Rock burst early warning method based on coal rock mass multi-scale microstructure parameter fusion

Abstract

The invention provides a rock burst early warning method based on coal and rock mass multi-scale microstructure parameter fusion, and the method comprises the steps: collecting coal and rock mass microstructure monitoring data through a multi-scale microstructure parameter monitoring system, and carrying out the processing and analysis of the monitoring data, and obtaining multi-scale microstructure parameters; determining a quantitative relation between the multi-scale microstructure parameters and the rock burst occurrence risk and a core association mechanism; constructing and training a multi-scale microstructure parameter fusion model based on the quantitative relation and the core association mechanism; and through a multi-scale microstructure parameter monitoring system, collecting real-time monitoring data of a to-be-predicted coal-rock mass and inputting the real-time monitoring data into the trained fusion model to obtain a rock burst dynamic early warning result. According to the method, multi-scale microstructure parameter change information of the coal and rock mass from microcosmic to macroscopic can be accurately obtained, real-time and accurate rock burst early warning information is provided through the multi-source network model, and the accuracy and real-time performance of rock burst early warning are improved.

Description

Technical Field

[0001] The present application relates to the field of coal mine safety engineering technology, and in particular to a rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock masses. Background Art

[0002] Rock bursts pose a serious threat to production safety in coal mining operations. Rock bursts are closely linked to changes in the internal microstructure of coal and rock masses. Any change in these parameters, from the microscopic mineral crystal structure, micropores, and microcracks, to the macroscopic structures of bedding and joints, can alter stress distribution and, in turn, induce rock bursts. Therefore, monitoring the microstructural parameters of coal and rock masses is essential to provide early warning of rock bursts based on this data.

[0003] In related technologies, a single microstructure parameter monitoring technology is generally used, which cannot obtain comprehensive coal rock microstructure information, and the process of processing and analyzing the collected data is also relatively simple, and it is impossible to accurately obtain the information required for rock burst warning. As a result, the rock burst warning results may have large deviations and cannot meet actual warning needs. Summary of the Invention

[0004] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] To this end, the first purpose of this application is to propose a rock burst warning method based on the fusion of multi-scale microstructural parameters of coal and rock masses. This method constructs a comprehensive and efficient monitoring system and uses advanced data processing and analysis algorithms to accurately obtain multi-scale microstructural parameter change information of coal and rock masses from micro to macro, providing a solid and reliable basis for the early prediction and active prevention and control of rock burst, thereby improving the safety of coal mining.

[0006] The second purpose of this application is to propose a rock burst warning system based on the fusion of multi-scale microstructure parameters of coal and rock masses.

[0007] A third object of the present application is to provide a non-transitory computer-readable storage medium.

[0008] To achieve the above objectives, the first aspect of this application is to propose a rock burst early warning method based on the fusion of multi-scale microstructure parameters of coal and rock masses, comprising the following steps:

[0009] Collecting coal and rock mass microstructure monitoring data through a multi-scale microstructure parameter monitoring system comprising microscopic monitoring, mesoscopic monitoring, and macroscopic monitoring, and processing and analyzing the monitoring data to obtain multi-scale microstructure parameters, wherein the multi-scale microstructure parameters include microstructure sensitivity parameters, mesoscopic mechanical response parameters, and macroscopic energy release parameters;

[0010] Establishing a quantitative relationship between the multi-scale microstructural parameters and the risk of rock burst, and determining the core correlation mechanism between the multi-scale microstructural parameters and the risk of rock burst;

[0011] Based on the quantitative relationship and the core association mechanism, a multi-scale microstructure parameter fusion model is constructed and trained, wherein the fusion model is used to output the rock burst risk probability according to the input multi-scale fusion parameters;

[0012] The multi-scale microstructure parameter monitoring system is used to collect real-time monitoring data of the coal and rock mass to be predicted, and the real-time monitoring data is input into the trained fusion model to obtain a dynamic early warning result of rock burst.

[0013] Optionally, in one embodiment of the present application, establishing a quantitative relationship between the multi-scale microstructure parameters and the risk of rock burst includes: establishing a nonlinear mapping relationship between the risk of rock burst and the multi-scale microstructure parameters based on historical rock burst cases; determining the relationship between the risk warning triggering rules and the risk probability enhancement rules and the relevant microstructure parameters according to the nonlinear mapping relationship; and using the Shapley value analysis method to quantify the contribution of each microstructure parameter to the rock burst risk.

[0014] Optionally, in one embodiment of the present application, the core correlation mechanism between the multi-scale microstructural parameters and the risk of rock burst includes: determining the correlation mechanism between the microstructural deterioration of the coal rock mass and the stress concentration effect based on the mechanical correlation analysis results; determining the correlation mechanism between the mesoscopic damage evolution of the coal rock mass and the energy transfer anomaly by analyzing the mesoscopic mechanical response parameters; and determining the correlation mechanism between the macroscopic energy release and the instability criticality of the coal rock mass by analyzing the macroscopic energy release parameters.

[0015] Optionally, in one embodiment of the present application, before constructing the multi-scale microstructure parameter fusion model, it also includes: normalizing the multi-scale microstructure parameters; calculating the degree of correlation between each microstructure parameter after normalization and the impact ground pressure event through the mutual information method, and calculating the Spearman correlation coefficient of each microstructure parameter according to the correlation degree; using the Spearman correlation coefficient of each microstructure parameter, a plurality of key parameters are screened out from the multi-scale microstructure parameters through the recursive feature elimination (RFE) algorithm, wherein the Spearman correlation coefficient of each key parameter is greater than a preset screening threshold.

[0016] Optionally, in one embodiment of the present application, the multi-scale microstructure parameter fusion model includes: a feature extraction layer, a cross-scale fusion layer and a risk assessment layer; wherein the feature extraction layer is the bottom layer, which is used to extract data features corresponding to the key parameters from the input multi-scale microstructure parameters, wherein for microscopic image data, a convolutional neural network CNN is used to extract data features, and for time series data, a long short-term memory network LSTM is used to extract data features; the cross-scale fusion layer is the middle layer, which is used to map different data features to a unified feature space and calculate the contribution weight of each data feature to rock burst; the risk assessment layer is the top layer, which is used to output the rock burst risk probability.

