An oil reservoir inter-well connectivity determination method based on data driving

Abstract

The invention discloses an oil reservoir inter-well connectivity determination method based on data driving, and the method comprises the steps of firstly collecting related parameters of an oil fieldblock, obtaining a filtering coefficient of each injection signal, carrying out the preprocessing of injection and production data, and correcting the time lag and attenuation of the injection and production data; performing normalization processing on the injection-production data to form a standard sample set of neural network learning and training; building a neural network, using a conjugategradient algorithm as a learning algorithm, and achieving the rapid optimization solution of neural network model parameters; and performing parameter sensitivity analysis based on the trained neuralnetwork model to obtain a connection coefficient for representing the inter-well connectivity of the oil reservoir. The method is simple and convenient, is high in calculation efficiency, is used forevaluating the dynamic connectivity between oil reservoir wells, has a better yield prediction effect while having the same inter-well connectivity coefficient calculation precision of a traditional inter-well connectivity judgment method, and can further guide formulation of optimization measures such as profile control and water plugging and intelligent oil field layered injection and productionhistory fitting and production optimization.

Description

technical field [0001] The invention belongs to the field of oil and gas field development, and in particular relates to a data-driven method for determining connectivity between oil reservoirs. Background technique [0002] The study of reservoir interwell connectivity is an important part of reservoir evaluation, and also the basis for successful oilfield development and management programs. By quantifying the connectivity between wells and improving the understanding of the flow direction of injected water, it is helpful to guide the optimal implementation of process measures such as profile control during high water-cut periods and formulation of development adjustment plans. important guiding significance. [0003] There are many analysis methods for interwell connectivity, which are mainly divided into static analysis and dynamic analysis. Commonly used static analysis methods mainly include: geochemical methods, interference well test analysis methods, tracer test m...

AI Technical Summary

Problems solved by technology

The correlation analysis model is based on the Spearman rank correlation analysis, and the connectivity between injection wells is judged by calculating the value of the Spearman correlation coefficient; the linear regression model establishes a linear relationship between production wells and injection wells, and fits historical production data. On the basis, the weight coefficients in the linear model are used as the connection coefficients between production wells and injection wells. Since the established model is too simple, it is easy to cause over-fitting, and it cannot accurately simulate the nonlinear response relationship between injection and production wells; The capacitance model is an improvement of the multiple linear regression model. On the premise that the connectivity between wells remains unchanged during the analysis and evaluation, this method combines the compressibility, pore volume and oil recovery index from the perspect

Images