Intelligent evaluation method and system for stability of surrounding rock under influence of coal mining

Abstract

The present application belongs to the technical field of surrounding rock stability monitoring and evaluation, and particularly relates to a coal mining influenced surrounding rock stability intelligent evaluation method and system, which fuses a mining cumulative effect factor, a ground stress environment factor, a surrounding rock structure integrity factor and a support effective factor through a nonlinear product formula, truly reflects the synergistic hazard law of surrounding rock instability under the coupling action of multiple factors, simultaneously adopts a mixed form combining harmonic mean and coupling enhancement for a current comprehensive risk index, can effectively capture the risk jump phenomenon when deformation anomaly and hazard factors deteriorate at the same time, and adopts a situation prediction model fusing a grey prediction and a Markov chain, corrects the residual error of the grey prediction by the Markov chain, significantly reduces the prediction error of a single model, combines the instability probability calculated by a logistic regression, realizes the quantitative trend prediction of the surrounding rock stability within a certain time window in the future, and greatly improves the advance and accuracy of the early warning.

Description

Technical Field

[0001] This invention belongs to the field of surrounding rock stability monitoring and assessment technology, specifically relating to an intelligent assessment method and system for surrounding rock stability under the influence of coal mine mining. Background Technology

[0002] As coal mining extends to deeper levels and mining intensity increases, the destructive effect of mining disturbance on the surrounding rock underground becomes increasingly prominent. Safety accidents such as roadway spalling, roof collapse, and floor heave caused by the instability of the surrounding rock occur frequently. These accidents not only seriously threaten the lives of underground workers but also lead to the interruption of mining operations, significantly reduce coal mine production efficiency, and cause huge economic losses. Currently, there are still many technical bottlenecks in the field of coal mine mining surrounding rock stability assessment, which make it difficult to meet the refined and intelligent needs of safe production in deep coal mines. Existing methods for assessing the stability of surrounding rock have many limitations. On the one hand, most assessment schemes rely on a single monitoring indicator and fail to comprehensively integrate multiple risk factors such as the cumulative effect of mining, the geostress environment, the structural integrity of the surrounding rock, and the effectiveness of support. This results in one-sided assessment results that cannot truly reflect the actual state of the surrounding rock under the coupled effects of multiple mining factors. On the other hand, the core quantitative formulas in existing technologies are mostly conventional linear weighting or simple ratio calculations, lacking targeted innovation and failing to accurately depict the dynamic evolution of various risk factors during mining. This leads to low assessment accuracy and an inability to detect early signs of surrounding rock instability. Furthermore, existing assessment systems often suffer from a disconnect between assessment, prediction, early warning, and response. They can either only assess the current state and lack the ability to scientifically predict future trends, or the early warning levels are vaguely defined and lack clear differentiated response strategies, making it impossible to form a closed-loop management system.

[0003] To address the aforementioned issues, this application presents an intelligent assessment method and system for the stability of surrounding rock under the influence of coal mining. Summary of the Invention

[0004] To address the shortcomings of the prior art mentioned in the background section, this application proposes an intelligent assessment method and system for the stability of surrounding rock under the influence of coal mine mining. By integrating multi-source data such as microseismic monitoring, roadway deformation monitoring, anchor bolt stress monitoring, and mining advancement parameters, a dynamic evolution model of the mining stress field and a multi-dimensional risk assessment system are constructed. Combined with grey prediction and Markov chain analysis, the stability trend of surrounding rock is predicted, achieving accurate assessment and graded early warning of surrounding rock stability, thereby solving the problems in the background section.

[0005] Firstly, to achieve the above objectives, this application provides an intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining, which includes the following specific steps: Step 1: Obtain multi-source monitoring data of the surrounding rock under the influence of mining. The multi-source monitoring data includes microseismic monitoring data, roadway deformation monitoring data, anchor bolt stress monitoring data, and mining face advancement parameters. Step 2: Construct a dynamic evolution model of the mining-induced stress field based on the spatial distribution and energy release characteristics of microseismic events, and extract precursor features of surrounding rock fracturing; Step 3: Calculate the surrounding rock deformation anomaly index D based on tunnel deformation monitoring data and anchor bolt stress data; Step 4: Calculate the mining-induced risk index M of the surrounding rock based on the mining-induced cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor. Step 5: Based on the calculation results of the surrounding rock deformation anomaly index and the mining-induced risk index, calculate the current comprehensive risk index Rc of the surrounding rock. The formula for calculating the current comprehensive risk index Rc is: Where D is the abnormal deformation index of the surrounding rock, M is the mining-induced risk index, P is the coupling enhancement coefficient, with a value range of 0.1-0.3, and the value range of Rc is controlled within the interval (0,1) by truncation; Step 6: Construct a situation prediction model based on grey prediction and Markov chain, and output the future trend prediction index and instability probability; Step 7: Calculate the overall stability (SFC) of the surrounding rock based on the current comprehensive risk index, trend prediction index, and instability probability; Step 8: Based on the calculation results of the comprehensive stability of the surrounding rock, conduct graded early warning and implement differentiated treatment strategies.

