Coal mine goaf early warning method, system, device and medium

Abstract

The application provides a coal mine goaf early warning method and system, equipment and medium, and belongs to the technical field of coal mine monitoring. The method comprises the following steps: acquiring multi-field monitoring data of a target goaf at a current time; constructing a multi-field coupling relationship based on the multi-field monitoring data, each coupling relationship being a coupling relationship formed by each two fields of monitoring data and being used for representing the mutual influence relationship between the two fields of monitoring data; and performing prediction based on the multi-field monitoring data and the multi-field coupling relationship to obtain target multi-field monitoring data and a target early warning state. The target multi-field monitoring data and the target early warning state are multi-field monitoring data and an early warning state corresponding to a future target time. The coal mine goaf early warning method and system, equipment and medium provided by the application can realize accurate prediction of multi-field data of the goaf in the future and accurate early warning of the future state of the goaf.

Description

Technical Field

[0001] This application belongs to the field of coal mine monitoring technology, and more specifically, it relates to a method, system, equipment, and medium for early warning of coal mine goaf areas. Background Technology

[0002] With the continuous expansion of coal mining depth and scale, the risk of geological disasters induced by goaf areas is becoming increasingly prominent. After the formation of a goaf, its internal stress field undergoes significant reconstruction, leading to the continuous development and expansion of rock fissures. The development of these fissures, in turn, alters the migration paths of groundwater and gas, triggering multiple disasters such as water inrush and gas outbursts. These multiple field parameters, including stress, fissures, water inrush, and gas, do not exist in isolation but rather exhibit complex coupling relationships of mutual influence and interaction. Traditional goaf monitoring often focuses on the analysis of single physical fields, making it difficult to comprehensively reflect the evolution of disasters under the coupling effects of multiple fields. This results in delayed early warnings or misjudgments, seriously threatening safe coal mine production.

[0003] Therefore, how to achieve accurate prediction of future data from multiple sources in the goaf and accurate early warning of the future state of the goaf has become a key issue that urgently needs to be addressed in the field of coal mine safety. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, equipment, and medium for early warning of coal mine goaf areas, which can achieve accurate prediction of multiple data points in the future of goaf areas and accurate early warning of the future state of goaf areas.

[0005] A first aspect of this application provides a method for early warning of coal mine goaf areas, comprising:

[0006] Acquire multi-field monitoring data of the target goaf at the current moment; the multi-field monitoring data includes stress field data, fracture field data, water inrush field data, and gas field data;

[0007] Multi-field coupling relationships are constructed based on multi-field monitoring data. Each coupling relationship is formed by two monitoring data and is used to characterize the mutual influence relationship between the two monitoring data.

[0008] Prediction is made based on multi-field monitoring data and multi-field coupling relationships to obtain target multi-field monitoring data and target early warning status; the target multi-field monitoring data and target early warning status are the multi-field monitoring data and early warning status corresponding to the target at future time.

[0009] A second aspect of this application provides a coal mine goaf early warning system, comprising:

[0010] The data acquisition module is used to acquire multi-field monitoring data of the target goaf at the current moment; the multi-field monitoring data includes stress field data, fracture field data, water inrush field data, and gas field data;

[0011] The coupling relationship construction module is used to construct multi-field coupling relationships based on multi-field monitoring data. Each coupling relationship is the coupling relationship formed by every two monitoring data, and is used to characterize the mutual influence relationship between the two monitoring data.

[0012] The early warning module is used to make predictions based on multi-field monitoring data and multi-field coupling relationships to obtain target multi-field monitoring data and target early warning status; the target multi-field monitoring data and target early warning status are the multi-field monitoring data and early warning status corresponding to the target at future time.

[0013] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described coal mine goaf early warning method.

[0014] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described coal mine goaf early warning method.

[0015] A fifth aspect of this application provides a computer program product, including a computer program or computer-executable instructions, wherein when the computer program or computer-executable instructions are executed by a processor, the steps of the above-described coal mine goaf early warning method are implemented.

[0016] The beneficial effects of the coal mine goaf early warning method, system, equipment, and medium provided in this application embodiment are as follows:

[0017] This application's embodiments, by simultaneously collecting full-dimensional data on stress field, fracture field, water inrush field, and gas field, solve the problem of incomplete information in traditional single-field monitoring. This provides complete and accurate data source support for constructing multi-field coupling relationships, ensuring the matching of subsequent coupling analysis with the actual physical field evolution laws of the goaf, which is a prerequisite for achieving multi-field collaborative early warning. By constructing multi-field coupling relationships, this application's embodiments overcome the limitations of traditional methods that rely on independent single-field analysis or partial field coupling, accurately depicting the collaborative disaster-causing mechanism among multiple physical fields in the goaf. This provides a physical model foundation that conforms to engineering reality for subsequent multi-field prediction, ensuring the scientific validity of the prediction results. Through accurate prediction of future multi-field data and accurate early warning of the future state of the goaf, this application's embodiments can, on the one hand, capture the evolution trends and coupling risks of stress, fracture, water inrush, and gas in advance; on the other hand, provide clear decision-making basis for mine safety management, buying crucial time for emergency response and personnel evacuation, thus achieving accurate prediction of future multi-field data and accurate early warning of the future state of the goaf. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for early warning of coal mine goaf areas provided in an embodiment of this application;

[0020] Figure 2 A diagram illustrating the linkage mechanism of multi-field coupling relationships in a coal mine goaf early warning method provided in an embodiment of this application;

[0021] Figure 3 A logic diagram of a coal mine goaf early warning method provided in an embodiment of this application;

[0022] Figure 4 This is a structural block diagram of a coal mine goaf early warning system provided in an embodiment of this application;

[0023] Figure 5 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0026] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a coal mine goaf early warning method according to an embodiment of this application. The method can be executed by an electronic device, specifically a computer, server, or similar equipment. The method may include:

[0027] S101: Acquire multi-field monitoring data of the target goaf at the current moment; the multi-field monitoring data includes stress field data, fracture field data, water inrush field data and gas field data.

