Dynamic disaster early warning system and method based on stope global multi-source information fusion

Abstract

The invention provides a dynamic disaster early warning system and method based on stope global multi-source information fusion, and relates to the technical field of safe mining. Stope stress data are obtained, and a rock mass fracture precursor coefficient is analyzed and generated; stope micro-seismic data and stope electromagnetic data are obtained, a micro-seismic fracture coefficient and an electromagnetic fracture coefficient are generated through analysis, and a rock mass fracture coefficient is generated according to the micro-seismic fracture coefficient and the electromagnetic fracture coefficient; acquiring acoustic emission data of the stope, and analyzing to generate a rock mass expansion coefficient; and acquiring charge data of the stope, analyzing and generating a rock mass dynamic coefficient, generating a dynamic disaster assessment coefficient according to the rock mass fracture precursor coefficient, the rock mass fracture coefficient, the rock mass expansion coefficient and the rock mass dynamic coefficient, and completing early warning of the dynamic disaster according to the dynamic disaster assessment coefficient. According to the method, dynamic disaster risk assessment can be more advanced, visual and accurate, a scientific basis is provided for safe production management of a stope, and errors of subjective judgment of dynamic disaster prevention and control are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of safe mining, and in particular to a power disaster early warning system and method based on multi-source information fusion in the entire mining area. Background Art

[0002] In the mining process, dynamic disasters in the mining area (such as rock burst, rock burst, roof collapse, etc.) are one of the main factors threatening mine safety. Traditional dynamic disaster early warning methods mainly rely on single monitoring data (such as stress and microseismic data). This method has obvious limitations and cannot fully reflect the complexity and diversity of dynamic disasters. Specifically, traditional methods ignore multi-level data such as electromagnetic waves, charges and acoustic emissions, resulting in incomplete assessments, which may underestimate the risk of dynamic disasters, increase the probability of safety accidents, waste monitoring resources, and affect the scientificity and effectiveness of management decisions. Therefore, it is urgent to invent an early warning method that can integrate multi-source information and comprehensively and accurately assess the risk of dynamic disasters in order to improve the safety and stability of mining.

[0003] In the prior art, the publication number CN118133490A discloses an intelligent prediction method and system for coal mine compound dynamic disasters, which obtains data of coal mine compound dynamic disasters through microseismic monitoring technology and real-time stress monitoring technology; preprocesses and analyzes the data to obtain a compound dynamic disaster prediction relationship model; predicts coal mine compound dynamic disasters based on the compound dynamic disaster prediction relationship model to obtain prediction results; uploads the prediction results to a central station, and the central station displays the data and prediction results of the coal mine compound dynamic disasters. However, the prior art still has defects. The degree of dynamic disasters can be reflected from multiple levels such as stress, microseismic, electromagnetic waves, charge and acoustic emission data, while the prior art only analyzes the dynamic disaster situation through stress and microseismic, ignoring multiple levels of data such as electromagnetic waves, charge and acoustic emission, resulting in incomplete evaluation, which may underestimate the risk of dynamic disasters, increase the probability of safety accidents, waste monitoring resources, and affect the scientificity and effectiveness of management decisions.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a power disaster early warning system and method based on multi-source information fusion in the whole area of ​​the mining area, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A power disaster early warning system based on multi-source information fusion in the whole area of ​​the mining area, specifically including: The precursor analysis module is used to obtain the three-dimensional stress distribution data of the stope, perform feature extraction on the three-dimensional stress distribution data of the stope, obtain stress characteristic data, and generate the rock mass fracture precursor coefficient according to the stress characteristic data; The fracture analysis module is used to obtain the microseismic data and electromagnetic data of the mining field, and perform feature extraction on the microseismic data and electromagnetic data of the mining field to obtain microseismic characteristic data and electromagnetic characteristic data, and generate the microseismic fracture coefficient according to the microseismic characteristic data; generate the electromagnetic fracture coefficient according to the electromagnetic characteristic data, and generate the rock fracture coefficient according to the microseismic fracture coefficient and the electromagnetic fracture coefficient; Expansion analysis module, used to obtain stope acoustic emission data, perform feature extraction on the stope acoustic emission data, obtain acoustic emission feature data, and generate rock mass expansion coefficient according to the acoustic emission feature data; A comprehensive analysis module is used to obtain the charge data of the mining area, extract the features of the charge data of the mining area, obtain the charge characteristic data, generate the rock mass dynamic coefficient according to the charge characteristic data, and generate the dynamic disaster assessment coefficient according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; The early warning classification module is used to compare the power disaster assessment coefficient with the preset power disaster assessment threshold, and classify the power disaster situation in the mining area according to the comparison. The classification results include: no-impact power disaster, low-impact power disaster, early warning power disaster and severe power disaster.

[0007] Furthermore, multiple stress monitors are evenly installed in the mining field to obtain three-dimensional stress distribution data of the mining field, and the three-dimensional stress distribution data is analyzed to obtain stress characteristic data, wherein the stress characteristic data includes: maximum stress change rate, stress fluctuation amplitude, maximum stress gradient and stress gradient change rate corresponding to the maximum stress gradient position; the stress fluctuation amplitude is the difference between the maximum stress and the minimum stress in the space; Furthermore, the specific logic for generating the rock mass rupture precursor coefficient is as follows: generating the rock mass rupture precursor coefficient according to the maximum stress change rate, the stress fluctuation amplitude, the abnormal stress gradient and the corresponding abnormal stress gradient change rate; The specific formula for generating the rock mass rupture precursor coefficient is: ; in, is the rock mass rupture precursor coefficient, is the maximum stress change rate, is the stress fluctuation amplitude, For the An abnormal stress gradient, For the The abnormal stress gradient change rate, is the number of abnormal stress gradients, is the index of abnormal stress gradient, and .

