Mine vibration safety detection method and system during mining blasting

Abstract

The invention provides a mine vibration safety detection method and system during mining blasting. The method comprises the following steps: acquiring three-component signals of explosion fluctuation at a plurality of sampling points in a warning range through an intelligent sensor network during mine blasting; decomposing each three-component signal into a plurality of attenuation waves, determining cross correlation coefficients of the attenuation waves in the same component direction among different sampling points, and performing reverse time back propagation on each sampling point according to all the cross correlation coefficients to obtain a reverse time wave field of blasting vibration at each sampling point; inputting all the reverse time wave fields into a pre-trained multi-seismic-source positioning model to obtain a plurality of explosion points; and determining the risk value of miss-fire of each blast hole in the detonation network according to the coordinate positions of all the explosion points, and performing explosion aftershock evaluation on the mine according to all the risk values. According to the scheme, the miss-fire risk of each blast hole can be evaluated after mine blasting.

Description

Technical Field

[0001] The present application relates to the technical field of mining blasting. More specifically, the present application relates to a method and system for detecting the safety of mine vibrations during mining blasting. Background Art

[0002] Mining blasting is a widely used rock-breaking method in mine exploitation. By using the shock wave and high-pressure gas generated by the explosion of explosives in the blast holes, the rock is fractured and caved in, so as to achieve the purpose of mining ore or stripping surrounding rock. Blasting technology is widely used in fields such as underground mines, open-pit mines, tunnel excavation, and water conservancy projects. In mine blasting operations, the explosion energy of explosives is not only used to break rocks, but also generates strong shock waves that propagate to the surrounding rock masses. These vibrations may cause damage to the surrounding rock of the mine, instability of the roadway, damage to equipment, and even trigger mine tremors and secondary disasters. Therefore, the safety detection of mine vibrations is crucial for ensuring the safety of personnel, equipment, and the mine structure.

[0003] During mining blasting, due to environmental factors and equipment reasons, misfires may occur in some blast holes. Misfire refers to the situation where the explosives in the blast holes do not explode, do not explode completely, or the direction of the shock wave generated by the explosion is incorrect. The blast holes with misfires will not only result in unsatisfactory blasting results and cause the mine to collapse, but the remaining explosives also pose a risk of secondary explosion triggering aftershocks. In the prior art, misfires are usually solved from the prevention aspect, that is, by adjusting parameters through technical means or tests before blasting to reduce the risk of misfires. There is a lack of detection of whether misfires occur in the blast holes after blasting in the prior art. However, in actual operations, if there are sudden factors in the environment, even if the misfires of the blast holes are prevented in advance, misfires may still occur in some blast holes, and there may be a risk of aftershocks in the subsequent mine, posing a hidden danger to the safety of subsequent operators. Therefore, how to evaluate the misfire risk of each blast hole after mine blasting has become a difficult problem faced by the industry. Summary of the Invention

[0004] The present application provides a method and system for detecting the safety of mine vibrations during mining blasting, which can evaluate the misfire risk of each blast hole after mine blasting.

[0005] In a first aspect, the present application provides a method for detecting the safety of mine vibrations during mining blasting, including: Performing vibration simulation on the warning range of mine blasting based on the number of blast holes in the initiation network to obtain multiple groups of simulation data, and then training a multi-source localization model through all the simulation data; Arranging an intelligent sensor network within the warning range, and collecting the three-component signals of the explosion fluctuations at multiple sampling points within the warning range through the intelligent sensor network during mine blasting; Decompose each three-component signal into multiple attenuated waves, determine the cross-correlation coefficients between the attenuated waves in the same component direction at different sampling points, perform reverse time backpropagation on each sampling point according to all the cross-correlation coefficients, and obtain the reverse time wave field of the blasting vibration at each sampling point; Input all the reverse time wave fields into the multi-source location model to obtain multiple explosion points; Determine the risk value of misfiring for each blast hole in the initiation network according to the coordinate positions of all the explosion points, and evaluate the aftershocks of the mine blasting based on all the risk values.

[0006] In some embodiments, perform vibration simulation on the warning range of the mine blasting based on the number of blast holes in the initiation network to obtain multiple sets of simulation data, specifically including: Simulate multiple blasting events according to the number of blast holes in the initiation network; Set the event label for each blasting event; For each event label, set the number of seismic sources for each event label; Generate a vibration model for each event label according to the number of seismic sources for each event label, and then determine multiple sets of simulation data for each vibration model.

