A surrounding rock failure early warning method based on multi-source data

Abstract

The present application discloses a surrounding rock failure warning method based on multi-source data, belonging to the technical field of data processing. The method includes: arranging a plurality of measuring stations at a predetermined interval along the retreat roadway in the working face, and installing sensor groups on the roof, solid coal side, and roadside filling body of the measuring stations; processing the collected data by using the moving average method, fast Fourier transform, difference, and cumulative summation, and aligning the processed data according to the measuring point position and time tag; performing principal component analysis and hierarchical clustering on the aligned data, dividing the measuring points into three regions, respectively establishing corresponding prediction models, and performing normalization processing on the calculation results of the models; setting abnormal judgment parameters according to the normalization processing results, calculating a warning index by weighted summation, and sending a warning signal according to the comparison result between the warning index and the preset level threshold. Through the solution of the present application, the deformation trend of the surrounding rock in each region can be predicted more accurately.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular, to a surrounding rock failure early warning method based on multi-source data. Background Art

[0002] With the continuous expansion of coal mining scale and the continuous deepening of mining depth, the dynamic disasters caused by the failure of coal mine surrounding rock are becoming increasingly serious, posing a major threat to the safe production of coal mines. The coal mine surrounding rock failure early warning technology refers to a technical method that obtains the change characteristics of parameters such as surrounding rock deformation and stress through various monitoring means, and combines intelligent analysis algorithms to predict and warn in advance the occurrence of surrounding rock failure. The core of this technology lies in monitoring the stability state of the surrounding rock in real time, timely discovering the precursors of surrounding rock failure, and providing a decision-making basis for taking preventive and control measures. The existing coal mine surrounding rock failure early warning technologies mainly include methods such as displacement monitoring, stress monitoring, and microseismic monitoring. Among them, the displacement monitoring technology judges the stability of the surrounding rock by measuring the deformation of the roadway roof and wall; the stress monitoring technology evaluates the failure risk by measuring the change of the surrounding rock stress field; the microseismic monitoring technology predicts the failure by capturing the weak seismic signals generated during the surrounding rock fracture process. However, there are many deficiencies in the current conventional early warning technologies: First, a single monitoring means is difficult to comprehensively reflect the complex evolution process of surrounding rock failure, resulting in low reliability of the early warning results; Second, traditional early warning methods often rely on empirical judgment and lack a scientific early warning index system and early warning model; Third, due to the complexity and variability of coal mine geological conditions, there are large differences in the adaptability and accuracy of existing early warning technologies under different geological conditions; Finally, the layout and maintenance costs of the early warning system are relatively high, and the monitoring equipment is prone to failure in the harsh underground environment, affecting the continuity and reliability of the monitoring data.

[0003] To address the above technical problems, researchers have disclosed a variety of improvement solutions. First, the development of multi-parameter collaborative monitoring technology, by integrating various monitoring data such as displacement, stress, and microseismic, to establish a more comprehensive early warning index system. Second, the introduction of artificial intelligence algorithms, such as deep learning and pattern recognition technologies, to improve the intelligence level and prediction accuracy of the early warning model. Third, the development of adaptive early warning models, by considering influencing factors such as geological conditions and mining methods, to improve the applicability of early warning technologies under different conditions. In addition, it also includes the research and development of new sensors and monitoring equipment to improve the reliability and durability of monitoring equipment. However, there are still some problems with these improved technologies in practical applications: First, the fusion method of multi-parameter monitoring data is not yet mature, making it difficult to effectively extract and utilize the early warning information contained in various types of data; Second, the stability and interpretability of artificial intelligence algorithms in dealing with the non-linear and non-stationary surrounding rock failure process need to be improved; Third, due to the lack of long-term and systematic on-site monitoring data, it is difficult to train and validate the early warning model; Finally, the intelligence level and anti-interference ability of monitoring equipment still need to be further improved to adapt to the complex underground environment. In addition, the real-time performance and reliability of the early warning system also face challenges. How to shorten the early warning time while ensuring the accuracy of early warning, and how to reduce the false alarm rate and missed alarm rate are all technical problems that need to be solved urgently.

[0004] Therefore, there is an urgent need for a technical solution that can more accurately predict the deformation trend of the surrounding rock in each area. Summary of the Invention

[0005] To solve the deficiencies of the prior art, the embodiments of the present application disclose a surrounding rock failure early warning method based on multi-source data. The present application solves the technical problems of single model and linear superposition in the prior art.

[0006] The embodiments of the present application disclose a surrounding rock failure early warning method based on multi-source data, including: setting a plurality of measuring stations at a predetermined interval along the withdrawal roadway of the working face, and installing sensor groups on the roof, solid coal side, and roadside filling body of the measuring stations; processing the collected data using the moving average method, fast Fourier transform, difference, and cumulative summation, and aligning the processed data according to the measuring point position and time tag; performing principal component analysis and hierarchical clustering on the aligned data, dividing the measuring points into three regions, respectively establishing corresponding prediction models, and normalizing the calculation results of the models; setting abnormal judgment parameters according to the normalization processing results, calculating the early warning index using weighted summation, and sending out an early warning signal based on the comparison result between the early warning index and the preset level threshold.