[0006] Based on the above scheme, the preferred embodiment of obtaining multi-source monitoring data of the surrounding rock under the influence of mining includes the following steps: Step 11: Collect data on the occurrence time, three-dimensional spatial coordinates, energy release, and magnitude of microseismic events in real time using distributed microseismic monitoring instruments deployed underground; Step 12: Real-time data collection of roadway roof subsidence, sidewall convergence, floor bulge, instantaneous rate of change, and cumulative change of each index using fiber optic grating deformation sensors. Step 13: Collect the axial force, shear force and force change rate of the anchor bolts using an intelligent anchor bolt force gauge. The monitoring range covers all support anchor bolts within a 10-50m radius around the mining face. Step 14: Real-time data collection of advance speed, advance step distance, mining intensity, and working face dip angle using the mining parameter monitoring system; Step 15: Use an adaptive filtering algorithm to reduce noise in the monitoring data, use a density-based outlier detection algorithm to remove outlier data, use an improved interpolation algorithm to supplement missing data, and store the processed data in a distributed database.

[0007] Based on the above scheme, the preferred embodiment of constructing a dynamic evolution model of the mining-induced stress field based on the spatial distribution and energy release characteristics of microseismic events, and extracting precursor features of surrounding rock fracturing, includes the following steps: Step 21: Perform coordinate calibration on the spatial coordinates in the microseismic monitoring data, and use the DBSCAN spatial clustering algorithm to divide the concentrated areas of microseismic events; Step 22: Introduce a time decay factor to weight microseismic events by time, construct a time series of energy release intensity, and construct a dynamic evolution model of mining stress field by tracing the spatial migration trajectory of the center of each concentrated area of ​​microseismic events. Step 23: Based on the output results of the dynamic evolution model of mining stress field, and combined with the temporal changes of microseismic event energy, extract three types of precursor features of surrounding rock rupture, including the energy mutation threshold of microseismic events, the abnormal growth rate of microseismic frequency, and the mutation of migration rate of stress concentration area.

[0008] In a preferred embodiment based on the above scheme, the calculation of the surrounding rock deformation anomaly index D based on tunnel deformation monitoring data and anchor bolt stress data includes the following steps: Step 31: Standardize the roadway deformation monitoring data and anchor bolt force data using the range normalization method, and map each index to the (0, 1) interval; Step 32: Set the allowable threshold for each monitoring indicator and calculate the deviation rate of each indicator. The deviation rate is defined as the relative amount by which the monitored value exceeds the allowable threshold. When the value does not exceed the threshold, the deviation rate is 0. Step 33: Use the entropy weight method to determine the weight of each monitoring index, and obtain the surrounding rock deformation anomaly index D by weighted summation. The value range of the surrounding rock deformation anomaly index is (0, 1).

[0009] Based on the above scheme, the preferred formula for calculating the risk index M in step 4 is: Where F1, F2, F3, and F4 are the mining-induced cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor, respectively, with each factor taking values ​​in the range (0,1). W1, W2, W3, and W4 are the corresponding weight coefficients, determined by the analytic hierarchy process (AHP), and satisfying the following conditions: .

[0010] Based on the above scheme, the preferred quantification methods for the mining-induced cumulative effect factor, geostress environment factor, surrounding rock structure integrity factor, and support effectiveness factor are as follows: Cumulative effect factor Where V is the actual advance speed, V0 is the allowable advance speed, S is the cumulative advance step distance, and S0 is the safe cumulative advance step distance. The formula adopts a product form. When either speed or step distance exceeds the limit, the cumulative effect increases. When both exceed the limit, the effect approaches 1. Geostress Environmental Factors Where Qmax is the maximum principal stress value after mining and superposition, and Qcr is the critical failure stress value of the surrounding rock; Surrounding rock structural integrity factor Wherein, RQD is the rock quality index, Vp is the longitudinal wave velocity of the rock mass, and Vp0 is the longitudinal wave velocity of the intact rock block; Supporting effective factors Where Fa is the average actual force on the anchor bolt, F0 is the designed anchoring force of the anchor bolt, and K is the support sensitivity coefficient.

[0011] Based on the above scheme, the preferred embodiment of constructing a situation prediction model based on grey prediction and Markov chain, and outputting a future trend prediction index and instability probability, includes the following steps: Step 61: Using the current comprehensive risk index sequence of the past 7-30 days as input, construct the grey prediction model GM(1,1) to make preliminary predictions and obtain grey prediction values; Step 62: Divide the residual sequence between the gray predicted value and the actual value into several state intervals, calculate the state transition probability matrix, predict the residual state at the next moment based on the current residual state, take the mean residual value corresponding to the state to correct the gray predicted value, and obtain the future trend prediction index with a value range of (0, 1). Step 63: Calculate the instability probability using a Logistic regression model. The formula for calculating the instability probability is: Where PK is the probability of surrounding rock instability within a set future time window, with a value range of (0, 1), Rt is the future trend prediction index, Rc is the current comprehensive risk index, and a, b, and c are regression coefficients.

[0012] Based on the above scheme, the preferred formula for calculating the overall stability SFC in step 7 is: Among them, the comprehensive stability index ranges from (0, 1), and the larger the value, the higher the comprehensive stability of the surrounding rock. Rc is the current comprehensive risk index, Rt is the future trend prediction index, PK is the instability probability, and α is the stability sensitivity coefficient, with a value range of 1.0-3.0.

