摘要
The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes.
The knowledge of flow regimes is very important in the study of a two phase flow system. A new flow regime identification method based on a Probability Density Function (PDF) and a neural network is proposed in this paper. The instantaneous differential pressure signals of a horizontal flow were acquired with a differential pressure sensor. The characters of differential pressure signals for different flow regimes are analyzed with the PDF. Then, four characteristic parameters of the PDF curves are defined, the peak number (K 1 ), the maximum peak value (K 2 ), the peak position (K 3 ) and the PDF variance (K 4 ). The characteristic vectors which consist of the four characteristic parameters as the input vectors train the neural network to classify the flow regimes. Experimental results show that this novel method for identifying air water two phase flow regimes has the advantages with a high accuracy and a fast response. The results clearly demonstrate that this new method could provide an accurate identification of flow regimes.
基金
Project supported by the National High Technology and Research Development Program Special Fund of China (GrantNo: 2002AA616050).