[0007] In one possible implementation, a plurality of measurement stations are arranged at predetermined intervals along the retreat roadway on the working face. Sensor groups are installed on the roof, the solid coal rib, and the roadside packing body of the measurement stations, including: a plurality of measurement stations are arranged in sequence along the retreat roadway on the working face at a preset spacing, and a pressure sensor, an axial stress sensor, a displacement sensor, and a velocity sensor are installed at each measurement station; pressure sensors are installed on the roof, the solid coal rib, and the roadside packing body of the working face respectively, and an axial stress sensor is installed at the end measurement station; the measurement data of the sensors are collected and stored through a data collector to form a data file containing pressure, stress, displacement, and deformation velocity.

[0008] In one possible implementation, the collected data is processed by using the moving average method, the fast Fourier transform, the difference method, and the cumulative summation method, and the processed data is aligned according to the measurement point position and the time tag, including: the collected pressure data is smoothed by using the moving average method, and the spatial distribution characteristics of the pressure data are fitted by using the least squares method; the fast Fourier transform method is used to calculate the spectral characteristics of the bolt axial stress data and extract the main frequency component; the difference method is used to calculate the displacement increment of the displacement data and statistically analyze the time series characteristics; the cumulative summation method is used to calculate the cumulative deformation amount of the deformation velocity data; the processed data is aligned according to the measurement point position and the time tag to form a processed data table.

[0009] In one possible implementation, principal component analysis and hierarchical clustering are performed on the aligned data, the measurement points are divided into three regions, corresponding prediction models are established respectively, and the calculation results of the models are normalized, including: principal component analysis is used to extract the main change characteristics of the data of each measurement point and calculate the correlation coefficient between each measurement point; hierarchical clustering is used to divide the measurement points into three regions: behind the stop line, above the retreat roadway, and above the coal wall of the working face; a prediction equation of the creep constitutive model is established for the region behind the stop line; a prediction equation of the viscoelastic-plastic constitutive model is established for the region above the retreat roadway; a prediction equation of the rheological damage coupling model is established for the region above the coal wall; the predicted values of the three regions are normalized to obtain the normalized predicted values.

[0010] In one possible implementation, abnormal judgment parameters are set according to the normalization result, the early warning index is calculated by using weighted summation, and an early warning signal is issued according to the comparison result between the early warning index and the preset level threshold, including: judgment parameters for pressure abnormality, stress abnormality, displacement abnormality, and velocity abnormality are set; the early warning index of each measurement point is calculated by using the weighted summation method, and the weight coefficient is determined through experimental calibration; the early warning index is divided into preset levels according to the numerical size, and an early warning signal is issued when the early warning index exceeds the corresponding level threshold.

[0011] In one possible implementation, principal component analysis is used to extract the main change characteristics of the data at each measuring point, and the correlation coefficients between the measuring points are calculated, including: subtracting the measurement mean of the previous preset time period of each measuring point from the data of the roof pressure, bolt load, roof-to-floor convergence amount, and rib convergence amount of each measuring point and then dividing by the standard deviation; constructing a covariance matrix for the normalized data, calculating the eigenvalues and eigenvectors of the covariance matrix; selecting the eigenvectors with the cumulative contribution rate reaching the preset threshold as the principal components, and projecting the normalized data into the principal component space to obtain the principal component scores of each measuring point.

[0012] In one possible implementation, hierarchical clustering is used to divide the measuring points into three regions: behind the stop line, above the withdrawal roadway, and above the coal face wall, including:

[0013] Calculating the Euclidean distance of the principal component scores based on the roof pressure, bolt load, roof-to-floor convergence amount, and rib convergence amount between any two measuring points; constructing a distance matrix based on the Euclidean distance and performing hierarchical clustering using the minimum variance; determining the optimal number of clusters by calculating the ratio of the inter-class distance to the intra-class distance, and dividing the measuring points into the preset regions.

[0014] In one possible implementation, a prediction equation of the creep constitutive model is established for the region behind the stop line, including: calculating the roof subsidence velocity and acceleration of the measuring points in the region behind the stop line; based on the creep relationship between the roof pressure and the roof-to-floor displacement, using historical data for non-linear fitting to solve the instantaneous elastic modulus and viscosity coefficient; introducing a surrounding rock damage factor and establishing a surrounding rock damage equation including plastic strain and critical strain; constructing a roof pressure prediction equation and substituting the measured data to solve the initial pressure.

[0015] In one possible implementation, a prediction equation of the viscoelastic-plastic constitutive model is established for the region above the withdrawal roadway, including: establishing a viscoelastic relationship equation between the axial stress and displacement of the bolt, including the elastic modulus and viscosity coefficient; introducing a plastic damage term including a softening coefficient and a yield stress, and establishing a bolt load prediction equation including the initial bolt load; using historical data for non-linear least squares fitting to solve the elastic modulus, viscosity coefficient, softening coefficient, and yield stress.