[0013] Based on the above-mentioned scheme, a graded early warning system is selected based on the calculation results of the comprehensive stability of the surrounding rock, and a differentiated treatment strategy is implemented. The specific steps are as follows: Step 81: Divide the warning levels into 4 categories based on the value of the Comprehensive Stability Index (SFC): When At the time, it was a Level 1 warning. At that time, it was a level-two warning. At the time, it was a level three warning. The alert level was Level 4. Step 82: For Level 1 early warning, maintain the regular monitoring frequency and continue normal mining operations; Step 83: Under Level 2 early warning, reduce the mining speed, increase monitoring frequency to once every 12 hours, and regularly inspect the support system; Step 84: Level 3 warning: Stop mining operations, evacuate workers, strengthen monitoring every 6 hours, and temporarily reinforce the surrounding rock. Step 85: Level 4 warning. Immediately stop all underground operations, evacuate all personnel from the mine, activate the emergency rescue plan, and carry out emergency reinforcement of the surrounding rock.

[0014] Secondly, this application provides an intelligent assessment system for the stability of surrounding rock under the influence of coal mining, which specifically includes: a data acquisition module, a data preprocessing module, a stress field modeling and precursor extraction module, a deformation anomaly index calculation module, a mining-induced risk index calculation module, a current comprehensive risk index calculation module, a situation prediction module, a comprehensive stability calculation module, a graded early warning module, a differentiated treatment module, and a database module; The data acquisition module is used to collect multi-source monitoring data in real time and transmit it to the data preprocessing module; The data preprocessing module is used to perform noise reduction, anomaly removal, normalization, and missing value supplementation on the monitoring data. The stress field modeling and precursor extraction module is used to construct a dynamic evolution model of the mining stress field and provide precursor features of surrounding rock fracture, and transmit the precursor features and stress field evolution data to the subsequent calculation module. The deformation anomaly index calculation module is used to calculate the surrounding rock deformation anomaly index. The mining-induced risk index calculation module is used to calculate the mining-induced risk index based on the mining cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor, according to the formula in step 4, and transmit the calculation results to the current comprehensive risk index calculation module. The current comprehensive risk index calculation module is used to integrate the surrounding rock deformation anomaly index and the mining-induced risk index, calculate the current comprehensive risk index according to the formula in step 5, and transmit the calculation results to the situation prediction module and the comprehensive stability calculation module. The situation prediction module is used to construct a situation prediction model and output a trend prediction index and instability probability, and transmit the prediction results to the comprehensive stability calculation module. The comprehensive stability calculation module is used to calculate the comprehensive stability index based on the current comprehensive risk index, trend prediction index and instability probability, according to the formula in step 7, to determine the stability level, and transmit the result to the graded early warning module. The graded early warning module is used to classify early warning levels and generate early warning information; The differentiated processing module is used to execute differentiated processing strategies; The database module adopts a distributed database design to store multi-source monitoring data, preprocessed data, calculation results of various indices, prediction results, early warning information, disposal plans and disposal files. It supports data querying, updating, backup and export, providing data support for subsequent evaluation, optimization and data analysis. It also includes a human-computer interaction module, which is used to display the working status, data and results of each module, and supports managers to manually input parameters, adjust weight coefficients, view historical data and disposal files. The intelligent rock stability assessment system also supports docking with the existing safety production management system of coal mines to achieve data sharing and linkage control.

[0015] Thirdly, this application provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the aforementioned intelligent assessment method for the stability of surrounding rock under the influence of coal mining by calling the computer program stored in the memory.

[0016] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining as described above.

[0017] Compared with the prior art, the beneficial effects of the present invention are: First, this invention achieves deep integration of multi-source monitoring information on mining-induced surrounding rock by simultaneously collecting four types of data: microseismic data, roadway deformation data, anchor bolt stress data, and mining advance parameters. This overcomes the data silo problem inherent in traditional single-indicator monitoring and enables comprehensive perception of the surrounding rock state from multiple dimensions, including stress field, displacement field, support force field, and mining intensity. This lays a solid data foundation for accurate assessment. Furthermore, this invention constructs a dynamic evolution model of the mining-induced stress field based on spatial clustering and time-weighted energy release of microseismic events. This model can quantitatively track the migration trajectory of the stress peak area as the working face advances and extract various precursor features of surrounding rock fracture, such as energy mutations, frequency anomalies, and sudden changes in the migration rate of stress concentration areas. This represents a leap from post-event response to pre-event warning.

[0018] Secondly, this invention integrates mining-induced cumulative effect factors, geostress environment factors, surrounding rock structural integrity factors, and support effectiveness factors through a nonlinear multiplicative formula, truly reflecting the synergistic risk-causing law of surrounding rock instability under the coupled effects of multiple factors. Simultaneously, the current comprehensive risk index adopts a hybrid form combining harmonic averaging and coupled enhancement, effectively capturing the risk surge phenomenon when deformation anomalies and risk-causing factors simultaneously worsen, exhibiting higher risk sensitivity than conventional linear weighted methods. Furthermore, this invention employs a situation prediction model that integrates grey prediction and Markov chain analysis. By using Markov chain analysis to correct the residuals of grey prediction, the prediction error of a single model is significantly reduced. Combined with the instability probability calculated by logistic regression, a quantitative trend prediction of surrounding rock stability within a certain time window is achieved, greatly improving the lead time and accuracy of early warnings.

