Abstract
As the important data basis of surrounding rock classification, rock mass structural information obtained by traditional image processing and feature extraction algorithms could not be quantitatively analyzed because of the uncertainty and geometric randomness of structural planes. In this paper, based on straight line detection, intelligent scissors, and morphological edge detection algorithms, the multiple interpretation system of rock mass image including linear bunching extraction, magnetic tracking extraction, and multiparameter characterization was researched and developed, and the actual distribution information and the related probability distribution model of structural planes could be obtained directly. On the basis of this, plenty of corresponding random rating-values meeting the probability distribution models of these evaluation indices were gained by Monte Carlo Simulation. The distribution probability affiliated with different rock mass grade was attained by inductive statistics, and the robust evaluation of surrounding rock classification could be carried out. Taking the robust results as learning samples, the response model of surrounding rock grade based on Gaussian process classification was established, making the evaluation of surrounding rock subclassification more rapid and robust.
Highlights
With the development of rock mechanics theory, rock quality evaluation has played a key role in rock engineering [1,2,3,4]
The Q-system classification method emphasizes on the numbers, roughness, and alterations of joints; if considering the directions of joints, this method is not suitable [9]. e Rock Mass Rating (RMR) method can reflect the quality of hard rock mass, but it is not suitable for weak rock mass; the evaluation results are correspondingly conservative. e Hydropower Classification (HC) method is only used in the classification of surrounding rocks in low ground stress areas instead of high ground stress areas, that is, the rock burst areas [1]
Plenty of corresponding random rating-values meeting the probability distribution models of these evaluation indices were gained by Monte Carlo Simulation. e distribution probability affiliated with different rock mass grade was attained by inductive statistics, and the robust evaluation of surrounding rock classification could be carried out
Summary
With the development of rock mechanics theory, rock quality evaluation has played a key role in rock engineering [1,2,3,4]. Based on straight line detection, intelligent scissors, and morphological edge detection algorithm, the multiple interpretation system of rock mass image including linear bunching extraction, magnetic tracking extraction, and multiparameter characterization was researched and developed, and the actual distribution information and the related probability distribution model of structural planes could be obtained directly. On this basis, plenty of corresponding random rating-values meeting the probability distribution models of these evaluation indices were gained by Monte Carlo Simulation. Taking the robust results as learning samples, the response model of surrounding rock grade based on Gaussian process classification was established, in order to evaluate surrounding rock subgrade more rapidly
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
