1.香港科技大学土木与环境工程学系,香港 中国
2.哈尔滨工业大学(深圳)智能土木与海洋工程学院,广东 深圳 518055
刘军乐(1997—),男,博士后。主要从事人工智能和风工程研究。E-mail: jliueb@connect.ust.hk
胡钢(1987—),男,教授,博导,博士。主要从事人工智能和风工程研究。E‑mail: hugang@hit.edu.cn
收稿:2024-12-19,
修回:2025-02-27,
纸质出版:2025-04-28
移动端阅览
刘军乐,沈其庆,谢锦添等.基于人工智能技术的钝体尾流时空预报[J].防灾减灾工程学报,2025,45(02):263-270.
LIU Junle,SHUM Kihing,Tse K.T.,et al.Spatiotemporal Forecast of Bluff‑body Wakes Using Artificial Intelligence Technologies[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(02):263-270.
刘军乐,沈其庆,谢锦添等.基于人工智能技术的钝体尾流时空预报[J].防灾减灾工程学报,2025,45(02):263-270. DOI: 10.13409/j.cnki.jdpme.20241219002.
LIU Junle,SHUM Kihing,Tse K.T.,et al.Spatiotemporal Forecast of Bluff‑body Wakes Using Artificial Intelligence Technologies[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(02):263-270. DOI: 10.13409/j.cnki.jdpme.20241219002.
湍流在机械工程、流体力学、土木工程等领域中广泛存在。以往,湍流信息获取主要依赖数值模拟和风洞试验,但数值模拟花费时间长,风洞试验经济成本高昂。新时代技术发展背景下,人工智能技术因其高效、高精度和可信赖等特点受到工程领域广泛关注。本研究构建了Turbulent Flow‑Vision‑Transformer(TF‑ViT)的人工智能算法,TF‑ViT可以基于数据驱动的方式来实现时空序列的湍流预报。具体来说,TF‑ViT主要包含两个部分:Transformer框架及UNet结构。在TF‑ViT算法中,每一个部分都有独特的功能,其中Transformer框架为编码器,主要用于湍流时空特征处理,UNet网络是解码器,对编码器处理的时空湍流信息进行解耦,整体框架可以预测未来的时空湍流信息。用经典的矩形柱体绕流来验证开发的TF‑ViT算法,开源计算求解器OpenFOAM用于矩形柱体绕流模拟,矩形柱体的尾流场数据用于TF‑ViT模型的训练和验证。使用8帧连续瞬态湍流信息预报未来8帧的湍流信息,研究结果表明本研究开发的TF‑ViT算法可以较为准确地预报未来短时间内尾流区的湍流时空发展。本研究展示了TF‑ViT预报时空湍流的能力,为获得湍流尾流场提供了一种有效的方法。
Turbulent flow is ubiquitous in mechanical engineering
fluid mechanics
civil engineering
and other related disciplines. Traditionally
acquisition of turbulent flow data mainly depended on numerical simulations and wind tunnel tests. However
numerical simulations require substantial computational time
and wind tunnel tests involve high economic costs. With the rapid development of modern technologies
artificial intelligence technologies have attracted widespread attention in engineering fields due to their high efficiency
high precision
and reliability. This study developed an artificial intelligence algorithm named Turbulent-Flow-Vision Transformer (TF-ViT)
which enabled spatiotemporal forecast of turbulent flow based on data-driven approaches. Specifically
the TF-ViT mainly consisted of two components: Transformer framework and UNet structure. In TF-ViT
each component had distinct functions. The Transformer framework served as the encoder
mainly responsible for processing and extracting spatiotemporal features of turbulent flow. Meanwhile
the UNet functioned as the decoder to decouple the encoded spatiotemporal turbulent flow information. The overall framework enabled the forecast of future spatiotemporal turbulent flow information. This study used the classical problem of the flow past rectangular cylinders to validate the developed TF-ViT algorithm. The open-source computational solver OpenFOAM was utilized to simulate the flow past rectangular cylinders
and the obtained wake flow field data was then used for the training and validation of the TF-ViT model. 8 continuous frames of transient turbulent flow data were used to forecast the subsequent 8 frames of turbulent flow information. The results showed that the developed TF-ViT algorithm in this study could accurately forecast the short-term spatiotemporal development of turbulent flow in the wake region. This study demonstrates the strong capability of TF-ViT in forecasting spatiotemporal turbulent flow
providing an effective method for turbulent wake field acquisition.
