Coal mine fault water control and scouring whole domain real-time early warning system

Abstract

This invention discloses a real-time, comprehensive early warning system for water inrush and rockburst prevention in coal mines caused by mining, belonging to the field of coal mine safety monitoring technology. Addressing the problems of large spatial blind spots, delayed dynamic response of seepage fields, and insufficient early warning accuracy in existing monitoring technologies, this system utilizes a comprehensive sensor array to perform real-time, three-dimensional monitoring of seepage and mechanical parameters in the fault zone of the mining area. It employs a seepage-dominated coupling analysis module to fuse multi-source data, dynamically allocates monitoring weights using the entropy weight method, and calculates fault water conductivity and comprehensive risk indicators. Based on a three-level early warning mechanism, the system issues real-time warning signals according to the risk level and can be linked with mine safety control devices to execute emergency responses. This invention achieves comprehensive, real-time, and intelligent early warning for water inrush and rockburst disasters induced by fault activation, significantly improving the proactive prevention and control capabilities and safety assurance level during coal mining.

Description

Technical Field

[0001] This invention relates to the field of coal mine safety and geological disaster monitoring and early warning technology, specifically to a real-time early warning system for controlling water and preventing erosion in coal mine mining faults. Background Technology

[0002] Fault activation during coal mining is a major trigger for water inrush and rockburst disasters, and existing monitoring technologies have significant systemic shortcomings. Firstly, regarding monitoring range, traditional methods use discrete point sensors, making it difficult to achieve full three-dimensional spatial coverage of the fault zone, resulting in the ineffective capture of stress-seepage anomalies in key structural areas. Secondly, regarding monitoring parameters, existing systems rely excessively on single physical field indicators such as displacement and microseismic activity, with insufficient dynamic monitoring of key seepage parameters such as pore water pressure, seepage velocity, and hydraulic gradient, failing to accurately identify hydraulic fracturing signs preceding fault activation. This severely restricts the effectiveness of coal mine fault disaster prevention and control, necessitating the development of a new technological system integrating comprehensive monitoring, dynamic analysis of the seepage field, and intelligent early warning. Summary of the Invention

[0003] This invention addresses the problems of large monitoring blind spots, lagging dynamic response of seepage fields, and insufficient early warning accuracy in existing coal mine fault monitoring systems. It proposes a real-time early warning system and deployment method based on a global sensor network and seepage field-dominant monitoring. The aim is to eliminate the blind spots of traditional point-based monitoring by using a three-dimensional fault sensor network with full coverage and a seepage-stress coupling monitoring mechanism. This will establish a multi-parameter fusion dynamic early warning model, thereby significantly improving the accuracy and response speed of early warnings for rockbursts and water inrush disasters, and providing reliable technical support for safe coal mine production.

[0004] To achieve the above objectives, the present invention provides a real-time early warning system for water control and scour prevention across the entire coal mine mining fault zone, comprising: A global sensor array is deployed in the fault zone of the mining area to monitor seepage and mechanical parameters in real time during the fault activation process. The seepage-stress coupling analysis module is connected to the global sensor array and is used to receive the seepage parameters and mechanical parameters. It also performs fusion analysis on the multi-source monitoring data according to the seepage-dominated weight allocation strategy to calculate the fault water conductivity index and comprehensive risk index. The dynamic early warning module, connected to the seepage-stress coupling analysis module, is used to determine the fault activation risk level based on the real-time changes of the water conductivity index and the comprehensive risk index, and to execute graded early warning and emergency response.

[0005] Preferably, the global sensor array includes: The fault seepage sensor group consists of high-precision pore water pressure gauges installed at intervals of no more than 5 meters along the main fracture zone of the fault, and permeability monitoring instruments installed in areas with dense fractures, forming a three-level monitoring network of the main fault zone, secondary fracture zone, and influence transition zone. The stress-displacement sensor group, including a fiber optic grating three-dimensional stress sensor, a high-sensitivity microseismic monitoring instrument, and a distributed fiber optic displacement meter, is deployed at the same site as the fault seepage sensor group to achieve spatiotemporal synchronous sensing of the stress field and the seepage field.

[0006] Preferably, the seepage-stress coupling analysis module uses the entropy weight method to dynamically assign weights to the monitoring parameters, wherein the seepage parameters include pore water pressure and permeability, with a weight of not less than 0.6, and the stress parameters include fault normal stress, displacement strain and microseismic energy release rate, with a weight of not more than 0.4.