[0007] In some embodiments, decomposing each three-component signal into multiple attenuated waves specifically includes: Select one three-component signal as the selected three-component signal; Filter the selected three-component signal to obtain the smoothed signal of each component signal in the selected three-component signal; Decompose each smoothed signal into multiple attenuated waves to obtain multiple attenuated waves of the selected three-component signal; Continue to determine multiple attenuated waves of the remaining three-component signals.

[0008] In some embodiments, performing reverse time backpropagation on each sampling point according to all the cross-correlation coefficients to obtain the reverse time wave field of the blasting vibration at each sampling point specifically includes: Select one component direction as the selected component direction, and determine the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the attenuated waves in the selected component direction; Continue to determine the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the attenuated waves in the remaining selected component directions; For each homologous wave cluster, convert all the homologous waves in each homologous wave cluster into the reverse time wave field of the blasting vibration at each sampling point.

[0009] In some embodiments, inputting all the reverse time wave fields into the multi-source location model to obtain multiple explosion points specifically includes: For each reverse-time wave field, input each reverse-time wave field into the multi-source positioning model to obtain multiple source coordinates of each reverse-time wave field; Determine multiple explosion points based on all the source coordinates.

[0010] In some embodiments, the blasting aftershock assessment of the mine based on all the risk values specifically includes: Preset a misfire risk threshold; Compare all the risk values with the preset misfire risk threshold, and regard the blast holes with all risk values greater than the misfire risk threshold as risk blast holes; Determine the risk area of the blasting aftershock risk based on all the risk blast holes.

[0011] In some embodiments, the intelligent sensor network is a sensor network composed of multiple three-component geophones.

[0012] In a second aspect, the present application provides a mine vibration safety detection system during mining blasting, and the mine vibration safety detection system during mining blasting includes: A pre-training module, configured to perform vibration simulation on the warning range of the mine blasting based on the number of blast holes in the initiation network to obtain multiple groups of simulation data, and then train a multi-source positioning model through all the simulation data; An acquisition module, configured to arrange an intelligent sensor network within the warning range, and collect three-component signals of explosion fluctuations at multiple sampling points within the warning range through the intelligent sensor network during mine blasting; A processing module, configured to decompose each three-component signal into multiple attenuated waves, determine the cross-correlation coefficients of the attenuated waves in the same component direction between different sampling points, perform reverse-time backpropagation on each sampling point according to all the cross-correlation coefficients to obtain the reverse-time wave field of the blasting vibration at each sampling point; The processing module is further configured to input all the reverse-time wave fields into the multi-source positioning model to obtain multiple explosion points; An execution module, configured to determine the risk value of misfire of each blast hole in the initiation network according to the coordinate positions of all the explosion points, and perform blasting aftershock assessment on the mine based on all the risk values.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned mine vibration safety detection method during mining blasting.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned mine vibration safety detection method during mining blasting is implemented.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In the mine vibration safety detection method and system during mining blasting provided by this application, first, an intelligent sensor network is arranged within the warning range of mine blasting, and during mine blasting, three-component signals of explosion fluctuations at multiple sampling points within the warning range are collected through the intelligent sensor network; each three-component signal is decomposed into multiple attenuation waves, the cross-correlation coefficients of the attenuation waves in the same component direction between different sampling points are determined, and inverse time reversal is performed on each sampling point according to all the cross-correlation coefficients to obtain the inverse time wave field of blasting vibration at each sampling point; event tags for multiple blasting events are set based on the number of blast holes in the initiation network, vibration simulation is performed on the warning range of the mine according to all the event tags to obtain multiple groups of simulation data, and a multi-source location model is trained through all the simulation data; all the inverse time wave fields are input into the multi-source location model to obtain multiple explosion points; the risk value of misfiring of each blast hole in the initiation network is determined according to all the explosion points, and the blasting aftershock of the mine is evaluated based on all the risk values.

[0016] It can be seen that in this application, by decomposing the three-component signals during explosion, attenuation waves from different vibration sources are obtained. Subsequently, through the correlation between the attenuation waves (i.e., the cross-correlation coefficient), the attenuation waves from the same explosion point source are screened out from each sampling point through the correlation, and then inverse time reversal is performed on all the attenuation waves from the same explosion point source, that is, the inverse time wave field of blasting at each sampling point can be obtained. Subsequently, a model trained by simulating the data during blasting in the mine through software (i.e., the multi-source location model) analyzes all the inverse time wave fields, and then determines whether the blast holes in the initiation network misfire (i.e., the risk value of misfiring) according to the analysis results. Finally, the blasting aftershock is evaluated based on all the risk values. In summary, this application can evaluate the misfiring risk of each blast hole after mine blasting. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a mine vibration safety detection method during mining blasting shown in some embodiments of this application; Figure 2 is an exemplary flowchart of inverse time reversal shown in some embodiments of this application; Figure 3 is an exemplary flowchart of blasting aftershock evaluation shown in some embodiments of this application; Figure 4 is a schematic structural diagram of a mine vibration safety detection system during mining blasting shown in some embodiments of this application; Figure 5It is a schematic structural diagram of a computer device for implementing the mine vibration safety detection method during mining blasting as shown in some embodiments of the present application. Detailed implementation manners

[0018] To better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the specification drawings and specific implementation manners.

