Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks

• Main Authors: Po-Hung LIN, 林柏宏
• Other Authors: An-Shik YANG
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/32220713276223260253

碩士 === 大葉大學 === 機械工程研究所 === 90 === The phase transport phenomenon of the high-pressure two-phase turbulent bubbly flow involves complicated interfacial interactions of the mass, momentum, and energy transfer processes between phases, revealing that an enormous effort is required in charactering the liquid-gas flow behavior. Nonetheless, the immediate information of bubbly flow characteristics is often desired for many industrial applications. This investigation aims to demonstrate the successful use of neural networks in the real-time determination of two-phase flow properties at elevated pressures. Three back-propagation neural networks, trained with the simulation results from Liu’s experimental database and comprehensive theoretical model, are established to predict the distributions of void fraction and axial liquid/gas velocities of upward turbulent bubbly pipe flows at pressures covering 1 MPa and 3.5 to 7.0 MPa. Comparisons of the predictions with the test target vectors indicate that the averaged root-mean- squared error for each one of three back-propagation neural networks is well within 4.59 %. In addition, this study appraises the effects of different network parameters, including number of hidden nodes, type of transfer function, number of training pairs, learning rate-increasing ratio, learning rate-decreasing ratio, and momentum value, on the training quality of neural networks.