航空学报 > 2021, Vol. 42 Issue (4): 524689-524689   doi: 10.7527/S1000-6893.2020.24689

智能赋能流体力学展望

张伟伟, 寇家庆, 刘溢浪   

  1. 西北工业大学 航空学院, 西安 710072
  • 收稿日期:2020-09-01 修回日期:2020-09-25 发布日期:2020-12-14
  • 通讯作者: 张伟伟 E-mail:aeroelastic@nwpu.edu.cn
  • 基金资助:
    国家自然科学基金(91852115,12072282);国家数值风洞项目(2018-ZT1B01,NNW2019ZT2-A05)

Prospect of artificial intelligence empowered fluid mechanics

ZHANG Weiwei, KOU Jiaqing, LIU Yilang   

  1. School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, China
  • Received:2020-09-01 Revised:2020-09-25 Published:2020-12-14
  • Supported by:
    National Natural Science Foundation of China (91852115, 12072282);National Numerical Windtunnel Project (2018-ZT1B01,NNW2019ZT2-A05)

摘要: 人工智能(AI)是21世纪的前沿科技,流体力学如何在智能化时代焕发青春是值得本领域研究者思考的话题。从智能赋能流体力学角度,就其研究内涵、研究内容、近期研究及难点进行了总结,并对智能流体力学未来的发展进行了展望。研究指出,流体力学计算或试验中所产生的数据是天生的大数据,如何通过深度神经网络、随机森林、强化学习等机器学习方法来利用这些数据,缓解甚至替代理论和方法层面对人脑的依赖,挖掘新的知识,成为一种新的研究范式;相关研究将涵盖流动控制方程的机器学习、湍流模型的机器学习、物理量纲分析与标度的智能化以及数值模拟方法的智能化;借助人工智能技术,发展流动信息特征提取与多源数据融合的智能化是流体力学发展的迫切需求;研究内容应至少涵盖海量数据挖掘方法以及多源气动数据的智能融合;发展数据驱动的流体力学多学科、多物理场耦合建模与控制是工程应用的迫切需求,相关工作涉及多场耦合建模、气动外形智能优化设计以及流动智能自适应控制等方面。

关键词: 湍流建模, 数据融合, 特征提取, 流动控制, 人工智能(AI)

Abstract: Artificial Intelligence (AI) is an advanced technology in the 21 st century. For researchers in related fields, rejuvenation of fluid mechanics in the age of intelligence is worth consideration. This paper proposes intelligence empowered fluid mechanics, explaining and summarizing its meaning, important topics, research progress, and research difficulties. The future development of intelligent fluid mechanics is also discussed. The research points out that the data generated in computational fluid dynamics or experiments are inherently big data, and how to use these data through machine learning methods, like the deep neural network, random forest, and reinforcement learning, to alleviate or even replace the dependence on human brain is a new research paradigm; at the theoretical and methodological level, main research topics cover machine learning of the governing equations and turbulence modeling, the intellectualization of dimensional and scaling analysis, as well as numerical simulation; there is also an urge to develop the intellectualization of flow feature extraction and data fusion from multiple sources through AI; in this branch, data mining of flow dynamics and intelligent fusion of multi-source aerodynamic data are mainly included; moreover, the development of multidisciplinary and multiphysics modeling for fluid mechanics is in urgent need in many engineering applications, involving modeling of multi-field coupling problems, multi-disciplinary intelligent optimization design and adaptive flow control.

Key words: turbulence modeling, data fusion, feature extraction, flow control, Artificial Intelligence (AI)

中图分类号: