Oil-water separation prediction method and device based on microcosmic distribution derivation of liquid drops

Abstract

The invention relates to an oil-water separation prediction method and device based on droplet microscopic distribution derivation, and the method comprises the following steps: 1) obtaining basic structure parameters and common operation conditions of a three-phase separator based on design or on-site operation, so as to determine the initial boundary conditions of the evolution process of oil-water droplets at the inlet of the three-phase separator; 2) solving the evolution process of the average diameter of the liquid drops of the oil-water emulsion in the oil-water retention time of the three-phase separator based on the test data of the demulsifier used by the three-phase separator in field operation or experimental test; 3) based on a Stokes formula sedimentation theory, oil-water emulsion droplet diameter distribution and a droplet two-dimensional coalescence model, solving droplet sedimentation separation efficiency under different droplet diameters; and 4) simulating by adopting a deep learning model and an SVM algorithm, and finally predicting the water content of the crude oil at the outlet of the three-phase separator. According to the method, a mechanism model and an artificial intelligence algorithm are integrated, and influence factors of the oil-water separation effect are considered as comprehensively as possible.

Description

technical field [0001] The invention relates to an oil-water separation prediction method, device, medium and equipment based on the microscopic distribution derivation of droplets, and belongs to the technical field of oilfield development. Background technique [0002] With the extension of my country's oilfield development cycle, many oilfields have entered the stage of medium-high water-cut development, and the content of produced water in the oil and gas water of the wellhead production fluid continues to increase. In order to quickly demulsify, dehydrate and process crude oil, horizontal three-phase separators, Oil-water settling tanks have become important mechanical equipment for oil-gas-water mixture treatment in oilfield joint stations, which is also the first process of oil-gas field gathering and transportation treatment projects. The horizontal oil-gas-water three-phase separator is mainly used to separate the imported oil production fluid into wet natural gas, c...

AI Technical Summary

Problems solved by technology

For the prediction and analysis of the oil-water separation effect of the horizontal three-phase separator, scholars at home and abroad mainly conduct research through indoor dehydration experiments, sedimentation physical models, and CFD numerical simulations. However, the indoor dehydration experiments ignore the influence of the structure of the three-phase separator itself. , methods such as sedimentation physical model and CFD simulation are also difficult to describe complex factors such as demulsifiers, and there are problems such as complex modeling and difficult operation

The machine learning algorithm using artificial intelligence can directly learn and train through the on-site operation database, so as to obtain a prediction model that can predict the effect of oil-water separation. However, this prediction model is not supported by a complete physical theory, and has problems in terms of extension and stability. insufficient

Images