Aiming at the complex nonlinear relationship among factors affecting blasting fragmentation, the input weight and hidden layer threshold of ELM (extreme learning machine) were optimized by gray wolf optimizer (GWO) and the prediction model of GWO-ELM blasting fragmentation was established. Taking No. 2 open-pit coal mine of Dananhu as an example, seven factors including the rock tensile strength, compressive strength, hole spacing, row spacing, minimum resistance line, super depth, and specific charge are selected as the input factors of the prediction model. The average size of blasting fragmentation X50 is selected as the output factor of the prediction model and compared with the results of PSO-ELM and ELM. The results show that MAPE of GWO-ELM, PSO-ELM, and ELM are 1.78%, 5.40%, and 10.90%, respectively; their RMSE are 0.007, 0.022, and 0.045, respectively. The ELM model optimized by the gray wolf optimizer is more accurate and has stronger data fitting ability than PSO-ELM and ELM models, and the prediction accuracy of GWO-ELM is much higher than that of PSO-ELM and ELM.

In an open-pit mine in Xinjiang, part of the stripped area is covered by burnt rock. Due to the low strength and fragility of burnt rock, dust is more easily generated during blasting. Taking the mining area as the research background, the mechanical property parameters of burnt rock were tested, and the blasting parameter design of on-site operation was understood. The blasting numerical simulation of burnt rock step was carried out by using a numerical simulation software (LS-DYNA). From the angle of stress on rock, the stress cloud and stress curve of numerical simulation are analyzed, and it is concluded that the fundamental reason for the large dust production in blasting operation is that the burnt rock is crushed excessively after the action of explosion wave, and the explosive energy is too large, which is converted into kinetic energy to drive the dust to escape. In order to improve the utilization rate of explosives and reduce the output of blasting dust, the original blasting parameters were optimized as 8-m hole spacing, 6.5-m row spacing, 0.21-kg/m³ unit explosive consumption, 1-m interval charge, and 55-ms short-delay blasting through numerical simulation and orthogonal experiment. In the mining area, the measures of dustproof and dust reduction by blasting protection blanket and dust absorption cotton are adopted. Combined with the optimized blasting parameters, the field test proves that the dust removal efficiency is up to 82.4%.

No abstract

Highwall mining with backfill technology will be one of the main techniques of raising the recovery rate of coal resources under the end-slope all over the world in the future, in which the coal pillar setting is the key to ensure the successful application of this technology, and the calculation of inelastic zone width of a coal pillar has important guiding significance for the coal pillar setting in highwall mining with backfill. However, at present, in order to accurately calculate the inelastic zone width of a coal pillar under the condition of highwall mining with backfill, a calculation model of the inelastic zone width of highwall mining with backfill independent of empirical parameters is established by using a limit equilibrium method, orthogonal experiment method, and non-linear fitting method. In order to verify the correctness and reliability of the model, this study takes the geological conditions of the Antaibao open-pit mine in Pingshuo, Shanxi Province, China, as the engineering background to verify the calculation accuracy of the model. The results show that the calculation model established in this study can accurately calculate the inelastic zone width of the coal pillar under highwall mining with backfill and can meet the engineering needs.

No abstract