Using ART2 networks to deduce flow velocities

A novel algorithm for obtaining flow velocity vectors using ART2 networks (based on adaptive resonance theory) is presented. The method involves tracking the movement of groups of seeding particles in a fluid space through the analysis of two successive images. Simulated flows, created artificially by shifting the particles through known distances or rotating through known angles, were used to establish the accuracy of the technique in predicting displacements. Accuracies were quantified by comparison with known displacements and were found to improve with increasing displacement, angle of rotation and size of the sampling window. In addition, the technique has been extended to derive qualitative and quantitative information for a practical case of natural convective flow.