[0008] ; in, is the rock mass rupture precursor coefficient, is the maximum stress change rate, is the stress fluctuation amplitude, is the maximum stress gradient, is the stress gradient change rate corresponding to the maximum stress gradient position.

[0009] Furthermore, microseismic data of the mining field is obtained by using a seismic detector; the microseismic data includes: the magnitude, quantity and source coordinates of microseismic events, and the microseismic characteristic data includes the energy of microseismic events, the frequency of microseismic events and the concentration of sources; Divide the mine into Block areas, electromagnetic wave detectors and fluxgate sensors are arranged in the central area of ​​each block, and features are extracted from the electromagnetic signals collected by the electromagnetic wave detector to obtain the mean square error of the abnormal electromagnetic amplitude and the duration of the abnormal electromagnetic signal; the magnetic induction intensity collected by the fluxgate sensor is analyzed to obtain the rate of change of the magnetic induction intensity. The specific logic for defining the abnormality of the electromagnetic signal is as follows: a normal electromagnetic signal frequency range is preset, and the normal electromagnetic signal frequency refers to the industry standard; if the electromagnetic wave signal is not in the normal range, the electromagnetic signal is defined as an abnormal electromagnetic signal.

[0010] Furthermore, the specific logic for generating the microseismic rupture coefficient is: the microseismic event energy, microseismic event frequency and source concentration are analyzed to generate the microseismic rupture coefficient; the specific formula for generating the microseismic rupture coefficient is: ; in, is the microseismic rupture coefficient, is the energy of the microseismic event, is the frequency of microseismic events, It is the focal concentration; The specific logic for generating the electromagnetic rupture coefficient is: the electromagnetic rupture coefficient is generated by the mean square error of the abnormal electromagnetic amplitude, the duration of the abnormal electromagnetic signal and the rate of change of the magnetic induction intensity; the specific formula for generating the electromagnetic rupture coefficient is: ; in, is the electromagnetic rupture coefficient, For the The mean square error of the abnormal electromagnetic amplitude in the block area, For the The duration of abnormal electromagnetic signals in the block area, For the The rate of change of magnetic induction intensity in the block area, is the total number of stope areas, Index for the stope area; The specific logic for generating the rock mass rupture coefficient is: the rock mass rupture coefficient is generated according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; the specific formula for generating the rock mass rupture coefficient is: ; in, is the rock mass rupture coefficient.

[0011] Furthermore, an acoustic emission sensor is arranged in the stope, the sampling frequency is set to be above 1 kHz, the sampling time is set to 1 s, and the frequency of acoustic emission events, the duration of acoustic emission events and the acoustic emission event signal are obtained; the acoustic emission signal is subjected to Fourier transform to obtain the main frequency and power spectrum density of the acoustic emission signal; the main frequency is the frequency when the frequency domain amplitude of the acoustic emission signal is the largest; The specific logic for generating the rock mass expansion coefficient is as follows: the rock mass expansion coefficient is generated according to the frequency of acoustic emission events, the duration of acoustic emission events, and the main frequency and power spectrum density of the acoustic emission signal; the specific formula for generating the rock mass expansion coefficient is as follows: ; in, is the rock mass expansion coefficient, is the frequency of acoustic emission events, For the Duration of acoustic emission events collected from infrasound emission events, For the The main frequency of the acoustic emission signal collected from the infrasound emission event, For the The power spectral density of the acoustic emission signal collected during an infrasound emission event.

[0012] Furthermore, a charge detector is arranged in each area to collect the charge density, charge accumulation and charge distribution center position of the area, and the charge density, charge accumulation and charge distribution center position are analyzed to obtain the charge density growth rate, charge accumulation rate and charge distribution center transfer rate; if the charge density has a negative growth or charge has a negative accumulation, the charge density growth rate and charge accumulation rate are recorded as 0; the specific formula for calculating the charge distribution center transfer rate is: ; in, is the charge distribution center transfer rate, is the current charge distribution center coordinate, is the coordinate of the center of charge distribution at the previous moment.

[0013] Furthermore, the specific logic for generating the dynamic disaster assessment coefficient is as follows: the rock mass dynamic coefficient is generated according to the charge density growth rate, charge accumulation rate and charge distribution center transfer rate; the dynamic disaster assessment coefficient is generated according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; the specific formula for generating the rock mass dynamic coefficient is as follows: ; in, is the rock mass dynamic coefficient, For the The charge density growth rate in the bulk region, For the The charge accumulation rate in the bulk region, For the The charge distribution center transfer rate of the bulk region, is the total number of stope areas, Index for the stope area; The specific formula for generating the dynamic disaster assessment coefficient is: ; in, is the dynamic disaster assessment coefficient, is the rock mass rupture precursor coefficient, is the rock mass rupture coefficient, is the rock mass expansion coefficient.

