Video based classification of two phase flows using linear discriminant analysis and expectation maximization clustering

Abstract

Paper presented at the 8th International Conference on Heat Transfer, Fluid Mechanics and Thermodynamics, Mauritius, 11-13 July, 2011.

Two-phase adiabatic flow of refrigerant R134a was studied and an automated flow regime detection algorithm was developed. For a saturation temperature of 15°C video data was captured for mass fluxes from 100 kg/m²s to 400 kg/m²s in smooth horizontal tubes. The vapour quality varied between 0 and 1, the I.D. was 8 mm. Slug flow, intermittent flow and annular flow were discerned. Several parameters are computed for each video, characterizing the video with both temporal and spatial information. Linear discriminant analysis is used to reduce the dimension of the data. The classification is done by unsupervised clustering with the expectation maximization algorithm. All of the slug and annular flows are correctly recognized, intermittent flows are identified with 95% accuracy.