Classifying vortex wakes using neural networks. (16th February 2018)

• Record Type: Journal Article
• Authors: Colvert, Brendan; Alsalman, Mohamad; Kanso, Eva
• Is Part Of: Bioinspiration & biomimetics. Volume 13:Number 2(2018:Jun.)
• Publication Date: 2018-02-16
• Subjects: sensing -- swimming -- unsteady flows; Biomimetics -- Periodicals; Biomedical materials -- Periodicals; Medical innovations -- Periodicals; Biomedical engineering -- Periodicals; 600
• DOI: 10.1088/1748-3190/aaa787
• Languages: English
• ISSNs: 1748-3182

Abstract

Abstract: Unsteady flows contain information about the objects creating them. Aquatic organisms offer intriguing paradigms for extracting flow information using local sensory measurements. In contrast, classical methods for flow analysis require global knowledge of the flow field. Here, we train neural networks to classify flow patterns using local vorticity measurements. Specifically, we consider vortex wakes behind an oscillating airfoil and we evaluate the accuracy of the network in distinguishing between three wake types, 2S, 2P + 2S and 2P + 4S. The network uncovers the salient features of each wake type.