张伟政 , 赵吉军 , 马学忠 , 等 . 湍流效应对高速机械密封端面型槽冷却性能影响分析 [J]. 化工学报 , 2023 , 74 ( 3 ): 1228 - 1238 .
Zhang W H , Zhao J J , Ma X Z , et al . Analysis of turbulence effect on face groove cooling performance of high-speed mechanical seals [J]. CIESC Journal , 2023 , 74 ( 3 ): 1228 - 1238 . (in Chinese)
于丽波 , 罗敏 . 基于 CFD 不同湍流模型的超高层连体结构风荷载和流场对比研究 [J]. 特种结构 , 2017 , 34 ( 5 ): 44 - 51 .
Yu L B , Luo M . Research on wind loads and flow field of high-rise tower of conjoined buildings based on different CFD turbulence models [J]. Special Structures , 2017 , 34 ( 5 ): 44 - 51 . (in Chinese)
张志田 , 张显雄 , 陈政清 . 桥梁气动力CFD模拟中湍流模型的应用现状 [J]. 工程力学 , 2016 , 33 ( 6 ): 1 - 8 .
Zhang Z T , Zhang X X . Chen Z Q. Status of the application of turbulence models in CFD simulations of bridge aerodynamic loads [J]. Engineering Mechanics , 2016 , 33 ( 6 ): 1 - 8 . (in Chinese)
吴冬 . 瞬态多循环 CFD 航空发动机模型的耦合数值传热研究 [J]. 工业加热 , 2019 , 48 ( 2 ): 42 - 44 .
Wu D . Study on coupled numerical heat transfer of transient multi-cycle CFD aeroengine model [J]. Industrial Heating , 2019 , 48 ( 2 ): 42 - 44 . (in Chinese)
周铸 , 黄江涛 , 黄勇 , 等 . CFD 技术在航空工程领域的应用, 挑战与发展 [J]. 航空学报 , 2017 , 38 ( 3 ): 1 - 25 .
Zhou Z , Huang J T , Huang Y , et al . CFD technology in aeronautic engineering field: Applications, challenges and development [J]. Acta Aeronautica et Astronautica Sinica , 2017 , 38 ( 3 ): 1 - 25 . (in Chinese)
杨俊伟 , 杨华 , 付士凤 , 等 . 短试验段内格栅湍流场风洞试验研究 [J]. 实验流体力学 , 2021 , 35 ( 6 ): 86 - 93 .
Yang J W , Yang H , Fu S F , et al . Wind tunnel experimental study of the grille-generated turbulence in the short test section [J]. Journal of Experiments in Fluid Mechanics , 2021 , 35 ( 6 ): 86 - 93 . (in Chinese)
王建明 , 刘炜 , 艾延廷 , 等 . 圆柱一平板角区湍流流动控制的风洞试验研究 [J]. 实验流体力学 , 2011 , 25 ( 5 ): 10 - 15,20 .
Wang J M , Liu W , Ai Y T , et al . Experimental study on control of the cylinder-flat-plate turbulent junction flow [J]. Journal of Experiments in Fluid Mechanics , 2011 , 25 ( 5 ): 10 - 15,20 . (in Chinese)
朱博 , 汤更生 . 声学风洞流场低湍流度及频谱测量研究 [J]. 实验流体力学 , 2015 ( 4 ): 58 - 64 .
Zhu B , Tang G S . Low turbulence intensity and spectrum measurement research in aeroacoustic wind tunnel [J]. Journal of Experiments in Fluid Mechanics , 2015 , ( 4 ): 58 - 64 . (in Chinese)
曹贵瑜 , 潘亮 , 徐昆 . 高阶气体动理学格式在湍流数值模拟中的应用 [J]. 空气动力学学报 , 2021 , 39 ( 1 ): 168 - 176 .
