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

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...

Full description

Bibliographic Details
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
id ndltd-TW-090DYU00489004
record_format oai_dc
spelling ndltd-TW-090DYU004890042015-10-13T17:39:42Z http://ndltd.ncl.edu.tw/handle/32220713276223260253 Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks 類神經網路應用於雙相氣泡流相傳遞特性之即時決定 Po-Hung LIN 林柏宏 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. An-Shik YANG 楊安石 2002 學位論文 ; thesis 95 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 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.
author2 An-Shik YANG
author_facet An-Shik YANG
Po-Hung LIN
林柏宏
author Po-Hung LIN
林柏宏
spellingShingle Po-Hung LIN
林柏宏
Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks
author_sort Po-Hung LIN
title Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks
title_short Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks
title_full Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks
title_fullStr Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks
title_full_unstemmed Real-Time Determination of Phase Transport Characteristics in Bubbly Pipe Flows with Artificial Neural Networks
title_sort real-time determination of phase transport characteristics in bubbly pipe flows with artificial neural networks
publishDate 2002
url http://ndltd.ncl.edu.tw/handle/32220713276223260253
work_keys_str_mv AT pohunglin realtimedeterminationofphasetransportcharacteristicsinbubblypipeflowswithartificialneuralnetworks
AT línbǎihóng realtimedeterminationofphasetransportcharacteristicsinbubblypipeflowswithartificialneuralnetworks
AT pohunglin lèishénjīngwǎnglùyīngyòngyúshuāngxiāngqìpàoliúxiāngchuándìtèxìngzhījíshíjuédìng
AT línbǎihóng lèishénjīngwǎnglùyīngyòngyúshuāngxiāngqìpàoliúxiāngchuándìtèxìngzhījíshíjuédìng
_version_ 1717783206742196224