A Hopfield neural network for flow field computation based on particle image velocimetry/particle tracking velocimetry image sequences

Author

Knaak, M. ; Rothlübbers, C. ; Orglmeister, R.

Author_Institution

Inst. of Electron. & Lighting Technol., Tech. Univ. Berlin, Germany

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

48

Abstract

A new application of a Hopfield network for the detection of particle pairs in particle image velocimetry/particle tracking velocimetry (PIV/PTV) is described. PIV/PTV are the most advanced techniques for the examination of flow fields. Our aims are to apply these techniques to fluid mechanics and the investigation of hydraulic turbomachinery and artificial heart valves. To obtain correct particle correspondences in subsequent images, a specific cost function is defined and then mapped onto a two-dimensional Hopfield network. First investigations show better performance than conventional techniques for PTV/PIV. In comparison to conventional nearest neighbor techniques, the number of correct particle pairs detected significantly increases, whereas the number of mismatches decreases

Keywords

Hopfield neural nets; fluid dynamics; image sequences; physics computing; velocimeters; Hopfield neural network; artificial heart valves; flow field computation; fluid mechanics; hydraulic turbomachinery; image sequences; particle image velocimetry; particle pairs; particle tracking velocimetry; Artificial heart; Blades; Computer networks; Cost function; Heart valves; Hopfield neural networks; Image sequences; Nearest neighbor searches; Particle tracking; Turbomachinery;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611633

Filename

611633