PROJECT TITLE :

Identification of Oil–Water Flow Patterns in a Vertical Well Using a Dual-Ring Conductance Probe Array

ABSTRACT:

During this paper, a dual-ring conductance probe array-based mostly well logging instrument was developed and a method based mostly on the support vector classification (SVC) and voting strategies was proposed to spot the oil–water flow patterns in an exceedingly vertical well. The patterns of the oil–water flow during a vertical well are classified into five patterns, i.e., pure oil part, pure water part, water-in-oil, oil-in-water, and transition. The conductance probe records the time-varying electrical characteristics of the oil–water flow, which is known as the initial signals. Various features are extracted to characterize every original signal. The options are initial treated through principal component analysis (PCA) to decrease knowledge redundancy in the original features. A nonlinear SVC model is then established to map the PCA-treated options into a flow pattern. To identify the flow pattern, it will be voted by a private probe or by probe combos. Experiments were administrated in a vertical pipe with an inner diameter of 125 mm and a height of 24 m on the economic-scale experimental multiphase flow setup in Daqing Oilfield, China. Within the experiment, the oil–water two-section flow was tested and the entire flow rate was varied from 10 to 200 per day, cherish zero.0094 to zero.1886 m , and therefore the water cut was varied from zero% to one hundred%. The results obtained demonstrate that the developed probe array-primarily based instrument will increase the reliability of flow pattern recognition, compared with the single probe-based instrument. The identification accuracy obtained using the optimal probe combination and the proposed method is ninety seven.ninety five% ± two.01% (mean ± std), and better than that obtained employing a single probe and also the SVC model.