[0017] Optionally, in one embodiment of the present application, the microstructure sensitivity parameters include: multiple micropore parameters, multiple microcrack parameters and multiple mineral structure parameters, and the processing and analysis of the monitoring data to obtain multi-scale microstructure parameters include: binarizing the microscopic image data collected using microscopic imaging technology, and calculating the multiple micropore parameters based on the binarization processing results; extracting the crack centerline from the microscopic image data, identifying the crack initiation position and crack propagation trajectory from the in-situ CT sequence image, and calculating the multiple microcrack parameters based on the obtained crack information; calculating the multiple mineral structure parameters by performing mineral phase identification and grain boundary change analysis in combination with the in-situ CT sequence image.

[0018] Optionally, in one embodiment of the present application, the microscopic mechanical response parameters include: ultrasonic attenuation coefficient and microscopic strain localization degree, and the processing and analysis of the monitoring data to obtain multi-scale microstructure parameters also includes: processing the collected ultrasonic CT signals to calculate the ultrasonic attenuation coefficient; analyzing the coal rock deformation images collected using digital image correlation (DIC) technology to calculate the microscopic strain localization degree.

[0019] Optionally, in one embodiment of the present application, the macro-energy release parameters include: the cumulative value of microseismic energy and the proportion of high-frequency components of the geoacoustic signal. The processing and analysis of the monitoring data to obtain multi-scale microstructure parameters also includes: analyzing the microseismic event parameters collected by the microseismic monitoring system to calculate the cumulative value of the microseismic energy; analyzing the geoacoustic signal inside the coal rock mass collected using geoacoustic monitoring technology to calculate the proportion of high-frequency components of the geoacoustic signal.

[0020] To achieve the above objectives, the second aspect of this application also proposes a rock burst warning system based on the fusion of multi-scale microstructural parameters of coal and rock masses, comprising the following modules:

[0021] A monitoring and analysis module is used to collect coal and rock mass microstructure monitoring data through a multi-scale microstructure parameter monitoring system including microscopic monitoring, mesoscopic monitoring, and macroscopic monitoring, and to process and analyze the monitoring data to obtain multi-scale microstructure parameters, wherein the multi-scale microstructure parameters include microstructure sensitivity parameters, mesoscopic mechanical response parameters, and macroscopic energy release parameters;

[0022] a determination module for establishing a quantitative relationship between the multi-scale microstructure parameters and the risk of rock burst, and determining a core correlation mechanism between the multi-scale microstructure parameters and the risk of rock burst;

[0023] A construction module is used to construct and train a multi-scale microstructure parameter fusion model based on the quantitative relationship and the core association mechanism, wherein the fusion model is used to output a rock burst risk probability according to the input multi-scale fusion parameters;

[0024] The early warning module is used to collect real-time monitoring data of the coal and rock mass to be predicted through the multi-scale microstructure parameter monitoring system, and input the real-time monitoring data into the trained fusion model to obtain a dynamic early warning result of rock burst.

[0025] In order to implement the above-mentioned embodiments, the third aspect embodiment of the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor, the impact ground pressure warning method based on the fusion of multi-scale microstructure parameters of coal and rock mass in the above-mentioned first aspect is implemented.

[0026] The technical solutions provided by the embodiments of the present application bring at least the following beneficial effects: First, the present application constructs a comprehensive monitoring system for the multi-scale microstructure of coal and rock masses, organically combining microscopic, mesoscopic, and macroscopic monitoring technologies. This system can obtain information on coal and rock structural changes from different scales and angles, breaking the limitations of traditional single monitoring methods and providing more comprehensive and in-depth data support for rock burst prevention and control. Then, a multi-scale microstructure parameter fusion model is constructed. With the help of a series of specialized processing and analysis algorithms for different monitoring data, the characteristics of microstructure parameter changes related to rock burst are accurately extracted from massive monitoring data, achieving efficient conversion from data to knowledge and significantly improving the accuracy and reliability of rock burst prediction. Finally, in practical applications, real-time monitoring and dynamic analysis of multi-scale microstructure parameters of coal and rock masses can be achieved. By constructing a high-speed data acquisition and transmission system, the structural changes of coal and rock masses during the mining process can be captured in a timely manner. The extracted key parameters are input into the multi-scale microstructure parameter fusion model for parameter fusion and rock burst risk assessment. This provides a strong guarantee for early warning and active prevention and control of rock burst, fully meeting the strict real-time requirements of coal mine safety production. Therefore, this application can provide accurate rock burst warning information for coal mining, help coal mine production departments take prevention and control measures in advance, effectively reduce the risk of rock burst, ensure coal mine safety production, and improve production efficiency.

[0027] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0029] Figure 1 This is a flow chart of a rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock masses proposed in an embodiment of the present application;

[0030] Figure 2 A flowchart of a method for generating a quantitative relationship proposed in an embodiment of the present application;

[0031] Figure 3 This is a structural schematic diagram of a rock burst warning system based on the fusion of multi-scale microstructure parameters of coal and rock masses proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0033] It should be noted that the single multi-scale microstructural parameter monitoring method for coal and rock masses in the relevant embodiments cannot fully obtain the multi-scale microstructural information of coal and rock masses. For example, conventional stress monitoring can only reflect the macroscopic stress state and is difficult to penetrate into the microstructural level; while microscopic analysis methods such as scanning electron microscopy or tomographic CT scanning can observe the internal microstructure of coal and rock masses, it is difficult to establish an effective correlation with the macroscopic mining environment and cannot achieve real-time, dynamic monitoring. On the other hand, the data processing and analysis methods in the relevant embodiments are relatively simple and crude, and cannot accurately extract the microstructural parameter change characteristics directly related to rock burst from the massive monitoring data, resulting in a lack of accurate basis for the prediction and prevention of rock burst, making it difficult to meet the actual needs of safe and efficient coal mine mining.

[0034] To this end, this application proposes a rock burst warning method based on the fusion of multi-scale microstructural parameters of coal and rock masses. This method can accurately obtain the multi-scale microstructural parameter change information of coal and rock masses from microscopic to macroscopic, and provide real-time and accurate rock burst warning information through a multi-source network model, thereby improving the accuracy and real-time performance of rock burst warning.

[0035] The following describes, with reference to the accompanying drawings, a rock burst warning method and system based on the fusion of multi-scale microstructure parameters of coal and rock masses proposed in an embodiment of the present application.