[0014] Furthermore, the power disaster assessment threshold is preset. , then the mining site power disaster situation is defined as no impact power disaster; if , then the mining site dynamic disaster situation is defined as a low-impact dynamic disaster; if , then the mining site power disaster situation is defined as a warning power disaster; if , then the mining site power disaster situation is defined as a serious power disaster; is the dynamic disaster assessment coefficient, Assessing thresholds for dynamic hazards.

[0015] The present invention further provides a power disaster early warning method based on multi-source information fusion in the whole area of ​​the mine. The system is used to implement the power disaster early warning system based on multi-source information fusion in the whole area of ​​the mine, and specifically includes: Step 1: Acquire the three-dimensional stress distribution data of the stope, perform feature extraction on the three-dimensional stress distribution data of the stope, obtain stress characteristic data, and generate the rock mass fracture precursor coefficient according to the stress characteristic data; Step 2: Acquire the microseismic data and electromagnetic data of the mining area, and extract the features of the microseismic data and electromagnetic data of the mining area to obtain microseismic characteristic data and electromagnetic characteristic data, generate the microseismic rupture coefficient according to the microseismic characteristic data; generate the electromagnetic rupture coefficient according to the electromagnetic characteristic data, and generate the rock mass rupture coefficient according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; Step 3: Acquire the stope acoustic emission data, perform feature extraction on the stope acoustic emission data, obtain acoustic emission feature data, and generate the rock mass expansion coefficient according to the acoustic emission feature data; Step 4: Acquire the charge data of the mining area, extract the features of the charge data of the mining area, obtain the charge characteristic data, generate the rock mass dynamic coefficient according to the charge characteristic data, and generate the dynamic disaster assessment coefficient according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; Step 5: Compare the power disaster assessment coefficient with the preset power disaster assessment threshold, and classify the power disaster situation in the mining area according to the comparison. The classification results include: no-impact power disaster, low-impact power disaster, warning power disaster and severe power disaster.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention evaluates the dynamic effects of rock mass cracks before and during fracture expansion from multiple perspectives, including microseismic, stress, electromagnetic waves, charge and acoustic emission, and generates a dynamic disaster assessment coefficient based on multi-source data that can reflect the dynamic disaster risk situation. This coefficient can quantify the risk level of dynamic disasters, making risk assessment more advanced, intuitive and accurate, providing scientific basis and technical support for safe production management of mining sites, and reducing the error of subjective judgment in dynamic disaster prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall system structure of the present invention.

[0018] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0020] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0021] Example: See also Figure 1 , the present invention provides a technical solution: A power disaster early warning system based on multi-source information fusion in the whole area of ​​the mining area, specifically including: The precursor analysis module is used to obtain the three-dimensional stress distribution data of the stope, extract the characteristics of the three-dimensional stress distribution data of the stope stress data, obtain stress characteristic data, and generate the rock mass fracture precursor coefficient according to the stress characteristic data; Multiple stress monitors are evenly installed in the stope to collect three-dimensional stress data at multiple locations in the stope. The specific arrangement method is as follows: the stope area and the detection radius of the stress monitor are obtained, and the arrangement interval and arrangement density of the stress monitor are obtained according to the stope area and the detection radius of the stress monitor; in order to ensure that the detector can cover the stope, the arrangement interval is set to the side length of the inscribed square of the detection range (circle) of the stress monitor (that is, the detection radius of the stress monitor). The layout density is obtained by dividing the stope area by the area of ​​the inscribed square of the stress monitor detection range (circle).

[0022] The collected three-dimensional stress data are summarized to form the three-dimensional stress distribution data of the stope, and the three-dimensional stress distribution data are analyzed to obtain stress characteristic data, wherein the stress characteristic data includes: the maximum stress change rate, the stress fluctuation amplitude, the maximum stress gradient and the stress gradient change rate corresponding to the maximum stress gradient position; the stress fluctuation amplitude is the difference between the maximum stress and the minimum stress in the space; The stress change rate is the difference between the stress collected at the current moment and the stress collected at the previous moment divided by the time interval between the two. The maximum stress change rate is obtained by comparing all stress change rates in space; the method for obtaining the maximum stress gradient is: input the three-dimensional stress distribution data into the COMSOL Multiphysics software for analysis to obtain the maximum stress gradient. The method for obtaining the stress gradient change rate corresponding to the maximum stress gradient position is: the difference between the maximum stress gradient at the current moment and the stress gradient at the same position at the previous moment is divided by the time interval between the two moments; The specific logic for generating the rock mass rupture precursor coefficient is as follows: generating the rock mass rupture precursor coefficient according to the stress change rate, stress fluctuation amplitude, abnormal stress gradient and the corresponding abnormal stress gradient change rate; The specific formula for generating the rock mass rupture precursor coefficient is: ; in, is the rock mass rupture precursor coefficient, is the maximum stress change rate, is the stress fluctuation amplitude, is the maximum stress gradient, is the stress gradient change rate corresponding to the maximum stress gradient position.