[0019] Third, this invention maps the current comprehensive risk index, trend prediction index, and instability probability into a comprehensive stability index through an exponential decay model. This index is monotonic, smooth, and strictly bounded. Based on this, the four-level early warning system and differentiated handling strategies form a complete closed loop of monitoring-assessment-prediction-early warning-handling, which can directly guide on-site safety production management. Moreover, the assessment system provided by this invention adopts a modular architecture, supports human-computer interaction and dynamic parameter adjustment, and can flexibly adjust the weight coefficients and early warning thresholds according to the actual working conditions of the mine. It can also be connected with the existing safety production management system of the coal mine, and has good engineering adaptability and promotion and application value. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the overall process of the intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining, as described in this invention. Figure 2 This is a flowchart of the intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining, as described in this invention. Figure 3 This is a schematic diagram of the framework of the intelligent assessment system for the stability of surrounding rock under the influence of coal mine mining, as per the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1 To address the technical problems raised in the background art, this application provides a preferred embodiment: such as Figures 1-3 As shown, the intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining includes the following specific steps: Step 1: Obtain multi-source monitoring data of the surrounding rock under the influence of mining. The multi-source monitoring data includes microseismic monitoring data, roadway deformation monitoring data, anchor bolt stress monitoring data, and mining face advancement parameters. Step 2: Construct a dynamic evolution model of the mining-induced stress field based on the spatial distribution and energy release characteristics of microseismic events, and extract precursor features of surrounding rock fracturing; Step 3: Calculate the surrounding rock deformation anomaly index D based on tunnel deformation monitoring data and anchor bolt stress data; Step 4: Calculate the mining-induced risk index M of the surrounding rock based on the mining-induced cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor. Step 5: Based on the calculation results of the surrounding rock deformation anomaly index and the mining-induced risk index, calculate the current comprehensive risk index Rc of the surrounding rock. The formula for calculating the current comprehensive risk index Rc is: Where D is the abnormal deformation index of the surrounding rock, M is the mining-induced risk index, P is the coupling enhancement coefficient, with a value range of 0.1-0.3, and the value range of Rc is controlled within the interval (0,1) by truncation; It should be noted that the current comprehensive risk index formula adopts a hybrid form combining harmonic mean and coupling enhancement, which has the following advantages: First, the harmonic mean better reflects the synergistic effect of the two indices than the arithmetic mean, and the result is more prominent when both are large; second, the coupling enhancement factor... It generates additional increments when D and M are both at moderately high levels, effectively capturing the phenomenon of risk leap; thirdly, the overall form ensures that the Rc value range is between 0 and 1, and the response to input changes is smooth and continuous.

[0023] Step 6: Construct a situation prediction model based on grey prediction and Markov chain, and output the future trend prediction index and instability probability; Step 7: Calculate the overall stability (SFC) of the surrounding rock based on the current comprehensive risk index, trend prediction index, and instability probability; Step 8: Based on the calculation results of the comprehensive stability of the surrounding rock, conduct graded early warning and implement differentiated treatment strategies.

[0024] The advantages of this embodiment compared to the prior art are as follows: By integrating multi-source data such as microseismic monitoring, roadway deformation monitoring, anchor bolt stress monitoring, and mining advancement parameters, a dynamic evolution model of mining-induced stress field and a multi-dimensional risk assessment system are constructed. By combining grey prediction and Markov chain to predict the trend of surrounding rock stability, accurate assessment and graded early warning of surrounding rock stability can be achieved, which can significantly reduce the prediction error of a single model. By combining the instability probability calculated by logistic regression, quantitative trend prediction of surrounding rock stability within a certain time window in the future can be achieved, greatly improving the lead time and accuracy of early warning.

[0025] Furthermore: In an optional embodiment, acquiring multi-source monitoring data of the surrounding rock under the influence of mining includes the following steps: Step 11: Collect data on the occurrence time, three-dimensional spatial coordinates, energy release, and magnitude of microseismic events in real time using distributed microseismic monitoring instruments deployed underground; Step 12: Real-time data collection of roadway roof subsidence, sidewall convergence, floor bulge, instantaneous rate of change, and cumulative change of each index using fiber optic grating deformation sensors. Step 13: Collect the axial force, shear force and force change rate of the anchor bolts using an intelligent anchor bolt force gauge. The monitoring range covers all support anchor bolts within a 10-50m radius around the mining face. Step 14: Real-time data collection of advance speed, advance step distance, mining intensity, and working face dip angle using the mining parameter monitoring system; Step 15: Use an adaptive filtering algorithm to reduce noise in the monitoring data, use a density-based outlier detection algorithm to remove outlier data, use an improved interpolation algorithm to supplement missing data, and store the processed data in a distributed database.

[0026] In an optional embodiment, a dynamic evolution model of the mining-induced stress field is constructed based on the spatial distribution and energy release characteristics of microseismic events, and precursor features of surrounding rock fracturing are extracted, including the following steps: Step 21: Perform coordinate calibration on the spatial coordinates in the microseismic monitoring data, and use the DBSCAN spatial clustering algorithm to divide the concentrated areas of microseismic events; Step 22: Introduce a time decay factor to weight microseismic events by time, construct a time series of energy release intensity, and construct a dynamic evolution model of mining stress field by tracing the spatial migration trajectory of the center of each concentrated area of ​​microseismic events. Step 23: Based on the output results of the dynamic evolution model of mining stress field, and combined with the temporal changes of microseismic event energy, extract three types of precursor features of surrounding rock rupture, including the energy mutation threshold of microseismic events, the abnormal growth rate of microseismic frequency, and the mutation of migration rate of stress concentration area.

[0027] Furthermore: In an optional embodiment, the surrounding rock deformation anomaly index D is calculated based on tunnel deformation monitoring data and anchor bolt stress data, including the following steps: Step 31: Standardize the roadway deformation monitoring data and anchor bolt force data using the range normalization method, and map each index to the (0, 1) interval; Step 32: Set the allowable threshold for each monitoring indicator and calculate the deviation rate of each indicator. The deviation rate is defined as the relative amount by which the monitored value exceeds the allowable threshold. When the value does not exceed the threshold, the deviation rate is 0. Step 33: Use the entropy weight method to determine the weight of each monitoring index, and obtain the surrounding rock deformation anomaly index D by weighted summation. The value range of the surrounding rock deformation anomaly index is (0, 1).