[0007] Preferably, the seepage-stress coupling analysis module calculates the comprehensive risk index according to the following formula. Rt The expression is as follows: In the formula, wi No. i Entropy weighting of each monitoring parameter; Indicates the first i Dimensionless characteristic values ​​of each monitoring parameter; n This indicates the total number of monitoring parameters involved in the risk assessment.

[0008] Preferably, the seepage-stress coupling analysis module calculates the fault water conductivity index according to the following formula. Cw : in, Let be the stress influence function, satisfying , α This is the empirical attenuation coefficient.

[0009] Preferably, the dynamic early warning module adopts a three-level early warning mechanism: The primary warning is triggered when the pore water pressure gradient reaches 0.2 MPa per meter or when the permeability suddenly increases by more than 20%. The intermediate warning is triggered when the seepage rate reaches 0.3 MPa per minute and the stress decreases by more than 3 MPa. The advanced warning is triggered when the seepage rate exceeds 0.5 MPa per minute and the stress change exceeds 5 MPa, and the emergency shutdown protection device is automatically activated.

[0010] Preferably, the dynamic early warning module also incorporates a machine learning optimization algorithm to dynamically adjust the early warning threshold based on historical monitoring data and disaster cases, thereby achieving adaptive risk assessment.

[0011] Preferably, the system also includes an interface for linkage with the mine safety control device, used to automatically execute emergency operations such as stopping mining and draining water when an early warning is triggered.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention constructs a dual-sensor network of "fault seepage + stress displacement" to achieve three-dimensional, co-located, full-area three-dimensional monitoring, eliminating the spatial blind spots of traditional point-based monitoring. Simultaneously, it introduces multi-dimensional monitoring indicators such as pore water pressure, permeability, stress, microseismic activity, and displacement to comprehensively reflect the mechanical-seepage coupling characteristics of fault activation. The system employs entropy weighting and machine learning algorithms to dynamically optimize monitoring weights and thresholds, possessing adaptive adjustment and intelligent judgment capabilities, significantly improving early warning accuracy and response speed. The deployment follows the principle of "geological structure control and seepage field dominance," achieving hierarchical monitoring and precise deployment of faults in mining areas. Furthermore, through the linkage between the early warning system and mine safety control devices, it automatically executes emergency measures such as stopping mining and drainage upon triggering an early warning, constructing an integrated proactive safety control system for preventing rockbursts and water inrushes. Attached Figure Description To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of the multi-source data fusion and three-level early warning system of the early warning system according to an embodiment of the present invention. Detailed Implementation

[0014] 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0016] Example This embodiment provides a real-time, comprehensive early warning system for water control and scour prevention along mining-induced faults in coal mines, comprising a comprehensive sensor array, a seepage-stress coupling analysis module, and a dynamic early warning module. The following will, in conjunction with this embodiment, detail how this invention solves technical problems in practical applications.

[0017] The global sensor array employs a seepage-stress composite monitoring network to achieve three-dimensional, blind-spot-free coverage of faults and mining-affected areas through multi-parameter collaborative monitoring. The array consists of a fault seepage sensor group and a stress-displacement sensor group, with both types of sensors deployed in a spatially co-located manner to ensure the spatiotemporal consistency of the monitoring data.

[0018] The fault seepage sensor cluster, as the core monitoring unit of the system, is deployed according to the principle of "geological structure control and seepage field dominance." Specifically, the deployment involves: first, determining the extent of the main fault fracture zone based on geological exploration data, and then deploying high-precision pore water pressure gauges along the fault strike at intervals of ≤5m; second, based on the development characteristics of derivative fractures, denser permeability monitoring instruments are deployed in fracture-dense areas, forming a three-tiered monitoring network of the main fault zone, secondary fracture zone, and influencing transition zone. For fault sections with high water conductivity, the monitoring density is increased to ≤3m; in weakly water-conducting sections, it is appropriately relaxed to ≤10m. All sensors employ anti-interference design to ensure data reliability under complex geological conditions.