[0023] The rock mass fracture precursor coefficient reflects the degree to which the rock mass tends to fracture. The larger its value, the more complex the mechanical environment inside the rock mass and the higher the fracture risk. The generation of this coefficient can provide a quantitative basis for early warning of dynamic disasters. The maximum stress change rate indicates the maximum stress change rate monitored in the mining area, which is the slope of stress change over time. The larger the value, the more drastic the stress change, indicating that the rock mass is in a state of stress concentration and rapid accumulation, and the possibility of approaching fracture increases. The stress fluctuation amplitude is the stress fluctuation amplitude in the monitoring area, that is, the maximum stress minus the minimum stress. A larger stress fluctuation amplitude indicates that the stress distribution inside the rock mass is uneven, and there may be high stress concentration areas in some areas, which can easily trigger rock mass fracture. The maximum stress gradient is the maximum spatial change rate of stress distribution. The larger its value, the more drastic the stress distribution inside the rock mass, and there may be sudden stress concentration in some areas. The higher the fracture risk. The stress gradient change rate corresponding to the maximum stress gradient position reflects the change rate of the stress gradient at the maximum stress gradient position over time. The larger the value, the faster the change rate of the stress gradient at the maximum stress gradient position, indicating that more drastic stress adjustment and fracture precursors may occur in local areas of the rock mass. The higher the fracture risk.

[0024] The fracture analysis module obtains the microseismic data and electromagnetic data of the mining field respectively, and extracts the features of the microseismic data and electromagnetic data of the mining field to obtain the microseismic characteristic data and electromagnetic characteristic data, and generates the microseismic fracture coefficient according to the microseismic characteristic data; generates the electromagnetic fracture coefficient according to the electromagnetic characteristic data, and generates the rock fracture coefficient according to the microseismic fracture coefficient and the electromagnetic fracture coefficient; Multiple seismic detectors are evenly arranged in the mining area, and the arrangement method refers to the arrangement method of the above-mentioned stress monitor. The data collected by the seismic detectors within 0.5s is recorded as the mining area microseismic data; the microseismic data includes: the magnitude, number and source coordinates of the microseismic events, and the microseismic characteristic data includes the energy of the microseismic events, the frequency of the microseismic events and the source concentration; The energy of the microseismic event can be obtained by applying the Richter formula to the magnitude, which is expressed as: ; in, is the energy of the microseismic event, is the magnitude of the microseismic event.

[0025] The frequency of microseismic events is the number of microseismic events collected.

[0026] The specific logic for obtaining the focal concentration is as follows: the focal center is obtained by performing a mean operation on all focal coordinates, and the focal concentration is obtained based on the positional relationship between the focal center and each focal coordinate.

[0027] The specific logic for obtaining the source concentration is: ; in, is the focal concentration, For the The location of the earthquake source, is the epicenter; Divide the stope into equal areas Block areas, electromagnetic wave detectors and fluxgate sensors are arranged in each central area, and features of electromagnetic signals collected by the electromagnetic wave detectors are extracted to obtain the mean square error of abnormal electromagnetic amplitude and the duration of abnormal electromagnetic signals; the magnetic induction intensity collected by the fluxgate sensor is analyzed to obtain the rate of change of magnetic induction intensity; The specific logic for defining electromagnetic signal anomalies is as follows: a normal electromagnetic signal frequency range is preset, and the normal electromagnetic signal frequency refers to the industry standard; if the electromagnetic wave signal is not in the normal range, the electromagnetic signal is defined as an abnormal electromagnetic signal, and the time of each abnormal electromagnetic signal in each area is added to obtain the duration of the abnormal electromagnetic signal, and the average amplitude of each abnormal electromagnetic signal in each area is obtained, and then the variance operation is performed to obtain the mean square error of the abnormal electromagnetic amplitude in this area; the magnetic induction intensity change rate is the difference between the magnetic induction intensity collected by the fluxgate sensor at the current moment and the magnetic induction intensity collected by the fluxgate sensor at the previous moment, divided by the time interval between the previous two moments.

[0028] The specific logic for generating the microseismic rupture coefficient is: the microseismic event energy, microseismic event frequency and source concentration are analyzed to generate the microseismic rupture coefficient; the specific formula for generating the microseismic rupture coefficient is: ; in, is the microseismic rupture coefficient, is the energy of the microseismic event, is the frequency of microseismic events, The microseismic rupture coefficient reflects the degree of rock mass rupture revealed by microseismic events; the larger its value, the stronger the microseismic energy, the higher the frequency, and the more concentrated the source, indicating that the degree of internal rupture in the rock mass is greater. The generation of this coefficient can quantitatively evaluate the degree of rock mass rupture, thereby providing an important basis for evaluating dynamic disasters. Microseismic event energy, the energy released by microseismic events, is usually closely related to the stress state of the rock mass. The larger its value, the higher the energy released during the rupture process, and the higher the risk of rock mass rupture. The source concentration reflects the degree of spatial distribution concentration of the source of microseismic events. The larger its value, the more concentrated the source of microseismic events, indicating a higher risk of local rupture. The frequency of microseismic events is the number of microseismic events occurring per unit time. The larger its value, the more frequent the rupture process inside the rock mass and the greater the degree of internal rupture in the rock mass.