[0019] Refer to Figure 1 , which is an exemplary flowchart of the mine vibration safety detection method during mining blasting as shown in some embodiments of the present application. The mine vibration safety detection method 100 during mining blasting mainly includes the following steps: In step 101, vibration simulation is performed on the warning range of the mine blasting based on the number of blast holes in the initiation network to obtain multiple sets of simulation data, and then a multi-source localization model is trained through all the simulation data.

[0020] In some embodiments, the vibration simulation of the warning range of the mine blasting based on the number of blast holes in the initiation network to obtain multiple sets of simulation data can be implemented by the following steps, that is: Simulate multiple blasting events according to the number of blast holes in the initiation network; Set the event label for each blasting event; For each event label, set the number of seismic sources for each event label; Generate a vibration model for each event label according to the number of seismic sources for each event label, and then determine multiple sets of simulation data for each vibration model.

[0021] In specific implementation, simulating multiple blasting events according to the number of blast holes in the initiation network can be implemented by the following method, that is: First, obtain the number of blast holes in the initiation network, and then set the number of normally initiated blast holes to all integers between 1 and n. Each number of normally initiated blast holes corresponds to a blasting event, where n is the number of blast holes in the initiation network.

[0022] It should be noted that in the present application, a blasting event refers to an event in which a specific number of blast holes in the mine are normally initiated.

[0023] In specific implementation, setting the event label for each blasting event can be implemented by the following method, that is: Set the number of normally initiated blast holes in the initiation network corresponding to each blasting event as the event label for each blasting event.

[0024] It should be noted that in the present application, the event label is a label used to distinguish different blasting events.

[0025] In specific implementation, setting the number of seismic sources for each event label can be implemented by the following method, that is: Set the number of seismic sources to the same value as the event label.

[0026] In specific implementation, a vibration model for each event label is generated according to the number of seismic sources of each event label, and then multiple groups of simulation data for each vibration model can be obtained by the following method: First, select a number of seismic sources as the selected number of seismic sources. Then, the SPECFEM3D software in the prior art can be used to set k seismic sources in the SPECFEM3D software. The positions of the seismic sources can be set arbitrarily, and i stations are set to collect three-component data. All the set seismic sources and all the stations are used as the vibration model. Subsequently, the simulation of the SPECFEM3D software is started, and the three-component data collected by each station are used as a group of simulation data of the vibration model. Continue to determine a group of simulation data corresponding to the vibration model of the remaining number of seismic sources, where k is the selected number of seismic sources and i is the number of sampling points in this application.

[0027] It should be noted that the simulation data in this application refers to seismic data obtained by simulating with seismic simulation software.

[0028] In some embodiments, training a multi-seismic source location model according to all the simulation data can be implemented by the following method: Convert each group of simulation data into a simulation image; Use all the simulation images as training samples and train them through a fully convolutional neural network to obtain a multi-seismic source location model.

[0029] In specific implementation, converting each group of simulation data into a simulation image can be implemented by the following method: Select a group of simulation data as the selected simulation data. Use the data in the east-west direction in the selected simulation data as the blue channel, the data in the north-south direction as the green channel, and the data in the vertical direction as the red channel. Use the simulation data of all the same stations as the same row and stack them vertically by row into a two-dimensional image. Use this two-dimensional image as the simulation image of the selected simulation data. Continue to determine the simulation images of the remaining simulation data.

[0030] It should be noted that the simulation image in this application refers to a two-dimensional image stacked from simulation data.

[0031] In specific implementation, using all the simulation images as training samples and training them through a fully convolutional neural network to obtain a multi-seismic source location model can be implemented by the following method: The fully convolutional neural network in the literature "Application of Fully Convolutional Location Neural Network in the Case of Two Earthquakes Interfering with Each Other" can be used to train the training samples. Among them, the sample data is all the simulation images, and the sample labels are the number of seismic sources of each simulation image and the coordinates of each seismic source. Use the trained model as the multi-seismic source location model. In other embodiments, it can also be trained through other existing fully convolutional neural networks, which is not limited here.

[0032] It should be noted that in this application, the multi-source positioning model is a neural network model used to locate multiple underground seismic sources.