[0016] In one possible implementation, a prediction equation of the rheological damage coupling model is established for the region above the coal face wall, including: establishing a rheological equation of the stress concentration coefficient and time based on the rib convergence amount, including the elastic modulus and viscosity coefficient; introducing a damage evolution equation including a damage variable and material parameters, and establishing a stress concentration coefficient prediction equation including the initial stress concentration coefficient; using historical data for non-linear fitting to solve all parameters.

[0017] In a surrounding rock failure early warning method based on multi-source data disclosed above, in the embodiments of the present application, respective non-linear prediction models are established for different data clustering regions, and the damage mechanics theory is introduced to describe the deterioration process of the surrounding rock. A creep model is introduced in the area behind the stop line to characterize the rheological properties of the cantilever beam, a viscoelastic-plastic model is used in the area above the withdrawal roadway to describe the softening process of the immediate roof, and a rheological damage coupling model is used in the area above the coal wall to characterize the damage evolution in the stress concentration area, which can more accurately predict the deformation trend of the surrounding rock in each area. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flow chart of a surrounding rock failure early warning method based on multi-source data disclosed in the embodiments of the present application;

[0020] Figure 2 It is a schematic diagram of a fracture behind the stop line disclosed in the embodiments of the present application;

[0021] Figure 3 It is a schematic diagram of a fracture above the withdrawal roadway disclosed in the embodiments of the present application;

[0022] Figure 4 It is a schematic diagram of a fracture above the coal wall disclosed in the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] Now, various exemplary embodiments of the present disclosure will be described in detail with reference to the drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure.

[0024] Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate an inevitable logical order between them. It should also be understood that in the embodiments of the present disclosure, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more. It should also be understood that for any component, data or structure mentioned in the embodiments of the present disclosure, without clear limitation or contrary revelation in the context, it can generally be understood as one or more. In addition, the term "and / or" in the present disclosure is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the associated objects before and after. It should also be understood that the present disclosure emphasizes the differences between the various embodiments, and their similarities or similarities can be referred to each other. For the sake of brevity, they will not be elaborated one by one.

[0025] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn in actual proportional relationships. The following description of at least one exemplary embodiment is actually only illustrative and in no way restricts the present disclosure and its application or use. Technologies, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods and devices should be regarded as part of the specification. It should be noted that: similar reference numerals and letters denote similar items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0026] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0027] Figure 1 It is a schematic flow chart of a surrounding rock failure warning method based on multi-source data disclosed in the embodiments of the present application.

[0028] It should be understood that in the existing technologies for predicting the failure of surrounding rocks in coal mining faces, a single data source or a simple linear superposition model is generally used to predict the state of surrounding rocks. Some methods only establish warning indicators based on displacement monitoring data, without considering other important parameters such as pressure and stress, resulting in one-sided warning results; some methods collect multi-source data, but use a simple weighted summation method to establish a warning model, ignoring the non-linear characteristics and time effects of the deformation of surrounding rocks. Especially in the warning of the surrounding rocks in the withdrawal roadway, due to the advancement of the coal mining face, the overlying strata will produce complex movement and deformation laws due to mining influence. According to the breaking characteristics of the overlying strata in different regions, the deformation of surrounding rocks can be divided into three modes: the cantilever beam type deformation in the area behind the stop line, the direct roof stress-bearing deformation above the withdrawal roadway, and the stress concentration deformation above the coal wall. These three deformation modes have their own unique mechanical characteristics and evolution laws, and it is difficult to accurately describe their deformation mechanisms using traditional single models or linear superposition models. At the same time, during the coal mining process, the surrounding rocks will go through multiple stages such as elastic deformation, plastic softening, and damage deterioration, and the mechanical response of the rock mass shows significant non-linearity, time-variation, and damage evolution characteristics. Relying solely on simple elastic models or linear relationships to predict the state of surrounding rocks cannot accurately reflect these complex mechanical behaviors. Therefore, it is necessary to establish unique non-linear prediction models for different regions and introduce the theory of damage mechanics to describe the deterioration process of surrounding rocks.

[0029] In the embodiment of the present application, by introducing the Maxwell creep model in the area behind the stop line to characterize the rheological properties of the cantilever beam, using the Kelvin viscoelastic-plastic model in the area above the withdrawal roadway to describe the softening process of the direct roof, and using the Burgers rheological damage coupling model in the area above the coal wall to characterize the damage evolution in the stress concentration area, the deformation trend of the surrounding rocks in each area can be predicted more accurately. This zoning modeling method based on regional characteristics effectively solves the technical problems such as single model and linear superposition in the existing technologies.

