Rock Classification Using Multivariate Analysis of Measurement While Drilling Data: Towards a Better Sampling Strategy

Abstract

Measurement while drilling (MWD) data are gathered during drilling operations and can provide information about the strength of the rock penetrated by the boreholes. In this paper MWD data from a marble open-pit operation in northern Norway are studied. The rock types are represented by discrete classes, and the data is then modeled by a hidden Markov model (HMM). Results of using different MWD data variables are studied and presented. These results are compared and co-interpreted with optical televiewer (OTV) images, magnetic susceptibility and spectral gamma values collected in the borehole using down-the-hole sensors. A model with penetration rate, rotation pressure and dampening pressure data show a good visual correlation with OTV image for the studied boreholes. The marble class is characterized by medium penetration rate and medium rotation pressure, whereas the intrusions are characterized by low penetration rate and medium to high rotation pressure. The fractured marble is characterized by high penetration rate, high rotation and low dampening pressure. Future research will use the presented results to develop a heterogeneity index, develop an MWD-based 3D-geology model and an improved sampling strategy and investigate how to implement this in the mine planning process and reconciliation.

Preliminary Investigation into Measurement While Drilling as a Means to Characterize the Coalmine Roof

“…In theory, various methods, including analytical, numerical, and experimental, can be used to analyze the applicability of MWD to the characterization of coalmine roofs [2][3][4][5][6][7][8]11,[15][16][17]. Analytical and numerical methods provide a straightforward means to understand the immediate effect of various geotechnical parameters on drilling and bolting operations.…”

Geometallurgy—A Route to More Resilient Mine Operations

“…Over the last decade established methods have been created, such as understanding rock hardness and rock mass through rate of penetration (ROP) and torque [77]. Techniques are starting to differentiate lithologies using petrophysics and fuzzy interference systems by applying multivariate analysis, neuro-adaptive learning algorithms, and/or machine learning [78][79][80]. MWD real-time data can be processed and provide an approximation of rock strength whilst physically drilling [81].…”

Specifics of MWD Data Collection and Verification during Formation of Training Datasets

“…To overcome the difficulties associated with the uncertainty of geological data, the methods of artificial intelligence, machine learning [17,18], neural networks [12,13,19,20], fuzzy logic [21][22][23], etc., are gaining widespread use in the mining industry. Today there are numerous variations in the indicated methods and tools, which offer cutting-edge solutions to the problems of the mining industry in the presence of input data of different complexity [16,24].…”

“…The indicated methods are widely used for the analysis of geomechanical parameters [22], prediction of geological conditions of the rock mass [22,25], calculation of physical and mechanical parameters of the rocks [21], their classification, estimation and prediction of drilling and blasting parameters and indicators [12,13,[18][19][20][21], etc. A detailed review of computing technology applications and the indicated methods in mining is presented in the paper [10].…”