[0036] Figure 1 This is a flow chart of a rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock mass proposed in the embodiment of the present application, as shown in FIG. Figure 1 As shown, the method includes the following steps:

[0037] In step S101 , a multi-scale microstructure parameter monitoring system including microscopic monitoring, mesoscopic monitoring and macroscopic monitoring is used to collect coal and rock mass microstructure monitoring data, and the monitoring data is processed and analyzed to obtain multi-scale microstructure parameters.

[0038] Among them, the multi-scale microstructure parameters include multiple microstructure sensitivity parameters, multiple microscopic mechanical response parameters and multiple macroscopic energy release parameters.

[0039] Specifically, this application first constructs a multi-scale microstructure parameter monitoring system including micro, meso and macro monitoring, then builds a data acquisition and transmission system for data transmission, and then develops a multi-scale microstructure parameter analysis algorithm to perform corresponding processing and analysis on the various monitoring data collected by the multi-scale microstructure parameter monitoring system, so as to obtain corresponding microstructure sensitivity parameters, mesoscopic mechanical response parameters and macroscopic energy release parameters.

[0040] In one embodiment of the present application, the multi-scale monitoring system constructed for microscopic monitoring uses high-resolution microscopic imaging technology, such as field emission scanning electron microscopy (FESEM) combined with focused ion beam scanning electron microscopy (FIB-SEM) technology, to observe the microstructure of coal rock samples (resolution ≤ 10nm), and the directly collected data include: spatial distribution images of micropores (such as pore size, shape and three-dimensional coordinates), initiation position and extension trajectory of microcracks (such as crack starting point, bifurcation point coordinates and extension direction), and morphological parameters of mineral crystals (such as crystal type, particle size, arrangement orientation). On the other hand, multi-field coupled in-situ CT technology is used to collect sequence images (resolution 1-10μm) of the dynamic evolution of microcracks inside coal rocks under different environmental fields (such as stress, seepage and high and low temperature), as well as the original data of stress-strain curves under corresponding loading conditions. On the other hand, the surface morphology image of the microscopic area (accuracy up to nm level) and point-by-point mechanical parameters (such as the original test value matrix of elastic modulus and hardness) are measured by atomic force microscopy (AFM).

[0041] For microscopic monitoring, the multi-scale monitoring system constructed in this application uses ultrasonic CT technology to arrange N ultrasonic transmitters and M receiving probes in the coal mining area to construct a three-dimensional monitoring network with a network spacing of 5 to 10m. In this way, the propagation speed, attenuation and other characteristics of ultrasonic waves in the coal rock mass can be directly obtained. Black and white random speckles (particle size 50-100μm) can also be sprayed on the surface of the coal rock mass as deformation tracking marks. On the other hand, digital image correlation (DIC) technology is used to collect images of the coal rock mass before and after deformation through a high-speed camera (frame rate ≥100fps) to monitor the deformation of the coal rock mass surface.

[0042] For macro-monitoring, the multi-scale monitoring system constructed in this application utilizes a microseismic monitoring system. Six or more microseismic sensors (with a sensitivity of 100 Hz or higher) are deployed throughout the entire coal mining area. The system uses a time-of-day positioning method (SP wave arrival time difference) to calculate the three-dimensional coordinates of microseismic events, with a positioning error of 5 meters or less. Furthermore, geoacoustic monitoring technology is combined to capture geoacoustic signals generated by microcrack expansion and friction within the coal and rock mass, further supplementing information on macrostructural changes.

[0043] Furthermore, in this embodiment, a data acquisition and transmission system is also constructed to collect the data monitored by the above-mentioned multi-scale monitoring system and transmit it to the background center for data analysis and processing. During specific implementation, professional data acquisition devices are equipped to achieve high-speed and high-precision acquisition of various monitoring signals. For example, imaging data and mechanical test data in micro-monitoring technology are collected by professional data acquisition cards; ultrasonic CT, microseismic and ground sound monitoring data are collected through dedicated data collectors. In addition, a high-speed and stable wireless transmission network is constructed to transmit the collected data to the ground data processing center in real time. 5G communication technology is combined with dedicated underground wireless relay equipment to ensure the reliability and low latency of data transmission to meet the needs of real-time monitoring and analysis.

[0044] Furthermore, the collected raw monitoring data is processed and analyzed to obtain multi-scale microstructural parameters. Specifically, the raw monitoring data can be processed through image recognition and machine learning algorithms to obtain multiple micropore parameters (such as porosity, pore fractal dimension, average pore size, and pore size distribution probability density), multiple microcrack parameters (such as crack density, crack ratio, crack fractal dimension, and crack connectivity), and multiple mineral structure parameters (such as mineral interface debonding rate and crystal orientation consistency index). The data obtained from the preliminary analysis can also be used to analyze mechanical correlation parameters and dynamic evolution characteristics.

[0045] The following is an illustrative description of the specific process of processing and analyzing the monitoring data of this application to obtain microstructure parameters at various scales.

[0046] In one embodiment of the present application, the microstructure sensitivity parameters obtained include: multiple micropore parameters, multiple microcrack parameters and multiple mineral structure parameters, and the monitoring data is processed and analyzed to obtain multi-scale microstructure parameters, including: binarizing the microimage data collected using microscopic imaging technology, and calculating multiple micropore parameters based on the binarization processing results; extracting the crack centerline from the microimage data, identifying the crack initiation position and crack propagation trajectory from the in-situ CT sequence images, and calculating multiple microcrack parameters based on the obtained crack information; and calculating multiple mineral structure parameters by performing mineral phase identification and combining the in-situ CT sequence images to perform grain boundary change analysis.

[0047] Specifically, this example first analyzes micropore parameters. The image data collected by the monitoring system is preprocessed, including binarization of the FESEM / CT images using a threshold segmentation algorithm (such as the Otsu method) to separate pores (black areas) from the solid matrix (white areas). Based on the 3D tomographic images, a 3D spatial model of the pores is reconstructed using the Marching Cubes algorithm. This process allows for analysis and calculation to determine the following parameters:

[0048] First, the porosity η is calculated by calculating the percentage of the pore volume (the sum of the black voxels in the binary image) to the total volume of the sample, which can be calculated using the following formula:

[0049] η=V 孔隙 / V 样本 ×100%

[0050] Second, the pore fractal dimension. Using the box-counting method, the pore boundaries are covered by grids of different scales, and the relationship between the number of grids and the scale under logarithmic coordinates is fitted. The absolute value of the slope is the pore fractal dimension D. 孔隙 , which reflects the complexity of the pore shape.

