【作者】 白博峰； 郭烈锦； 王忠勇； 张西民；

【Author】 Bai Bofeng;Guo Liejin;Wang Zhongyong;Zhang Ximin;State Key lab of Multiphase Flow in Power Engineering Xi’an Jiaotong University;

【机构】 西安交通大学动力工程多相流国家重点实验室；

【摘要】 在宽广的实验参数范围内测量了水平管内油气水多相流动时压力和压差信号,对信号的时域、频域、小波尺度域、分形等特征进行了特征分析,建立了流型的规则识别和模式识别的融合方法。经过实验测试,该方法可以识别出泡状流、分层流、间歇流和环状流,流型识别率高于90%。更多还原

【Abstract】 Both pressure and differential pressure signals were measured for oil-gas-water multiphase flow in wide ranges of flow parameters in horizontal pipe.The signals’ features were extracted and analyzed,which included time domain features,frequency domain features,scale domain features and fractal features.On the bases of the feature analysis,the online recognition of flow regimes was proposed which was a fusion method combining the regulations of flow regimes and the pattern recognition.The proposed method was examined in the oil-gas-water loop and results showed that bubble flow,stratified flow,intermittent flow and annular flow could be identified with more than 90% accuracy.更多还原