[0030] As Figure 1 shown, at step S101, a plurality of measuring stations are arranged at a predetermined interval along the withdrawal roadway of the working face, and a sensor group is installed on the roof, the solid coal side, and the roadside filling body of the measuring station. It includes: arranging a plurality of measuring stations in sequence along the withdrawal roadway of the working face at a preset interval, and installing a pressure sensor, an axial stress sensor, a displacement sensor, and a velocity sensor at each measuring station; installing pressure sensors on the roof, the solid coal side, and the roadside filling body of the working face respectively, and installing an axial stress sensor at the end measuring station; collecting and storing the measurement data of the sensors through a data collector to form a data file containing pressure, stress, displacement, and deformation velocity.

[0031] In one embodiment, first, a first measuring station is arranged 20 m away from the transportation gateway along the working face, and a measuring station is arranged every 20 m along the retreat roadway. Pressure sensors are used to collect pressure data at different positions of the roof, solid coal rib, and roadside filling body, and the sampling frequency is set to once every 2 hours. A first measuring station is arranged at the end, and a measuring station is installed every 20 m to install axial stress sensors to collect bolt stress data, and the sampling frequency is set to once every 4 hours. Displacement sensors are used to collect displacement data of the roof subsidence and rib convergence of the roadway, and the sampling frequency is set to once every 6 hours. Velocity sensors are used to collect surrounding rock deformation velocity data, and the sampling frequency is set to once per hour. The measurement ranges of the sensors are calibrated as follows: the measurement range of the pressure sensor is 0 - 15 MPa; the measurement range of the axial stress sensor is 0 - 200 kN; the measurement range of the displacement sensor is 0 - 500 mm; the measurement range of the velocity sensor is 0 - 100 mm / d. The data measured by all sensors are collected and stored through a data collector to form a data file containing raw data such as pressure, stress, displacement, and deformation velocity.

[0032] In step S102, the collected data is processed using the moving average method, fast Fourier transform, difference, and cumulative summation, and the processed data is aligned according to the measuring point position and time tag. This includes: smoothing the collected pressure data using the moving average method and fitting the spatial distribution characteristics of the pressure data using the least squares method; calculating the spectral characteristics of the bolt axial stress data using the fast Fourier transform method and extracting the main frequency component; calculating the displacement increment of the displacement data using the difference method and statistically analyzing the time series characteristics; calculating the cumulative deformation amount of the deformation velocity data using the cumulative summation method; aligning the processed data according to the measuring point position and time tag to form a processed data table.

[0033] In one embodiment, for the pressure data collected at the measuring points, the moving average method is used to smooth the data, and the window length is set to 24 hours. The least squares method is used to fit the variation trend of the pressure data with the spatial position to obtain the spatial distribution characteristics of the pressure data. For the bolt axial stress data, the fast Fourier transform method is used to calculate the spectral characteristics of the stress data and extract the main frequency component. For the displacement data, the difference method is used to calculate the displacement increment and statistically analyze the time series characteristics. For the deformation velocity data, the cumulative summation method is used to calculate the cumulative deformation amount. The processed pressure, stress, displacement, and deformation velocity data are aligned according to the measuring point position and time tag to form a processed data table.

[0034] Taking a certain measuring station in the gob-side entry retaining face of a coal mine's extraction roadway as an example, the variation of the pressure data at this measuring station over multiple days is as follows: 2.3 MPa, 4.2 MPa, 6.6 MPa, 8.2 MPa, 10.1 MPa, 10.1 - 10.0 MPa, 9.8 MPa. Perform a fast Fourier transform on the axial stress data of the bolts to obtain the main frequency component. Use the difference method to calculate the displacement increment for the displacement data. For example, the surrounding rock deformation is small at 50 m ahead of the working face, and the roof-to-floor convergence rates on the solid coal side and the filling side are 9.2 mm / d and 9.5 mm / d respectively at 35 m, and the rib convergence rate is 5.2 mm / d. Use the cumulative summation method to calculate the total deformation amount for the deformation rate data. Align all the processed data according to the measuring points and time to generate a data table.

[0035] At step S103, perform principal component analysis and hierarchical clustering on the aligned data, divide the measuring points into three regions, establish corresponding prediction models respectively, and perform normalization processing on the calculation results of the models. This includes: using principal component analysis to extract the main change characteristics of the data of each measuring point and calculate the correlation coefficient between each measuring point; using hierarchical clustering to divide the measuring points into three regions: behind the stop line, above the extraction roadway, and above the coal wall of the working face; establish a prediction equation of the creep constitutive model for the region behind the stop line; establish a prediction equation of the viscoelastic-plastic constitutive model for the region above the extraction roadway; establish a prediction equation of the rheological damage coupling model for the region above the coal wall; perform normalization processing on the predicted values of the three regions to obtain the normalized predicted values.