[0051] Third, average pore size and pore size distribution. Mark the pores in the binary image, measure the equivalent diameter (equivalent circle diameter) of each pore, calculate the pore size distribution probability density f(d), and calculate the arithmetic mean, which can be calculated using the following formula:

[0052]

[0053] This embodiment also performs micropore parameter analysis. The data collected by the above-mentioned monitoring system is processed for crack identification and tracking, including: edge detection of FESEM / FIB-SEM images (for example, the Canny operator can be used), combined with the skeletonization algorithm to extract the crack centerline; then, for the in-situ CT sequence images, the dynamic difference method is used to identify the crack initiation location (Δ gray value ≥ threshold), and the crack propagation trajectory is tracked by the optical flow method, recording the starting point, bifurcation point coordinates and propagation direction. Based on this processing process, the following parameters can be obtained through analysis and calculation:

[0054] First, the crack density ρc. First calculate the unit area (mm 2 ) and then calculated using the following formula:

[0055] ρc=N 裂纹 / A 观测面积 (bar / mm 2 )

[0056] Second, the crack ratio. This is the percentage of the total crack area to the observed area. The calculation method for this parameter is similar to the porosity calculation method, but pores can be replaced by cracks.

[0057] Third, the crack fractal dimension Df. Based on the crack network skeleton, the box dimension method or box counting dimension method is used to analyze the complexity of the crack spatial distribution.

[0058] Fourth, crack connectivity. This parameter is calculated by counting the proportion of interconnected cracks to the total number of cracks, and using graph theory algorithms (such as the adjacency matrix) to determine the connectivity of crack nodes.

[0059] This example also performed mineral structure parameter analysis. The data collected by the monitoring system was used for mineral phase identification and interface analysis. This included using the energy dispersive spectrometer (EDS) included with the FESEM to analyze the mineral composition and mark the boundaries of different mineral phases. Image segmentation techniques were then used to extract grain boundaries, and the changes in grain boundaries before and after loading the in-situ CT sequence data were compared to identify debonding interfaces (for example, an interface spacing Δ ≥ 2 nm was considered debonding). Based on this process, the following parameters were obtained through analysis and calculation:

[0060] First, the mineral interface debonding rate δ can be calculated by the following formula:

[0061] δ=L 脱粘晶界 / L 总晶界 ×100%

[0062] Second, the crystal orientation consistency index. This parameter is calculated based on electron backscatter diffraction (EBSD) data and the standard deviation of the angle between the crystal c-axis and the loading direction. The smaller the standard deviation, the higher the orientation consistency.

[0063] In one embodiment of the present application, the obtained mesoscopic mechanical response parameters include: ultrasonic attenuation coefficient and mesoscopic strain localization degree. The monitoring data is processed and analyzed to obtain multi-scale microstructure parameters. It also includes: processing the collected ultrasonic CT signals to calculate the ultrasonic attenuation coefficient; analyzing the coal rock deformation images collected using digital image correlation (DIC) technology to calculate the mesoscopic strain localization degree.

[0064] Specifically, this embodiment first processes the ultrasonic CT signals collected by the monitoring system. This includes bandpass filtering the received signals (the filtering range can be selected to be 50-500kHz) and extracting the first wave arrival time using the cross-correlation method. The internal velocity distribution of the coal and rock mass is then inverted using the algebraic reconstruction technique (SIRT) or iterative reconstruction technique (ART) to obtain the longitudinal wave velocity Vp and the shear wave velocity Vs. Based on this processing, the ultrasonic attenuation coefficient can be calculated.

[0065] The ultrasonic attenuation coefficient is defined as the signal amplitude attenuation rate per unit distance and can be calculated using the following formula:

[0066]

[0067] The unit of this parameter is dB / m, A0 is the emission amplitude, A dis the received amplitude at the distance d. Based on the above processing, the ultrasonic longitudinal wave velocity attenuation rate (Δv / v0, in %) can also be obtained.

[0068] This embodiment also analyzes the parameters collected by the above-mentioned DIC technology to calculate the microscopic strain localization degree ε l First, the displacement vector is calculated, and the displacement vector (u, v) of each point is calculated using a sub-pixel cross-correlation algorithm (for example, a window size of 32×32 pixels and an overlap rate of 50%). Then, the strain is calculated, and the gradient matrix is fitted using the least squares method based on the calculated displacement field to calculate the engineering strain. Finally, the microscopic strain localization degree ε is calculated. l , which is defined as the area ratio of the local strain concentration region (strain ≥ 2 times the mean) in the calculation process, reflecting the deformation heterogeneity.

[0069] In one embodiment of the present application, the macro-energy release parameters obtained include: the cumulative value of microseismic energy and the proportion of high-frequency components of the geoacoustic signal. The monitoring data is processed and analyzed to obtain multi-scale microstructure parameters. It also includes: analyzing the microseismic event parameters collected by the microseismic monitoring system to calculate the cumulative value of microseismic energy; analyzing the geoacoustic signal inside the coal rock mass collected using geoacoustic monitoring technology to calculate the proportion of high-frequency components of the geoacoustic signal.

[0070] Specifically, this embodiment first analyzes the microseismic monitoring parameters and first calculates the microseismic energy, which can be calculated based on the relationship between magnitude and energy expressed by the following formula:

[0071] E=10 1.5M+4.8

[0072] Where M is the magnitude.

[0073] Alternatively, the kinetic energy of the velocity signal can be directly integrated, that is, calculated using the following formula:

[0074]

[0075] Where ρ is the medium density and V is the source volume.

[0076] Then, the microseismic energy cumulative value Eacc is calculated, and the energy can be accumulated according to a time window (for example, 1 hour).

[0077] The spatial distribution concentration can also be calculated by calculating the standard deviation of the coordinates of microseismic events to reflect the spatial concentration of energy release.

[0078] This embodiment also analyzes ground sound monitoring parameters. The collected ground sound signal is first preprocessed, including wavelet denoising of the original ground sound signal (corresponding to a sensor bandwidth of 10-200 kHz) and decomposition into different frequency layers (for example, a 5-layer decomposition for the db4 wavelet).

