Ma, Kuiqian (Tianjin Branch of CNOOC (China) Co., Ltd) | Chen, Cunliang (Tianjin Branch of CNOOC (China) Co., Ltd) | Zhang, Wei (Tianjin Branch of CNOOC (China) Co., Ltd) | Liu, Bin (Tianjin Branch of CNOOC (China) Co., Ltd) | Han, Xiaodong (CNOOC Ltd and China University of Petroleum, Beijing)
Abstract Performance prediction is one of the important contents of oilfield development. It is also an important content affecting investment decision-making, especially for offshore oilfields with large investment. At present, most oilfields in China have entered high water cut stage or even extra high water cut stage, which requires higher prediction accuracy. Water drive curve is an important method for predicting performance. Traditional methods are based on exponential formulas, but these methods have poor adaptability in high water cut period. Because traditional methods deviate from straight line in high water cut period. In this paper, a robust method for predicting performance of offshore oilfield in high water cut period based on big data and artificial intelligence is proposed. Firstly, the reasons for the "upward warping" phenomenon of traditional methods deviating from the straight line are analyzed. It is found that the main reason for the deviation is that the relationship between the relative permeability ratio of oil to water and the water saturation curve no longer conforms to the exponential relationship. So a new percolation characteristic characterization equation with stronger adaptability is proposed, which focuses on the limit of high water flooding development. On this basis, the equation of the new water drive characteristic curve is deduced theoretically, and the dynamic prediction method is established. What's more, the solution of the method is based on large data and AI algorithm. This method has been applied to many high water flooding phase permeability curves, and the coincidence rate is more than 95.6%. The new water drive characteristic curve can better reflect the percolation characteristics of high water cut reservoirs. At the same time, the performance of adjustment wells and measures on the curve of development dynamic image is analyzed. Curve warping indicates that adjustment wells or measures are effective. Field application shows that the prediction error of the new method is less than 6%, which is more in line with the needs of oilfield development. Because of the application of artificial intelligence algorithm, the application is more convenient and saves a lot of time and money. This is a process of self-learning and self-improvement. As the oil field continues over time, each actual data will be recalculated into the database. Then the fitting and correction are carried out, and then the solution is learned again. This method has been applied to several oil fields in Bohai. And the effect is remarkable, which provides a good reference for the development of other oil fields.