[0036] Using principal component analysis to extract the main change characteristics of the data of each measuring point and calculate the correlation coefficient between each measuring point, including: subtract the measured mean value of the previous preset time period of each measuring point from the data of the roof pressure, bolt load, roof-to-floor convergence amount, and rib convergence amount of each measuring point and then divide by the standard deviation; construct a covariance matrix for the normalized data, calculate the eigenvalues and eigenvectors of the covariance matrix; select the eigenvectors with the cumulative contribution rate reaching the preset threshold as the principal components, and project the normalized data into the principal component space to obtain the principal component scores of each measuring point.

[0037] Using hierarchical clustering to divide the measuring points into three regions: behind the stop line, above the extraction roadway, and above the coal wall of the working face, including: calculate the Euclidean distance of the principal component scores based on the pressure, bolt load, roof-to-floor convergence amount, and rib convergence amount between any two measuring points; construct a distance matrix according to the Euclidean distance, and perform hierarchical clustering using the minimum variance; determine the optimal number of clusters by calculating the ratio of the inter-class distance to the intra-class distance, and divide the measuring points into the preset regions.

[0038] Establish a prediction equation for the creep constitutive model in the area behind the stop line, including: calculating the roof subsidence velocity and acceleration of the measuring points in the area behind the stop line; based on the creep relationship between the roof pressure and the roof-floor displacement, using historical data for nonlinear fitting to solve the instantaneous elastic modulus and viscosity coefficient; introducing the surrounding rock damage factor and establishing a surrounding rock damage equation containing plastic strain and critical strain; constructing a roof pressure prediction equation and substituting the measured data to solve the initial pressure.

[0039] Establish a prediction equation for the viscoelastic-plastic constitutive model in the area above the retreat roadway, including: establishing a viscoelastic relationship equation between the axial stress and displacement of the bolt, including the elastic modulus and viscosity coefficient; introducing a plastic damage term containing the softening coefficient and yield stress, and establishing a bolt load prediction equation, including the initial bolt load; using historical data for nonlinear least squares fitting to solve the elastic modulus, viscosity coefficient, softening coefficient and yield stress.

[0040] Establish a prediction equation for the rheological damage coupling model in the area above the coal wall, including: establishing a rheological equation between the stress concentration coefficient and time based on the convergence of the two sides, including the elastic modulus and viscosity coefficient; introducing a damage evolution equation, including the damage variable and material parameters, and establishing a stress concentration coefficient prediction equation, including the initial stress concentration coefficient; using historical data for nonlinear fitting to solve all parameters.

[0041] It should be noted that for identifying the failure characteristics of different positions of the surrounding rock, the currently widely used methods mainly include the deep learning method based on neural network, the classification method based on support vector machine, and the method based on grey system theory. Among them, the deep learning method based on neural network directly trains and predicts the monitoring data by constructing a multi-layer perceptron network structure. However, this method requires a large amount of historical data to train the model parameters, and it is often difficult to obtain sufficient training samples in a newly excavated mining face. The classification method based on support vector machine uses a kernel function to map the monitoring data to a high-dimensional feature space for classification and early warning. However, its essence is a classification algorithm based on statistics and cannot describe the physical mechanism of the surrounding rock deformation. The method based on grey system theory predicts the deformation trend of the surrounding rock by constructing a GM(1,1) model. However, this method assumes that the system has a quasi-exponential development trend, which does not conform to the segmented deformation characteristics of the surrounding rock in the actual mining process.

[0042] The common technical problems of these methods are as follows: they completely ignore the movement and fracture law of the overlying strata in the coal mining face and fail to establish corresponding mechanical models according to the deformation mechanism of surrounding rocks in different regions. The deformation of surrounding rocks under mining conditions is affected by multiple factors such as mining depth, mining thickness, and rock stratum structure, showing obvious spatio-temporal evolution and regional differences. For example, in the area behind the stop line, since the main roof rock stratum exists in the form of a cantilever beam, the deformation of the surrounding rock is mainly controlled by the rheological properties of the rock stratum; in the area above the withdrawal roadway, the direct roof stress causes obvious elastoplastic deformation of the surrounding rock; in the area above the coal wall, stress concentration causes progressive damage to the surrounding rock. These complex mechanical behaviors cannot be accurately described by a single data-driven model or a simple mathematical model. Therefore, it is necessary to establish prediction equations based on the Maxwell creep model, the Kelvin viscoelastic-plastic model, and the Burgers rheological damage coupling model respectively for the deformation mechanism of surrounding rocks in different regions, and depict the deformation evolution process of surrounding rocks from the level of physical mechanism. This zoning modeling method based on regional characteristics not only considers the mechanical mechanism of surrounding rock deformation under mining conditions but also calibrates the model parameters through measured data, overcoming the deficiencies of existing early warning methods at both the theoretical basis and engineering practice levels.

[0043] In one embodiment, for the data in the processed data table, the principal component analysis method is used to extract the main change characteristics of the data at each measuring point. Calculate the correlation coefficients between the pressure and stress at each measuring point, and the correlation coefficients between the displacement and deformation velocity. The hierarchical clustering method is used to classify the measuring point data, and the measuring points are divided into three regions: behind the stop line, above the withdrawal roadway, and above the coal wall of the working face. Mathematical models are established respectively for the measuring point data in each region: for the measuring points in the area behind the stop line, a cantilever beam stress model is established; for the measuring points in the area above the withdrawal roadway, a direct roof stress model is established; for the measuring points in the area above the coal wall, a rock stratum fracture model is established. The calculation results of the models in the three regions are normalized.

