自动编码器在流场降阶中的应用
Applications of autoencoder in reduced-order modeling of flow field
查看参考文献18篇
文摘
|
自动编码器作为一种压缩算法,在数据降维和去噪等方面有着广泛实践,有条件作为一种降阶方法在流场识别与数据处理方面得到应用。文章中以圆柱绕流为例,首先对圆柱后速度场建立了编码模型,用来对原始数据进行降维和特征提取,之后将编码后的数据与流场特征量相关联,建立了由流场编码回归圆柱表面压力系数的神经网络,探索了降维后数据的应用。结果表明,自动编码得到的结果能够承载原始速度场的主要信息,解码后速度场与原速度场测试均方根误差小于0.02,压力回归测试均方根误差可小于0.1。说明自动编码器能够作为一种流场的特征提取和降阶方法,在未来得到更广泛的应用。 |
其他语种文摘
|
Known as a compression algorithm,autoencoder is widely used for dimensional reduction and image denoising.It can be used in flow field identification and data processing as a reduced-order method.Moreover,massive labeled flow field data makes it promising to apply machine learning in fluid dynamics.Taking the flow around a cylinder as an example,the autoencoder model of the velocity field behind the cylinder is established to reduce the order and extract features from the original data.This model encodes the 1394 velocity components into 32- dimensional data,and trains them through self-supervised learning.For well-trained autoencoder models,the basis for evaluating them is to discuss whether the original flow field could be reconstructed.The application of the low dimensional encoded data is explored by correlating it with the flow field sensitive outputs,and a neural network for the regression of surface pressure of cylinder based on encoded data is established.It is verified that the result of the autoencoder has inherited the main information in the original velocity field.The root mean square error of the decoded velocity field compared with the original field is less than 0.02,and the root mean square error of the pressure coefficient regression network can be less than 0.1.The above results indicate that the autoencoder can be used in the future as a feature extraction and order reduction method of flow field. |
来源
|
空气动力学学报
,2019,37(3):498-504 【核心库】
|
DOI
|
10.7638/kqdlxxb-2019.0039
|
关键词
|
机器学习
;
自动编码器
;
圆柱绕流
;
流场特征提取
;
压力预测
|
地址
|
1.
中国科学院力学研究所, 中国科学院流固耦合系统力学重点实验室, 北京, 100190
2.
中国科学院大学工程科学学院, 北京, 100049
3.
北京大学工学院, 北京, 100871
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
0258-1825 |
学科
|
自动化技术、计算机技术;航空 |
基金
|
国家重点研发计划
|
文献收藏号
|
CSCD:6540701
|
参考文献 共
18
共1页
|
1.
Lecun Y. Deep learning.
Nature,2015,521:436-444
|
被引
2890
次
|
|
|
|
2.
Trancy B D.
A machine learning strategy to assist turbulence model development. AIAA 2015-1287,2015
|
被引
1
次
|
|
|
|
3.
Ling J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance.
Journal of Fluid Mechanics,2016,807:155-166
|
被引
60
次
|
|
|
|
4.
Strofer. Data-driven,physicsbased feature extraction from fluid flow fields.
Communications in Computational Physics,2018,25(3):625-650
|
被引
1
次
|
|
|
|
5.
Jin X. Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder.
Physics of Fluids,2018,30(4):047105
|
被引
11
次
|
|
|
|
6.
Farahat A K. Efficient greedy feature selection for unsupervised learning.
Knowledge and Information Systems,2013,35(2):285-310
|
被引
1
次
|
|
|
|
7.
Kaiser E. Cluster-based reduced-order modelling of a mixing layer.
Journal of Fluid Mechanics,2014,754:365-414
|
被引
6
次
|
|
|
|
8.
O'shea T J. An introduction to deep learning for the physical layer.
IEEE Transactions on Cognitive Communications & Networking,2017,3(4):563-575
|
被引
79
次
|
|
|
|
9.
Liou C Y. Autoencoder for words.
Neurocomputering,2014,139:84-96
|
被引
10
次
|
|
|
|
10.
Iliadis M. Deep fully-connected networks for video compressive sensing.
Digital Signal Processing,2017
|
被引
1
次
|
|
|
|
11.
Zhang Z. Application of deep learning method to Reynolds stress models of channel flow based on reduced-order modeling of DNS data.
Journal of Hydrodynamics,2018,31(11):58-65
|
被引
2
次
|
|
|
|
12.
Nair V. Rectified linear units improve restricted Boltzmann machines.
Proceedings of the 27th International Conference on Machine Learning,2010:807-814
|
被引
118
次
|
|
|
|
13.
Chai T. Root mean square error(RMSE) or mean absolute error(MAE)?-Arguments against avoiding RMSE in the literature.
Geoscientific Model Development,2014(7):1247-1250
|
被引
1
次
|
|
|
|
14.
Krizhevsky A. Image net classification with deep convolutional neural networks.
Neural Information Processing Systems-Volume 1(NIPS'12),2012:1097-1105
|
被引
1
次
|
|
|
|
15.
陈海. 基于深度学习的翼型气动系数预测.
空气动力学学报,2018,36(2):294-299
|
被引
29
次
|
|
|
|
16.
Sun W. A sparse auto-encoderbased deep neural network approach for induction motor faults classification.
Measurement,2016,89(ISFA):171-178
|
被引
27
次
|
|
|
|
17.
Schafer M. Benchmark computations of laminar flow around a cylinder.
Notes on Numerical Fluid Mechanics,1996,48:547-566
|
被引
3
次
|
|
|
|
18.
Hinton G E. Reducing the dimensionality of data with neural networks.
Science,2006,313:504-507
|
被引
1668
次
|
|
|
|
|