Predicting pillar stability in underground mines is a critical problem because the instability of the pillar can cause large-scale collapse hazards. To predict the pillar stability for underground coal and stone mines, two new models (random tree and C4.5 decision tree algorithms) are proposed in this paper. Pillar stability depends on the parameters: width of the pillar (W), height of the pillar (H), W/H ratio, uniaxial compressive strength of the rock (σ_ucs), and pillar stress (σ_p). These parameters are taken as input variables, while underground mines pillar stability as output. Various performance indices, i.e., accuracy, precision, recall, F-measure, Matthews correlation coefficient (MCC) were used to evaluate the performance of the models. The performance evaluation of the established models showed that both models were able to predict pillar stability with reasonable accuracy. Results of the random tree and C4.5 decision tree were also compared with available models of support vector machine (SVM) and fishery discriminant analysis (FDA). The results show that the proposed random tree provides a reliable and feasible method of evaluating the pillar stability for underground mines.

Block anchor is an interface element used to restrain horizontal movement of structures. This paper investigates the effect of moisture conditions (or degree of saturation) on the pullout capacity of block anchor embedded in sand at three different moisture conditions. The approach taken consists of experimental work, and analytical calculation. The experimental work is pullout tests, made in the laboratory, on 0.15 x 0.15 x 0.15m concrete block anchors embedded in sand, at a depth of 0.15m. The sand is deposited in a 1.2 x 0.6 x 0.8m box using a pluviation method to ensure a uniform and reproducible density. Materials used were characterized to find their properties, and the equipments used were calibrated before usage. The load and the corresponding horizontal and vertical displacements were recorded. In addition, visual observations were made on the failed soil body. The experimental results are compared with the analytical calculations. The 3-D effect was also considered. The block anchor was found to have higher pullout capacity than a plate anchor. The results show that the moisture condition significantly affects the pullout capacity of the block anchor. The pullout capacity of the block anchor embedded in unsaturated (wet) sand is about double that for the block embedded in dry sand, while that for the block embedded in saturated sand is only about one half of that for the block embedded in dry sand. These findings have very significant implications in the analysis and design of the block anchor embedded in unsaturated sand. Also, these have contributions to the hazard risk assessment of block anchors embedded in sand subjected to variations in degree of saturation.

This article presents a constitutive model for dense sand that exhibits a post-peak strain-softening behavior. This model combines elements of plasticity with damage mechanics to simulate the stress—strain behavior. The post-peak stress drop is captured by the elasto-damage formulation, while the plasticity is superimposed beyond the elastic range. The total strain increment is composed of an elasto-damage strain increment and a plastic strain increment. The elasto-damage strain increment is found using the elasto-damage formulation, while the plastic strain increment is found using either the Drucker—Prager classical plasticity model or as a function of the damage strain. To calibrate this model, an experimental program was conducted on dense sand at different relative densities. The various physical and mechanical properties of the sand were determined. Both triaxial compression tests and hydrostatic tests were performed under different confining pressures, in order to obtain the model parameters at various conditions. These parameters were used to calibrate the model, which was coded in FORTRAN computer programs to simulate the stress—strain behavior of dense sand. The model was verified and found to be a good predictor of the response of dense sand for the selected stress path.