[0044] Furthermore, in another embodiment, first, the measured data is normalized. For the data of roof pressure, bolt load, roof-to-floor convergence, and rib convergence obtained for each measuring point, subtract the measurement mean value of the previous 168 hours at this measuring point and then divide by the standard deviation. A covariance matrix is constructed for the normalized data, and the eigenvalues and eigenvectors are calculated. Select the eigenvectors with a cumulative contribution rate reaching 92.7% as the principal components, and project the normalized data into the principal component space to obtain the principal component scores of each measuring point.

[0045] Cluster analysis is performed according to the spatial correlation between the measuring points. Calculate the Euclidean distance between any two measuring points i and j: , where P, L, D, and M respectively represent the principal component scores of pressure, bolt load, roof-to-floor convergence, and rib convergence, 、 , , is the corresponding standard deviation. After constructing the distance matrix, the Ward minimum variance method was used for hierarchical clustering. The optimal number of clusters was determined to be 3 by calculating the ratio of the inter-class distance to the intra-class distance. The measuring points were divided into three areas: behind the stop line, above the withdrawal channel, and above the coal wall of the working face.

[0046] For the measuring points in the rear area of ​​the stop mining line, a pressure has occurred before the working face advances to the predetermined position of the withdrawal channel and stops mining. When the withdrawal channel is connected, the next period of pressure in the mining field has not occurred. At this time, the old top rock beam overlying the withdrawal channel is in a stable stage. The structure of the overlying rock layer is as follows: Figure 2 As shown. After the working face stops mining and the overlying roof of the withdrawal channel stabilizes, the rock block A between the coal pillar of the withdrawal channel and the last old roof fracture position can be regarded as the overlying rock block that has an important influence on the activity of the withdrawal channel roof. At this moment, the overlying rock structure of the withdrawal channel can be approximately simplified to a L-long cantilever beam with one end fixed and the other end suspended. A prediction equation based on the Maxwell creep constitutive model can be established. First, calculate the roof sinking velocity vi and acceleration ai at time i in this area. Based on the roof pressure Displacement with top and bottom plates Maxwell creep relation: ,in is the instantaneous elastic modulus, is the viscosity coefficient, and t is the loading time. The measured data are solved by nonlinear fitting and Then the surrounding rock damage factor is introduced ,in is the plastic strain, is the critical strain, and is the material constant. Finally, the prediction equation of the roof pressure in this area is obtained: , represents the sinking speed of the top plate, that is, vi, Represents the sinking acceleration of the top plate, which is ai, and then substitute the historical data for the solution.

[0047] For the measuring points in the area above the withdrawal channel, when the exposed length of the old roof of the working face reaches the pressure step distance, another pressure will occur in the final mining stage. When the pressure step distance is small, the old roof will break above the withdrawal channel, and the spatial structure of the overburden will be as follows: Figure 3 As shown. In this structural state, the rock block B has a significant impact on the withdrawal channel and the support. And the length of the old top periodic pressure step of the overlying broken rock block B is the length L. A prediction equation based on the Kelvin viscoelastic-plastic constitutive model can be established. Anchor bolt axial stress The Kelvin model expression with displacement D is: , where is the elastic modulus, is the viscosity coefficient. Introduce the plastic damage term , where k is the softening coefficient, is the yield stress. Establish the bolt load prediction equation: , where is the initial bolt load. Conduct non - linear least - squares fitting on the measured data to solve the parameters , , k and .

[0048] For the measuring points in the area above the coal wall, when the weighting interval is large, the overlying main roof breaks above the coal wall in front of the working face, and the spatial structure of the overlying strata is as Figure 4 shown. The main roof breaks on the coal body in front of the retreat roadway. In this structural state, the rock block C with length L has a significant impact on the retreat roadway and its support. A prediction equation based on the Burgers rheological damage coupling model can be established. First, establish the Burgers creep equation of the stress concentration coefficient K and time t according to the convergence M of the two sides:

[0049] ;

[0050] where , are the elastic moduli, , are the viscosity coefficients. Introduce the damage evolution equation: , where is the damage variable, and A, n, m are material parameters. Finally, establish the stress concentration coefficient prediction equation: . Conduct non - linear fitting on the measured data to solve all parameters.

[0051] Normalize the predicted values of the three regions. For the area behind the stop line, normalize the predicted roof pressure value P to ; for the area above the retreat roadway, normalize the predicted bolt load value L to ; for the area above the coal wall, normalize the predicted stress concentration coefficient value K to . Where the subscripts min and max represent the minimum and maximum values of the predicted values of all measuring points in this region respectively. Finally, obtain the normalized predicted values of the measuring points in the three regions for the establishment of subsequent warning indicators.

