The use of neural techniques in PIV and PTV

The neural network method uses ideas developed from the physiological modelling of the human brain in computational mechanics. The technique provides mechanisms analogous to biological processes such as learning from experience, generalizing from learning data to a wider set of stimuli and extraction of key attributes from excessively noisy data sets. It has found frequent application in optimization, image enhancement and pattern recognition, key problems in particle image velocimetry (PIV). The development of the method and its principal categories and features are described, with special emphasis on its application to PIV and particle tracking velocimetry (PTV). The application of the neural network method to important categories of the PIV image analysis procedure is described in the present paper. These are image enhancement, fringe analysis, PTV and stereo view reconciliation. The applications of common generic net types, feed-forwards and recurrent, are discussed and illustrated by example. The key strength of the neural technique, its ability to respond to changing circumstances by self-modification or regulation of its processing parameters, is illustrated by example and compared with conventional processing strategies adopted in PIV.

[1]  The application of an in-line, stereoscopic, PIV system to 3-component velocity measurements , 1995 .

[2]  T. Utami,et al.  Visualization and picture processing of turbulent flow , 1984 .

[3]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[4]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[5]  B Kosko,et al.  Adaptive bidirectional associative memories. , 1987, Applied optics.

[6]  I. Grant,et al.  An investigation of the performance of multi layer, neural networks applied to the analysis of PIV images , 1995 .

[7]  Brian J. Thompson,et al.  Holographic Methods For Particle Size And Velocity Measurement - Recent Advances , 1989, Other Conferences.

[8]  Ian Grant,et al.  Directional ambiguity resolution in particle image velocimetry by pulse tagging , 1990 .

[9]  Antonio Cenedese,et al.  Recognition of partially overlapped particle images using the Kohonen neural network , 1995 .

[10]  Xu Wang,et al.  Directionally-unambiguous, digital particle image velocimetry studies using a image intensifier camera , 1995 .

[11]  Ya-Fan Zhao,et al.  Three component flow mapping - Experiences in stereoscopic PIV and holographic velocimetry , 1991 .

[12]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[13]  Ian Grant,et al.  Neural network method applied to particle image velocimetry , 1993, Optics & Photonics.

[14]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[15]  G. B. Tatterson,et al.  Application of image processing to the analysis of three-dimensional flow fields , 1984 .

[16]  Antonio Cenedese,et al.  Neural Net for Trajectories Recognition in a Flow , 1992 .

[17]  I. Grant.  Particle image velocimetry: A review , 1997 .

[18]  Ian Grant,et al.  Method for the efficient incoherent analysis of particle image velocimetry images , 1989 .

[19]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.