Identification of Boiling Two-phase Flow Patterns in Water Wall Tube Based on BP Neural Network

In this paper, the boiling phenomena of steam boiler under atmospheric pressure are simulated by using the UDF program of CFD software. Characteristics including pressure, temperature and vapor fraction respectively for bubble, slug and annular flow patterns are extracted as the input characteristic vectors of the BP neural network for the purpose of identifying the two-phase (vapor/liquid) boiling flow patterns within wall tubes. It reveals that the rate of recognition accuracy of flow patterns is up to 95.24%. By analyzing relations between flow pattern, wall temperature and wall heat transfer coefficient, it is found that changes in flow patterns will cause drastic variation in heat transfer coefficient of the wall surface, and the coefficient reduces rapidly as the wall temperature increases and eventually converge to a minimum.