[0052] At step S104, abnormal judgment parameters are set according to the normalization result, the warning index is calculated by weighted summation, and a warning signal is issued based on the comparison result between the warning index and the preset level threshold. This includes: setting judgment parameters for pressure abnormality, stress abnormality, displacement abnormality, and velocity abnormality; calculating the warning index of each measuring point by the weighted summation method, and the weight coefficient is determined through experimental calibration; dividing the warning index into preset levels according to the numerical value, and issuing a warning signal when the warning index exceeds the corresponding level threshold.

[0053] Specifically, according to the calculation result of the normalized model, warning parameters are set: when the measured pressure value of a measuring point is greater than 1.5 times the average pressure value of the previous 24 hours at this measuring point, it is recorded as pressure abnormality; when the measured stress value of a measuring point is greater than 1.8 times the average stress value of the previous 24 hours at this measuring point, it is recorded as stress abnormality; when the displacement increment of a measuring point is greater than 2.0 times the average displacement increment value of the previous 24 hours at this measuring point, it is recorded as displacement abnormality; when the deformation velocity of a measuring point is greater than 2.2 times the average deformation velocity value of the previous 24 hours at this measuring point, it is recorded as velocity abnormality. The warning index of each measuring point is calculated by the weighted summation method, and the weight coefficient is determined through experimental calibration. The warning index is divided into three levels according to the numerical value, and a warning signal is issued when the warning index exceeds the corresponding level threshold.

[0054] In one embodiment, taking a certain coal mine working face described above as an example: when the measured pressure value of a measuring point exceeds 1.5 times the average pressure value of the previous 24 hours at this point, it is recorded as pressure abnormality. For example, if the average pressure value of a certain measuring point in the previous 24 hours is 6.0 MPa, when the measured pressure value is greater than 9.0 MPa, it is recorded as abnormal; when the measured stress value of a measuring point exceeds 1.8 times the average stress value of the previous 24 hours at this point, it is recorded as stress abnormality. For example, if the average stress value of a certain measuring point in the previous 24 hours is 50 kN, when the measured stress value is greater than 90 kN, it is recorded as abnormal; when the displacement increment of a measuring point exceeds 2.0 times the average displacement increment value of the previous 24 hours at this point, it is recorded as displacement abnormality. For example, if the average displacement increment value of a certain measuring point in the previous 24 hours is 5 mm / d, when the measured displacement increment is greater than 10 mm / d, it is recorded as abnormal; when the deformation velocity of a measuring point exceeds 2.2 times the average deformation velocity value of the previous 24 hours at this point, it is recorded as velocity abnormality. For example, if the average deformation velocity value of a certain measuring point in the previous 24 hours is 8 mm / d, when the measured deformation velocity is greater than 17.6 mm / d, it is recorded as abnormal. The weight coefficients of each abnormal item are determined through on-site experimental calibration. The weights of pressure, stress, displacement, and velocity are 0.3, 0.3, 0.2, and 0.2 respectively. The warning index is divided into three levels in the range of 0 - 1.0. 0 - 0.6 is the first-level warning, 0.6 - 0.8 is the second-level warning, and 0.8 - 1.0 is the third-level warning.

[0055] Furthermore, an embodiment of the present application also discloses a surrounding rock failure warning device, including: a processor, a memory, and a system bus; the processor and the memory are connected through the system bus; the memory is used to store one or more programs, and the one or more programs include instructions that, when executed by the processor, cause the processor to execute any of the above methods.

[0056] Furthermore, an embodiment of the present application also discloses a computer program product that, when running on a terminal device, causes the terminal device to execute any of the above methods.

[0057] From the description of the above embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in each embodiment or some parts of the embodiments of the present application.

[0058] It should be noted that the various embodiments in this specification are described in a progressive manner, and the key point of each embodiment is to describe the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0059] It should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0060] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A surrounding rock damage early warning method based on multi-source data, characterized in that: include: A plurality of measuring stations are arranged at predetermined intervals along the retreat channel of the working face, and sensor groups are installed on the roof, solid coal wall, and filling bodies beside the roadway at the measuring stations; The collected data are processed using sliding average method, fast Fourier transform, difference and cumulative summation, and the processed data are aligned according to the measurement point location and time label; The aligned data are subjected to principal component analysis and hierarchical clustering, the measurement points are divided into three regions, corresponding prediction models are established respectively, and the model calculation results are normalized, including: The principal component analysis is used to extract the main variation characteristics of the data at each measuring point and calculate the correlation coefficient between the measuring points; Hierarchical clustering was used to divide the measuring points into three areas: behind the stop-mining line, above the withdrawal channel, and above the coal wall of the working face. The prediction equation of the creep constitutive model is established for the area behind the stop-mining line, including: calculating the roof sinking speed and acceleration of the measuring points in the area behind the stop-mining line; based on the creep relationship between the roof pressure and the displacement of the roof and floor, using historical data for nonlinear fitting to solve the instantaneous elastic modulus and viscosity coefficient; introducing the surrounding rock damage factor and establishing the surrounding rock damage equation including plastic strain and critical strain; constructing the roof pressure prediction equation and substituting the measured data into solving the initial pressure; The prediction equation of the viscoelastic-plastic constitutive model is established for the area above the retracement channel; The prediction equation of rheological damage coupling model is established for the area above the coal wall; The predicted values ​​of the three regions are normalized to obtain normalized predicted values; The abnormal judgment parameters are set according to the normalized processing results, the warning index is calculated by weighted summation, and the warning signal is issued based on the comparison result between the warning index and the preset level threshold.

