中文摘要：

基于单相流组合仪表和数据挖掘技术,提出了一种液液两相流参数测量的新方法。单相流组合仪表由文丘里管和椭圆齿轮流量计组成。所采用的数据挖掘技术包括偏最小二乘法（Partial Least Squares,PLS）和最小二乘支持向量机（Least-Squares Support Vector Machine,LS-SVM）。为克服相含率对液液两相流参数测量的影响,基于16电极阵列式电导传感器和数据挖掘技术设计两相流主导相判别器,以提供文丘里管仪表系数的选择依据。实际测量过程中,文丘里管和椭圆齿轮流量计分别获得油水两相流差压和总体积流量,主导相判别器识别两相流中起主导作用的相,然后根据判别结果选择文丘里管仪表系数,最终获得油水两相流的总体积流量、混合密度和总质量流量。研究结果表明,所提出的油水两相流测量新方法是有效的,总体积流量、混合密度和总质量流量的最大测量误差分别小于1.0%、4.6%和4.5%。

英文摘要：

Based on a hybrid flowmeter and data mining techniques,a new method was proposed for oil-water two-phase flow measurement.The hybrid flowmeter consists of an oval gear flowmeter and a Venturi meter.The adopted data mining techniques include Partial Least Squares（PLS） and Least-Squares Support Vector Machine（LS-SVM）.In order to overcome the influence of oil phase fraction in the two-phase flow on the measurement results,a dominant phase identifier was developed based on a 16-electrode conductivity sensor and data mining techniques,so that the meter coefficient of Venturi meter could be selected according to the identified dominant phase of the oil-water two-phase flow.In the practical measurement process,the differential pressure and the total volume flowrate are firstly obtained by the Venturi meter and the oval gear flowmeter,respectively.Meanwhile,the dominant phase of the oil-water two-phase flow is identified and the meter coefficient of the Venturi meter is selected.Finally,the total volume flow rate,the density and the total mass flow rate of the two-phase flow are obtained.Research results show that the proposed method is effective and the measurement accuracy is satisfactory.The maximum relative measurement errors of total volume flow rate,equivalent density and total mass flow rate are less than 1%,4.6% and 4.5%,respectively.