[0033] In step 102, an intelligent sensor network is arranged within the warning range of the mine blasting, and during the mine blasting, the three-component signals of the explosion fluctuations at multiple sampling points within the warning range are collected through the intelligent sensor network.

[0034] Specifically, arranging the intelligent sensor network within the warning range of the mine blasting can be achieved in the following way: multiple sampling points are set within the warning range, an intelligent sensor is set at each sampling point, a connection is established between all intelligent sensors through wireless communication technology, and the network composed of all interconnected intelligent sensors is used as the intelligent sensor network. Among them, 50 positions can be randomly selected within the warning range as sampling points.

[0035] It should be noted that in this application, the intelligent sensor is a three-component geophone.

[0036] In addition, it should be noted that in this application, the warning range is a preset area range to ensure personnel safety. This area range is the range demarcated through on-site investigation and explosive dosage before blasting. For example, in this application, the range within 500 of all blast holes is set as the warning range.

[0037] Specifically, collecting the three-component signals of the explosion fluctuations at multiple sampling points within the warning range through the intelligent sensor network during the mine blasting can be achieved in the following way: one sampling point is selected as the selected sampling point, and the intelligent sensor at the selected sampling point collects the vibration velocities in three different directions at the selected sampling point according to a preset sampling interval. The vibration velocities in the same direction are arranged in chronological order, and all the arranged sequences are used as the component signals in the corresponding directions. Then, the component signals in the three different directions are all used as the three-component signals of the explosion fluctuations at the selected sampling point, and the three-component signals of the explosion fluctuations at the remaining sampling points are continuously collected. Among them, the sampling interval can be preset according to actual needs. For example, in this application, the sampling interval is preset to 0.01 seconds, and the three different directions refer to the vertical direction, the east-west direction, and the north-south direction.

[0038] It should be noted that in this application, the three-component signal refers to a signal composed of component signals in three component directions, where the three component directions refer to the vertical direction, the east-west direction, and the north-south direction.

[0039] In step 103, each three-component signal is decomposed into multiple attenuated waves, the cross-correlation coefficients between the attenuated waves in the same component direction at different sampling points are determined, and backpropagation in time is performed on each sampling point according to all the cross-correlation coefficients to obtain the backpropagated wave field of the blasting vibration at each sampling point.

[0040] In some embodiments, decomposing each three-component signal into multiple attenuated waves can be implemented by the following steps, that is: Select a three-component signal as the selected three-component signal; Filter the selected three-component signal to obtain the smoothed signal of each component signal in the selected three-component signal; Decompose each smoothed signal into multiple attenuated waves to obtain multiple attenuated waves of the selected three-component signal; Continue to determine multiple attenuated waves of the remaining three-component signals.

[0041] Specifically, filtering the selected three-component signal to obtain the smoothed signal of each component signal in the selected three-component signal can be implemented in the following way, that is: each component signal in the selected three-component signal can be filtered by wavelet transform in the prior art, and all the filtered signals are respectively used as the smoothed signals of each component signal. In other embodiments, the selected three-component signal can also be filtered by other prior arts, which is not limited here.

[0042] It should be noted that in this application, the smoothed signal is the component signal after filtering and denoising.

[0043] Specifically, decomposing each smoothed signal into multiple attenuated waves to obtain multiple attenuated waves of the selected three-component signal can be implemented in the following way, that is: each smoothed signal can be decomposed into multiple intrinsic mode functions by empirical mode decomposition in the prior art, and all the intrinsic mode functions obtained by decomposing each smoothed signal are used as the attenuated waves of each smoothed signal. Among them, the termination condition of the empirical mode decomposition is set that the number of intrinsic mode functions reaches the number of sampling points.

[0044] It should be noted that in this application, the number of attenuated waves obtained by decomposing each three-component signal is the same as the number of blast holes in the initiation network.

[0045] It should be noted that in this application, the attenuated wave is a signal describing the attenuation characteristics of the blasting vibration during the underground propagation process.

[0046] In some embodiments, determining the cross-correlation coefficients between the attenuated waves in the same component direction at different sampling points can be implemented by the following steps, that is: Classify all the attenuated waves according to the component direction to obtain multiple clusters of attenuated waves; Select a cluster of decaying waves as the selected cluster of decaying waves, and determine the cross-correlation coefficient between the decaying waves at every two different sampling points in the selected cluster of decaying waves; Continue to determine the cross-correlation coefficient between the decaying waves at every two different sampling points in the remaining clusters of decaying waves.