[0019] A cluster of stress-displacement sensors and seepage sensors form a complementary monitoring system, creating a multi-parameter collaborative sensing network. The system employs fiber optic grating three-dimensional stress sensors to monitor real-time stress state changes on both sides of the fault. Simultaneously, it is equipped with a high-sensitivity microseismic monitoring instrument to accurately capture micro-fracture events during fault activation, and continuously tracks the relative displacement dynamics of the upper and lower plates of the fault using distributed fiber optic displacement gauges. These sensors and seepage monitoring points are deployed at the same site, constructing a "one-point, multi-parameter" three-dimensional monitoring unit, effectively extending the monitoring range to the mining-affected area and achieving spatiotemporal synchronous sensing of the stress and seepage fields. Through the collaborative monitoring of multiple physical quantities, the system can comprehensively reflect the mechanical-seepage coupling response characteristics of the fault under mining influence, providing multi-dimensional data support for disaster early warning.

[0020] The multi-source data fusion module forms the core of the system's intelligent decision-making, enabling accurate assessment of disaster risks through multi-dimensional data analysis. At the data processing level, the system employs a seepage-dominated fusion strategy, assigning core weights of over 0.6 to seepage parameters such as pore water pressure and permeability, while controlling the weight of stress parameters below 0.4 to ensure that monitoring focuses on hydrogeological indicators. This weight allocation is not fixed but dynamically adjusted using the entropy weighting method, automatically optimizing the contribution of each indicator based on real-time monitoring data characteristics to ensure that the analysis results always closely reflect the actual situation on site.

[0021] The main set of parameters monitored by the system is as follows: ,in: P The pore water pressure is (MPa). K σ is the permeability (m²), σ is the fault normal stress (MPa), and ε is the displacement strain (%). VmThe energy release rate of the microseismic event is expressed as J / s.

[0022] To reflect the different degrees of influence of each parameter on disaster risk, the entropy weight method is used to determine the weights. wi ,Right now: in: In the formula, pij For the first i Parameters in the first j The normalized value at time , k It is a constant.

[0023] Comprehensive risk indicators Rt The expression is as follows: In the formula, wi No. i Entropy weighting of each monitoring parameter; Indicates the first i Dimensionless characteristic values ​​of each monitoring parameter; n This indicates the total number of monitoring parameters involved in the risk assessment.

[0024] when R t Continuously rising or exceeding the dynamic safety threshold R cr At that time, the system automatically enters the risk assessment stage.

[0025] Based on the coupling principle of seepage field and stress field, the system establishes a dynamic calculation model to solve the water conductivity index of the fault in real time. This model comprehensively considers the interaction of water pressure gradient, permeability change, and stress state, and assesses the risk of fault activation by quantifying the evolution trend of the permeability coefficient. When the calculation results show that the permeability coefficient exceeds the preset safety threshold, the system immediately initiates a risk warning process.

[0026] Considering the coupling effect of seepage and stress, the system defines the fault water conductivity index. Cw : in, Let be the stress influence function, satisfying , α This is the empirical attenuation coefficient.

[0027] when When the critical water-conducting threshold is reached, the system determines that the fault has a tendency to be activated by sudden water inrush and enters the early warning process.

[0028] The early warning module adopts a three-level progressive response architecture, such as... Figure 1As shown, a tiered prevention and control system for disaster risks is implemented. The initial warning stage primarily monitors abnormal changes in seepage parameters. When a pore water pressure gradient reaches 0.2 MPa per meter, or a sudden increase in permeability exceeding 20%, the system issues a yellow warning signal. An intermediate warning requires simultaneous occurrences of abrupt changes in seepage and abnormal mechanical parameters, specifically a seepage rate variation of 0.3 MPa per minute, accompanied by a stress drop exceeding 3 MPa. At this point, the system upgrades to an orange warning. The highest level, a red warning, requires simultaneous and drastic changes in seepage and stress, i.e., a seepage rate exceeding 0.5 MPa per minute while a stress change exceeds 5 MPa. In this case, the system not only issues the highest-level alarm but also automatically triggers the emergency shutdown protection device.

[0029] The overall risk assessment function is: in, and These are the adjustment coefficients for seepage and stress channels, respectively. .

[0030] To further improve the rationality of early warning threshold settings and the stability of risk assessment, the dynamic early warning module introduces a machine learning optimization algorithm based on Support Vector Machine (SVM). This algorithm uses historical monitoring data and known disaster event samples as training sets to learn the multidimensional features of fault seepage parameters and mechanical parameters, constructing a risk level classification model to achieve intelligent identification of fault activation status.

