With the development of artificial intelligence, artificial neural network (ANN) has been widely used
in recent years. In this paper, the method is applied to the prediction of the fluid force exerted on the bluff body
when flow passes around. Firstly, back propagation (BP) model and convolutional neural network (CNN) model
are introduced; then the mapping relation between the shape of bluff body and the fluid force, which is calculated
by computational fluid dynamics (CFD), is established by sample training. Finally, it is used to predict the fluid
force of the new shape bluff body. By taking the CFD results as benchmark, CNN model is capable of predicting
both the resistance and lift force, while BP model is incompetent to predict lift force. Furthermore, both CNN
and BP models have a significant advantage in prediction efficiency, compared by CFD calculation method.
ZHAO Yong (赵勇), MENG Yang (孟杨), YU Pengyao (于鹏垚), WANG Tianlin (王天霖), SU Shaojuan (苏绍娟)
. Prediction of Fluid Force Exerted on Bluff Body by Neural Network Method[J]. Journal of Shanghai Jiaotong University(Science), 2020
, 25(2)
: 186
-192
.
DOI: 10.1007/s12204-019-2140-0
[1] WANG Y L, LIU Y Z, MIAO G P. Three-dimensional numerical simulation of viscous flow around circular cylinder [J]. Journal of Shanghai Jiao Tong University,2001, 35(10): 1464-1469 (in Chinese).
[2] JOHNSON S A, THOMPSON M C, HOURIGAN K.Flow past elliptical cylinders at low Reynolds numbers[C]//14th Australasian Fluid Mechanics Conference.Adelaide, Australia: Elsevier, 2001: 343-346.
[3] JAIMAN R K, SEN S, GURUGUBELLI P S. A fully implicit combined field scheme for freely vibrating square cylinders with sharp and rounded corners [J].Computers & Fluids, 2015, 112: 1-18.
[4] MIYANAWALA T P, JAIMAN R K. An efficient deep learning technique for the Navier-Stokes equations: Application to unsteady wake flow dynamics [EB/OL]. (2018-08-25) [2019-05-20].https://arxiv.org/abs/1710.09099.
[5] LI B Y, LI Y X, WANG H T, et al. Compensation of automatic weighing error of belt weigher based on BP neural network [J]. Measurement, 2018, 129: 625-632.
[6] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradientbased learning applied to document recognition [J].Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[7] HUBEL D H, WIESEL T N. Early exploration of the visual cortex [J]. Neuron, 1998, 20(3): 401-412.
[8] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017,60(6): 84-90
[9] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks [C]//13th European Conference on Computer Vision. Zurich, Switzerland:Springer, 2014: 818-833.
[10] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [EB/OL]. (2015-04-10) [2019-05-20].https://arxiv.org/abs/1409.1556.
[11] GIRSHICK R, DONAHUE J, DARRELLAND T, et al. Rich feature hierarchies for object detection and semantic segmentation [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus,OH: IEEE, 2014: 580-587.
[12] GIRSHICK R. Fast R-CNN [C]//IEEE International Conference on Computer Vision. Santiago, Chile:IEEE, 2015: 1440-1448.
[13] REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(6): 1137-1149.
