The model training process achieves prediction of well leakage risk by modeling features such as collapse pressure, leakage pressure, pore pressure, and actual drilling fluid density.
The data fields are schematized as follows:
depth: well depth (m);
Collapse pressure: Collapse pressure (Mpa);
Leakage pressure: Leakage pressure (Mpa);
Pore pressure: pore pressure (Mpa);
Density: Actual drilling fluid density (g/cc).
The logging dataset from the Tarim Basin in western China contains a total of 6,800 sample data for 25 geologic features.
Machine Learning Modeling Using Collapse Pressure, Leakage Pressure, Pore Pressure, and Actual Drilling Fluid Density Data from the Tarim Oilfield in Western China.
Data quality is good.
| # | number | name | type |
| 1 | XDA14000000 | Strategy Priority Research Program (Category A) of Chinese Academy of Sciences | |
| 2 | XDA14040000 | Key technologies for ultra-deep guided drilling | Strategy Priority Research Program (Category A) of Chinese Academy of Sciences |
This work is licensed under a
Creative
Commons Attribution 4.0 International License.
CSTR:11738.11.NCDC.XDA14.DB6397.2024
10.12072/ncdc.xda14.db6397.2024