[0028] In an optional embodiment, the formula for calculating the risk index M in step 4 is as follows: Where F1, F2, F3, and F4 are the mining-induced cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor, respectively, with each factor taking values ​​in the range (0,1). W1, W2, W3, and W4 are the corresponding weight coefficients, determined by the analytic hierarchy process (AHP), and satisfying the following conditions: .

[0029] It should be noted that the risk-inducing index formula adopts a product-type nonlinear fusion in the form of joint probability, which has the following advantages: First, any factor can contribute to risk when it acts alone, and it will not be masked by other factors being zero; second, when multiple factors act together, the degree of risk tends to be close to 1 but will never exceed 1, which conforms to the physical constraint that risk cannot increase indefinitely; third, it can better reflect the synergistic risk-inducing effect of multi-factor coupling than conventional linear weighting, and avoids the over-limit or underestimation problems that may occur in linear superposition.

[0030] In an optional embodiment, the quantification methods for the mining cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor are as follows: Cumulative effect factor Where V is the actual advance speed, V0 is the allowable advance speed, S is the cumulative advance step distance, and S0 is the safe cumulative advance step distance. The formula adopts a product form. When either speed or step distance exceeds the limit, the cumulative effect increases. When both exceed the limit, the effect approaches 1. Geostress Environmental Factors Where Qmax is the maximum principal stress value after mining and superposition, and Qcr is the critical failure stress value of the surrounding rock; Surrounding rock structural integrity factor Wherein, RQD is the rock quality index, Vp is the longitudinal wave velocity of the rock mass, and Vp0 is the longitudinal wave velocity of the intact rock block; Supporting effective factors Where Fa is the average actual force on the anchor bolt, F0 is the designed anchoring force of the anchor bolt, and K is the support sensitivity coefficient.

[0031] It should be noted that the formula for the cumulative effect factor of mining adopts the product of the speed ratio and the step distance ratio, and is truncated with an upper limit of 1. This has the following advantages: First, the form is extremely simple, requiring only two easily obtainable mining parameters for calculation, which facilitates rapid application in engineering sites; second, the product form reflects the cumulative amplification effect of the advance speed and cumulative advance distance on the surrounding rock disturbance, and the factor increases rapidly when both increase simultaneously; third, the upper limit truncation ensures that the physical meaning of the factor is clear and will not produce meaningless values ​​greater than 1 due to exceeding the limit. The formula for geostress environment factor adopts a truncation form based on the ratio of maximum principal stress to critical failure stress, which has the following advantages: First, it is based on the physical criteria for surrounding rock failure, with sufficient theoretical basis; second, only one key stress ratio is needed to reflect the degree of danger of geostress environment, making the calculation simple; third, the truncation process ensures the standardization of factor value range, which facilitates subsequent fusion. The formula for the structural integrity factor of surrounding rock integrates two classic integrity indices: rock quality index and rock mass wave velocity ratio. It has the following advantages: First, it considers both the degree of development of structural planes and the physical and mechanical properties of rock mass, providing more comprehensive information. Second, the product form amplifies the deterioration effect of the two indices, more realistically reflecting the instability tendency of fractured surrounding rock. Third, the factor value decreases from 1 to 0 as integrity decreases, making the physical meaning intuitive. The formula for the effective support factor adopts an exponential decay function, which has the following advantages: First, when the anchor bolt force is much lower than the design value, the factor approaches 0, and the support effect is ideal; second, when the anchor bolt force is close to the design value, the factor rises rapidly, reflecting the critical state of impending support failure; third, the exponential form makes the factor nonlinearly sensitive to changes in the force ratio, and the sensitivity can be flexibly adjusted by the coefficient K to adapt to different support forms.

[0032] In an optional embodiment, a situation prediction model is constructed based on grey prediction and Markov chain, outputting a future trend prediction index and an instability probability. The specific steps are as follows: Step 61: Using the current comprehensive risk index sequence of the past 7-30 days as input, construct the grey prediction model GM(1,1) to make preliminary predictions and obtain grey prediction values; Step 62: Divide the residual sequence between the gray predicted value and the actual value into several state intervals, calculate the state transition probability matrix, predict the residual state at the next moment based on the current residual state, take the mean residual value corresponding to the state to correct the gray predicted value, and obtain the future trend prediction index with a value range of (0, 1). Step 63: Calculate the instability probability using a Logistic regression model. The formula for calculating the instability probability is: Where PK is the probability of surrounding rock instability within a set future time window, with a value range of (0, 1), Rt is the future trend prediction index, Rc is the current comprehensive risk index, and a, b, and c are regression coefficients.

[0033] It should be noted that the formula for calculating the instability probability uses the standard Logistic function, which has the following advantages: First, the S-shaped curve naturally maps the linear combination to the (0,1) probability interval, and the output has a clear probability meaning; second, the regression coefficients can be fitted through historical data to achieve adaptive calibration of the model; and third, the function form is mature and stable, and has been widely verified to be suitable for binary classification probability prediction problems.

