Reservoir logging characteristic parameter extraction method based on target preference coding

Abstract

The invention discloses a reservoir logging characteristic parameter extraction method based on target preference coding, and belongs to the technical field of petroleum logging. The method mainly comprises the following steps: step 1, screening out a logging curve capable of reflecting reservoir characteristics according to evaluation characteristics of a target reservoir, determining priority levels, and sorting the logging curves for data coding; 2, eliminating top and bottom segment data, and statistically analyzing distribution characteristics of remaining data; 3, performing encoding processing on the logging data based on reservoir evaluation target preferences; 4, feature codes are combined, feature code analysis rules are formulated, and feature value sampling depth points are found out; and step 5, re-sampling the sampling depth points, and determining the characteristic value of each logging curve of the target reservoir for reservoir parameter modeling and fluid identification plate modeling. According to the method, through feature depth point and feature value extraction based on target preference coding, compared with manual feature value extraction, the speed is high, the accuracy is high, and the reservoir logging data interpretation and evaluation efficiency is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of petroleum logging, and in particular relates to a method for extracting characteristic parameters of reservoir logging based on target preference coding. Background technique [0002] Reservoir logging evaluation is an important part of reservoir evaluation, and reservoir logging eigenvalues ​​are the core parameters for reservoir physical parameter model research and fluid identification chart establishment, so the selection of reservoir logging eigenvalues ​​is particularly important. The traditional extraction method mainly relies on experienced experts to use manual extraction. This method requires high experience in regional well logging interpretation, and it is often prone to the phenomenon of "thousands of people and thousands of faces". In order to reduce artificial extraction errors and improve eigenvalue extraction Therefore, it is urgent to propose a reservoir eigenvalue extraction method, whi...

AI Technical Summary

Problems solved by technology

The traditional extraction method mainly relies on experienced experts to use manual extraction. This method requires high experience in regional well logging interpretation, and it is often prone to the phenomenon of "thousands of people and thousands of faces". In order to reduce artificial extraction errors and improve eigenvalue extraction Therefore, it is urgent to propose a reservoir eigenvalue extraction method, which can greatly improve the efficiency and stability, so as to realize the rapid evaluation of reservoirs and the rapid identification of fluid properties

Images