[0028] In this embodiment, the goaf refers to the underground space area formed after coal mining that has the risk of stress concentration, fissure development, water inrush and gas accumulation; the target goaf is a specific goaf selected for multi-field data monitoring, multi-field coupling relationship construction and disaster early warning.

[0029] In this embodiment, stress field data can be coal pillar stress and roof stress; stress sensors can be deployed at key locations in the coal pillar and roof to monitor stress changes in real time. Fracture field data can be fracture density and fracture opening / closing degree; this can be obtained by observing rock cores extracted from the area, calculating the fracture density by statistically analyzing the total fracture surface area per unit volume of rock, and obtaining the fracture opening / closing degree by measuring the offset between the two sides of the fracture. Water inrush field data can be pore water pressure and inflow rate; pore water pressure sensors can be deployed near underground rock strata or aquifers to monitor dynamic changes in pore water pressure, and the inflow rate can be calculated using methods such as the buoy method, weir method, and volumetric method. Gas field data can be gas concentration and gas pressure; this can be obtained by using a gas detector to sample gas at a specified location, obtaining the gas concentration, and using an underground rapid gas measuring instrument to calculate the gas pressure.

[0030] In this embodiment, major disasters such as water inrush, gas outburst, and roof collapse in coal mine goaf areas are not caused by a single physical field anomaly, but rather are the synergistic product of the mutual driving and constraint of four fields: stress, fissures, water inrush, and gas. The stress field is the driving force; when the stress exceeds the rock mass strength threshold, it induces fissure initiation and propagation. The fissure field is the pivotal zone; fissures are both channels for stress release and channels for groundwater and gas migration. The water inrush field and the gas field are the risk terminals and compete with each other. Groundwater and gas compete for seepage space in fissures; increased water saturation compresses gas migration channels, leading to a sharp increase in gas concentration. Increased gas pressure also hinders groundwater seepage, resulting in water pressure accumulation. (Reference) Figure 2 It can be seen that, due to stress concentration, stress concentration will increase the fracture density and opening degree in the fracture field data according to the first coupling relationship. The fracture field data with increased fracture density and opening degree will affect the water inrush field data through the second coupling relationship and the gas field data through the third coupling relationship. Finally, the water inrush field data and the gas field data will influence each other due to the fourth coupling relationship.

[0031] S102: Construct multi-field coupling relationships based on multi-field monitoring data. Each coupling relationship is the coupling relationship formed by every two monitoring data, and is used to characterize the mutual influence relationship between the two monitoring data.

[0032] In this embodiment, the multi-field coupling relationship refers to the overall correlation model set constructed based on monitoring data of stress field, fracture field, water inrush field and gas field. Essentially, it is a mathematical-physical model that uses a series of equations to quantitatively describe how the four physical fields of stress, fracture, water and gas interact.

[0033] In one embodiment of this application, constructing a multi-field coupling relationship based on multi-field monitoring data may specifically include:

[0034] The first coupling relationship is constructed based on stress field data and fracture field data; the first coupling relationship is determined by the damage rate coefficient and the rock mass strength threshold.

[0035] A second coupling relationship is constructed based on fracture field data and water inrush field data; the second coupling relationship is determined by the water permeability coefficient and the water-rock softening coefficient.

[0036] A third coupling relationship is constructed based on fracture field data and gas field data; the third coupling relationship is determined by the gas permeability growth coefficient and the gas permeability growth index.

[0037] A fourth coupling relationship is constructed based on water inrush field data and gas field data; the fourth coupling relationship is determined by bound water saturation, residual gas saturation, water relative permeability curve index, and gas relative permeability curve index.

[0038] In this embodiment, the stress field needs to indirectly affect the water inrush field and the gas field through the crack, so no direct coupling relationship is established.

[0039] In this embodiment, the first coupling relationship is used to quantify the driving relationship of stress concentration leading to rock mass damage, which in turn leads to the development of fissures. That is, when the stress exceeds the rock mass's bearing capacity, damage begins to accumulate; when the damage accumulates to a certain extent, the rock mass fractures, and fissures are generated and expand.

[0040] Furthermore, the first coupling relationship is constructed based on damage mechanics, and its specific construction process is shown below.

[0041] 1) Define rock mass damage variables: ;

[0042] in, Stress field data refers to the actual stress (unit: MPa) borne by the coal and rock in the goaf, which can be coal pillar stress data or roof stress data. The rock mass strength threshold is the minimum critical stress value at which rock mass begins to suffer damage, reflecting the rock mass's ability to resist stress damage (unit: MPa). The rock mass damage variable is dimensionless, representing the degree of damage to the rock mass caused by stress, and its value ranges from [0,1]. The rock mass began to be damaged.

[0043] 2) Construct the functional relationship between fracture density and damage variables: ;

[0044] in, Fracture density represents the number of fractures per unit volume of rock mass, directly reflecting the degree of fracture development (unit: fractures / m). 3 ); Initial fracture density refers to the number of naturally occurring fractures in a rock mass before it is subjected to current stress (unit: fractures / m). 3 ); Damage rate coefficient, which is the number of new fractures generated per unit volume of rock mass per unit time due to unit damage (unit: fractures / (m)). 3 h); t is the stress application time (unit: h).

[0045] In this embodiment, the second coupling relationship describes how existing fractures provide flow channels for groundwater and affect flow efficiency, while water, in turn, weakens the rock mass. The degree of fracture development directly determines the water's permeability. Simultaneously, water soaking softens the rock mass, reducing its strength.

[0046] Furthermore, the second coupling relationship is constructed based on Darcy's law of seepage, and its specific construction process is shown below.