[0047] In specific implementation, classifying all the decaying waves according to the component direction to obtain multiple clusters of decaying waves can be implemented in the following manner, that is: all the decaying waves with the same component direction are taken as a set, and all the obtained sets are respectively taken as clusters of decaying waves, where the component direction refers to the direction of each component signal in the three-component signal, and the component direction includes the vertical direction, the east-west direction, and the north-south direction.

[0048] It should be noted that in this application, a cluster of decaying waves refers to a set composed of decaying waves with the same component direction.

[0049] In specific implementation, determining the cross-correlation coefficient between the decaying waves at every two different sampling points in the selected cluster of decaying waves can be implemented in the following manner, that is: First, obtain the sampling points of each decaying wave in the selected cluster of decaying waves, then, select a decaying wave in the selected cluster of decaying waves as the selected decaying wave, determine the cross-correlation coefficient between the selected decaying wave and each decaying wave with different sampling points from the selected decaying wave in the selected cluster of decaying waves, and continue to determine the cross-correlation coefficient between the remaining decaying waves at every two different sampling points in the selected cluster of decaying waves.

[0050] It should be noted that in this application, each sampling point corresponds to a three-component signal, each three-component signal includes three component directions, and each component direction corresponds to a component signal.

[0051] It should be noted that in this application, the cross-correlation coefficient is a parameter value that measures the degree of correlation between two decaying waves. The larger the cross-correlation coefficient, the greater the degree of correlation between the two decaying waves; the smaller the cross-correlation coefficient, the smaller the degree of correlation between the two decaying waves. The two decaying waves with a greater degree of correlation are more likely to be caused by the vibration from the explosion of the same blast hole.

[0052] In some embodiments, refer to Figure 2 , this figure is an exemplary flowchart of performing time reversal according to some embodiments of this application. In this application, performing time reversal on each sampling point according to all the cross-correlation coefficients to obtain the time-reversed wave field of the blasting vibration at each sampling point can be implemented in the following steps, that is: In step 1031, select a component direction as the selected component direction, and determine the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the decaying waves in the selected component direction; In step 1032, continue to determine the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the decaying waves in the remaining selected component directions; In step 1033, for each homologous wave cluster, all the homologous waves in each homologous wave cluster are converted into the reverse-time wave field of the blasting vibration at each sampling point.

[0053] It should be noted that in this application, performing reverse-time backpropagation on each sampling point according to all the cross-correlation coefficients means: selecting a component direction as the selected component direction, determining the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the attenuated waves in the selected component direction; continuing to determine the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the attenuated waves in the remaining selected component directions; for each homologous wave cluster, converting all the homologous waves in each homologous wave cluster into the reverse-time wave field of the blasting vibration at each sampling point.

[0054] When specifically implemented, determining the homologous wave cluster of each sampling point according to the cross-correlation coefficients of all the attenuated waves in the selected component direction can be achieved by the following method, that is: first, selecting a sampling point as the selected sampling point, selecting an attenuated wave in the selected component direction of the selected sampling point as the central attenuated wave, obtaining all the cross-correlation coefficients corresponding to the central attenuated wave, dividing the other attenuated wave corresponding to the maximum cross-correlation coefficient among them and the central attenuated wave into the same set, and using the other attenuated wave corresponding to the maximum cross-correlation coefficient among them as the new central attenuated wave, repeating the above division steps until at least one attenuated wave in each sampling point is divided into the set, taking the obtained set as the homologous wave cluster of the selected sampling point, and continuing to determine the homologous wave clusters of the remaining sampling points, where the above division step refers to "obtaining all the cross-correlation coefficients corresponding to the central attenuated wave, dividing the other attenuated wave corresponding to the maximum cross-correlation coefficient among them and the central attenuated wave into the same set, and using the other attenuated wave corresponding to the maximum cross-correlation coefficient among them as the new central attenuated wave".

[0055] It should be noted that in this application, the homologous wave cluster refers to a set composed of attenuated waves from the explosion vibration of the same blast hole.

[0056] When specifically implemented, converting all the homologous waves in each homologous wave cluster into the reverse-time wave field of the blasting vibration at each sampling point can be achieved by the following method, that is: first, normalizing all the attenuated waves to the range of 0 - 255, then, selecting a homologous wave cluster as the selected homologous wave cluster, dividing all the attenuated waves in the selected homologous wave cluster into three categories according to the component direction, subsequently, using the attenuated waves in the east-west direction as the blue channel, using the attenuated waves in the north-south direction as the green channel, using the attenuated waves in the vertical direction as the red channel, and then taking the attenuated waves with the same sampling points as the same row, stacking them vertically by row into a two-dimensional image, taking this two-dimensional image as the reverse-time wave field of the blasting vibration at the sampling points of the selected homologous wave cluster, and continuing to determine the reverse-time wave fields of the blasting vibrations at the sampling points of the remaining homologous wave clusters.

