水平井油水两相流含水率解释预测

水平井油水两相流产液剖面测井解释中流型复杂,准确解释含水率是难点。在进行了大量的近水平油水两相流动模拟实验的基础上,针对电容及阻抗含水率计测量响应特性,建立基于含水率计响应时域及频域特征值的支持向量机回归模型(SVR Model),采用该模型对不同倾斜角度的模拟井动态实验含水率标定结果进行模型预测,模型验证结果表明解释模型可实现较高的含水率预测精度,与室内实验配比含水率比较,达到预测含水率解释精度目标。在解释方法研究的基础上,对实际测井资料进行解释。

Water Cut Prediction of Oil-water Two-phase Flow in Horizontal Well

Because of complex flow types,it is difficult to accurately interpret water cut of oil-water two-phase flow of production profile logging in horizontal wells.On the basis of a large number of simulation experiments on nearly horizontal oil-water two-phase flow and the measuring response characteristics of water cut meter of capacitance and resistance,SVR model(support vector machine regression model) is established based on frequency domain eigenvalue of water cut meter response,and this model is used to predict the calibration results of water cut for simulation wells with different angles.Validation results show that higher prediction accuracy can be obtained by using this log interpretation model.Compared with the matching water cut of laboratory experiment,prediction accuracy of water cut can be achieved by using SVR model.In addition,the actual log data is interpreted on the basis of the development of interpretation methods.