4/18/2017

find all related papers and write parts of the outline

Today, I find all related papers and write parts of the outline.

Summary:

First, I find all related papers and review their abstracts again.

Second, I write two parts of the outline, introduction and methods.
The following is my outline written today.

Outline
Top-level outline (sections)

1.   Introduction – nobody predict 6 parameters before. Some use 6 or 9 parameters to predict permeability or pore types.

2.   Methods- build an ANN model to predict 6 parameters

Second-level outline (paragraphs)

1.   Introduction – nobody predict 6 parameters before.
1.1.  Predict NMR T2 distribution can save time and money as well as know the characteristics of the reservoir.
1.2.  Some use ANN and other models to predict porosity, permeability, water saturation, TOC, etc. But they did not predict NMR.
1.3.  Some use ANN and other models to predict data related to NMR such as free fluid, irreducible water, effective porosity obtained from NMR.
1.4.  Some use ANN and other models to predict bin porosities and T2 logarithmic mean values instead of T2 distribution.
1.5.  6 parameters are predicted in this paper. They are very close to T2 distribution.
2.   Methods - build an ANN model to predict 6 parameters
2.1.  Select target depths in Hess data, there are 7 different lithologies in target depths.
2.2.  Select 12 different logging data
2.3.  Select 10 different inversion data (QElan)
2.4.  Set one category for different lithologies, there are 7 different lithologies.
2.5.  Set four different categories according to the shape of T2 distribution. Each different categories have 2 or 3 levels.
2.6.  Use k-nearest neighbor method to predict four different categories, with best k=3.
2.7.  Fit T2 distribution with normal distributions. Each normal distribution corresponds to 3 parameters. There are 6 parameters for each T2 distribution at each depth.
2.8.  Show the accuracy of fitting
2.9.  Preprocess data
2.10.                   Build an ANN model with 2 hidden layers
2.11.                   Use R and matlab to build the model, the results are similar but R takes much more time than matlab. So matlab is recommended to build and test the model.
2.12.                   Build an ANN model with 2 hidden layers using matlab
2.13.                   Show the accuracy of the model

Tomorrow, I will try to finish the outline.


8 comments:

  1. Replies
    1. prediction of nmr t2 distribution by 6 parameters with an artificial neural netwok model

      Delete
  2. will you talk about the 64 bin prediction in this paper ?

    ReplyDelete
  3. 2.1. Select target depths in Hess data, there are 7 different lithologies in target depths.

    qill ou talk about the effect of 11 lithologies?

    ReplyDelete
  4. write the outline for results... following is an outline for results written by Sang..

    Abstract
    Chapter 1. Introduction
    1.1. Background
    1.2. Outline of the thesis

    Chapter 2. Methodology
    2.1. Asymptotic solution for diffusivity equation
    2.2. Multistencils Fast Marching Method
    2.3. Drainage Volume and Pressure Transient Analysis

    Chapter 3. Results
    3.1. Accuracy of MFM method
    3.1.1. Singlestencil Fast Marching VS Multistencils Fast Marching
    3.1.2. MFM model VS Texas A&M’s model
    3.1.3. MFM model VS KAPPA analytical VS KAPPA numerical
    3.2. Validation
    3.2.1. Basic reservoir properties
    3.2.2. Boundary condition
    3.2.3. Effect of Fractures
    3.2.4. Well interference
    3.3. Application [Synthetic example]

    Chapter 4. Conclusions

    ReplyDelete