[0057] It should be noted that in this application, the inverse time wave field is an image used to trace the source of blasting vibration in a mine.

[0058] In step 104, all the inverse time wave fields are input into the multi-source location model to obtain multiple explosion points.

[0059] In some embodiments, inputting all the inverse time wave fields into the multi-source location model to obtain multiple explosion points can be achieved by the following steps, namely: For each inverse time wave field, input the each inverse time wave field into the multi-source location model to obtain multiple source coordinates of the each inverse time wave field; Determine multiple explosion points according to all the source coordinates.

[0060] When specifically implemented, inputting the each inverse time wave field into the multi-source location model to obtain multiple source coordinates of the each inverse time wave field can be achieved by the following method, namely: select one inverse time wave field as the selected inverse time wave field, input the selected inverse time wave field as input data into the multi-source location model, take all the coordinates output by the multi-source location model as the source coordinates of the selected inverse time wave field, and continue to determine the multiple source coordinates of the remaining inverse time wave fields.

[0061] It should be noted that in this application, the source coordinate refers to the coordinate of the center point of the vibration.

[0062] When specifically implemented, determining multiple explosion points according to all the source coordinates can be achieved by the following method, namely: First, calculate the Euclidean distance between every two source coordinates, divide all the source coordinates with the Euclidean distance less than the preset distance threshold into the same set, then, calculate the average coordinate of all the source coordinates in each set, and take all the obtained average coordinates as the coordinates of the explosion points.

[0063] It should be noted that in this application, the explosion point refers to the center point of the blasting vibration during mining blasting.

[0064] In step 105, determine the risk value of misfiring of each blast hole in the initiation network according to the coordinate positions of all the explosion points, and evaluate the aftershock of the mine blasting based on all the risk values.

[0065] In some embodiments, determining the risk value of misfiring of each blast hole in the initiation network according to the coordinate positions of all the explosion points can be achieved by the following steps, namely: Obtain the coordinates of each explosion point and the coordinates of each blast hole in the initiation network For each blast hole, determine the explosion point closest to the each blast hole, and take the explosion point closest to the each blast hole as the matching point of the each blast hole; Determine the misfire risk value of each blast hole according to the coordinates of each blast hole and the coordinates of the corresponding matching points of each blast hole.

[0066] When specifically implemented, determining the explosion point closest to each blast hole can be achieved by the following method, that is: First, select a blast hole as the selected blast hole, calculate the Euclidean distance between the coordinates of the selected blast hole and the coordinates of each explosion point, and then take the explosion point with the smallest Euclidean distance as the explosion point closest to the selected blast hole, and continue to determine the explosion point closest to each remaining blast hole.

[0067] It should be noted that in this application, the matching point refers to the explosion point closest to each blast hole.

[0068] When specifically implemented, determining the misfire risk value of each blast hole according to the coordinates of each blast hole and the coordinates of the corresponding matching points of each blast hole can be achieved by the following method, that is: First, calculate the Euclidean distance between the coordinates of each blast hole and the coordinates of the corresponding matching points of each blast hole, and then take all the Euclidean distances as the misfire risk values of each blast hole respectively.

[0069] It should be noted that in this application, the risk value is a parameter value used to measure the possibility of misfire during blast hole blasting. The larger the risk value, the greater the possibility of misfire during blast hole blasting, and the smaller the risk value, the smaller the possibility of misfire during blast hole blasting.

[0070] In some embodiments, refer to Figure 3 , this figure is an exemplary flowchart of blast aftershock assessment according to some embodiments of this application. The blast aftershock assessment of the mine based on all risk values can be achieved by the following steps, that is: In step 1051, preset a misfire risk threshold; In step 1052, compare all the risk values with the preset misfire risk threshold, and take all the blast holes with risk values greater than the misfire risk threshold as risk blast holes; In step 1053, determine the risk area of the blast aftershock risk according to all the risk blast holes.

[0071] It should be noted that the misfire risk threshold in this application is a value preset according to the equivalent amount of explosive in the blast hole. For example, twice the cube root of the equivalent amount of explosive in the blast hole can be used as the misfire risk threshold. That is, if the equivalent amount of explosive in the blast hole is 1000 kg, the misfire risk threshold is set to 20 meters. In other embodiments, the misfire risk threshold can also be set by other methods, which is not limited here.

[0072] It should be noted that the risk blast hole in this application refers to the blast hole with the risk of secondary blasting, and the secondary blasting risk refers to the second explosion after the first blasting.

[0073] In specific implementation, to determine the risk area of blasting aftershock based on all risk blast holes, the following method can be adopted, that is: the area within 30 meters around each risk blast hole can be used as the risk area of blasting aftershock.

