A Permeability Prediction Method of Porous Media Based on Machine Image Intelligent Learning

Abstract

The invention discloses a porous medium permeability prediction method based on machine image intelligent learning, which selects multiple groups of the same porous medium material with different dry densities, and determines the real permeability of each group of porous medium materials; for each group of porous medium materials Use SEM electron microscope to scan to obtain its SEM image, and then calculate the gray level mean value, gray level variance, image energy, image entropy value and fractal dimension of each SEM image; use the extreme learning machine neural network model to analyze the five The five image feature parameters and their corresponding real permeability are trained and learned to determine the relationship between the five image feature parameters and the real permeability; when predicting, input the SEM image parameters of porous media materials with unknown permeability, and limit learning The machine neural network model can predict the permeability of the porous media material. The invention has the advantages of simple operation, short test period, high accuracy of predicted permeability and low test cost.

Description

technical field [0001] The invention relates to a method for predicting the permeability of porous media based on intelligent learning of machine images. Background technique [0002] Permeability is a key technical indicator in many engineering fields, such as coalbed methane and shale gas mining, gas migration in barrier systems during nuclear waste disposal, CO 2 Deep geological storage and other fields. At present, the testing methods for the permeability of porous media materials mainly include: mercury intrusion method, gas steady-state method and gas transient method. Although the test results of these relatively mature macroscopic test methods are very accurate, the test process is cumbersome and difficult for non-professional operators to operate; in addition, the test cycle of each of the above methods varies from a few days to a few months depending on the porous media material; And the equipment cost required for testing is expensive. Contents of the inventio...

AI Technical Summary

Problems solved by technology

Although the test results of these relatively mature macroscopic test methods are very accurate, the test process is cumbersome and difficult for non-professional operators to operate; in addition, the test cycle of each of the above methods varies from a few days to a few months depending on the porous media material; And the equipment required for testing is expensive

Images