[0047] 1) Establish the basic relationship between water permeability coefficient and fracture opening degree: ;

[0048] in, The water permeability coefficient characterizes the ability of a rock mass to allow groundwater to seep through. The larger the value, the easier it is for groundwater to flow through the rock mass fissures (unit: m / s). The initial water permeability coefficient; The crack opening degree, i.e., the distance between the two walls of the crack, reflects the degree of conduction of the crack and is dimensionless.

[0049] 2) Introducing correction for water-rock softening coefficient: when pore water pressure hour, ;

[0050] in, Corrected water permeability coefficient; This is the water-rock softening coefficient; the more pronounced the softening, the better. The more significant the magnification, the dimensionless it becomes.

[0051] In this embodiment, the third coupling relationship is used to describe how the fracture provides an escape channel for gas and controls its flow pattern. Similar to the second coupling relationship, but the gas seepage flow needs to consider the slippage effect, which differs from the flow pattern of water.

[0052] Furthermore, the third coupling relationship is constructed based on Fick's diffusion law, and its expression is shown below.

[0053]

[0054] in, Gas permeability growth coefficient (unit: m) 2 ); The initial gas permeability growth factor (unit: m) 2 ); Fracture density; For the crack opening degree, a dimensionless parameter; For gas pressure; , , These are the engineering calibration parameters, among which Used to characterize the intensity of the effect of fracture density on gas permeability. Used to characterize the intensity of the effect of fracture opening degree on gas permeability. Used to characterize the degree of influence of gas pressure on gas permeability; in actual calculations, it is necessary to... and After normalization, the values ​​are converted into dimensionless relative values, where a, b, and c represent the gas permeability growth index.

[0055] Furthermore, In power form The calculations demonstrate the nonlinear relationship between fracture density and gas permeability. In power form The calculations align with the physical principle that the larger the fissure opening, the larger the flow cross-section, and the smaller the seepage resistance. The index term This demonstrates the inverse relationship between gas pressure and the slippage effect.

[0056] In this embodiment, the fourth coupling relationship is used to describe the relationship between the two-phase fluids of groundwater and gas in a common fracture channel network. Since the fracture space is finite, a large water inrush field data will encroach on the space of the gas field data, leading to an increase in gas pressure; conversely, an increase in gas pressure will inhibit water flow.

[0057] Furthermore, the fourth coupling relationship is constructed based on the multiphase flow theory, and its specific construction process is shown below.

[0058] 1) Define saturation relationship: ;

[0059] in, Water saturation can be calculated using the fracture opening degree and pore water pressure, reflecting the degree to which water occupies the fracture space. Gas saturation can be calculated from fracture density and gas pressure, reflecting the degree to which gas occupies the fracture space; This represents the bound water saturation. All of these are dimensionless parameters.

[0060] 2) Construct a relative permeability curve, including the relative permeability of water: Relative gas permeability: .

[0061] in, The relative permeability of water increases monotonically with the increase of the fracture opening degree; The index of the relative permeability curve of water; The relative permeability of gas is positively correlated with fracture density. θ represents the residual gas saturation, and σ represents the exponent of the relative gas permeability curve. (The above is the definition of residual gas saturation.) All of these are dimensionless parameters.

[0062] As can be seen from the above, the embodiments of this application, by constructing multi-field coupling relationships, fully cover the entire physical field synergy chain of stress, fractures, water inrush, and gas in the goaf, solving the problem of the one-sided information and inability to reflect the multi-field linkage disaster caused by traditional single-field or local field coupling analysis. It accurately depicts the disaster evolution essence of the goaf and provides a foundation for comprehensive early warning of multiple types of disasters. The first coupling relationship transforms the abstract stress effect into a quantifiable fracture density evolution, which conforms to the actual law of rock mass fracture under load, providing a reliable basis for fracture development for subsequent analysis of water inrush field and gas field. The second coupling relationship reflects both the positive driving force of fracture development to enhance water permeability and the reverse effect of water soaking weakening the rock mass and further amplifying seepage, restoring the bidirectional nature of water-rock interaction, making water inrush risk analysis more consistent with engineering scenarios where long-term water erosion leads to increased seepage. The third coupling relationship, unlike the linear seepage law of water flow, more accurately matches the special mechanism of gas flow in fractures, improving the accuracy of gas outburst risk prediction. The fourth coupling relationship, through saturation constraints and relative permeability curves, reflects the competitive seepage of water and gas. This aligns with the synergistic disaster phenomenon where sudden water inrush encroaches on gas space, leading to a sharp increase in gas concentration and pressure, which in turn inhibits water flow. This provides theoretical support for early warning of combined water and gas disasters. Furthermore, the core parameters of each coupling relationship have clear physical meanings, facilitating on-site calibration using monitoring data or empirical assignment. This enables the abstract multi-field coupling model to be applied practically, guiding the deployment of monitoring equipment and parameter inversion.

[0063] S103: Based on multi-field monitoring data and multi-field coupling relationships, prediction is made to obtain target multi-field monitoring data and target early warning status; the target multi-field monitoring data and target early warning status are the multi-field monitoring data and early warning status corresponding to the future target time.

[0064] In this embodiment, target multi-site monitoring data refers to multi-site monitoring data for the future target time predicted based on current multi-site monitoring data and multi-site coupling relationships. Target early warning status refers to the risk level of the goaf at the future target time, determined by comparing the target multi-site monitoring data with a preset disaster threshold; this is the final output of the early warning. The risk level must cover the possibility of disaster caused by the synergy of multiple monitoring data points. The future target time refers to a pre-set time node that needs to be predicted, which must be determined in conjunction with the coal mine production plan, such as the mining progress, maintenance time, and disaster evolution cycle.

[0065] In this embodiment, after acquiring the current multi-field monitoring data, the data can be preprocessed, such as denoising and spatiotemporal alignment, to ensure data validity. If the coupling relationship update has been performed, the target multi-field coupling relationship is used for prediction; if it is the first prediction, the initial multi-field coupling relationship constructed at the beginning is used for prediction.

