SUMMARYArtificial neural networks are used to predict the micro-properties of particle flow code in three dimensions (PFC3D) models needed to reproduce macro-properties of cylindrical rock samples in uniaxial compression tests. Data for the training and verification of the networks were obtained by running a large number of PFC3D models and observing the resulting macro-properties. Four artificial networks based on two different architectures were used. The networks used different numbers of input parameters to predict the micro-properties. Multi-layer perceptron networks using Young's modulus, Poisson's ratio, uniaxial compressive strength, model particle resolution and the maximum-to-minimum particle ratio showed excellent performance in both training and verification. Adding one more variable-namely, minimum particle radius-showed degrading performance.

Most of the hydraulic fracturing experiments by the mining industry in hard rocks were conducted to precondition the rockmass with the aim of improving caveability and fragmentation for block caving mining operations through the creation of hydraulic fractures (HF). Based on an extensive literature survey and models, it is suggested that successful preconditioning could be obtained through hydraulic treatment of the rockmass. This paper discusses the interaction between hydraulic fluid injection and the pre-existing discrete fracture network (DFN) in a rockmass subject to in-situ stresses. Three-dimensional numerical studies have been used in an initial attempt towards understanding how the rockmass and the pre-existing natural fractures response to fluid injection is affected by some of the DFN characteristics and borehole length. Results indicate that DFN characteristics control fluid percolation in low-permeability formations and influence stimulated rock volume. When injection pressures are lower than pressures required for hydraulic fracturing, borehole length does not influence significantly fracture surface area stimulated by slip. It is shown that representing the fractures explicitly in the numerical models and adopting a fully coupled hydromechanical modelling approach provide promising capabilities in the prediction of rockmass responses to fluid injection.