Modern Solution for Oil Well Multiphase Flows Water Cut Metering

Abstract

An innovative technology for determining the water cut in well products (without preliminary separation into liquid and gas fractions) uses the results of electrical impedance measurements and its dependence on the alternating current frequency. Water cut meter's sensor includes measuring and current electrodes, between which there is a well's multiphase flow. Imaginary and real components of the impedance quantitatively describe the component composition of the studied oil and gas-water mixtures. In this process, machine learning methods and developed algorithms for features extraction are used. Depending on the type of emulsion, two independent sensors are used in the oil pipeline, one of which measures in a direct emulsion, the other in an inverse emulsion. Tests of the described water cut meter on flow loops in the Russian Federation and in the Netherlands, as well as studies of well flows in oil production facilities in the Russian Federation and the Kingdom of Saudi Arabia, have shown high measurement accuracy in the full range of water cut, with high gas content, as well as at high salinity and in a wide range of flow rates. To do so, modern methods of data classification based on neural networks and regression modeling implemented using machine learning are employed. It was found that the flow rates of liquid and gas do not affect the results of measuring the water cut due to the high frequency of the impedance measurements - up to 100 thousand measurements per second. Use of in-line multiphase water cut meter makes it possible to apply intelligent methods of processing field information and accumulate statistical data for each well, as a big data element for predicting and modeling in-situ processes. It will also allow to introduce promising production processes aimed at increasing oil production and monitoring the baseline indicators of the well. Novelty of the presented technology: Solution of the problem of high-speed determination of water cut in a multiphase flow without preliminary separation using impedance metering. Creation of mathematical models of multiphase flow and methods for determining the type of flow and the type of emulsion. Machine learning methods and neural networks employment for high-speed analysis of flow changes. Development, successful testing and implementation of an affordable multiphase water cut meter of our own design, which has no analogs in industrial applications.