[0066] As can be seen from the above, the embodiments of this application, by simultaneously collecting full-dimensional data on stress field, fracture field, water inrush field, and gas field, solve the problem of one-sided information in traditional single-field monitoring. This provides complete and accurate data source support for constructing multi-field coupling relationships, ensuring the matching of subsequent coupling analysis with the actual physical field evolution law of the goaf, which is a prerequisite for achieving multi-field collaborative early warning. By constructing multi-field coupling relationships, the embodiments of this application break through the limitations of traditional methods that rely on independent analysis of a single field or partial field coupling, accurately depicting the collaborative disaster-causing mechanism among multiple physical fields in the goaf. This provides a physical model foundation that conforms to engineering reality for subsequent multi-field prediction, ensuring the scientific nature of the prediction results. Through accurate prediction of future multi-field data and accurate early warning of the future state of the goaf, the embodiments of this application can, on the one hand, capture the evolution trends and coupling risks of stress, fracture, water inrush, and gas in advance; on the other hand, provide clear decision-making basis for mine safety management, and buy critical time for emergency response and personnel evacuation, achieving accurate prediction of future multi-field data and accurate early warning of the future state of the goaf.

[0067] In one embodiment of this application, the predicted multi-field monitoring data corresponding to the current moment is obtained. The predicted multi-field monitoring data is the target multi-field monitoring data corresponding to the current moment obtained by predicting the multi-field monitoring data corresponding to the historical moment and the multi-field coupling relationship corresponding to the historical moment.

[0068] By comparing the predicted monitoring data with the monitoring data from multiple events, the deviation of each monitoring event is obtained.

[0069] The coupling relationships of each field are updated based on the deviation of the monitoring data of each field to obtain the multi-field coupling relationship of the target.

[0070] Among them, predictions based on multi-field monitoring data and multi-field coupling relationships are used to obtain target multi-field monitoring data and target early warning status, including:

[0071] Prediction is made based on multi-field monitoring data and the multi-field coupling relationship of the target to obtain multi-field monitoring data and early warning status of the target.

[0072] In this embodiment, historical time refers to a time node earlier than the current time used to provide basic data and coupling relationships for prediction; deviation is a quantitative indicator that measures the degree of deviation of each physical field data after comparing the predicted multi-field monitoring data with the current actual multi-field monitoring data, and the current actual multi-field monitoring data is obtained through actual measurement; target multi-field coupling relationship refers to the multi-field coupling relationship used for subsequent accurate prediction after updating the original multi-field coupling relationship based on the deviation of each field monitoring data.

[0073] In this embodiment, the predicted multi-field monitoring data at the current moment is obtained by retrieving multi-field monitoring data from historical moments and calculating the corresponding multi-field coupling relationship. The predicted data is compared with the current actual multi-field monitoring data to calculate the deviation. The coupling relationship is updated based on the deviation to obtain the target multi-field coupling relationship. In subsequent predictions, the target multi-field monitoring data and target early warning status at the future target moment are calculated using the current multi-field monitoring data and the target multi-field coupling relationship.

[0074] For example, setting the historical time point as T1, based on the stress field data, water inrush field data, and gas field data at time T1, and the multi-field coupling relationship at time T1, the stress field data, water inrush field data, and gas field data corresponding to time T2 are predicted. In response to the arrival of time T2 (which is now the current time), the corresponding stress field data, water inrush field data, and gas field data actually collected at time T2 are acquired. The deviation between the predicted multi-field data and the actually collected multi-field data at T2 is calculated. Based on the deviation of each field, the corresponding coupling relationship is updated to obtain the target multi-field coupling relationship. Finally, based on the corresponding field data actually collected at time T2 and the updated target multi-field coupling relationship, time T3 is predicted.

[0075] As can be seen from the above, the embodiments of this application update the coupling relationship by comparing historical predictions with actual data, and finally achieve a closed-loop mechanism for accurate prediction, solving the problem of static failure of multi-field coupling relationships due to dynamic changes in goaf conditions. On the one hand, the quantitative calculation of deviation provides an objective basis for updating the coupling relationship, avoiding the blindness of subjective adjustments; on the other hand, the case-specific update strategy ensures both update efficiency in small deviation scenarios and accuracy requirements in large deviation scenarios, making subsequent predictions based on the target multi-field coupling relationship closer to the actual evolution law of the goaf, ultimately improving the accuracy and timeliness of the target early warning status, and providing more reliable decision support for coal mine disaster prevention and control.

[0076] In one embodiment of this application, the deviation includes single-field deviation;

[0077] By comparing the predicted monitoring data with the actual monitoring data from multiple events, the deviation of each monitoring event is obtained, including:

[0078] The single-field deviation between the predicted multi-field monitoring data and the multi-field monitoring data is calculated based on the first calculation formula; the single-field deviation includes stress field deviation, fracture field deviation, water inrush field deviation, and gas field deviation; the first calculation formula is:

[0079]

[0080] in, For monitoring data; For X m The single-field deviation of the field, m=1,2,3,4; corresponding to the stress field, fracture field, water inrush field and gas field, respectively; Let m be the predicted value of the field at position i; This represents the actual monitored value of field m at location m; This represents the total number of monitoring points. The range of the actual monitored values ​​of field m is used to normalize the root mean square error. This represents the maximum value among the actual monitored values ​​for field m; This is the minimum value among the actual monitored values ​​of field m; This represents the actual monitoring value for field m.

[0081] In this embodiment, the single-field deviation is an index that calculates the degree of deviation between the predicted multi-field monitoring data and the actual collected multi-field monitoring data for a single physical field among the stress field, fracture field, water inrush field, and gas field. Correspondingly, the stress field deviation, fracture field deviation, water inrush field deviation, and gas field deviation are formed. The first calculation formula is a mathematical expression used to calculate the single-field deviation, and the core is to achieve normalization by combining the root mean square error with the range of the actual monitoring value.