[0029] The specific logic for generating the electromagnetic rupture coefficient is: the electromagnetic rupture coefficient is generated by the mean square error of the abnormal electromagnetic amplitude, the duration of the abnormal electromagnetic signal and the rate of change of the magnetic induction intensity; the specific formula for generating the electromagnetic rupture coefficient is: ; in, is the electromagnetic rupture coefficient, For the The mean square error of the abnormal electromagnetic amplitude in the block area, For the The duration of abnormal electromagnetic signals in the block area, For the The rate of change of magnetic induction intensity in the block area, is the total number of stope areas, It is the index of the mining area; the electromagnetic rupture coefficient captures the electromagnetic anomaly characteristics of rock mass rupture. The more significant the changes in amplitude, duration, and magnetic field, the more it reflects the degree of rock mass rupture. The larger its value, the more intense and continuous the abnormal electromagnetic activity, indicating that the degree of rock mass rupture is greater; the generation of this coefficient can quantitatively evaluate the degree of rock mass rupture, thereby providing an important basis for evaluating dynamic disasters. The abnormal electromagnetic amplitude mean square error refers to the intensity of the change in the amplitude of the electromagnetic signal. The larger its value, the more abnormal the electromagnetic activity and the greater the degree of rock mass rupture. The abnormal electromagnetic signal duration is the duration of the electromagnetic abnormal signal. The larger its value, the longer the duration of the electromagnetic anomaly, indicating that the rock mass rupture process is more persistent, indicating that the degree of rock mass rupture is greater. The magnetic induction intensity change rate reflects the rate of change of the magnetic induction intensity. The larger its value, the more drastic the magnetic field change, the more intense the internal crack activity of the rock mass, indicating that the degree of rock mass rupture is greater.

[0030] The specific logic for generating the rock mass rupture coefficient is: the rock mass rupture coefficient is generated according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; the specific formula for generating the rock mass rupture coefficient is: ; in, is the rock mass rupture coefficient. The rock mass rupture coefficient is the comprehensive result of microseismic and electromagnetic effects, indicating the overall risk of rock mass rupture. The larger its value, the higher the abnormality of the microseismic and electromagnetic environment inside the rock mass, and the greater the risk caused by rupture. The generation of this coefficient can provide a quantitative basis for early warning of dynamic disasters; the microseismic rupture coefficient and the electromagnetic rupture coefficient reflect the degree of rock mass rupture from the perspective of microseismic and electromagnetic respectively. The increase of any coefficient will lead to a greater risk of rock mass rupture.

[0031] Expansion analysis module, used to obtain stope acoustic emission data, perform feature extraction on the stope acoustic emission data, obtain acoustic emission feature data, and generate rock mass expansion coefficient according to the acoustic emission feature data; Multiple emission sensors are evenly arranged in the mining area. The specific arrangement method refers to the stress monitor, and the sampling frequency is set to above 1 kHz, and the sampling time is set to 1s to obtain the frequency, duration and signal of acoustic emission events; The acoustic emission event frequency is the number of acoustic emission events collected by the acoustic emission sensor in each sampling. Perform Fourier transform on the acoustic emission signal to obtain the main frequency and power spectrum density of the acoustic emission signal; the main frequency is the frequency when the frequency domain amplitude of the acoustic emission signal is the largest; The specific logic for generating the rock mass expansion coefficient is as follows: the rock mass expansion coefficient is generated according to the frequency of acoustic emission events, the duration of acoustic emission events, and the main frequency and power spectrum density of the acoustic emission signal; the specific formula for generating the rock mass expansion coefficient is as follows: ; in, is the rock mass expansion coefficient, is the frequency of acoustic emission events, For the Duration of acoustic emission events collected from infrasound emission events, For the The main frequency of the acoustic emission signal collected from the infrasound emission event, For the The power spectrum density of the acoustic emission signal collected by the infraacoustic emission event. The rock mass expansion coefficient reflects the rock mass crack expansion characteristics revealed by the acoustic emission signal; the larger its value, the more frequent the acoustic emission activity, the longer the duration, the higher the signal frequency and the larger the power spectrum density, and the rock mass crack expansion activity is significant. Rock mass crack expansion activity is closely related to dynamic disasters, and the generation of this coefficient can provide a quantitative basis for the early warning of dynamic disasters; the acoustic emission event frequency is the number of acoustic emission times collected by the acoustic emission sensor for each sampling. The larger its value, the more frequent the crack expansion activity inside the rock mass; the rock mass crack expansion activity is significant. The duration of the acoustic emission event reflects the duration of the acoustic emission signal. The larger its value, the longer the rock mass expansion activity process, the longer the impact of the rock mass crack expansion, and the rock mass crack expansion activity is significant. The signal with a main frequency of high frequency corresponds to the rapid expansion of small-scale cracks. The larger the main frequency of the acoustic emission signal, the faster the expansion of small-scale cracks, and the rock mass crack expansion activity is significant. The power spectrum density of the acoustic emission signal reflects the energy distribution intensity of the acoustic emission signal. The larger its value, the greater the energy released by the crack expansion activity. The rock mass crack expansion activity is significant.