[0074] It should be noted that in this application, the risk area refers to the dangerous area affected by the aftershock caused by the secondary blasting at the misfired point.

[0075] In addition, on the other hand of this application, in some embodiments, this application provides a mine vibration safety detection system during mining blasting. Refer to Figure 4 , this figure is a schematic structural diagram of the mine vibration safety detection system during mining blasting shown in some embodiments of this application. The mine vibration safety detection system 400 during mining blasting includes: a pre-training module 401, a collection module 402, a processing module 403, and an execution module 404, which are described as follows: Pre-training module 401. In this application, the pre-training module 401 is mainly used to perform vibration simulation on the warning range of mine blasting based on the number of blast holes in the initiation network to obtain multiple sets of simulation data, and then train a multi-source localization model through all the simulation data; Collection module 402. In this application, the collection module 402 is mainly used to arrange an intelligent sensor network within the warning range of mine blasting, and collect the three-component signals of the explosion fluctuations at multiple sampling points within the warning range through the intelligent sensor network during mine blasting; Processing module 403. In this application, the processing module 403 is mainly used to decompose each three-component signal into multiple attenuated waves, determine the cross-correlation coefficients between the attenuated waves in the same component direction at different sampling points, and perform reverse time propagation on each sampling point according to all the cross-correlation coefficients to obtain the reverse time wave field of the blasting vibration at each sampling point; It should be noted that in this application, the processing module 403 is also used to input all the reverse time wave fields into the multi-source localization model to obtain multiple explosion points; Execution module 404. In this application, the execution module 404 is mainly used to determine the risk value of misfiring of each blast hole in the initiation network according to all the explosion points, and evaluate the blasting aftershock of the mine based on all the risk values.

[0076] In addition, this application also provides a computer device. The computer device includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned mine vibration safety detection method during mining blasting.

[0077] In some embodiments, refer to Figure 5, which is a schematic structural diagram of a computer device for implementing the mine vibration safety detection method during mining blasting according to some embodiments of the present application. The mine vibration safety detection method during mining blasting in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0078] The processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0079] The communication bus 502 can be used to transmit information between the above components.

[0080] The memory 503 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CDROM), or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0081] Among them, the memory 503 is used to store the program code for executing the solution of the present application and is controlled by the processor 501 for execution. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The mine vibration safety detection method during mining blasting in the above embodiments can be implemented by one or more software modules in the processor 501 and the program code in the memory 503.

[0082] A communication interface 504, using any device such as a transceiver, for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0083] In a specific implementation, as an example, a computer device may include multiple processors, and each of these processors may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, the processor may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0084] The above computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0085] In addition, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned mine vibration safety detection method during mining blasting is implemented.

[0086] In summary, in the mine vibration safety detection method and system disclosed in the embodiments of the present application, first, an intelligent sensor network is arranged within the warning range of mine blasting, and during mine blasting, three-component signals of explosion fluctuations at multiple sampling points within the warning range are collected through the intelligent sensor network; each three-component signal is decomposed into multiple attenuation waves, the cross-correlation coefficients of the attenuation waves in the same component direction between different sampling points are determined, and based on all the cross-correlation coefficients, backpropagation in time is performed for each sampling point to obtain the time-reversed wave field of blasting vibration at each sampling point; event tags for multiple blasting events are set based on the number of blast holes in the initiation network, and vibration simulation is performed on the warning range of the mine according to all the event tags to obtain multiple sets of simulation data, and a multi-source localization model is trained through all the simulation data; all the time-reversed wave fields are input into the multi-source localization model to obtain multiple explosion points; according to all the explosion points, the risk value of misfiring of each blast hole in the initiation network is determined, and based on all the risk values, aftershock assessment of the mine is performed.

[0087] It can be seen that in this application, by decomposing the three-component signals during an explosion, the attenuated waves at different vibration sources are obtained. Subsequently, through the correlation between the attenuated waves (i.e., the cross-correlation coefficient), the attenuated waves from the same explosion source are screened out at each sampling point through the correlation. Then, by performing reverse time migration on all the attenuated waves from the same explosion source, the reverse time wave field of the blasting at each sampling point can be obtained. Subsequently, the model trained by simulating the data of the blasting in the mine by software (i.e., the multi-source location model) analyzes all the reverse time wave fields, and then determines whether the blast holes in the initiation network are misfired (i.e., the risk value of misfiring) according to the analysis results. Finally, the aftershocks of the blasting are evaluated through all the risk values. In summary, this application can evaluate the misfiring risk of each blast hole after the mine blasting.

