Identication of Oil-Water Flow Pattes Using
Conductance Probe in Vertical Well
this paper, a sensor of conductance probe is
proposed to detect the electrical characteristics of the oil-water
ow in vertical well. Statistic and wavelet packet decomposition
are employed to extract the features of the voltage response of
conductance probe. A method based on principal component
analysis (PCA) and support vector classication (SVC) is
proposed to identify the ow patterns from the water-in-oil,
transition, and oil-in-water ow patterns. Experiments were
carried out in a mm vertical well within the ow rate range of
m
3
/d and the water content range of in Daqing
Oileld, China. Experimental results reveal that the optimal
identication accuracy of training set is obtained as and
that of testing set is achieved as Corresponding quantity
of of principal component is and cross validation accuracy is
Consequently, the proposed method is feasible and effective
to identify the ow patterns of oil-water ow using conductance
probe sensor in vertical well.
61121003,
61225006,61327011, 61370016.