[0079] Then perform spectrum analysis and use fast Fourier transform (FFT) to calculate the power spectrum density, extract the main frequency fmain, and compare it with the initial state main frequency f0. The offset can be obtained by the following formula:

[0080] Δf=|f main -f0|

[0081] Then, calculate the high-frequency component proportion fH, that is, the percentage of the energy in the frequency band above 100kHz to the total energy can be calculated by the following formula:

[0082]

[0083] In one embodiment of the present application, a mechanical correlation analysis can also be performed based on the analysis process of the above-mentioned scale parameters. Specifically, this embodiment first establishes a quantitative relationship between microporosity and crack fractal dimension and elastic modulus (E) and hardness (H) based on the stress-strain curve involved in the above-mentioned AFM data and in-situ CT data analysis. This relationship can be expressed by the following formula:

[0084] E=f(η,D f )

[0085] This can characterize the coupling effect between mineral interface bonding strength and microcrack evolution.

[0086] This embodiment also analyzes the dynamic evolution characteristics, including determining the microcrack growth rate (μm / s) and pore expansion rate (% / loading step) under multi-field coupling conditions, as well as the influence coefficients of different environmental fields (such as stress gradients and temperature changes) on microstructural parameters (for example, determining the increase in porosity Δη for every 10°C increase in temperature).

[0087] It should be noted that the various levels of monitoring technology and corresponding data processing and analysis methods used in the above-mentioned multi-scale monitoring system can be adjusted according to monitoring needs, and this application does not impose any restrictions on this. In actual application, the monitoring system can be deployed according to the actual situation of the mining site, and the relevant data monitoring, collection, transmission, processing and analysis processes can be executed.

[0088] As an example, the first step is to select representative monitoring locations within the coal mining area and rationally deploy micro, meso, and macro monitoring equipment based on monitoring requirements at different scales. For example, micro-sample collection points can be set up near the working face, ultrasonic CT probes can be placed at regular intervals, and microseismic and geoacoustic sensors can be evenly distributed throughout the mining area. The second step is to install and debug the monitoring equipment to ensure proper operation. Regular equipment calibration and maintenance are performed to ensure the accuracy and reliability of the monitoring data. For example, the resolution of micro-imaging equipment can be regularly calibrated, the probe performance of ultrasonic CT equipment can be checked, and the sensitivity of micro-seismic and geoacoustic sensors can be tested. The third step is to activate the data acquisition device according to the set sampling frequency and acquisition mode to collect data generated by each monitoring module in real time. For example, micro-imaging data can be collected every hour, ultrasonic CT data every 10 minutes, and micro-seismic and geoacoustic data can be collected continuously in real time. The fourth step is to transmit the collected data in real time to the ground data processing center via a wireless transmission network. During transmission, data encryption and verification technologies are used to ensure data security and integrity. The fifth step is to process the transmitted data at the ground data processing center. First, the raw data is preprocessed, including denoising, filtering, and data format conversion. For example, a wavelet denoising algorithm is used to denoise microseismic and geophone data. Sixth, appropriate data processing and analysis algorithms are applied to extract multi-scale microstructural parameters.

[0089] Step S102: establishing a quantitative relationship between multi-scale microstructure parameters and rock burst risk, and determining a core correlation mechanism between multi-scale microstructure parameters and rock burst risk.

[0090] Specifically, according to the method described in the previous step, a large number of multi-scale microstructure parameters can be obtained. By analyzing the multi-scale microstructure parameters under a large number of different rock burst events, a quantitative relationship between the multi-scale microstructure parameters and the risk of rock burst can be established.

[0091] For example, a multivariate linear regression model or a neural network model can be constructed and trained using historical data. The trained model can generate quantitative relationships between different scale parameters and the overall mechanical properties of coal and rock masses and the risk of rock burst. The model parameter input set is the three types of scale parameters mentioned above, among which the microstructural sensitivity parameters are: microporosity (η), microcrack density (ρc, bars / mm 2 ), mineral interface debonding rate (δ,%), crack fractal dimension (D f , reflecting the complexity of the crack); microscopic mechanical response parameters: ultrasonic longitudinal wave velocity attenuation rate (Δv / v0,%), microscopic strain localization degree (ε l, local strain concentration factor measured by DIC technology); macroscopic energy release parameters: cumulative energy of microseismic events (Eacc, J), proportion of high-frequency components of geophone signals (fH, proportion of energy of signals >100 kHz), and stress gradient change rate (dσ / dx, MPa / m).

[0092] In order to more clearly illustrate the specific implementation process of generating the above-mentioned quantitative relationship in the present application, a method for generating a quantitative relationship proposed in an embodiment of the present application is exemplified below. Figure 2 This is a flow chart of a method for generating a quantitative relationship proposed in an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps:

[0093] Step S201 : Based on historical rock burst cases, a nonlinear mapping relationship between the rock burst risk and the multi-scale microstructure parameters is established.

[0094] Specifically, according to the method described in the above embodiment, a large amount of historical data of multi-scale microstructure parameters can be obtained. For example, multi-scale microstructure parameters under historical impact cases (n=500+) and related parameters of rock burst events are obtained. The obtained data are used as training data to train the above-mentioned multivariate linear regression model or neural network model, so that a nonlinear mapping relationship between the risk of rock burst and the multi-scale microstructure parameters can be established, as shown in the following formula:

[0095] R=f(η,ρ c ,δ,D f ,Δv / v0,ε l ,Eacc,fH,dσ / dx)

[0096] Furthermore, this nonlinear mapping relationship is used as a quantitative relationship for rock burst risk.

[0097] Step S202 : determining the relationships between the risk warning triggering rule and the risk probability enhancement rule and the relevant microstructure parameters according to the nonlinear mapping relationship.

[0098] Specifically, by combining the nonlinear mapping relationship established above and analyzing the patterns obtained from the historical impact case data, the impact of relevant microstructure parameters on risk warning triggers and risk probability enhancement is determined.

[0099] For example, the risk warning triggering rule is determined as follows: when the micro crack density ρc>5 / mm 2A risk warning is triggered when the daily increase in macro-microseismic energy (Eacc) exceeds 50%. The established rule for increasing the risk probability is: there is a multiplicative effect between the mineral interface debonding rate δ and the stress gradient change rate dσ / dx. Specifically, when δ×dσ / dx exceeds 0.1 MPa, the risk probability increases by 30%-50%.

