Water cut measurement of oil–water flow in vertical well by combining total flow rate and the response of a conductance probe

Abstract

In this paper, a conductance probe-based well logging instrument was developed and the total flow rate is combined with the response of the conductance probe to estimate the water cut of the oil–water flow in a vertical well. The conductance probe records the time-varying electrical characteristics of the oil–water flow. Linear least squares regression (LSR) and nonlinear support vector regression (SVR) were used to establish models to map the total flow rate and features extracted from the probe response onto the water cut, respectively. Principal component analysis (PCA) and partial least squares analysis (PLSA) techniques were employed to reduce data redundancy within the extracted features. An experiment was carried out in a vertical pipe with an inner diameter of 125 mm and a height of 24 m in an experimental multi-phase flow setup, Daqing Oilfield, China. In the experiment, oil–water flow was used and the total flow rate varied from 10 to 200 m3 per day and the water cut varied from 0% to 100%. As a direct comparison, the cases were also studied when the total flow rate was not used as an independent input to the models. The results obtained demonstrate that: (1) the addition of the total flow rate as an input to the regression models can greatly improve the accuracy of water cut prediction, (2) the nonlinear SVR model performs much better than the linear LSR model, and (3) for the SVR model with the total flow rate as an input, the adoption of PCA or PLSA not only decreases the dimensions of inputs, but also increases prediction accuracy. The SVR model with five PCA-treated features plus the total flow rate achieves the best performance in water cut prediction, with a coefficient of determination (R2) as high as 0.9970. The corresponding root mean squared error (RMSE) and mean quoted error (MQE) are 0.0312% and 1.99%, respectively.

CNN-Based Volume Flow Rate Prediction of Oil–Gas–Water Three-Phase Intermittent Flow from Multiple Sensors

“…Mean quoted error (MQE) [ 13 ] where N is the sample size; denotes the i -th predicted volume flow rate of one individual phase, i.e., , or ; denotes the i -th reference volume flow rate of one individual phase, i.e., Q o , Q g or Q w ; represents the mean value of and represents the maximum of all reference volume flow rates of one individual phase.…”

“…In 2014, S. Fan and T. Yan presented a method based on a multilayer feedforward neural network and conductance probes to obtain the gas and liquid flow rates of an air–water two-phase slug flow [ 12 ]. In 2015, J. Chen and L. Xu et al measured the water cut of an oil–water two-phase flow on the basis of support vector regression (SVR) by combining the total flow rate and the response of a conductance probe [ 13 ]. In 2016, S. Azizi, E. Ahmadloo and M. M. Awad predicted the void fraction of a gas–liquid two-phase flow using multilayer perceptron neural networks with the pipe inclination angle and the superficial Reynolds number of gas and liquid as the input parameters [ 14 ].…”

Water holdup measurement of oil–water two-phase flow in a horizontal well using a dual-circle conductance probe array

“…The 24 probes are located on two concentric circles. The dual-circle conductance probe array was applied to measure the water cut and identify flow patterns of the oil-water flow in a 125 mm inner diameter vertical well, respectively [31,32]. In this paper, the dual-circle conductance probe array was used to measure the water holdup of the oil-water two-phase flow in a horizontal well.…”

Non-invasive measurement of oil-water two-phase flow in vertical pipe using ultrasonic Doppler sensor and gamma ray densitometer

“…Single sensing device is often use in measuring a parameter of flow such as velocity, phase volume fraction, pressure gradient, flow pattern identification and characterisation (Shamsul et al, 2015). For example, sensors frequently used in measuring oil-water flow include pressure transducers (Da et al, 2007;Flores et al, 1998;Shamsul et al, 2015), ultrasonic sensors (Dong et al, 2015;Kouame et al, 2003;Morriss and Hill, 1991;Tan et al, 2016), gamma densitometer (Descamps et al, 2006;Kumara et al, 2010a;Tesi, 2011), conductance probes (Chen et al, 2015;Du et al, 2012;Jana et al, 2006;Oddie, 1992;Shamsul et al, 2015) capacitance probes (Ismail et al, 2005) and electromagnetic flowmeters (Faraj et al, 2015;Jin et al, 2020).…”

“…Conductance sensor, even though it is an intrusive device, has been widely used for measuring the phase fraction or the flow velocity of oil-water two-phase flow (Chen et al, 2015). It records the time-varying electrical conductive characteristics of the oil-water flow, However, conductance sensors are significantly affected by phase inversion when flow changes from water-continuous flow to oil-continuous flow, the detection has to change from conductance to capacitance (Figueiredo et al, 2016).…”