[0082] For example, when m=1, it represents the stress field. It represents the single-field deviation of the stress field, used to measure the degree of deviation between the predicted stress value and the actual value; For stress monitoring data, such as coal pillar stress and roof stress; Let be the predicted value of the stress field at position i; Let be the actual monitored value of the stress field at position i. =3, This is the maximum value among the actual monitored values ​​at the three monitoring points in the stress field; It is the minimum value among the actual monitored values ​​of the three monitoring points in the stress field.

[0083] In this embodiment, when calculating the deviation of a single field, it is necessary to record the predicted values ​​of the stress field data, fracture field data, water inrush field data, and gas field data corresponding to the predicted multi-field monitoring data at each monitoring point. The actual values ​​of stress field data, fracture field data, water inrush field data, and gas field data at each monitoring point in the actual multi-field monitoring data at the corresponding time. And ensure that each monitoring point corresponds to a specific one. The deviation for each single field is calculated using the first calculation formula.

[0084] As can be seen from the above, the embodiments of this application quantify the single-field deviation through the first calculation formula, providing an objective basis for judging the deviation between the predicted and actual values ​​of each physical field, avoiding the subjectivity of judging the deviation based on experience, and at the same time, normalizing by using the range of actual monitoring values, effectively eliminating the comparison interference caused by the difference in the dimensions of different physical fields, ensuring that the single-field deviation is in the same quantitative dimension, and allowing direct horizontal comparison of the deviation degree of each field.

[0085] In one embodiment of this application, the method further includes:

[0086] The co-occurrence deviation between predicted multi-field monitoring data and multi-field monitoring data is calculated based on the second calculation formula; the second calculation formula is:

[0087]

[0088] in, For the degree of coordination deviation; Let m be the normalized single-field deviation of the m-th field; Let be the weight coefficient of the m-th field, and ;

[0089] The coupling relationships are updated based on the deviation values ​​corresponding to each field monitoring data to obtain the target multi-field coupling relationships, including:

[0090] Based on at least one of the single-field deviation and the cooperative deviation, the multi-field coupling relationship is updated to obtain the target multi-field coupling relationship.

[0091] In this embodiment, the coordination deviation degree is an index that measures the overall deviation of four fields: stress field, fracture field, water inrush field, and gas field. The second calculation formula is a mathematical expression used to calculate the coordination deviation degree, which achieves multi-field coordination quantification by multiplying the normalized single-field deviation degree of each field with the corresponding weight coefficient.

[0092] In this embodiment, when calculating the collaborative deviation, a weighting coefficient is assigned to each individual field deviation based on the actual working conditions, and the collaborative deviation is obtained through a second calculation formula. This process must ensure the spatiotemporal consistency of the data, meaning that the predicted multi-field monitoring data and the monitoring point locations and physical field parameter types of the multi-field monitoring data must completely correspond.

[0093] Furthermore, based on the multi-field coupling disaster mechanism in goaf areas, initial weights are assigned to each physical field. The fracture field, as the core hub of multi-field coupling, has the highest weight; the stress field, as the driving force for fracture development, has the next highest weight; the water inrush field and the gas field, as risk terminals and mutually constraining each other, have equal and the lowest weights. The initially assigned weights must sum to 1. Subsequently, fine-tuning is performed based on the disaster risk emphasis of the target goaf area, maintaining the priority and a total sum of 1. The weight values ​​can also be dynamically adjusted by verifying the matching degree of the adjusted coordination deviation with the actual risk level and engineering constraints through historical monitoring data.

[0094] As can be seen from the above, the embodiments of this application, through the second calculation formula, comprehensively analyze the deviations of the four fields using the collaborative deviation degree, and combine this with weighting coefficients to reflect the importance of different physical fields. This accurately characterizes the overall deviation features under multi-field coupling, overcoming the deficiency that considering only single-field deviation cannot reflect the collaborative risks of multiple fields. Finally, the single-field deviation degree and the collaborative deviation degree together constitute a complete system for deviation determination, providing quantitative support for subsequent updates to multi-field coupling relationships based on deviation degree. This ensures that the coupling relationship update strategy is more targeted, thereby improving the accuracy of subsequent predictions and laying the foundation for the scientific basis of early warning of coal mine goaf areas.

[0095] In one embodiment of this application, the multi-field coupling relationship is updated based on at least one of single-field deviation and cooperative deviation to obtain the target multi-field coupling relationship, including:

[0096] In response to the existence of Z single-field deviations greater than a preset single-field deviation, where Z is not greater than 2 and the cooperative deviation is less than or equal to a preset cooperative deviation, the coupling relationship corresponding to the single-field deviation greater than the preset single-field deviation is updated using the first method; the first method can be a linear correction method for single-field coupling parameters based on physical empirical formulas; Z is a positive integer;

[0097] In response to the existence of Z single-field deviations greater than the preset single-field deviation, Z being greater than 2, or the cooperative deviation being greater than the preset cooperative deviation, the multi-field coupling relationship is updated using a second method, which is the particle swarm algorithm.

[0098] In this embodiment, the first approach is a local optimization method for updating multi-field coupling relationships, specifically a linear correction method for single-field coupling parameters based on empirical physical formulas. For example, the first approach can adjust the parameters of a specific coupling relationship using a linear formula related to the deviation degree. Z represents the number of physical fields whose single-field deviation degree is greater than a preset single-field deviation degree, and is a positive integer. The second approach is a global optimization method for updating multi-field coupling relationships, specifically a particle swarm optimization algorithm, which iteratively searches for the optimal values ​​of all parameters to be optimized in the multi-field coupling relationships.

[0099] In this embodiment, when updating the coupling relationship, if the number of fields with a single field deviation greater than a preset threshold does not exceed 2, and the cooperative deviation is less than or equal to the preset threshold, the coupling relationship corresponding to the field with excessive deviation is linearly corrected using a physical empirical formula.

