Advanced neural network prediction and system identification of liquid-liquid flow patterns in circular microchannels with varying angle of confluence

Abstract

The flow pattern map for liquid-liquid system in a circular microchannel of 600μm was experimentally investigated for a varying confluence angle (10–170 degree) of inlet fluids. The experimental results showing distinguishing nature of transition boundaries were established using graphical interpretation. Investigations were carried out to find a better objective flow pattern indicator for a vast flow pattern observations. Studies on advanced feed-forward back-propagation networks and radial basis networks such as CFN, ANN-FF, ANN-PR, PNN, GRNN and ANFIS showed that GRNN (Generalized Regression Neural Network) showed a better prediction over other prediction techniques with a R2 value of 0.988. The relative impact of input variables such as confluence angle, superficial velocity of dodecane and superficial velocity of water on flow pattern formation was found to be 17.78%, 43.30% and 38.92% respectively. The discrete and continuous time state space models for the system was also developed and interpreted in detail using system identification technique for the better understanding of the system.