View in EDS

Correlation Analysis and Prediction of Sandstone Strength Considering Drilling Parameters and Petrographic Characteristics.

Saved in:
Bibliographic Details
Title: Correlation Analysis and Prediction of Sandstone Strength Considering Drilling Parameters and Petrographic Characteristics.
Authors: Kang, Jintao, Xu, Zhenhao, Lin, Peng, Xie, Huihui
Source: International Journal of Geomechanics; Feb2025, Vol. 26 Issue 2, p1-12, 12p
Subject Terms: SANDSTONE, BORING & drilling (Earth & rocks), PREDICTION models, MINERALOGY, GRAIN size, MINERALOGICAL chemistry, RANDOM forest algorithms, STRENGTH of material testing
Abstract: The objective of this study is to develop a reliable method for predicting sandstone strength by integrating drilling parameters and petrographic characteristics. The prediction of sandstone strength using drilling parameters has garnered widespread attention due to its speed and reliability. However, it faces challenges related to multiple possible solutions. To address this, an integrated strength prediction method of sandstone considering drilling parameters and petrographic characteristics was proposed. Using a self-developed digital drilling test system, laboratory drilling tests were conducted on sandstones with varying strengths. Core samples underwent uniaxial compression tests, splitting tests, mineral composition analyses, and grain size assessments. The correlation between strength parameters, drilling response parameters, and petrographic characteristics was analyzed. The results showed that using only drilling rate and torque for predicting sandstone strength resulted in multiple solutions, with a coefficient of determination (R2) below 0.6, which hindered the establishment of a reliable model. However, when combined with the quartz and feldspar content, these parameters significantly improved the accuracy of the sandstone strength prediction. A prediction index system and model for sandstone strength, based on feldspar content, quartz content, drilling rate, and torque, were developed and validated using a random forest algorithm. The proposed model demonstrated the best performance in terms of R2, mean absolute error (MAE), and root mean square error (RMSE). For uniaxial compressive strength prediction (ranging from 15.88 to 194.07 MPa), the R2 values were 0.98 and 0.89 for the training and test sets, the MAE values were 3.5 and 10.2 MPa, and the RMSE values were 4.8 and 15.6 MPa, respectively. The proposed method has proven to be highly effective in predicting sandstone strength, addressing the issue of multiple solutions when using drilling parameters, and enabling quick and accurate strength prediction during the drilling process. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Geomechanics is the property of American Society of Civil Engineers and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:The objective of this study is to develop a reliable method for predicting sandstone strength by integrating drilling parameters and petrographic characteristics. The prediction of sandstone strength using drilling parameters has garnered widespread attention due to its speed and reliability. However, it faces challenges related to multiple possible solutions. To address this, an integrated strength prediction method of sandstone considering drilling parameters and petrographic characteristics was proposed. Using a self-developed digital drilling test system, laboratory drilling tests were conducted on sandstones with varying strengths. Core samples underwent uniaxial compression tests, splitting tests, mineral composition analyses, and grain size assessments. The correlation between strength parameters, drilling response parameters, and petrographic characteristics was analyzed. The results showed that using only drilling rate and torque for predicting sandstone strength resulted in multiple solutions, with a coefficient of determination (R<sup>2</sup>) below 0.6, which hindered the establishment of a reliable model. However, when combined with the quartz and feldspar content, these parameters significantly improved the accuracy of the sandstone strength prediction. A prediction index system and model for sandstone strength, based on feldspar content, quartz content, drilling rate, and torque, were developed and validated using a random forest algorithm. The proposed model demonstrated the best performance in terms of R<sup>2</sup>, mean absolute error (MAE), and root mean square error (RMSE). For uniaxial compressive strength prediction (ranging from 15.88 to 194.07 MPa), the R<sup>2</sup> values were 0.98 and 0.89 for the training and test sets, the MAE values were 3.5 and 10.2 MPa, and the RMSE values were 4.8 and 15.6 MPa, respectively. The proposed method has proven to be highly effective in predicting sandstone strength, addressing the issue of multiple solutions when using drilling parameters, and enabling quick and accurate strength prediction during the drilling process. [ABSTRACT FROM AUTHOR]
ISSN:15323641
DOI:10.1061/IJGNAI.GMENG-11630