[0100] For example, if the deviation of the fracture field exceeds a preset value, the fracture field is associated with a first coupling relationship, a second coupling relationship, and a third coupling relationship, respectively. The parameters of each associated coupling relationship are then corrected one by one using a linear empirical formula derived from the first method. The linear empirical formula is as follows:

[0101]

[0102] in, In a coupled relationship, the original values ​​of the parameters need to be updated; In a coupled relationship, the corrected values ​​of the parameters need to be updated; k is the linear correction coefficient, where i is a positive integer. Different i correspond to different k, which are used to distinguish different coupling relationships or different parameters to be updated in the same coupling relationship. This represents the deviation rate for a single game.

[0103] When updating the damage rate coefficient D in the first coupling relationship: .

[0104] Update the water permeability coefficient in the second coupling relationship. hour .

[0105] Update the gas permeability growth coefficient in the third coupling relationship. hour: .

[0106] In this embodiment, when updating the coupling relationship, if the number of single-field deviation exceeding the limit is greater than 2, or the cooperative deviation is greater than the preset threshold, then the particle swarm algorithm is used to globally optimize the parameters of all coupling relationships to obtain the target multi-field coupling relationship.

[0107] As can be seen from the above, the embodiments of this application update the multi-field coupling relationship based on the deviation degree condition, effectively solving the shortcomings of the single-mode update method. The first method only adjusts the coupling parameters corresponding to the deviation exceeding the limit field, without the need for global optimization. This reduces the amount of computation, improves the update efficiency, and avoids the waste of resources caused by using complex algorithms for small deviations. At the same time, it is based on physical empirical formula correction to ensure that the parameter adjustment conforms to the physical mechanism of multi-field coupling. The second method, through global search for optimal parameters, can systematically solve the problem of overall failure of multi-field coupling relationship. Moreover, the algorithm iteration limits the physical reasonable range of parameters to ensure that the updated coupling relationship does not deviate from the engineering reality. The adapted application of the two update methods ensures that the target multi-field coupling relationship is always highly matched with the actual working conditions, providing reliable model support for subsequent multi-field data prediction and early warning status determination based on this relationship, and improving the accuracy and practicality of the coal mine goaf early warning method.

[0108] In one embodiment of this application, the multi-field coupling relationship is updated using a second method, including:

[0109] The parameters to be optimized in the multi-field coupling relationship are used as particle dimension parameters in the particle swarm optimization algorithm. The parameters to be optimized include damage rate coefficient, rock mass strength threshold, water permeability coefficient, water-rock softening coefficient, gas permeability growth coefficient, gas permeability growth index, bound water saturation, residual gas saturation, water relative permeability curve index, and gas relative permeability curve index.

[0110] The fitness function is the weighted sum of the deviations between the theoretical monitoring data and the corresponding actual monitoring data of all monitoring points in the target goaf area. The theoretical monitoring data is predicted based on the updated multi-field coupling relationship. The actual monitoring data is the multi-field monitoring data of the target goaf area at the current moment.

[0111] Initialize the position and velocity of the particle swarm, where the position parameter corresponds to the value of the parameter to be optimized, and the velocity parameter corresponds to the parameter adjustment rate;

[0112] Iteratively update the position and velocity of each particle in the particle swarm;

[0113] In response to the number of iterations reaching a preset threshold or the fitness value of the global optimum being less than or equal to a preset deviation threshold, the iteration stops, and the position parameters corresponding to the final global optimum are obtained.

[0114] The position parameters corresponding to the final global optimal solution are used as the target parameter values ​​in the multi-field coupling relationship;

[0115] Update multi-field coupling relationships based on target parameter values;

[0116] The process of updating the particle swarm includes:

[0117] The particle velocity update is determined based on the individual optimal solution and the global optimal solution. The individual optimal solution is the position parameter corresponding to the historical best fitness of a single particle, and the global optimal solution is the position parameter corresponding to the historical best fitness of the entire particle swarm.

[0118] The particle position parameters are adjusted according to the velocity update, and the adjustment range of the position parameters is limited to the physically reasonable range of the parameters to be optimized.

[0119] Calculate the fitness value of each particle after the update, and update the individual optimal solution and the global optimal solution.

[0120] In this embodiment, the parameters to be optimized refer to the core parameters in the multi-field coupling relationship that need to be adjusted by the particle swarm optimization algorithm, and are all key components of the multi-field coupling relationship. The particle dimension parameter is the constituent dimension of the particles in the particle swarm optimization algorithm; each dimension corresponds to one parameter to be optimized, and the number of particle dimensions is consistent with the number of parameters to be optimized. The fitness function is a mathematical function in the particle swarm optimization algorithm that measures the quality of particles; its core objective is to minimize the weighted sum of the deviations between the theoretical monitoring data and the actual monitoring data of all monitoring points within the target goaf area. Theoretical monitoring data refers to the multi-field monitoring data predicted based on the multi-field coupling relationship during the update process, and it completely corresponds to the type and location of the actual monitoring data. The position of the particle swarm is a parameter in the particle swarm optimization algorithm that characterizes the particle state; its value directly corresponds to the current value of the parameter to be optimized. The velocity of the particle swarm is a parameter in the particle swarm optimization algorithm that controls the speed of parameter adjustment; its value corresponds to the adjustment rate of the parameter to be optimized. The preset threshold for the number of iterations is a pre-set condition for terminating the iteration of the particle swarm optimization algorithm, determined based on the number of parameters to be optimized and computational efficiency requirements. The global optimal solution refers to the position parameter corresponding to the historical optimal fitness of all particles in the entire particle swarm during the iteration process. The individual optimal solution refers to the position parameter corresponding to the historical best fitness of a single particle during the iteration process. The preset deviation threshold is the fitness value condition for terminating the iteration of the particle swarm algorithm, determined based on the accuracy requirements of the multi-field coupling relationship in the target goaf area. The physically reasonable range of position parameters refers to the effective value interval of the parameter to be optimized under the constraints of engineering practice and physical mechanisms, conforming to the engineering experience and physical characteristics of multi-field coupling parameters.