[0034] In an optional embodiment, the formula for calculating the comprehensive stability SFC in step 7 is: Among them, the comprehensive stability index ranges from (0, 1), and the larger the value, the higher the comprehensive stability of the surrounding rock. Rc is the current comprehensive risk index, Rt is the future trend prediction index, PK is the instability probability, and α is the stability sensitivity coefficient, with a value range of 1.0-3.0.

[0035] It should be noted that the calculation formula for the comprehensive stability SFC adopts an exponential decay model, which has the following advantages: First, the exponential function maps the risk weighting and monotonically to a stability index, and the larger the value, the more stable it is, which is clear from a physical intuition; Second, the output is strictly within the (0,1) interval and will not have negative values ​​or exceed the limit; Third, the exponential decay rate can be adjusted by the stability sensitivity coefficient α, which is convenient for adjusting the early warning sensitivity according to different surrounding rock conditions; Fourth, it is naturally matched with the threshold division of subsequent graded early warning, which is convenient for engineering implementation.

[0036] In an optional embodiment, a graded early warning is performed based on the calculation results of the comprehensive stability of the surrounding rock, and a differentiated treatment strategy is implemented. The specific steps are as follows: Step 81: Divide the warning levels into 4 categories based on the value of the Comprehensive Stability Index (SFC): When At the time, it was a Level 1 warning. At that time, it was a level-two warning. At the time, it was a level three warning. The alert level was Level 4. Step 82: For Level 1 early warning, maintain the regular monitoring frequency and continue normal mining operations; Step 83: Under Level 2 early warning, reduce the mining speed, increase monitoring frequency to once every 12 hours, and regularly inspect the support system; Step 84: Level 3 warning: Stop mining operations, evacuate workers, strengthen monitoring every 6 hours, and temporarily reinforce the surrounding rock. Step 85: Level 4 warning. Immediately stop all underground operations, evacuate all personnel from the mine, activate the emergency rescue plan, and carry out emergency reinforcement of the surrounding rock.

[0037] Example 2 Based on the same inventive concept as in Embodiment 1, such as Figure 3 As shown, this embodiment provides an intelligent assessment system for the stability of surrounding rock under the influence of coal mine mining, which specifically includes: a data acquisition module, a data preprocessing module, a stress field modeling and precursor extraction module, a deformation anomaly index calculation module, a mining-induced risk index calculation module, a current comprehensive risk index calculation module, a situation prediction module, a comprehensive stability calculation module, a graded early warning module, a differentiated treatment module, and a database module; The data acquisition module is used to collect multi-source monitoring data in real time and transmit it to the data preprocessing module; The data preprocessing module is used to perform noise reduction, anomaly removal, normalization, and missing value supplementation on the monitoring data; The stress field modeling and precursor extraction module is used to construct a dynamic evolution model of the mining-induced stress field and provide precursor features of surrounding rock fracture, and transmit the precursor features and stress field evolution data to the subsequent calculation module; The deformation anomaly index calculation module is used to calculate the deformation anomaly index of the surrounding rock; The mining-induced risk index calculation module is used to calculate the mining-induced risk index based on the mining cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor, according to the formula in step 4, and then transmit the calculation results to the current comprehensive risk index calculation module. The current comprehensive risk index calculation module is used to integrate the surrounding rock deformation anomaly index and the mining-induced risk index, calculate the current comprehensive risk index according to the formula in step 5, and transmit the calculation results to the situation prediction module and the comprehensive stability calculation module. The situation prediction module is used to build a situation prediction model and output the trend prediction index and instability probability, and transmit the prediction results to the comprehensive stability calculation module. The comprehensive stability calculation module is used to calculate the comprehensive stability index based on the current comprehensive risk index, trend prediction index and instability probability, according to the formula in step 7, to determine the stability level, and transmit the results to the graded early warning module. The tiered early warning module is used to classify early warning levels and generate early warning information; The differentiated handling module is used to execute differentiated handling strategies; The database module adopts a distributed database design to store multi-source monitoring data, preprocessed data, calculation results of various indices, prediction results, early warning information, disposal plans and disposal files. It supports data querying, updating, backup and export, providing data support for subsequent evaluation, optimization and data analysis. It also includes a human-computer interaction module, which displays the working status, data and results of each module, and supports managers to manually input parameters, adjust weight coefficients, view historical data and disposal records. The intelligent rock stability assessment system also supports docking with the existing safety production management system of coal mines to achieve data sharing and joint control.

[0038] The steps for implementing the corresponding functions of each parameter and each unit module in the intelligent assessment system for the stability of surrounding rock under the influence of coal mining of the present invention can be referred to the parameters and steps in the embodiments of the intelligent assessment method for the stability of surrounding rock under the influence of coal mining mentioned above, and will not be repeated here.

[0039] Example 3 Based on the same inventive concept as Embodiment 1, this embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the aforementioned intelligent assessment method for the stability of surrounding rock under the influence of coal mining by calling the computer program stored in the memory.

[0040] It should be noted that all computer programs for the intelligent assessment method of surrounding rock stability under the influence of coal mine mining are implemented in C language.

[0041] Example 4 Based on the same inventive concept as in Embodiment 1, this embodiment proposes a computer-readable storage medium having an erasable and rewritable computer program stored thereon. When the computer program runs on the computer device, it enables the computer device to perform the aforementioned intelligent assessment method for the stability of surrounding rock under the influence of coal mining.

[0042] For example, computer-readable storage media can be read-only memory, random access memory, read-only optical disc, magnetic tape, floppy disk, and optical data storage devices.

