Flow Regime Identification for Wet Gas Flow Based on WPT and RBFN
A novel noninvasive approach to the on-line flow regime identification for wet gas flow in a horizontally mounted pipeline is proposed in this paper. Research into the flow-induced vibration response for the wet gas flow with the conditions of pipe diameter 50mm, pressure from 0.25MPa to 0.35MPa, Lockhart-Martinelli parameter from 0.02 to 0.6, and gas Froude Number from 0.5 to 2.7, was conducted. The flow-induced vibration signals were measured by a vibration transducer installed by outside wall of pipe, and then the features from the vibration signals were extracted though wavelet package transform (WPT). A radial basis function network (RBFN) classifier with Gaussian basis function and the extracted features as inputs was developed to identify the three typical flow regimes including stratified wavy flow, annular mist flow, and slug flow for wet gas flow. The results show that the method can identify flow patterns effectively and its identification accuracy arrives at above 89％.
flow regime identification wet gas flow flow-induced vibration wavelet package transform radial basis function network
Chenquan Hua Changming Wang Yanfeng Geng
College of Mechanical Engineering Nanjing University of Science and Technology Nanjing,China College of Information & Control Engineering China University of Petroleum Dongying,China
国际会议
上海
英文
2852-2855
2009-11-20（万方平台首次上网日期，不代表论文的发表时间）