Deep Feature Learning and Feature Clustering of Streamlines in 3D Flow Fields
Flow field visualization refers to converting data of fluid motion into visual forms for better understanding and analysis of flow in the field.Using streamlines for flow field visualization is currently the most popular method.This paper proposes a method for learning and clustering 3D flow field streamline features.Firstly,a convolutional autoencoder-based method is de-signed to extract streamline features.The autoencoder in this method consists of an encoder and a decoder.The encoder uses con-volutional layers to reduce the dimensions of input streamlines to extract features,while the decoder uses transpose convolution to upsample the streamline features to restore the streamlines.By continuously reducing the difference between input and restored streamlines through training,the encoder can extract more accurate streamline features.Secondly,this paper improves the CFS-FDP(clustering by fast search and find of density peaks)algorithm for clustering streamline features.To address the issue of manually selecting cluster centers and the problem of sensitivity to distance parameters in the CFSFDP algorithm,this paper im-proves its metric calculation method,realizes automatic selection of cluster centers,and introduces adaptive calculation of trunca-tion distance parameters using Gaussian kernel density estimation.Experimental results show that this method has good perfor-mance in learning streamline features and clustering.
Flow field visualizationStreamline featureConvolutional autoencoderClustering
NETL
NSTL
万方数据
