System and method for predicting wellhead water content of low gas yield oil wells based on deep long-term and short-term memory networks

Abstract

The invention relates to a system and a method for predicting the wellhead water content of low gas yield oil wells based on deep long-term and short-term memory networks. By a high-frequency double-loop capacitance sensor, the water content fluctuation information of a wellhead mixed fluid is measured, by performing windowing processing on the collected fluctuation time series of the water content, the collected fluctuation time series of the water content is divided into multiple time series-varying time segments, the time-frequency characteristics, non-linear characteristics, and time irreversible characteristics of each time-series segment are extracted to form characteristic vectors, thereby forming the wellhead water content characteristic vector time series. Afterwards, the extracted characteristic vector time series of the water content is used as the input of the deep long-term and short-term memory networks, and a model for predicting the water content based on the deep long-term and short-term memory networks and multiple characteristics is established. By adopting the model, the test value of the water content of the wellhead produced fluid is used as the water contentlabel for training, and finally the predicted value of the water content is obtained. Since the characteristic time series of the water content fluctuation signal is an accurate description of the wellhead produced fluid characteristics, such method can effectively eliminate the influence of a small amount of gas content at the wellhead on the measurement, and further improve the measurement accuracy of the water content of the wellhead produced fluid.

Description

technical field [0001] The invention belongs to the field of crude oil production, and relates to the measurement of water content of liquid produced in low-yield gas wells, in particular to a system and method for predicting the water content of low-yield oil wells based on a deep long-short-term memory network. Background technique [0002] In the process of crude oil production, timely mastering and controlling the water cut parameters of oil well production is not only the prerequisite for reliable estimation of crude oil net production, but also the basis for correct diagnosis and maintenance of oil well problems, and is also the basis for the adjustment of reservoir production mode. Therefore, it is of great significance to the detection of water cut parameters in oil well production. At present, the ultra-high water cut characteristic of oilfield production fluid has put forward new requirements for the water cut measurement of oil well production fluid, how to accura...

AI Technical Summary

Problems solved by technology

It solves the time-consuming and labor-intensive manual sampling of the water content of oil wells in existing oil wells, which affects the real-time performance of production monitoring and oil recovery data

Images