[0100] Step S203: Shapley value analysis is used to quantify the contribution of each microstructural parameter to rock burst risk.

[0101] Specifically, the Shapley value analysis method is used to quantify the contribution of each parameter, including: verifying the basic influence of microstructural parameters on risk (contribution accounting for 40%-60%), and the triggering effect of macro-energy parameters on risk (contribution accounting for 30%-40%). Among them, the Shapley value analysis method is a method based on game theory. This embodiment uses this algorithm to quantify the contribution of each microstructural parameter to the rock burst risk results predicted by the model. The importance of each feature is evaluated by calculating the average marginal contribution of each feature in all possible feature combinations. The SHAP framework, etc. can be used in the quantification process.

[0102] Furthermore, the present application also identifies the core correlation mechanism of rock burst risk. In one embodiment of the present application, determining the core correlation mechanism between multi-scale microstructure parameters and rock burst risk includes the following steps:

[0103] The first step is to determine the correlation mechanism between the microstructural degradation of the coal and rock mass and the stress concentration effect based on the results of the mechanical correlation analysis. This step is based on the mechanical correlation analysis performed in the embodiment of step S101. The core correlation mechanism determined in this step is that micropore expansion (η↑) and microcrack penetration (Df↑) lead to a decrease in coal and rock mass stiffness (elastic modulus E↓), forming a localized stress concentration zone (stress concentration factor K≥3), which provides energy accumulation conditions for rock burst.

[0104] The second step is to determine the correlation mechanism between the mesoscopic damage evolution of coal and rock mass and the energy transfer anomaly by analyzing the microscopic mechanical response parameters. The core correlation mechanism determined in this step is: the ultrasonic attenuation rate Δv / v0>15% indicates that the mesoscopic crack network is initially formed, at which time the strain localization ε l >0.8, resulting in a sudden change in the stress transfer path and inducing macroscopic stress imbalance.

[0105] The third step is to analyze macroscopic energy release parameters to determine the correlation mechanism between macroscopic energy release and critical instability of the coal and rock masses. The core correlation mechanism identified in this step is: when the microseismic energy Eacc exceeds twice the historical average for three consecutive days and the ground sound fH exceeds 40%, the coal and rock masses enter a critical instability state. At this point, the risk probability R ≥ 0.7, and immediate pressure relief measures are required.

[0106] Step S103: Based on the quantitative relationship and the core association mechanism, a multi-scale microstructure parameter fusion model is constructed and trained. The fusion model is used to output the rock burst risk probability according to the input multi-scale fusion parameters.

[0107] Specifically, based on the quantitative relationships and core association mechanisms obtained in the previous step, a multi-source network model is constructed. This multi-source network model utilizes these relationships to calculate the input multi-scale fusion parameters, thereby outputting the rockburst risk probability. The large number of historical rockburst cases obtained in the above-mentioned embodiments can be used as training data, with each set of training data including corresponding multi-scale microstructure parameters and rockburst event data.

[0108] In one embodiment of the present application, before constructing the multi-scale microstructure parameter fusion model, it also includes: normalizing the multi-scale microstructure parameters; calculating the correlation between each normalized microstructure parameter and the impact ground pressure event through the mutual information method, and calculating the Spearman correlation coefficient of each microstructure parameter according to the correlation degree; using the Spearman correlation coefficient of each microstructure parameter, a plurality of key parameters are screened out from the multi-scale microstructure parameters through the recursive feature elimination (RFE) algorithm, wherein the Spearman correlation coefficient of each key parameter is greater than a preset screening threshold.

[0109] Specifically, this embodiment performs a fusion analysis on multi-scale microstructure parameters to achieve preprocessing and feature screening of model input data. First, the multi-scale microstructure parameters are normalized. As a possible implementation method, the above-mentioned microscopic parameters (η, ρc, δ), mesoscopic parameters (Δv / v0, εl) and macroscopic parameters (Eacc, fH) are Z-score standardized to eliminate the dimension effect. Specifically, the following formula can be used for normalization:

[0110]

[0111] Then, feature screening is performed, using the mutual information method and recursive feature elimination (RFE) algorithm to screen key parameters with significant correlation with rock burst. Among them, the mutual information method (MI) is first used to calculate the correlation between each microstructural parameter and rock burst events. The mutual information method is a statistical method based on information theory, which is used to measure the mutual dependence between two random variables. Then, based on the calculation results of the mutual information method, the Spearman correlation coefficient of each microstructural parameter to the rock burst event is calculated. The Spearman correlation coefficient can measure the monotonic correlation between the two variables. The Spearman correlation coefficient is calculated by converting the original data of the two variables into ranks. Finally, based on the Spearman correlation coefficient of each parameter, the key parameters with significant correlation with rock burst are screened by recursive feature elimination. For example, the screening threshold is set to the absolute value of the Spearman correlation coefficient ≥ 0.3. When the Spearman correlation coefficient of each parameter is greater than the screening threshold, it is retained, so that 20-30 key parameters can be retained as the core features of the subsequent multi-source network model input.

[0112] Furthermore, a three-level fusion model is constructed. In one embodiment of the present application, a multi-scale microstructure parameter fusion model is constructed, including: a feature extraction layer, a cross-scale fusion layer and a risk assessment layer. Among them, the feature extraction layer is the bottom layer, which is used to extract data features corresponding to key parameters from the input multi-scale microstructure parameters. For microscopic image data, a convolutional neural network CNN is used to extract data features, and for time series data, a long short-term memory network LSTM is used to extract data features; the cross-scale fusion layer is the middle layer, which is used to map different data features to a unified feature space and calculate the contribution weight of each data feature to rock burst; the risk assessment layer is the top layer, which is used to output the rock burst risk probability.

