.png){kind=icon}
.png){kind=icon}
Return
Multi-parameter determination method for rock discontinuity roughness based on geometric properties intelligent extraction
.png){kind=icon}
PRE
AI
DOI：10.1016/j.tust.2025.106547.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To accurately and efficiently determine the rock joint roughness coefficient (JRC), a multi-parameter determination method for rock discontinuity roughness based on intelligent extraction of geometric properties was proposed. Firstly, a morphological characterization analysis program for rock discontinuities based on 3D point cloud reconstruction was developed. This program achieved the automatic extraction of arbitrary 2D profile lines and accurate calculation of multiple 2D characterization parameters. Then, two comprehensive characterization parameters were extracted from eight commonly used roughness characterization parameters by principal component analysis method. A multi-parameter determination method for rock discontinuity roughness based on the adaptive vigilance chaotic sparrow search algorithm optimizing extreme limit learning machine (ACSSAELM) was established to construct a nonlinear mapping relationship between the comprehensive characterization parameters and JRC to achieve an accurate prediction of discontinuity roughness. The proposed method's performance was validated using 112 2D profile samples and three granite discontinuity samples, and the reliability of the method was demonstrated by comparing it with other methods. The sensitivity of the method to sampling interval, anisotropy, and sampling size was discussed. Finally, the proposed method was applied to the construction of the Xinglong tunnel, providing effective guidance for practical construction activities.
Keywords:
Rock discontinuity
Roughness
Characterization parameters
Sparrow search algorithm
Extreme learning machine
Journal
IF:
7.4
Papers:
6.8K
Citations:
3.5W