[0088] Although the preferred embodiments of this application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of this application.

[0089] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application also intends to include these modifications and variations.

Claims

1. A mine vibration safety detection method during mining blasting, characterized in that: include: Based on the number of blastholes in the blasting network, the warning range of mine blasting is simulated to obtain multiple sets of simulation data, and then the multi-source location model is trained through all the simulation data; Arrange an intelligent sensor network within the warning range, and collect three-component signals of explosion fluctuations at multiple sampling points within the warning range through the intelligent sensor network during mine blasting; Decompose each three-component signal into multiple attenuation waves, determine the mutual correlation coefficients between attenuation waves of the same component direction at different sampling points, perform reverse time propagation on each sampling point based on all the mutual correlation coefficients, and obtain the reverse time wave field of blasting vibration at each sampling point; Inputting all the reverse time wave fields into the multi-seismic source positioning model to obtain multiple explosion points; The risk value of explosion rejection of each blast hole in the blasting network is determined according to the coordinate positions of all explosion points, and the blasting aftershock assessment of the mine is performed based on all the risk values.

2. The method according to claim 1, characterized in that Based on the number of blastholes in the blasting network, the warning range of mine blasting is simulated by vibration, and multiple sets of simulation data are obtained, including: Simulate multiple blasting events based on the number of blastholes in the blasting network; Set the event label for each blasting event; For each event label, set the number of sources per event label; A vibration model for each event label is generated according to the number of earthquake sources for each event label, and then multiple groups of simulation data for each vibration model are determined.

3. The method according to claim 1, characterized in that Decomposing each three-component signal into multiple decay waves specifically includes: selecting a three-component signal as a selected three-component signal; Filtering the selected three-component signal to obtain a smoothed signal of each component signal in the selected three-component signal; Decomposing each smoothed signal into a plurality of decaying waves to obtain a plurality of decaying waves of the selected three-component signal; Continue to determine multiple decaying waves of the remaining three component signals.

4. The method according to claim 1, characterized in that According to all the mutual correlation coefficients, each sampling point is reversed in time, and the reverse time wave field of the blasting vibration at each sampling point is obtained, which specifically includes: A component direction is selected as a selected component direction, and a homologous wave cluster of each sampling point is determined according to the mutual correlation coefficient of all decaying waves in the selected component direction; Continue to determine the homologous wave cluster of each sampling point according to the mutual correlation coefficients of all decaying waves in the directions of the remaining selected components; For each homologous wave cluster, all homologous waves in the homologous wave cluster are converted into reverse time wave fields of blasting vibrations at various sampling points.

5. The method according to claim 1, characterized in that Input all the reverse time wave fields into the multi-seismic source location model to obtain multiple explosion points, including: For each reverse-time wave field, inputting each reverse-time wave field into the multi-seismic source positioning model to obtain multiple seismic source coordinates of each reverse-time wave field; Multiple explosion points are determined based on all the hypocenter coordinates.

6. The method according to claim 1, characterized in that The blast aftershock assessment of the mine based on all risk values ​​includes: Preset explosion rejection risk threshold; Compare all risk values ​​with a preset explosion rejection risk threshold, and classify all blastholes with risk values ​​greater than the explosion rejection risk threshold as risk blastholes; Determine the risk areas of blast aftershock risk based on all risky blastholes.

7. The method according to claim 1, characterized in that The intelligent sensor network is a sensor network composed of multiple three-component detectors.

8. A mine vibration safety detection system during mining blasting, characterized in that: The mine vibration safety detection system during mining blasting includes: A pre-training module is used to simulate the vibration of the warning range of mine blasting based on the number of blastholes in the blasting network, obtain multiple sets of simulation data, and then train the multi-seismic source positioning model through all the simulation data; A collection module, used for arranging an intelligent sensor network within the warning range, and collecting three-component signals of explosion fluctuations at multiple sampling points within the warning range through the intelligent sensor network during mine blasting; A processing module is used to decompose each three-component signal into multiple attenuation waves, determine the mutual correlation coefficients between attenuation waves of the same component direction at different sampling points, perform reverse time propagation on each sampling point according to all the mutual correlation coefficients, and obtain the reverse time wave field of the blasting vibration at each sampling point; The processing module is also used to input all reverse time wave fields into the multi-seismic source positioning model to obtain multiple explosion points; The execution module is used to determine the risk value of explosion rejection of each blast hole in the blasting network according to the coordinate positions of all explosion points, and to evaluate the blasting aftershocks of the mine according to all the risk values.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the mine vibration safety detection method during mining blasting as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for safely detecting mine vibration during mining blasting as described in any one of claims 1 to 7 is implemented.

Images