[0113] Specifically, the model constructed in this embodiment includes a bottom feature extraction layer, a middle cross-scale fusion layer, and a top risk assessment layer. In the bottom feature extraction layer, for microscopic image data, a convolutional neural network (CNN) is used to automatically extract geometric features such as the fractal dimension of microcracks and the complexity of pore morphology; for time series microscopic and macroscopic data (such as ultrasonic CT inversion parameters and microseismic event sequences), a long short-term memory network (LSTM) is used to capture the dynamic evolution of parameters. In the middle cross-scale fusion layer, different modal features are mapped to a unified feature space through a fully connected layer, and an attention mechanism is introduced to calculate the contribution weight of each scale parameter to rock burst, highlighting key influencing factors (such as the coupling effect of microscopic crack connectivity and macroscopic microseismic energy). In the top risk assessment layer, a Softmax classifier or regression model is used to output the rock burst risk probability (0-1 continuous value) or risk level (grades I-IV), where a risk probability ≥ 0.6 is defined as a high-risk warning threshold.

[0114] Furthermore, the above-mentioned model is trained, and the specific training process can refer to the training method in the relevant technology, and this application does not limit this. After the training is completed, model verification and dynamic correction can also be performed. As a possible implementation method, cross-validation (5-fold) is used to evaluate the prediction accuracy of the model. In a typical mining area test, the model's recognition accuracy for rock burst is ≥85%, and the false alarm rate is ≤10%. The training set is continuously updated through real-time monitoring data (automatic incremental learning every week), and the parameter weights and risk thresholds are dynamically corrected, thereby adapting to changes in coal and rock properties under different geological conditions.

[0115] In step S104, real-time monitoring data of the coal and rock mass to be predicted is collected through the multi-scale microstructure parameter monitoring system, and the real-time monitoring data is input into the trained fusion model to obtain a dynamic early warning result of rock burst.

[0116] Specifically, in actual applications at underground mining sites, for the coal rock mass that is currently undergoing rock burst warning, the multi-scale microstructure parameter monitoring system and data processing and analysis method described in step S101 can be used to collect the current original monitoring data of the coal rock mass, and the original monitoring data can be processed and analyzed to obtain real-time monitoring results of the multi-scale microstructure parameters of the coal rock mass. The real-time monitoring results are then input into the trained fusion model to obtain dynamic rock burst warning results for the current coal rock mass.

[0117] Therefore, this application organically integrates the parameters obtained from microscopic, mesoscopic and macroscopic monitoring through the above-mentioned multi-source network model and quantitative relationship, realizes cross-scale mapping from microstructural parameters → mesoscopic damage characteristics → macroscopic energy signals, and constructs a closed-loop logic of parameter anomaly → risk classification → early warning response, providing a quantitative basis for rock burst prediction. This application inputs the extracted multi-scale microstructural parameters into the multi-scale microstructural parameter fusion model to perform parameter fusion and rock burst risk assessment. According to the assessment results, rock burst warning information can be promptly issued to the coal mine production department through relevant communication methods.

[0118] In summary, the rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock masses in the embodiment of the present application first constructs a monitoring system that comprehensively covers the multi-scale microstructure of coal and rock masses, organically combining microscopic, mesoscopic and macroscopic monitoring technologies. The system can obtain information on coal and rock structure changes from different scales and angles, breaking the limitations of traditional single monitoring methods and providing more comprehensive and in-depth data support for rock burst prevention and control. Then, a multi-scale microstructure parameter fusion model is constructed. With the help of a series of special processing and analysis algorithms for different monitoring data, the microstructure parameter change characteristics related to rock burst are accurately extracted from massive monitoring data, achieving efficient conversion from data to knowledge and significantly improving the accuracy and reliability of rock burst prediction. Finally, in practical applications, real-time monitoring and dynamic analysis of multi-scale microstructure parameters of coal and rock masses can be realized. By constructing a high-speed data acquisition and transmission system, the structural changes of coal and rock masses during the mining process can be captured in a timely manner, and the extracted key parameters are input into the multi-scale microstructure parameter fusion model for parameter fusion and rock burst risk assessment. This provides a strong guarantee for early warning and proactive prevention of rock bursts, fully meeting the stringent real-time requirements for coal mine safety production. This method can provide accurate rock burst warning information for coal mining, helping coal mine production departments to take preventive measures in advance, effectively reducing the risk of rock bursts, ensuring coal mine safety and improving production efficiency.

[0119] In order to implement the above embodiment, the present application also proposes a rock burst warning system based on the fusion of multi-scale microstructure parameters of coal and rock masses. Figure 3 This is a structural diagram of a rock burst warning system based on the fusion of multi-scale microstructure parameters of coal and rock masses proposed in an embodiment of the present application, as shown in FIG. Figure 3 As shown, the system includes: a monitoring and analysis module 100 , a determination module 200 , a construction module 300 and an early warning module 400 .

[0120] Among them, the monitoring and analysis module 100 is used to collect coal rock microstructure monitoring data through a multi-scale microstructure parameter monitoring system including microscopic monitoring, mesoscopic monitoring and macroscopic monitoring, and process and analyze the monitoring data to obtain multi-scale microstructure parameters, wherein the multi-scale microstructure parameters include microstructure sensitivity parameters, mesoscopic mechanical response parameters and macroscopic energy release parameters.

[0121] The determination module 200 is used to establish a quantitative relationship between the multi-scale microstructure parameters and the risk of rock burst, and to determine the core correlation mechanism between the multi-scale microstructure parameters and the risk of rock burst.

[0122] The construction module 300 is used to construct and train a multi-scale microstructure parameter fusion model based on the quantitative relationship and the core association mechanism. The fusion model is used to output the rock burst risk probability according to the input multi-scale fusion parameters.

[0123] The early warning module 400 is used to collect real-time monitoring data of the coal and rock mass to be predicted through a multi-scale microstructure parameter monitoring system, and input the real-time monitoring data into the trained fusion model to obtain dynamic early warning results of rock burst.

[0124] It should be noted that the above explanation of the embodiment of the rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock mass is also applicable to the system of this embodiment. The implementation principle is the same and will not be repeated here.

[0125] To sum up, the rock burst warning system based on the fusion of multi-scale microstructure parameters of coal and rock masses in the embodiment of the present application can provide accurate rock burst warning information for coal mining, help coal mine production departments take prevention and control measures in advance, effectively reduce the risk of rock burst, ensure safe production in coal mines, and improve production efficiency.

[0126] In order to implement the above-mentioned embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock mass as described in any one of the above-mentioned first aspect embodiments.

