The Identification Method Of Gas-Liquid Two-Phase Flow Regime Based On Wavelet And Hilbert-Huang Transform

There are widely gas-liquid two-phase flows in modern industry field. The gas-liquid two-phase flows which has different flow patterns have different flow and heat transfer features, so it is important to correctly recognize the flow patterns of two-phase flows. There are two traditional methods to recognize flow patterns, one of which is the observation or measurement and anther is transition formulas or the flow pattern maps. The traditional recognition methods of flow patterns depends largely on subjective judgment of researchers and make the on-line recognition of flow patterns impossible, so the traditional recognition methods need to be improved.The differential pressure fluctuation signals of the air-water two-phase flows in horizontal pipe are adopted and analyzed on air-water two-phase flow test equipment. wavelet transform, Hilbert-huang transform and neural network are used in flow regime identification. Intelligent regime-identification method using neural network is discussed systematically from the aspects of theory and experiment.Firstly, the pressure-difference fluctuation signals are analyzed by utilizing FFT(Fast Fourier Transform) transform, wavelet transform and Hilbert-huang transform. Then the flow features are obtained by extracting wavelet energy, wavelet packet energy, wavelet entropy and IMF(Intrinsic Mode Function) energy. Secondly air-water two-phase flow pattern recognition model by utilizing BP(Back Propagation) neutral network, RBF(Radial Basic Function) neutral network and Elman neutral network. Lastly by training network of BP RBF and Elman with different samples of different eigenvectors, these last identifying models are regarded as pattern recognition network. The simulation result shows that the combination of IMF energy and Elman neutral network is the best model among these models, but the difference of identifying rate is not distinct. All these provide a new way to identify the gas-liquid two-phase flow regimes from the aspects oftheory and technology.