Research on Measurement Model of Water Content of Oil Well Based on Data Fusion

Water content of oil well is an important parameter indicator for oilfield development. Since the measurement of water content is affected by many factors and the nonlinear relationship with its influencing factors is complex, the measurement accuracy is difficult to obtain satisfactory results. In this paper, the RF-based moisture detection method is combined with the multi-sensor data fusion technology. Based on the support vector machine optimized by genetic algorithm, an online water cut measurement model is established, which compensates for multiple parameters such as temperature, salinity and flow state. Through the learning and generalization of the sample data obtained by the experiment, the training and verification, the maximum error in the test data is less than 6%, indicating that the GA-SVM based measurement model can predict the crude oil moisture content with high precision.