Canadian Journal of Chemical Engineering, Vol.72, No.3, 440-445, 1994
Neural-Network-Based Objective Flow Regime Identification in Air-Water 2-Phase Flow
The Kohonen self-organising neural network was applied to identify flow regimes in horizontal air-water flow. The neural network was trained with stochastic features derived from turbulent absolute pressure signals obtained across a range of flow regimes. The feature map succeeded in classifying samples into distinctive flow regime classes consistent with the visual flow regime observation.