Abstract: Disclosed is a massive data-driven method for automatically locating a mine microseismic source, including: constructing a microseismic wave calibration data set by using a large-scale seismic data set containing seismic signals and non-seismic signals; constructing a pre-training calibration model based on a full convolution neural network through deep learning of a seismic wave calibration data set; using microseismic data of mine sites for transfer learning of an initial arrival time calibration model to construct an arrival time automatic calibration model suitable for mine microseismic signals; and automatically as well as accurately locating mine microseismic events based on an isokinetic homogeneous isotropic velocity model by using an optimization algorithm to deduce arrival time errors and through repeated iteration and fine-tuning.

Abstract: The present disclosure provides a physics-based and data-driven integrated method for rock burst hazard assessment, including the following steps: determining an initial stress concentration coefficient by conducting grid discretization on an assessment region, and assigning a value to each of grid nodes using a Weibull distribution function; obtaining a stress concentration coefficient value of each grid node under physics-based models; introducing seismic wave CT detection data to obtain stress concentration coefficient distribution in the assessment region under the integration of a seismic wave CT detection and its derived characterization stress model; introducing microseismic data to obtain stress concentration coefficient distribution in the assessment region under the integration of a microseismic damage reconstruction stress model; and assessing the degree of rock burst hazard according to the size of the stress concentration coefficient value.

Abstract: An online stress monitoring system is used to obtain a stress distribution of each position, a geophone monitoring system is used to monitor high-frequency vibration signals produced by coal and rock fracture, a support resistance monitoring system is used to monitor working resistance of hydraulic supports in a working face, a well-ground joint microseismic system is used to monitor low-frequency vibration signals produced by the coal and rock fracture, and realize position of a microseismic source and inversion imaging of mining fractures, and an anchor stress monitoring system is used to monitor stress states of anchor bolts and cables. A data processing center is used to comprehensively process data obtained from the above five systems using an early warning model, thereby to obtain a prediction result of rock burst and determine whether to make early warning, thus workers can take timely measures according to the early warning situation.

Abstract: Disclosed is a massive data-driven method for automatically locating a mine microseismic source, including: constructing a microseismic wave calibration data set by using a large-scale seismic data set containing seismic signals and non-seismic signals; constructing a pre-training calibration model based on a full convolution neural network through deep learning of a seismic wave calibration data set; using microseismic data of mine sites for transfer learning of an initial arrival time calibration model to construct an arrival time automatic calibration model suitable for mine microseismic signals; and automatically as well as accurately locating mine microseismic events based on an isokinetic homogeneous isotropic velocity model by using an optimization algorithm to deduce arrival time errors and through repeated iteration and fine-tuning.

Abstract: A method for improving a monitoring capability of a borehole-surface micro-seismic monitoring system includes selecting multiple candidate points for installing surface wireless sensors to form a natural-number-coded candidate point set and combining a fixed number of candidate points randomly selected from the candidate point set with an underground installed sensor set to form a borehole-surface micro-seismic monitoring network; carrying out multiple random selections until a certain scale of borehole-surface micro-seismic monitoring network deployment plans are generated; establishing an evaluation model for a monitoring capability of each borehole-surface micro-seismic monitoring network deployment plan according to a propagation relation equation between a micro-seismic energy and a first-arrival peak amplitude of a P-wave, forming an initial population; determining an optimal borehole-surface micro-seismic monitoring network deployment plan through a genetic algorithm; and determining an optimal surface

Abstract: A timing alignment method for data acquired by monitoring units of a borehole-surface micro-seismic monitoring system includes acquiring two rock-burst waveform data segments with GPS timestamps; calculating a time difference and a number of sampling points between each pair of adjacent GPS timestamps; adding, on an equal-interval basis, a sampling time to a sampling point missing a timestamp between each pair of adjacent GPS timestamps; calculating average sampling frequencies of the two rock-burst waveform data segments, adding, on an equal-interval basis, a sampling time to a sampling point missing a timestamp except first and last GPS timestamps in each of the two data segments; obtaining sampling times of all sampling points, resampling the sampling times according to a uniform sampling frequency; calculating a rock-burst waveform data segment at a new sampling time with a linear interpolation formula, and aligning the sampling times of the two rock-burst waveform data segments.

Abstract: The present disclosure provides a physics-based and data-driven integrated method for rock burst hazard assessment, including the following steps: determining an initial stress concentration coefficient by conducting grid discretization on an assessment region, and assigning a value to each of grid nodes using a Weibull distribution function; obtaining a stress concentration coefficient value of each grid node under physics-based models; introducing seismic wave CT detection data to obtain stress concentration coefficient distribution in the assessment region under the integration of a seismic wave CT detection and its derived characterization stress model; introducing microseismic data to obtain stress concentration coefficient distribution in the assessment region under the integration of a microseismic damage reconstruction stress model; and assessing the degree of rock burst hazard according to the size of the stress concentration coefficient value.

Abstract: A similar simulation experimental device of hydraulic energy-absorbing roadway support is provided. A similar model is placed in a model box, a roadway is excavated in the similar model, and hydraulic energy-absorbing support devices are placed in the roadway on the periphery of the roadway. Front and rear ends of the hydraulic energy-absorbing support device are connected to supporting plates, left and right sides of the model box are provided with horizontal hydraulic cylinders, and front ends of the horizontal hydraulic cylinders are connected to pressure plates. One or several cushion blocks are placed at the top of the model box, and an upper pressure plate is placed above the cushion block(s). Vertical hydraulic cylinders are installed at both ends of the upper pressure plate. An impact rod passing through the upper pressure plate is placed above the cushion block to apply vertical impact load to the similar model.