[0032] A comprehensive analysis module is used to obtain the charge data of the mining area, extract the features of the charge data of the mining area, obtain the charge characteristic data, generate the rock mass dynamic coefficient according to the charge characteristic data, and generate the dynamic disaster assessment coefficient according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; Since the detection range of the charge detector is small, the stope needs to be divided into equal areas like collecting electromagnetic data of the stope. In each area, a charge detector is arranged. The specific arrangement method refers to the stress monitor, so as to form a charge detector detection network, collect the charge density, charge accumulation and charge distribution center position of the area, analyze the charge density, charge accumulation and charge distribution center position, and obtain the charge density growth rate, charge accumulation rate and charge distribution center transfer rate; if the charge density negative growth and charge negative accumulation phenomenon occur, the charge density growth rate and charge accumulation rate are recorded as 0; the specific formula for calculating the charge distribution center transfer rate is: ; in, is the charge distribution center transfer rate, is the current charge distribution center coordinate, is the coordinate of the center of charge distribution at the previous moment.

[0033] The specific logic for generating the dynamic disaster assessment coefficient is as follows: the rock mass dynamic coefficient is generated according to the charge density growth rate, charge accumulation rate and charge distribution center transfer rate; the dynamic disaster assessment coefficient is generated according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; the specific formula for generating the rock mass dynamic coefficient is as follows: ; in, is the rock mass dynamic coefficient, For the The charge density growth rate in the bulk region, For the The charge accumulation rate in the bulk region, For the The charge distribution center transfer rate of the bulk region, is the total number of stope areas, It is the index of the mining area; the rock mass has obvious charge properties before, during and after the rock mass breaks. The dynamic coefficient of the rock mass reveals the dynamic and activity characteristics of the rock mass. The larger its value, the more significantly the charge activity inside the rock mass is enhanced, the stronger the dynamic effect, and the more significant the rock mass activity. The generation of this coefficient can provide a quantitative basis for the early warning of dynamic disasters. The charge density growth rate reflects the rate of change of the charge density. The larger its value, the more significant the charge anomaly in the area, the enhanced dynamic effect, and the enhanced rock mass activity. The charge accumulation rate reflects the speed of charge accumulation per unit time. The larger its value, the more concentrated the charge inside the rock mass is, the greater the dynamic effect, the greater the rock mass activity, and the increased risk of dynamic disasters. The charge distribution center transfer rate reflects the rate of movement of the charge distribution center over time. The larger its value, the more drastic the charge distribution changes, the more concentrated the fracture area is, the more significant the dynamic effect is, and the more significant the rock mass activity is.

[0034] The specific formula for generating the dynamic disaster assessment coefficient is: ; in, is the dynamic disaster assessment coefficient, is the rock mass rupture precursor coefficient, is the rock mass rupture coefficient, is the rock mass expansion coefficient. The dynamic disaster assessment coefficient is the result of a comprehensive risk assessment of dynamic disasters combined with multi-source data. The larger its value, the more significant the comprehensive fracture, expansion and charge anomaly inside the rock mass, and the higher the risk of dynamic disasters. This coefficient can quantify the risk level of dynamic disasters, making risk assessment more advanced, intuitive and accurate, providing a scientific basis and technical support for safe production management in the mine, and reducing the error of subjective judgment in dynamic disaster prevention and control. The rock mass fracture precursor coefficient, rock mass fracture coefficient and rock mass expansion coefficient reflect the dynamic risk situation before, during and after the rock mass fracture respectively. The rock mass dynamic coefficient reflects the dynamic effects and activity characteristics of the rock mass at all times; the increase of any coefficient will lead to a greater risk of dynamic disasters in the mine.

[0035] The early warning classification module is used to compare the power disaster assessment coefficient with the preset power disaster assessment threshold, and classify the power disaster situation in the mining area according to the comparison. The classification results include: no-impact power disaster, low-impact power disaster, early warning power disaster and severe power disaster.

[0036] Preset power disaster assessment threshold, if , then the mining site dynamic disaster situation is defined as no impact dynamic disaster; the mining site dynamic disaster risk is extremely low, the rock mass is relatively stable, and the impact of dynamic disasters on the mining site can be ignored. , then the mining site dynamic disaster situation is defined as a low-impact dynamic disaster; the mining site dynamic disaster risk is low, there are certain fractures and expansion phenomena inside the rock mass, but the overall risk is controllable and the impact on the mining site is small. , the mining site dynamic disaster situation is defined as a warning dynamic disaster; the mining site dynamic disaster risk is high, and the comprehensive fracture, expansion and charge anomaly inside the rock mass are significant, which requires high attention and corresponding warning measures. , the mining site power disaster situation is defined as a severe power disaster; the mining site power disaster risk is extremely high, there are serious fractures, expansions and charge anomalies inside the rock mass, the power disaster has a great impact on the mining site, and emergency response measures must be taken immediately to prevent the disaster from further expanding.

[0037] is the dynamic disaster assessment coefficient, Assessing thresholds for dynamic hazards.

[0038] The power disaster assessment threshold is determined by experts based on local specific conditions. For example, the power disaster assessment coefficient of the area to be analyzed can be calculated by the above method, and then experts in this field are invited to demonstrate the power disaster situation and the power disaster assessment coefficient of the area to be analyzed to determine the power disaster assessment threshold. This is existing technology and will not be elaborated here.