[0031] The discriminant function of a support vector machine can be expressed as: in, x It represents the monitoring feature vector composed of fault seepage parameters and mechanical parameters, used to characterize the comprehensive state of the fault under the influence of mining. w The feature weight vector consists of components that reflect the relative importance of different monitoring parameters in risk assessment and are learned from training samples. b This is a bias term used to adjust the position of the discriminant hyperplane in the feature space, thereby improving the model's ability to distinguish samples of different risk levels.

[0032] The optimal classification hyperplane is determined by solving the following objective function: in, C This is the penalty coefficient, used to balance the classification margin and the misclassification rate; These are slack variables; m This represents the number of training samples.

[0033] After training, the system uses real-time monitoring data as input to predict the risk level of the current fault state, and dynamically adjusts the warning thresholds at each level based on the prediction results, thereby achieving adaptive optimization of the warning model.

[0034] This system significantly improves the early warning efficiency of water inrush and rock burst disasters through real-time monitoring and dynamic control of the entire area dominated by seepage, providing reliable technical support for safe coal mining.

[0035] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A real-time early warning system for water control and scour prevention across the entire coal mine mining fault zone, characterized in that, include: A global sensor array is deployed in the fault zone of the mining area to monitor seepage and mechanical parameters in real time during the fault activation process. The seepage-stress coupling analysis module is connected to the global sensor array and is used to receive the seepage parameters and mechanical parameters. It also performs fusion analysis on the multi-source monitoring data according to the seepage-dominated weight allocation strategy to calculate the fault water conductivity index and comprehensive risk index. The dynamic early warning module, connected to the seepage-stress coupling analysis module, is used to determine the fault activation risk level based on the real-time changes of the water conductivity index and the comprehensive risk index, and to execute graded early warning and emergency response.

2. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The global sensor array includes: The fault seepage sensor group consists of high-precision pore water pressure gauges installed at intervals of no more than 5 meters along the main fracture zone of the fault, and permeability monitoring instruments installed in areas with dense fractures, forming a three-level monitoring network of the main fault zone, secondary fracture zone, and influence transition zone. The stress-displacement sensor group, including a fiber optic grating three-dimensional stress sensor, a high-sensitivity microseismic monitoring instrument, and a distributed fiber optic displacement meter, is deployed at the same site as the fault seepage sensor group to achieve spatiotemporal synchronous sensing of the stress field and the seepage field.

3. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The seepage-stress coupling analysis module uses the entropy weight method to dynamically assign weights to the monitoring parameters. The seepage parameters include pore water pressure and permeability, with a weight of not less than 0.

6. The stress parameters include fault normal stress, displacement strain, and microseismic energy release rate, with a weight of not more than 0.

4.

4. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The seepage-stress coupling analysis module calculates the comprehensive risk index according to the following formula. Rt The expression is as follows: In the formula, wi No. i Entropy weighting of each monitoring parameter; Indicates the first i Dimensionless characteristic values ​​of each monitoring parameter; n This indicates the total number of monitoring parameters involved in the risk assessment.

5. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The seepage-stress coupling analysis module calculates the fault water conductivity index according to the following formula. Cw : in, Let be the stress influence function, satisfying , α This is the empirical attenuation coefficient.

6. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The dynamic early warning module adopts a three-level early warning mechanism: The primary warning is triggered when the pore water pressure gradient reaches 0.2 MPa per meter or when the permeability suddenly increases by more than 20%. The intermediate warning is triggered when the seepage rate reaches 0.3 MPa per minute and the stress decreases by more than 3 MPa. The advanced warning is triggered when the seepage rate exceeds 0.5 MPa per minute and the stress change exceeds 5 MPa, and the emergency shutdown protection device is automatically activated.

7. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The dynamic early warning module also incorporates machine learning optimization algorithms to dynamically adjust the early warning threshold based on historical monitoring data and disaster cases, thereby achieving adaptive risk assessment.

8. The real-time early warning system for water control and scour prevention across the entire coal mine mining fault area according to claim 1, characterized in that, The system also includes an interface for linkage with the mine safety control device, which is used to automatically execute emergency operations such as stopping mining and draining water when an early warning is triggered.

Images