帮助 关于我们

返回检索结果

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

叶舒然 1,2   张珍 1,2   宋旭东 3   杜特专 1,2   王一伟 1,2 *   黄晨光 1,2   陈耀松 3  
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    
引证文献 6 篇

1 文永 基于深度学习的超高速碰撞碎片云模拟 固体力学学报,2020,41(5):455-469
被引 2 次

2 武频 基于自编码器和LSTM的模型降阶方法 空气动力学学报,2021,39(1):73-81
被引 2 次

显示所有6篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号