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

作     者：Alberto Fernández JoséA.Sanchidrián Pablo Segarra Santiago Gómez Enming Li Rafael Navarro Alberto Fernández;José A.Sanchidrián;Pablo Segarra;Santiago Gómez;Enming Li;Rafael Navarro

作者机构：Universidad Politécnica de Madrid–ETSI Minas y EnergíaSpain Universidad de Salamanca–GIR CharrockSpain 

出 版 物：《International Journal of Mining Science and Technology》 (矿业科学技术学报（英文版）)

年 卷 期：2023年第33卷第5期

页      面：555-571页

核心收录：

学科分类：0820[工学-石油与天然气工程] 081901[工学-采矿工程] 0819[工学-矿业工程] 08[工学] 081104[工学-模式识别与智能系统] 0818[工学-地质资源与地质工程] 0903[农学-农业资源与环境] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：conducted under the illu MINEation project, funded by the European Union’s Horizon 2020 research and innovation program under grant agreement (No. 869379) supported by the China Scholarship Council (No. 202006370006) 

主　　题：Drill monitoring technology Rock mass characterization Underground mining Similarity metrics of binary vectors Structural rock factor Machine learning 

摘      要：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.