Int J Performability Eng ›› 2018, Vol. 14 ›› Issue (3): 434-444.doi: 10.23940/ijpe.18.03.p4.434444

• Original articles • Previous Articles     Next Articles

CNN-based Flow Field Feature Visualization Method

Tang Bina and Li Yib   

  1. aCollege of Shipbuilding Engineering, Harbin Engineering University, Harbin, 150001, China
    bCollege of Computer Science & Technology, Harbin Engineering University, Harbin, 150001, China

Abstract:

The feature-based visualization method can separate important areas for users from flow field data, which can better highlight the feature structure. However, most of the current feature extraction methods are only applicable to single typical features, and they need complex mathematical analysis. Based on the above reasons, this paper proposes a universal feature visualization method, recognizes demand in the region of flow data, shows the characteristics of structure protruding from the global visual effect in the design of a multi-dimension parallel convolution kernel that contains the recognition model, and further puts forward the method of feature visualization based on a convolutional neural network. Compared with the classical three level BP neural network model, our model gets a high accuracy rate. We verify the effectiveness of the method and solve the problem of insufficient expansion of existing methods.


Submitted on December 6, 2017; Revised on January 24, 2018; Accepted on February 15, 2018
References: 15