2. The surrounding rock damage early warning method according to claim 1, characterized in that: in, A plurality of measuring stations are arranged at predetermined intervals along the retreat channel of the working face, and a sensor group is installed on the roof, solid coal wall, and filling body beside the roadway at the measuring station, including: Multiple measuring stations are arranged in sequence along the retreat channel of the working face at preset intervals, and each measuring station is equipped with a pressure sensor, an axial stress sensor, a displacement sensor and a velocity sensor; Pressure sensors are installed on the working face roof, solid coal wall and roadside filling respectively, and axial stress sensors are installed at the end measuring station; The measurement data of the sensor is collected and stored by a data collector to form a data file containing pressure, stress, displacement and deformation speed.

3. The surrounding rock damage early warning method according to claim 1, characterized in that: in, The collected data is processed using sliding average method, fast Fourier transform, difference and cumulative summation, and the processed data is aligned according to the measurement point location and time label, including: The collected pressure data are smoothed by the sliding average method, and the spatial distribution characteristics of the pressure data are fitted by the least square method; The fast Fourier transform method is used to calculate the spectrum characteristics of the anchor axial stress data and extract the main frequency component; The displacement data is subjected to differential method to calculate displacement increment and statistical time series characteristics; The cumulative deformation is calculated by using the cumulative summation method for the deformation velocity data; The processed data are aligned according to the measurement point locations and time tags to form a processed data table.

4. The surrounding rock damage early warning method according to claim 1, characterized in that: in, According to the normalized processing results, the abnormal judgment parameters are set, and the warning index is calculated by weighted summation. The warning signal is issued according to the comparison result between the warning index and the preset level threshold, including: Set the judgment parameters for pressure anomaly, stress anomaly, displacement anomaly and velocity anomaly; The weighted summation method is used to calculate the early warning index of each measuring point, and the weight coefficient is determined through experimental calibration; The warning index is divided into preset levels according to its numerical value, and a warning signal is issued when the warning index exceeds the corresponding level threshold.

5. The surrounding rock damage early warning method according to claim 1, characterized in that: in, The principal component analysis is used to extract the main change characteristics of the data at each measuring point and calculate the correlation coefficients between the measuring points, including: The roof pressure, anchor load, top and bottom plate displacement and two side displacement data of each measuring point are respectively deducted from the measurement mean value of the preset time period before the measuring point and then divided by the standard deviation; Constructing a covariance matrix for the normalized data, and calculating the eigenvalues ​​and eigenvectors of the covariance matrix; The eigenvectors whose cumulative contribution rate reaches the preset threshold are selected as principal components, and the normalized data are projected into the principal component space to obtain the principal component scores of each measuring point.

6. The surrounding rock damage early warning method according to claim 1, characterized in that: in, Hierarchical clustering is used to divide the measuring points into three areas: behind the stop-mining line, above the withdrawal channel, and above the coal wall of the working face, including: Calculate the Euclidean distance between any two measuring points based on the principal component scores of pressure, anchor load, top and bottom plate displacement, and two side displacement; Constructing a distance matrix according to the Euclidean distance, and performing hierarchical clustering using minimum variance; The optimal number of clusters is determined by calculating the ratio of inter-class distance to intra-class distance, and the measurement points are divided into preset areas.

7. The surrounding rock damage early warning method according to claim 1, characterized in that: in, The prediction equation of the viscoelastic-plastic constitutive model is established for the area above the retracement channel, including: Establish the viscoelastic relationship equation between the axial stress and displacement of the anchor rod, including the elastic modulus and viscosity coefficient; The plastic damage term including softening coefficient and yield stress is introduced, and the anchor load prediction equation including the initial anchor load is established; The elastic modulus, viscosity coefficient, softening coefficient and yield stress are solved by nonlinear least squares fitting using historical data.

8. The surrounding rock damage early warning method according to claim 1, characterized in that: in, The prediction equation of the rheological damage coupling model is established for the area above the coal wall, including: According to the displacement of the two sides, a rheological equation of stress concentration factor and time is established, including elastic modulus and viscosity coefficient; The damage evolution equation is introduced, including damage variables and material parameters, and the stress concentration factor prediction equation is established, including the initial stress concentration factor; All parameters are solved by nonlinear fitting using historical data.

Images