Method for optimizing of model selection based on clustering analysis

Abstract

The invention discloses a method for optimizing of model selection based on clustering analysis. The method comprises the following steps of 1, establishing a plurality of three-dimensional quantitative geological models, calculating the attribute value of each grid node of each model, standardizing the attribute value, calculating the Euclidean distance between any two models, and obtaining a dissimilarity matrix for representing the difference of each model; 2, reducing the dimension of the dissimilarity matrix, and distinguishing the similarity of the model by vectors in a two-dimensional space; 3, clustering the model by a clustering analysis method, and selecting one or a plurality of models from each type for the research of numerical reservoir simulation; 4, comparing a well point attribute value histogram and a histogram of the selected model, and judging whether the selected model meets the geological concept or not; 5, comparing the reservoir calculated by the selected model and the P10, P50 and P90 reservoirs, and judging the representativeness of the selected model. The method has the characteristics that the simplicity and objectivity are realized, the application range is wide, and the method can be applied to the field of reservoir description.

Description

technical field [0001] The invention relates to the field of reservoir description, in particular to a method for model optimization using cluster analysis. Background technique [0002] Reservoir stochastic modeling technology was produced in the early 1980s, and it is now more and more widely used in the practice of oil and gas field exploration and development. Stochastic modeling can provide multiple equiprobable model realizations, which can be used to evaluate the uncertainty of the reservoir. In reservoir numerical simulation, considering the computational cost, usually only a limited number of realizations can be simulated, so one or several models must be selected for numerical simulation research. Commonly used stochastic model screening methods include arithmetic mean method, geological model screening method, numerical simulation method, probabilistic reserve method, experimental design, Latin hypercube sampling and sorting method. The principle of the arithmet...

AI Technical Summary

Problems solved by technology

The principle of the arithmetic mean method is to carry out the arithmetic mean of multiple realizations, and use the obtained average model as the optimal model, which has the advantage of being simple and fast, but the disadvantage is that it has a smoothing effect, which changes the reservoir heterogeneity and the statistical distribution characteristics of the model; The principle of the geological model screening method is to select the model with a higher degree of agreement by comparing the differences between each model and the geological model. The obtained model can better meet the geological concept model, but it is very time-consuming and subject to subjective factors. The influence is relatively large; the numerical simulation method uses streamline simulation, history fitting and other methods to optimize the model, and the disadvantage is that it is time-consuming; while the probabilistic reserve method, experimental design, Latin hypercube sampling and sorting method are all based on geological reserves. Model optimization is not applicable to the optimization of permeability model and facies model

[0003] In view of the above-mentioned problems existing in the existing model optimization methods, it is urgent to develop a simpler and more objective model optimization method to solve the industry problem that it is difficult to select a representative model for reservoir numerical simulation due to the large number of models

Images