[0121] In this embodiment, 10 parameters to be optimized are sequentially used as 10 dimensions of a particle. The value range of each dimension corresponds to the physically reasonable range of the parameter to be optimized, ensuring that the particle dimensions correspond one-to-one with the parameters and conform to physical constraints. Using the actual multi-field monitoring data of all monitoring points in the target goaf at the current moment, and updating the multi-field coupling relationship based on the combination of parameters to be optimized corresponding to a certain particle, the theoretical monitoring data of each monitoring point is predicted. The sum of the deviation between the theoretical and actual values ​​of each monitoring point multiplied by the weight of that monitoring point is calculated, and minimizing this sum is the fitness function objective. A particle swarm size is set, for example, 30 particles. The initial position of each particle is randomly generated, with each dimension's value within the physically reasonable range of the corresponding parameter to be optimized; simultaneously, the initial velocity of each particle is randomly generated. When iteratively updating particles, first, the fitness value of each particle is calculated, and the updated individual optimal solution is compared with the global optimal solution; then, the velocity update amount is calculated based on the individual optimal solution and the global optimal solution; finally, the particle position is adjusted according to the velocity update amount. If the adjusted position exceeds the physically reasonable range of the parameter to be optimized, the position is truncated to the range boundary. If the number of iterations reaches a preset threshold or the fitness value of the global optimum is less than or equal to a preset deviation threshold, the iteration stops; otherwise, the iteration is repeated to update the particles. Finally, the position parameters corresponding to the final global optimum are used as the target parameter values ​​and substituted into the original multi-field coupling relationship to obtain the updated target multi-field coupling relationship.

[0122] In this embodiment, the fitness function formula is as follows:

[0123]

[0124] in, The fitness function; is the total number of monitoring points; k is the index of the monitoring point; The spatial weight coefficient for the k-th monitoring point; This is an index for the physical field type, where m=1,2,3,4, representing stress field, fracture field, water inrush field, and gas field, respectively. The weighting coefficient for the m-th physical field; The number of monitoring points for the m-th physical field; An index for a monitoring point within a certain physical field; The predicted value is given by the k-th monitoring point, the m-th physical field, and the i-th sensor. This represents the actual monitoring value of the k-th monitoring point, the m-th physical field, and the i-th sensor. The range of the actual monitored values ​​of the m-th physical field. =max(X m,act )-min(X m,act ), used for normalization to eliminate the influence of differences in dimensions and numerical ranges between different physical fields.

[0125] Furthermore, the disaster risks vary significantly at different locations within the goaf; for example, stress concentration is observed near coal pillars, and the risk of water inrush is high at the contact zone with aquifers. Through By allowing the deviations of monitoring points in high-risk areas to contribute more to the overall fitness, the fitness value F is increased, forcing the optimization of coupling relationships to prioritize reducing prediction errors in high-risk areas. Stress field, fracture field, water inrush field, and gas field are not equally important; through... Amplify the contribution of important fields to F to ensure that the optimization of coupling relationships conforms to actual laws. The smaller the value, the more accurately the multi-field coupling relationship describes the collaborative evolution law between the fields, which can provide a reliable basis for subsequent disaster early warning and coupling relationship optimization.

[0126] For example, the second method is used to update the multi-field coupling relationship. The specific process is as follows: First, determine the particle dimension. Set the 10 parameters to be optimized as 10-dimensional particles. The physically reasonable range of each parameter is: damage rate coefficient 0.01~0.1 lines / (m 3 h), rock mass strength threshold 25~40MPa, water permeability coefficient 10 -8 ~10 -7 m / s, water-rock softening coefficient 0.6~0.9, gas permeability growth coefficient 10 -15 ~10 -14 m 2 The parameters for the gas permeability growth index are: 1.2–2.0, bound water saturation: 0.2–0.3, residual gas saturation: 0.1–0.2, water relative permeability curve index: 2.0–3.0, and gas relative permeability curve index: 1.5–2.5. The second step involves constructing a fitness function, selecting five monitoring points. The actual monitoring data showed an average stress of 34 MPa and an average fracture density of 2.3 fractures / m². 3 The theoretical data is based on particle parameter prediction, with each monitoring point having a weight of 0.2, and the objective is to minimize the fitness function value. The third step is to initialize the particle swarm to a size of 30 particles, with the initial position of a certain particle being: [0.04 lines / (m 3 h), 32MPa, 4×10 -8 m / s, 0.8, 2×10 -15 m 2 [1.5, 0.25, 0.15, 2.5, 2.0], initial velocity is: [0.002 strands / (m 3 h) / iteration, 0.5MPa / iteration, 2×10 -10 m / s / iteration, 0.02 / iteration, 2×10 -16 m 2 / iteration, 0.05 / iteration, 0.01 / iteration, 0.005 / iteration, 0.05 / iteration, 0.05 / iteration]. Fourth step, iterative update: In the first iteration, the particle's fitness value is calculated to be 0.08, the individual optimal solution is the current position, and the global optimal solution is another particle (fitness 0.07); in the 10th iteration, based on the individual optimal (fitness 0.06) and the global optimal (fitness 0.055), the velocity update is calculated, and the adjusted particle position is: [0.042 lines / (m 3 h), 32.5MPa, 4.1×10 -8 m / s, 0.78, 2.1×10 -15 m 2 [1.55, 0.24, 0.16, 2.45, 2.05], the fitness value drops to 0.058. Fifth step, terminate the iteration. After 35 iterations, the fitness value of the global optimum is 0.048 (≤ preset deviation threshold 0.05), stop the iteration, and the global optimum position parameters are: [0.043 lines / (m 3 h), 32.8MPa, 4.2×10 -8 m / s, 0.77, 2.15×10 -15 m 2 [1.58, 0.245, 0.155, 2.42, 2.08]. Step 6: Update the coupling relationship by substituting the above globally optimal parameters into the original multi-field coupling relationship. For example, in the first coupling relationship, the damage rate coefficient changes from 0.04 lines / (m²) to... 3 h) updated to 0.043 entries / (m 3 h) The rock mass strength threshold was updated from 32MPa to 32.8MPa, and the target multi-field coupling relationship was obtained. The weighted sum of the deviations between the predicted theoretical monitoring data and the actual data was reduced to 0.048, which meets the accuracy requirements.