[0043] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, the embodiments for IoT devices and media are relatively simple in description because they are fundamentally similar to the method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0044] The systems, media, and methods provided in the embodiments of the present invention are in one-to-one correspondence. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0045] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0049] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0050] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0051] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0052] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. An intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining, characterized in that, Includes the following steps: Step 1: Obtain multi-source monitoring data of the surrounding rock under the influence of mining. The multi-source monitoring data includes microseismic monitoring data, roadway deformation monitoring data, anchor bolt stress monitoring data, and mining face advancement parameters. Step 2: Construct a dynamic evolution model of the mining-induced stress field based on the spatial distribution and energy release characteristics of microseismic events, and extract precursor features of surrounding rock fracturing; Step 3: Calculate the surrounding rock deformation anomaly index D based on tunnel deformation monitoring data and anchor bolt stress data; Step 4: Calculate the mining-induced risk index M of the surrounding rock based on the mining-induced cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor. Step 5: Based on the calculation results of the surrounding rock deformation anomaly index and the mining-induced risk index, calculate the current comprehensive risk index Rc of the surrounding rock. The formula for calculating the current comprehensive risk index Rc is: Where D is the abnormal deformation index of the surrounding rock, M is the mining-induced risk index, P is the coupling enhancement coefficient, with a value range of 0.1-0.3, and the value range of Rc is controlled within the interval (0,1) by truncation; Step 6: Construct a situation prediction model based on grey prediction and Markov chain, and output the future trend prediction index and instability probability; Step 7: Calculate the overall stability (SFC) of the surrounding rock based on the current comprehensive risk index, trend prediction index, and instability probability; Step 8: Based on the calculation results of the comprehensive stability of the surrounding rock, conduct graded early warning and implement differentiated treatment strategies.

2. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 1, characterized in that: The acquisition of multi-source monitoring data of the surrounding rock under the influence of mining includes the following steps: Step 11: Collect data on the occurrence time, three-dimensional spatial coordinates, energy release, and magnitude of microseismic events in real time using distributed microseismic monitoring instruments deployed underground; Step 12: Real-time data collection of roadway roof subsidence, sidewall convergence, floor bulge, instantaneous rate of change, and cumulative change of each index using fiber optic grating deformation sensors. Step 13: Collect the axial force, shear force and force change rate of the anchor bolts using an intelligent anchor bolt force gauge. The monitoring range covers all support anchor bolts within a 10-50m radius around the mining face. Step 14: Real-time data collection of advance speed, advance step distance, mining intensity, and working face dip angle using the mining parameter monitoring system; Step 15: Use an adaptive filtering algorithm to reduce noise in the monitoring data, use a density-based outlier detection algorithm to remove outlier data, use an improved interpolation algorithm to supplement missing data, and store the processed data in a distributed database.

3. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 2, characterized in that: The method for constructing a dynamic evolution model of the mining-induced stress field based on the spatial distribution and energy release characteristics of microseismic events, and extracting precursor features of surrounding rock fracturing, includes the following steps: Step 21: Perform coordinate calibration on the spatial coordinates in the microseismic monitoring data, and use the DBSCAN spatial clustering algorithm to divide the concentrated areas of microseismic events; Step 22: Introduce a time decay factor to weight microseismic events by time, construct a time series of energy release intensity, and construct a dynamic evolution model of mining stress field by tracing the spatial migration trajectory of the center of each concentrated area of ​​microseismic events. Step 23: Based on the output results of the dynamic evolution model of mining stress field, and combined with the temporal changes of microseismic event energy, extract three types of precursor features of surrounding rock rupture, including the energy mutation threshold of microseismic events, the abnormal growth rate of microseismic frequency, and the mutation of migration rate of stress concentration area.

4. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 3, characterized in that: The calculation of the surrounding rock deformation anomaly index D based on tunnel deformation monitoring data and anchor bolt stress data includes the following steps: Step 31: Standardize the roadway deformation monitoring data and anchor bolt force data using the range normalization method, and map each index to the (0, 1) interval; Step 32: Set the allowable threshold for each monitoring indicator and calculate the deviation rate of each indicator. The deviation rate is defined as the relative amount by which the monitored value exceeds the allowable threshold. When the value does not exceed the threshold, the deviation rate is 0. Step 33: Use the entropy weight method to determine the weight of each monitoring index, and obtain the surrounding rock deformation anomaly index D by weighted summation. The value range of the surrounding rock deformation anomaly index is (0, 1).

5. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 4, characterized in that: The formula for calculating the risk index M in step 4 is as follows: Where F1, F2, F3, and F4 are the mining-induced cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor, respectively, with each factor taking values ​​in the range (0,1). W1, W2, W3, and W4 are the corresponding weight coefficients, determined by the analytic hierarchy process (AHP), and satisfying the following conditions: .

6. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 5, characterized in that: The quantification methods for the mining cumulative effect factor, geostress environment factor, surrounding rock structure integrity factor, and support effectiveness factor are as follows: Cumulative effect factor Where V is the actual advance speed, V0 is the allowable advance speed, S is the cumulative advance step distance, and S0 is the safe cumulative advance step distance. The formula adopts a product form. When either speed or step distance exceeds the limit, the cumulative effect increases. When both exceed the limit, the effect approaches 1. Geostress Environmental Factors Where Qmax is the maximum principal stress value after mining and superposition, and Qcr is the critical failure stress value of the surrounding rock; Surrounding rock structural integrity factor Wherein, RQD is the rock quality index, Vp is the longitudinal wave velocity of the rock mass, and Vp0 is the longitudinal wave velocity of the intact rock block; Supporting effective factors Where Fa is the average actual force on the anchor bolt, F0 is the designed anchoring force of the anchor bolt, and K is the support sensitivity coefficient.

7. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 6, characterized in that: The specific steps for constructing a situation prediction model based on grey prediction and Markov chain, which outputs a future trend prediction index and instability probability, are as follows: Step 61: Using the current comprehensive risk index sequence of the past 7-30 days as input, construct the grey prediction model GM(1,1) to make preliminary predictions and obtain grey prediction values; Step 62: Divide the residual sequence between the gray predicted value and the actual value into several state intervals, calculate the state transition probability matrix, predict the residual state at the next moment based on the current residual state, take the mean residual value corresponding to the state to correct the gray predicted value, and obtain the future trend prediction index with a value range of (0, 1). Step 63: Calculate the instability probability using a Logistic regression model. The formula for calculating the instability probability is: Where PK is the probability of surrounding rock instability within a set future time window, with a value range of (0, 1), Rt is the future trend prediction index, Rc is the current comprehensive risk index, and a, b, and c are regression coefficients.

8. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 7, characterized in that: The formula for calculating the overall stability SFC in step 7 is as follows: Among them, the comprehensive stability index ranges from (0, 1), and the larger the value, the higher the comprehensive stability of the surrounding rock. Rc is the current comprehensive risk index, Rt is the future trend prediction index, PK is the instability probability, and α is the stability sensitivity coefficient, with a value range of 1.0-3.

0.

9. The intelligent assessment method for surrounding rock stability under the influence of coal mine mining as described in claim 8, characterized in that: Based on the calculation results of the comprehensive stability of the surrounding rock, a graded early warning system is established, and differentiated treatment strategies are implemented. The specific steps are as follows: Step 81: Divide the warning levels into 4 categories based on the value of the Comprehensive Stability Index (SFC): When At the time, it was a Level 1 warning. At that time, it was a level-two warning. At the time, it was a level three warning. The alert level was Level 4. Step 82: For Level 1 early warning, maintain the regular monitoring frequency and continue normal mining operations; Step 83: Under Level 2 early warning, reduce the mining speed, increase monitoring frequency to once every 12 hours, and regularly inspect the support system; Step 84: Level 3 warning: Stop mining operations, evacuate workers, strengthen monitoring every 6 hours, and temporarily reinforce the surrounding rock. Step 85: Level 4 warning. Immediately stop all underground operations, evacuate all personnel from the mine, activate the emergency rescue plan, and carry out emergency reinforcement of the surrounding rock.

10. An intelligent assessment system for the stability of surrounding rock under the influence of coal mine mining, which is based on the intelligent assessment method for the stability of surrounding rock under the influence of coal mine mining as described in any one of claims 1-9, characterized in that, Specifically, it includes: a data acquisition module, a data preprocessing module, a stress field modeling and precursor extraction module, a deformation anomaly index calculation module, a mining-induced risk index calculation module, a current comprehensive risk index calculation module, a situation prediction module, a comprehensive stability calculation module, a graded early warning module, a differentiated handling module, and a database module; The data acquisition module is used to collect multi-source monitoring data in real time and transmit it to the data preprocessing module; The data preprocessing module is used to perform noise reduction, anomaly removal, normalization, and missing value supplementation on the monitoring data. The stress field modeling and precursor extraction module is used to construct a dynamic evolution model of the mining stress field and provide precursor features of surrounding rock fracture, and transmit the precursor features and stress field evolution data to the subsequent calculation module. The deformation anomaly index calculation module is used to calculate the surrounding rock deformation anomaly index. The mining-induced risk index calculation module is used to calculate the mining-induced risk index based on the mining cumulative effect factor, the geostress environment factor, the surrounding rock structure integrity factor, and the support effectiveness factor, according to the formula in step 4, and transmit the calculation results to the current comprehensive risk index calculation module. The current comprehensive risk index calculation module is used to integrate the surrounding rock deformation anomaly index and the mining-induced risk index, calculate the current comprehensive risk index according to the formula in step 5, and transmit the calculation results to the situation prediction module and the comprehensive stability calculation module. The situation prediction module is used to construct a situation prediction model and output a trend prediction index and instability probability, and transmit the prediction results to the comprehensive stability calculation module. The comprehensive stability calculation module is used to calculate the comprehensive stability index based on the current comprehensive risk index, trend prediction index and instability probability, according to the formula in step 7, to determine the stability level, and transmit the result to the graded early warning module. The graded early warning module is used to classify early warning levels and generate early warning information; The differentiated processing module is used to execute differentiated processing strategies; The database module adopts a distributed database design to store multi-source monitoring data, preprocessed data, calculation results of various indices, prediction results, early warning information, disposal plans and disposal files. It supports data querying, updating, backup and export, providing data support for subsequent evaluation, optimization and data analysis. It also includes a human-computer interaction module, which is used to display the working status, data and results of each module, and supports managers to manually input parameters, adjust weight coefficients, view historical data and disposal files. The intelligent rock stability assessment system also supports docking with the existing safety production management system of coal mines to achieve data sharing and linkage control.

11. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor, characterized in that: the processor executes the intelligent assessment method for the stability of surrounding rock under the influence of coal mining as described in any one of claims 1-9 by calling the computer program stored in the memory.

12. A computer-readable storage medium, characterized in that: The system stores instructions that, when executed on a computer, cause the computer to perform the intelligent assessment method for the stability of surrounding rock under the influence of coal mining as described in any one of claims 1-9.

Images