[0127] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0128] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0129] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0130] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0131] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0132] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0133] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0134] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A rock burst early warning method based on the fusion of multi-scale microstructure parameters of coal and rock mass, characterized in that: The following steps are involved: Collecting coal and rock mass microstructure monitoring data through a multi-scale microstructure parameter monitoring system comprising microscopic monitoring, mesoscopic monitoring, and macroscopic monitoring, and processing and analyzing the monitoring data to obtain multi-scale microstructure parameters, wherein the multi-scale microstructure parameters include microstructure sensitivity parameters, mesoscopic mechanical response parameters, and macroscopic energy release parameters; Establishing a quantitative relationship between the multi-scale microstructural parameters and the risk of rock burst, and determining the core correlation mechanism between the multi-scale microstructural parameters and the risk of rock burst; Based on the quantitative relationship and the core association mechanism, a multi-scale microstructure parameter fusion model is constructed and trained, wherein the fusion model is used to output the rock burst risk probability according to the input multi-scale fusion parameters; The multi-scale microstructure parameter monitoring system is used to collect real-time monitoring data of the coal and rock mass to be predicted, and the real-time monitoring data is input into the trained fusion model to obtain a dynamic early warning result of rock burst.

2. The method according to claim 1, characterized in that The establishing of a quantitative relationship between the multi-scale microstructure parameters and the risk of rock burst includes: Based on historical rock burst cases, a nonlinear mapping relationship between the rock burst risk and the multi-scale microstructure parameters is established; According to the nonlinear mapping relationship, the relationship between the risk warning triggering rule and the risk probability enhancement rule and the relevant microstructure parameters is determined respectively; The Shapley value analysis method is used to quantify the contribution of each microstructural parameter to rock burst risk.

3. The method according to claim 1, characterized in that The core correlation mechanism between the multi-scale microstructure parameters and the risk of rock burst includes: Based on the results of mechanical correlation analysis, the correlation mechanism between the microstructural degradation of coal and rock mass and the stress concentration effect is determined; By analyzing the microscopic mechanical response parameters, the correlation mechanism between the microscopic damage evolution of coal and rock mass and the energy transfer anomaly is determined; By analyzing the macro energy release parameters, the correlation mechanism between the macro energy release and the instability criticality of the coal rock mass is determined.

4. The method according to claim 1, wherein Before constructing the multi-scale microstructure parameter fusion model, the method further includes: performing normalization processing on the multi-scale microstructure parameters; The correlation between each normalized microstructural parameter and the rock burst event is calculated using the mutual information method, and the Spearman correlation coefficient of each microstructural parameter is calculated based on the correlation. The Spearman correlation coefficient of each microstructure parameter is used to screen out multiple key parameters from the multi-scale microstructure parameters through a recursive feature elimination (RFE) algorithm, wherein the Spearman correlation coefficient of each key parameter is greater than a preset screening threshold.

5. The method according to claim 4, characterized in that The multi-scale microstructure parameter fusion model includes: a feature extraction layer, a cross-scale fusion layer and a risk assessment layer; wherein, The feature extraction layer is the bottom layer, which is used to extract data features corresponding to the key parameters from the input multi-scale microstructure parameters. For microscopic image data, the convolutional neural network (CNN) is used to extract data features, and for time series data, the long short-term memory network (LSTM) is used to extract data features. The cross-scale fusion layer is a middle layer, which is used to map different data features into a unified feature space and calculate the contribution weight of each data feature to rock burst; The risk assessment layer is the top layer and is used to output rock burst risk probability.

6. The method according to claim 1, characterized in that The microstructure sensitivity parameters include: multiple micropore parameters, multiple microcrack parameters and multiple mineral structure parameters. The processing and analysis of the monitoring data to obtain multi-scale microstructure parameters includes: performing binarization processing on microscopic image data collected using microscopic imaging technology, and calculating the plurality of micropore parameters according to the binarization processing result; Extracting a crack centerline from the microscopic image data, identifying a crack initiation location and a crack propagation trajectory from in-situ CT sequence images, and calculating the plurality of microcrack parameters based on the obtained crack information; The multiple mineral structure parameters are calculated by performing mineral phase identification and grain boundary change analysis in combination with the in-situ CT sequence images.

7. The method according to claim 1, characterized in that The microscopic mechanical response parameters include: ultrasonic attenuation coefficient and microscopic strain localization degree. The processing and analysis of the monitoring data to obtain multi-scale microstructure parameters also includes: Processing the collected ultrasonic CT signals to calculate the ultrasonic attenuation coefficient; The coal and rock deformation images collected by using the digital image correlation (DIC) technique are analyzed to calculate the microscopic strain localization degree.

8. The method according to claim 1, characterized in that The macro energy release parameters include: the accumulated value of microseismic energy and the proportion of high-frequency components of the ground sound signal. The processing and analysis of the monitoring data to obtain multi-scale microstructure parameters also includes: Analyzing the microseismic event parameters collected by the microseismic monitoring system and calculating the accumulated microseismic energy value; The ground sound signals inside the coal and rock mass collected by using the ground sound monitoring technology are analyzed, and the proportion of high-frequency components of the ground sound signals is calculated.

9. A rock burst warning system based on the fusion of multi-scale microstructure parameters of coal and rock mass, characterized by: Includes the following modules: A monitoring and analysis module is used to collect coal and rock mass microstructure monitoring data through a multi-scale microstructure parameter monitoring system including microscopic monitoring, mesoscopic monitoring, and macroscopic monitoring, and to process and analyze the monitoring data to obtain multi-scale microstructure parameters, wherein the multi-scale microstructure parameters include microstructure sensitivity parameters, mesoscopic mechanical response parameters, and macroscopic energy release parameters; a determination module for establishing a quantitative relationship between the multi-scale microstructure parameters and the risk of rock burst, and determining a core correlation mechanism between the multi-scale microstructure parameters and the risk of rock burst; A construction module is used to construct and train a multi-scale microstructure parameter fusion model based on the quantitative relationship and the core association mechanism, wherein the fusion model is used to output a rock burst risk probability according to the input multi-scale fusion parameters; The early warning module is used to collect real-time monitoring data of the coal and rock mass to be predicted through the multi-scale microstructure parameter monitoring system, and input the real-time monitoring data into the trained fusion model to obtain a dynamic early warning result of rock burst.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the rock burst warning method based on the fusion of multi-scale microstructure parameters of coal and rock masses as described in any one of claims 1 to 8 is implemented.

Images