Abstract: The present disclosure provides a coal bump control method for sectional hydraulic fracturing regions of a near vertical ultra thick coal seam. The method includes: deepening a main shaft from a mining level to a fracturing level; excavating a cross-hole from a roof rock layer of a coal seam at the fracturing level to enter a coal seam being mined, and excavating a roadway along the strike of the coal seam; and drilling hydraulic fracturing boreholes in a dedicated fracturing roadway along an inclination angle of the coal seam to the coal seam above the roadway, wherein the length of the borehole makes the borehole in communication with a goaf, and the spacing of the boreholes along the strike and the sectional spacing of the boreholes in an inclination direction are designed according to the parameters of fracturing equipments and the fracturing length.

Abstract: In neural-network-based approaches to sequence modeling, an output sequence may be modeled via segmentations, the probability of the output sequence being constructed as a sum of products of output-segment probabilities, taken over all valid output-sequence segmentations. A set of artificial neural networks may model the distribution of the output-sequence probability with a recurrent neural network modeling the distributions of the individual output-segment probabilities, optionally in conjunction with a second recurrent neural network modeling concatenations of output segments. In various embodiments, this approach is applied to neural phrase-based machine translation.