Rock mass structural recognition from drill monitoring technology in underground mining using discontinuity index and machine learning techniques

A procedure to recognize individual discontinuities in rock mass from measurement while drilling(MWD)technology is developed,using the binary pattern of structural rock characteristics obtained from in-hole images for calibration.Data from two underground operations with different drilling technology and different rock mass characteristics are considered,which generalizes the application of the methodology to different sites and ensures the full operational integration of MWD data analysis.Two approaches are followed for site-specific structural model building:a discontinuity index(DI)built from variations in MWD parameters,and a machine learning(ML)classifier as function of the drilling parameters and their variability.The prediction ability of the models is quantitatively assessed as the rate of recognition of discontinuities observed in borehole logs.Differences between the parameters involved in the models for each site,and differences in their weights,highlight the site-dependence of the resulting models.The ML approach offers better performance than the classical DI,with recognition rates in the range 89%to 96%.However,the simpler DI still yields fairly accurate results,with recognition rates 70%to 90%.These results validate the adaptive MWD-based methodology as an engineering solution to predict rock structural condition in underground mining operations.

Correlations between various rock mass classification/characterization systems for the Zagros tunnel-W Iran

This study deals with the comparative investigation on various classification/characterization systems for sedimentary rocks in two parts,40 kmlong of the Zagros tunnel,west of Iran.The results of extensive geotechnical explorations and field measurements were applied to obtain the rock mass classification/characterization systems such as Rock Mass Rating(RMR),Rock Condition Rating(RCR),Q-system(Q),Rock Mass Number(QN),Rock Mass index(RMi),Rock Structure Rating(RSR),and Geological Strength Index(GSI)for a wide range of sedimentary rocks.A set of systems inter-relationship is proposed.Some of these correlation relations such as RMR-Q,RMR-RMi,RMi-Q,RCR,GSI-GSI(Cai)are similar to the one or more relations proposed in the previous studies,however,some of them such as RSR-RMR,RSR-Q,RCR-QN and GSI-RMR are not similar to the previous works.Joint set orientation and joint set number are more important parameters that cause weak correlation coefficients where both side classifications are not similar in considering them in calculating values.So it is proposed to find relations between any pairs of systems that both of them consider or not consider these parameters.The relations are proposed for a wide range of sedimentary rocks and can be applied for similar geological environments.

Revisiting support optimization at the Driskos tunnel usinga quantitative risk approach

With the scale and cost of geotechnical engineering projects increasing rapidly over the past few decades,there is a clear need for the careful consideration of calculated risks in design.While risk is typically dealt with subjectively through the use of conservative design parameters,with the advent of reliability-based methods,this no longer needs to be the case.Instead,a quantitative risk approach can be considered that incorporates uncertainty in ground conditions directly into the design process to determine the variable ground response and support loads.This allows for the optimization of support on the basis of both worker safety and economic risk.This paper presents the application of such an approach to review the design of the initial lining system along a section of the Driskos twin tunnels as part of the Egnatia Odos highway in northern Greece.Along this section of tunnel,weak rock masses were encountered as well as high in situ stress conditions,which led to excessive deformations and failure of the as built temporary support.Monitoring data were used to validate the rock mass parameters selected in this area and a risk approach was used to determine,in hindsight,the most appropriate support category with respect to the cost of installation and expected cost of failure.Different construction sequences were also considered in the context of both convenience and risk cost.