Measurement of three-dimensional velocity profiles using forward-scattering particle image velocimetry (FSPIV) and neural net pattern recognition

We employ Forward Scattering Particle Image Velocimetry (FSPIV) to measure all three components of the velocity of a buoyant polystyrene particle in oil. Unlike conventional particle image velocimetry (PIV) techniques, FSPIV employs coherent or partially coherent back illumination and collects the forward scattered wavefront; additionally, our field-of-view is microscopic. Using FSPIV, it is possible to easily identify the particle's centroid and to simultaneously obtain the fluid velocity in different planes perpendicular to the viewing direction without changing the collection or imaging optics. We have trained a neural network to identify the scattering pattern as function of displacement along the optical axis (axial defocus) and determine the transverse velocity by tracking the centroid as function of time. We present preliminary results from Mie theory calculations which include the effect of the imaging system. To our knowledge, this is the first work of this kind; preliminary results are encouraging.