks-based aerodynamic data modeling: A comprehensive review[J]. IEEE Access, 2020, 8: 90805-90823.
[7] WANG L, ZHANG H, WANG C, et al. A review of intelligent airfoil aerodynamic optimization methods based on data-driven advanced models[J]. Mathematics, 2024, 12(10): 1417.
[8] PANCHIGAR D, KAR K, SHUKLA S, et al. Machine learning-based cfd simulations: a review, models, open threats, and future tactics[J]. Neural Computing and Applications, 2022, 34(24): 21677-21700.
[9] CAO Y, BABANEZHAD M, REZAKAZEMI M, et al. Prediction of fluid pattern in a shear flow on intelligent neural nodes using anfis and lbm[J]. Neural Computing and Applications, 2020, 32(17): 13313-13321.
[10] BRUNTON S L, NOACK B R. Closed-loop turbulence control: Progress and challenges[J]. Applied Mechanics Reviews, 2015, 67(5): 050801.
[11] REUTHER J, JAMESON A, FARMER J, et al. Aerodynamic shape optimization of complex aircraft configurations via an adjoint formulation[C]//34th aerospace sciences meeting and exhibit. 1996: 94.
[12] QU Y H, PAN Q, YAN J G. Flight path planning of uav based on heuristically search and genetic algorithms[C]// 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005. IEEE, 2005: 5-pp.