Title :
Identification of gas-liquid two-phase flow regime and quality
Author :
Sun, Tao ; Zhang, Hongjian ; Hu, Chiying
Author_Institution :
Dept. of Control Sci. & Eng., Zhejiang Univ., Hangzhou, China
fDate :
6/24/1905 12:00:00 AM
Abstract :
A novel scheme to identify flow regime and measure quality in gas-liquid two-phase using differential pressure signal is proposed. Flow regime is identified based on wavelet analysis and back-propagation (BP) neural network. Nine-scale Haar wavelet decomposition is performed on differential pressure signal. The scale energy ratio is extracted as the input of BP network to identify flow regime. Based on the flow regime information, relation between quality and pressure signal is fitted by polynomial. Experiments show that in annular flow, the polynomial fits well.
Keywords :
backpropagation; flow measurement; neural nets; polynomials; two-phase flow; wavelet transforms; Haar wavelet decomposition; annular flow; backpropagation neural network; differential pressure signal; flow regime identification; gas-liquid two-phase flow; polynomial fitting; quality measurement; scale energy ratio; wavelet analysis; Chemical industry; Data acquisition; Fluid flow measurement; Neural networks; Polynomials; Pressure measurement; Signal analysis; Signal processing; Testing; Wavelet analysis;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 2002. IMTC/2002. Proceedings of the 19th IEEE
Print_ISBN :
0-7803-7218-2
DOI :
10.1109/IMTC.2002.1007175
