Tight sandstone fluid type identification method based on support vector machine simulation cross plot

Abstract

The invention relates to a tight sandstone fluid type identification method based on a support vector machine simulation cross plot. Parameters best reflecting oil gas and water layer characteristics in a reservoir layer are firstly selected to be taken as fluid sample data; a support vector machine algorithm is applied then, and a proper penalty parameter and a proper kernel function are selected to construct a classification prediction model; vector data points obtained by the classification prediction model are projected to a cross plot plane so that a support vector machine simulation cross plot plate is formed; and to-be-recognized sample data are input into the support vector machine simulation cross plot plate to form projection distribution points, distances between the various projection distribution points and various fluid type center points in the support vector machine simulation cross plot are calculated, and the fluid type represented by a shortest-distance center point is taken as a to-be-identified fluid type. The method can integrate multiple characteristic parameters of research objects to perform accurate division on types of the objects, and limitation that the cross plot only can integrate two characteristic parameters to perform type division is made up.

Description

technical field [0001] The invention relates to a method for identifying tight sandstone fluid types based on a support vector machine simulation intersection graph, and belongs to the technical field. Background technique [0002] As an important type of continuous unconventional oil and gas reservoirs, tight sandstone reservoirs are widely distributed in various basins in China and have good prospects for exploration and development. However, due to the low permeability of the reservoir, various pore types, and strong heterogeneity, the electrical characteristics are greatly affected by the physical properties and rock skeleton, and the logging response characteristics are complex. It is difficult to identify oil, gas, and water layers with the conventional crossplot method. , it is easy to miss or even misidentify the fluid type of tight sandstone oil and gas reservoirs, which will affect the calculation accuracy of tight sandstone oil and gas reservoir reserves. [0003...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for identifying the tight sandstone fluid type based on the support vector machine simulation intersection graph, to solve the problem that the traditional intersection graph is difficult to accurately and quickly identify the category to which the sample point belongs when there are many data points

Images