A data-driven fracture-cavity oil reservoir oil well water breakthrough time prediction method

Abstract

The invention provides a data-driven oil well water breakthrough time prediction method and belongs to the field of oil well water breakthrough time prediction in order to solve the problems that an existing fracture-cavity oil reservoir oil well water breakthrough time prediction method is poor in practicability and low in prediction accuracy. The method comprises the following steps: collectingproduction data of all water-seen oil wells of a studied oil field; Screening high-yield typical wells with water and dividing the wells according to karst backgrounds; Counting water breakthrough early warning parameters of the water breakthrough high-yield typical well under each karst background; Establishing a water breakthrough time prediction multivariate regression equation corresponding toeach karst background; Training a neural network model used for water breakthrough time prediction under each karst background; Verifying the accuracy of two water breakthrough time prediction methods, namely a multivariate regression method and a neural network method, according to the karst background, and selecting a prediction method with higher accuracy under each karst background. The method can effectively avoid the problem that accurate geological data of the fractured-vuggy reservoir are difficult to obtain, and can be popularized to fractured-vuggy reservoirs with various karst backgrounds.

Description

technical field [0001] The invention relates to the prediction of the water breakthrough time of an oil well in a fracture-cavity reservoir, in particular to a method for predicting the water breakthrough time of an oil well in a fracture-cavity reservoir driven by data. Background technique [0002] The oil-water relationship in fractured-vuggy reservoirs is complicated, and the production of oil wells often decreases sharply after water breakthrough, and water flooding of oil wells is the dominant factor leading to production decline. Accurately predicting the water breakthrough time of oil wells, delaying the water breakthrough time and increasing the water-free oil production period of oil wells have become the key technologies for enhancing oil recovery in fractured-vuggy reservoirs. The coincidence rate of the water breakthrough early warning time of the existing oil well water breakthrough early warning technology is about 63.1%. From the perspective of application sc...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned problems of poor practicability and low prediction accuracy of the existing fracture-vuggy oil well water breakthrough time prediction method, the present invention provides a data-driven oil well water breakthrough time prediction method. As a black box, based on the big data of oilfield production, the early warning of water breakthrough in oil wells and the prediction of water breakthrough time can avoid the problem that it is difficult to obtain accurate geological data of fracture-vuggy reservoirs. The accuracy is high, and it can be extended to various Types of Fractured-Vuggy Reservoir Fields

Images