Author:
Zadhesh Jamal,Majdi Abbas
Abstract
Jointed rock masses modeling needs the geometrical parameters of joints such as orientation, spacing, trace length, shape, and location. The rock joint trace length is one of the most critical design parameters in rock engineering and geotechnics. It controls the stability of the rock slope and tunnels in jointed rock masses by affecting rock mass strength. This parameter is usually determined through a joint survey in the field. Among the parameters, trace length is challenging because a complete joint plane within rock mass cannot be observed directly. The development of predictive models to determine rock joint length seems to be essential in rock engineering. This research made an effort to introduce a support vector machine (SVM) model to estimate rock joint trace length. The SVM is an advanced intelligence method used to solve the problem characterized by a small sample, non-linearity, and high dimension with a good generalization performance. In this study, three data sets from the sedimentary, igneous, and metamorphic rocks were organized, which location of joints on the scanline, aperture, spacing, orientation (D/DD), roughness, Schmidt rebound of the joint’s wall, type of termination, trace lengths in both sides of the scanline and joint sets were measured. The results of SVM prediction demonstrate that predicted and measured results are in good agreement. The SVM model-based results were compared with those obtained from field surveys. The proposed SVM model-based model was very efficient in predicting rock joint trace length values. The actual trace length could be estimated; thus, the expensive, difficult, time-consuming, and destructive joint surveys related to obscured joints could be avoided.
Publisher
Faculty of Mining, Geology and Petroleum Engineering
Subject
General Earth and Planetary Sciences,Geology,General Energy,Geotechnical Engineering and Engineering Geology,Water Science and Technology
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献