Using Neural Networks for Determining Velocity Vectors of Air Flow Visualized by Helium Bubbles

SŤASTNÝ JIŘI, RICHTER JAN, SŤASTNÝ PETR. 2014. Using Neural Networks for Determining Velocity Vectors of Air Flow Visualized by Helium Bubbles. Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, 62(4): 757–768. One of the important characteristics of air fl ow is the velocity of fl ow. To determine the speed, in addition to other methods, we also use the helium bubbles seeding visualization method, when bubbles are injected into the air stream so that the air fl ow is obvious to the eye. If a video of such fl ow is taken, it is possible to determine velocity vectors in a pair of consecutive frames of this video footage, derived from the change in position of individual bubbles. This article describes a method of monitoring the bubbles in consecutive video frames. During this process, helium bubbles are detected in the fi rst image of the pair, either by a fi rmly defi ned procedure, or with the use of a neural network. For detected bubbles, the velocity vectors are determined according to the way in which they move, therefore, according to their location in the following frame. Another neural network then determines the velocity vector at any point of image, which will be implemented in the construction of vector maps for the fi rst image. A vector map is used for comprehensive evaluation of air fl ow and thus, plays an important role in the development of ventilation and air conditioning systems.