Cao G Y , Pan L , Xu K . High-order gas-kinetic scheme for numerical simulation of turbulence [J]. Acta Aerodynamica Sinica , 2021 , 39 ( 1 ): 168 - 176 . (in Chinese)
冯俊 , 郑源 . 基于 CFD 的轴流泵三维湍流数值模拟 [J]. 流体机械 , 2012 , 40 ( 11 ): 33 - 36 .
Feng J , Zheng Y . Three-dimensional viscous numerical simulation of axial-flow pump based on CFD [J]. Fluid Machinery , 2012 , 40 ( 11 ): 33 - 36 . (in Chinese)
Brunton S L , Noack B R , Koumoutsakos P . Machine learning for fluid mechanics [J]. Annual Review of Fluid Mechanics , 2020 , 52 ( 1 ): 477 - 508 .
Zhang W W , Noack B R . Artificial intelligence in fluid mechanics [J]. Acta Mechanica Sinica , 2021 , 37 ( 12 ): 1715 - 1717 .
Brunton S L . Applying machine learning to study fluid mechanics [J]. Acta Mechanica Sinica , 2021 , 37 ( 12 ): 1718 - 1726 .
Abduljabbar R L , Dia H , Tsai P W , et al . Short-term traffic forecasting: An LSTM network for spatial-temporal speed prediction [J]. Future Transportation , 2021 , 1 ( 1 ): 21 - 37 .
周雪晴 , 张占松 , 朱林奇 , 等 . 基于双向长短期记忆网络的流体高精度识别新方法 [J]. 中国石油大学学报 (自然科学版) , 2021 , 45 ( 1 ): 69 - 76 .
Zhou X Q , Zhang Z S , Zhu L Q , et al . A new method for high-precision fluid identification in bidirectional long short-term memory network [J]. Journal of China University of Petroleum(Edition of Natural Science) , 2021 , 45 ( 1 ): 69 - 76 . (in Chinese)
朱静远 , 马思敏 , 袁坚 . 学习流体仿真中的高效长时序运动预测 [J]. 系统仿真学报 , 2023 , 35 ( 3 ): 435 - 453 .
Zhu J Y , Ma S M , Yuan J . Learning-based high-performance algorithm for long-term motion prediction of fluid flows [J]. Journal of System Simulation , 2023 , 35 ( 3 ): 435 - 453 . (in Chinese)
高榕 , 万以亮 , 邵雄凯 , 等 . 面向改进的时空 Transformer 的交通流量预测模型 [J]. 计算机工程与应用 , 2023 , 59 ( 7 ): 250 - 260 .
Gao R , Wan Y L , Shao X K , et al . Traffic flow forecasting model for improved spatio-temporal transformer [J]. Journal of Computer Engineering & Applications , 2023 , 59 ( 7 ): 250 - 260 . (in Chinese)
管林涛 , 黄志强 , 陈洋 . 一种基于时空Transformer的交通事故预测方法 [J]. 电脑与信息技术 , 2022 , 30 ( 1 ): 8 - 13 .
Guan L T , Huang Z Q , Chen Y . A method of traffic accident prediction based on spatio-temporal transformer [J]. Computer and Information Technology , 2022 , 30 ( 1 ): 8 - 13 . (in Chinese)
Jiang J , Li G , Jiang Y , et al . TransCFD: A transformer-based decoder for flow field prediction [J]. Engineering Applications of Artificial Intelligence , 2023 , 123 : 106340 .
Wang X , Zou S , Jiang Y , et al . Swin-FlowNet: Flow field oriented optimization aided by a CNN and Swin-Transformer based model [J]. Journal of Computational Science , 2023 , 72 : 102121 .
Yousif M Z , Zhang M , Yu L , et al . A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers [J]. Journal of Fluid Mechanics , 2023 , 957 : A6 .
Liu J , Shum K , Tse T K T , et al . Bidirectional prediction between wake velocity and surface pressure using deep learning techniques [J]. Physics of Fluids , 2024 , 36 ( 2 ): 025162 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
苏公网安备32010202012147号