[0039] The present invention further provides a power disaster early warning method based on multi-source information fusion in the whole area of ​​the mine. The system is used to implement the power disaster early warning system based on multi-source information fusion in the whole area of ​​the mine, and specifically includes: Step 1: Acquire the three-dimensional stress distribution data of the stope, perform feature extraction on the three-dimensional stress distribution data of the stope, obtain stress characteristic data, and generate the rock mass fracture precursor coefficient according to the stress characteristic data; Step 2: Acquire the microseismic data and electromagnetic data of the mining area, and extract the features of the microseismic data and electromagnetic data of the mining area to obtain microseismic characteristic data and electromagnetic characteristic data, generate the microseismic rupture coefficient according to the microseismic characteristic data; generate the electromagnetic rupture coefficient according to the electromagnetic characteristic data, and generate the rock mass rupture coefficient according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; Step 3: Acquire the stope acoustic emission data, perform feature extraction on the stope acoustic emission data, obtain acoustic emission feature data, and generate the rock mass expansion coefficient according to the acoustic emission feature data; Step 4: Acquire the charge data of the mining area, extract the features of the charge data of the mining area, obtain the charge characteristic data, generate the rock mass dynamic coefficient according to the charge characteristic data, and generate the dynamic disaster assessment coefficient according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; Step 5: Compare the power disaster assessment coefficient with the preset power disaster assessment threshold, and classify the power disaster situation in the mining area according to the comparison. The classification results include: no-impact power disaster, low-impact power disaster, warning power disaster and severe power disaster.

[0040] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0041] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0042] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0043] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A power disaster early warning system based on multi-source information fusion in the whole mining area, characterized in that: Specifically include: The precursor analysis module is used to obtain the three-dimensional stress distribution data of the stope, extract the characteristics of the three-dimensional stress distribution data, obtain stress characteristic data, and generate the rock mass fracture precursor coefficient according to the stress characteristic data; A fracture analysis module is used to obtain microseismic data and electromagnetic data of the mining field, and perform feature extraction on the microseismic data and electromagnetic data of the mining field to obtain microseismic feature data and electromagnetic feature data, and generate a microseismic fracture coefficient according to the microseismic feature data; The electromagnetic characteristic data generates the electromagnetic rupture coefficient, and the rock mass rupture coefficient is generated according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; Expansion analysis module, used to obtain stope acoustic emission data, perform feature extraction on the stope acoustic emission data, obtain acoustic emission feature data, and generate rock mass expansion coefficient according to the acoustic emission feature data; A comprehensive analysis module is used to obtain the charge data of the mining area, extract the features of the charge data of the mining area, obtain the charge characteristic data, generate the rock mass dynamic coefficient according to the charge characteristic data, and generate the dynamic disaster assessment coefficient according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; The early warning classification module is used to compare the power disaster assessment coefficient with the preset power disaster assessment threshold, and classify the power disaster situation in the mining area according to the comparison. The classification results include: no-impact power disaster, low-impact power disaster, early warning power disaster and severe power disaster.

2. According to claim 1, a power disaster early warning system based on multi-source information fusion in the whole stope area is characterized by: A plurality of stress monitors are evenly installed in the mining field to obtain three-dimensional stress distribution data of the mining field, and the three-dimensional stress distribution data are analyzed to obtain stress characteristic data, wherein the stress characteristic data include: maximum stress change rate, stress fluctuation amplitude, maximum stress gradient and stress gradient change rate corresponding to the maximum stress gradient position; the stress fluctuation amplitude is the difference between the maximum stress and the minimum stress in the space.

3. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 2 is characterized by: The specific logic for generating the rock mass rupture precursor coefficient is as follows: generating the rock mass rupture precursor coefficient according to the maximum stress change rate, stress fluctuation amplitude, abnormal stress gradient and the corresponding abnormal stress gradient change rate; The specific formula for generating the rock mass rupture precursor coefficient is: ； in, is the rock mass rupture precursor coefficient, is the maximum stress change rate, is the stress fluctuation amplitude, is the maximum stress gradient, is the stress gradient change rate corresponding to the maximum stress gradient position.

4. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 1 is characterized by: Acquire microseismic data of the mining field through a seismic detector; the microseismic data includes: the magnitude, quantity and source coordinates of microseismic events, and the microseismic characteristic data includes the energy of microseismic events, the frequency of microseismic events and the concentration of sources; Divide the mine into Block areas, electromagnetic wave detectors and fluxgate sensors are arranged in the central area of ​​each block, and features are extracted from the electromagnetic signals collected by the electromagnetic wave detectors to obtain the mean square error of the abnormal electromagnetic amplitude and the duration of the abnormal electromagnetic signal; the magnetic induction intensity collected by the fluxgate sensor is analyzed to obtain the rate of change of the magnetic induction intensity, and the specific logic for defining the abnormality of the electromagnetic signal is as follows: a normal electromagnetic signal frequency range is preset, and the normal electromagnetic signal refers to the frequency industry standard; if the electromagnetic wave signal is not in the normal range, the electromagnetic signal is defined as an abnormal electromagnetic signal.

5. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 1 is characterized by: The specific logic for generating the microseismic rupture coefficient is: the microseismic event energy, microseismic event frequency and source concentration are analyzed to generate the microseismic rupture coefficient; the specific formula for generating the microseismic rupture coefficient is: ； in, is the microseismic rupture coefficient, is the energy of the microseismic event, is the frequency of microseismic events, It is the focal concentration; The specific logic for generating the electromagnetic rupture coefficient is: the electromagnetic rupture coefficient is generated by the mean square error of the abnormal electromagnetic amplitude, the duration of the abnormal electromagnetic signal and the rate of change of the magnetic induction intensity; the specific formula for generating the electromagnetic rupture coefficient is: ； in, is the electromagnetic rupture coefficient, For the The mean square error of electromagnetic amplitude of block area anomalies, For the The duration of abnormal electromagnetic signals in the block area, For the The rate of change of magnetic induction intensity in the block area, is the total number of stope areas, Index for the stope area; The specific logic for generating the rock mass rupture coefficient is: the rock mass rupture coefficient is generated according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; the specific formula for generating the rock mass rupture coefficient is: ； in, is the rock mass rupture coefficient.

6. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 1 is characterized by: Arrange acoustic emission sensors in the mining area, set the sampling frequency to above 1 kHz, set the sampling time to 1 s, obtain the frequency of acoustic emission events, the duration of acoustic emission events and the acoustic emission event signals; perform Fourier transform on the acoustic emission signals to obtain the main frequency and power spectrum density of the acoustic emission signals; the main frequency is the frequency when the frequency domain amplitude of the acoustic emission signal is the largest; The specific logic for generating the rock mass expansion coefficient is as follows: the rock mass expansion coefficient is generated according to the frequency of acoustic emission events, the duration of acoustic emission events, and the main frequency and power spectrum density of the acoustic emission signal; the specific formula for generating the rock mass expansion coefficient is as follows: ； in, is the rock mass expansion coefficient, is the frequency of acoustic emission events, For the Duration of acoustic emission events collected from infrasound emission events, For the The main frequency of the acoustic emission signal collected from the infrasound emission event, For the The power spectral density of the acoustic emission signal collected during an infrasound emission event.

7. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 4 is characterized by: A charge detector is arranged in each area to collect the charge density, charge accumulation and charge distribution center position of the area, and the charge density, charge accumulation and charge distribution center position are analyzed to obtain the charge density growth rate, charge accumulation rate and charge distribution center transfer rate; if negative charge density growth and negative charge accumulation occur, the charge density growth rate and charge accumulation rate are recorded as 0; the specific formula for calculating the charge distribution center transfer rate is: ； in, is the charge distribution center transfer rate, is the current charge distribution center coordinate, is the coordinate of the center of charge distribution at the previous moment.

8. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 1 is characterized by: The specific logic for generating the dynamic disaster assessment coefficient is as follows: the rock mass dynamic coefficient is generated according to the charge density growth rate, charge accumulation rate and charge distribution center transfer rate; the dynamic disaster assessment coefficient is generated according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; the specific formula for generating the rock mass dynamic coefficient is as follows: ； in, is the rock mass dynamic coefficient, For the The charge density growth rate in the bulk region, For the The charge accumulation rate in the bulk region, For the The charge distribution center transfer rate of the bulk region, is the total number of stope areas, Index for the stope area; The specific formula for generating the dynamic disaster assessment coefficient is: ； in, is the dynamic disaster assessment coefficient, is the rock mass rupture precursor coefficient, is the rock mass rupture coefficient, is the rock mass expansion coefficient.

9. The power disaster early warning system based on multi-source information fusion in the whole stope area according to claim 1 is characterized by: Preset power disaster assessment threshold, if , then the mining site power disaster situation is defined as no impact power disaster; if , then the mining site dynamic disaster situation is defined as a low-impact dynamic disaster; if , then the mining site power disaster situation is defined as a warning power disaster; if , then the mining site power disaster situation is defined as a serious power disaster; is the dynamic disaster assessment coefficient, Assessing thresholds for dynamic hazards.

10. A power disaster early warning method based on multi-source information fusion in the whole area of ​​the stope, characterized by: The method is used to implement a power disaster early warning system based on multi-source information fusion in the whole stope area as described in any one of claims 1 to 9, and specifically comprises: Step 1: Acquire the three-dimensional stress distribution data of the stope, perform feature extraction on the three-dimensional stress distribution data of the stope, obtain stress characteristic data, and generate the rock mass fracture precursor coefficient according to the stress characteristic data; Step 2: Acquire the microseismic data and electromagnetic data of the mining area, and extract the features of the microseismic data and electromagnetic data of the mining area to obtain microseismic characteristic data and electromagnetic characteristic data, generate the microseismic rupture coefficient according to the microseismic characteristic data; generate the electromagnetic rupture coefficient according to the electromagnetic characteristic data, and generate the rock mass rupture coefficient according to the microseismic rupture coefficient and the electromagnetic rupture coefficient; Step 3: Acquire the stope acoustic emission data, perform feature extraction on the stope acoustic emission data, obtain acoustic emission feature data, and generate the rock mass expansion coefficient according to the acoustic emission feature data; Step 4: Acquire the charge data of the mining area, extract the features of the charge data of the mining area, obtain the charge characteristic data, generate the rock mass dynamic coefficient according to the charge characteristic data, and generate the dynamic disaster assessment coefficient according to the rock mass rupture precursor coefficient, rock mass rupture coefficient, rock mass expansion coefficient and rock mass dynamic coefficient; Step 5: Compare the power disaster assessment coefficient with the preset power disaster assessment threshold, and classify the power disaster situation in the mining area according to the comparison. The classification results include: no-impact power disaster, low-impact power disaster, warning power disaster and severe power disaster.

Images