Full text loading...
-
Method for Predicting Mercury Injection Capillary Pressure Curve of Tight Sandstone Using NMR Data
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 81st EAGE Conference and Exhibition 2019, Jun 2019, Volume 2019, p.1 - 5
Abstract
In this paper, a neural network called the radial basis function (RBF) method is applied to obtain the MICP curve using NMR T2 distribution. And the MICP curves of 19 tight sandstone core samples are predicted using this method. The results prove it to be a robust method. The advantages of this method include: No explicit model between the input and output is needed, and every input/output data is taken into consideration, which makes the result more accurate; and since the multi-dimension input/output is allowed in this method, the time consumption of calculation is low. In area where there are some core samples, we can use the NMR logging data to predict the MICP curve continuously with depth of well logging through this method.