[0127] In this embodiment, by Figure 3It is understood that the update logic in the coal mine goaf early warning method provided in this application is as follows: based on the current multi-field monitoring data, the current multi-field monitoring data can be used to update the multi-field coupling relationship and also participate in the prediction of the future target time. 1) After obtaining the current multi-field monitoring data and entering the update mechanism, the current time data predicted based on historical multi-field data and historical coupling relationship is compared with the actual collected current multi-field monitoring data. The single-field deviation degree and the collaborative deviation degree are calculated. According to the decision logic, if the number of single-field deviations exceeding the preset threshold N≤2 and the deviation degree is not greater than the preset collaborative deviation degree, the parameters of the corresponding coupling relationship are locally fine-tuned using physical empirical formulas. If N>2 or the deviation degree is greater than the preset collaborative deviation degree, the particle swarm algorithm is used to globally optimize all parameters of the multi-field coupling relationship. 2) After updating the target multi-field coupling relationship, the prediction is carried out based on the relationship and the current multi-field monitoring data. Finally, the target multi-field monitoring data and target early warning status at the future target time are output.

[0128] As can be seen from the above, the particle swarm optimization algorithm used in this application to update the multi-field coupling relationship can specifically solve the problem of large overall deviation in the multi-field coupling relationship, and improve the accuracy and adaptability of the coupling relationship. From the perspective of parameter optimization, the 10 parameters to be optimized are mapped to the particle dimension to achieve multi-parameter collaborative optimization, avoiding the defects of traditional single parameter adjustment that ignores the correlation between parameters. Moreover, the position parameters are strictly limited to a physically reasonable range, ensuring that the updated parameters conform to the physical mechanism of multi-field coupling in the goaf and preventing parameter values ​​that are out of touch with reality. From the perspective of optimization objectives, the fitness function is based on the weighted sum of deviations, which can comprehensively consider the multi-field data deviations of all monitoring points, so that the optimization results fit the overall working conditions of the target goaf, rather than local monitoring points. From the perspective of the iteration mechanism, the dual guidance of individual optimal solutions and global optimal solutions can ensure that the particles explore local optimal parameters, while avoiding falling into local optimal traps, and efficiently search for the global optimal parameter combination. This application embodiment updates the multi-field coupling relationship, providing reliable model support for subsequent multi-field data prediction and early warning status determination based on the target multi-field coupling relationship. It can better cope with the problem of coupling relationship failure under complex working conditions, and further ensure accurate prediction of multi-field data of the future goaf and accurate early warning of the future state of the goaf.

[0129] In this embodiment, the weight coefficients of each monitoring point in the deviation weighted sum are determined based on the importance of its spatial location.

[0130] In this embodiment, the weight coefficient of the monitoring point refers to the value assigned to each monitoring point to reflect its contribution in the weighted sum of deviations; the spatial importance refers to the different levels of importance that different monitoring points in the target goaf have due to the differences in disaster risk levels of their geographical locations. The higher the risk level, the stronger the spatial importance of the monitoring point, which is the core basis for determining the weight coefficient.

[0131] In this embodiment, the weighting coefficients are determined based on the spatial importance of monitoring points. This requires combining the disaster risk distribution patterns of the target goaf with the actual engineering needs, assigning weights according to risk zones and importance levels, and dynamically verifying and adjusting them in actual engineering to ensure the weight allocation aligns with the multi-field coupled disaster-causing logic. First, the target goaf is divided into high-risk, medium-risk, and low-risk zones. The high-risk zone includes coal pillar concentration areas, where stress is easily concentrated, the contact zone between the aquifer and the goaf, where the risk of water inrush is high, and low-lying areas rich in gas, where gas easily accumulates. The medium-risk zone includes the area below the key roof layer, where fractures are easily expanded, and the area ahead of the mining face, where stress dynamically changes. The low-risk zone includes the central part of the goaf, where stress has been released, there is no significant seepage risk, and it is a general area far from the disaster source. The importance levels are corresponding to the risk zones: high for high-risk zones, medium for medium-risk zones, and low for low-risk zones, with the importance level positively correlated with the weighting coefficient. Weights are assigned according to the principle that the weight of high-risk areas > the weight of medium-risk areas > the weight of low-risk areas, and the sum of the weights of all monitoring points is 1. The impact of the deviations of monitoring points in different risk areas on the early warning results is compared. For example, if the deviation of high-risk area monitoring points is not fully reflected in the deviation weighted sum, and its deviation contribution is masked by low-risk areas due to its low weight, then the weight of high-risk areas is appropriately increased and the weight of low-risk areas is decreased until the deviation weighted sum can accurately reflect the actual deviation of high-risk areas. Finally, the weight coefficient of each monitoring point is determined.

[0132] As can be seen from the above, the embodiment of this application determines the weighting coefficients based on the spatial importance of monitoring points, effectively solving the problem of bias weighting and distortion caused by equal weights for all monitoring points. This improves the pertinence and accuracy of bias assessment, accurately capturing biases in high-risk areas that are crucial for early warning, and avoiding the situation where small biases in low-risk areas mask large biases in high-risk areas. This weight allocation makes the optimization objective of the fitness function more focused on high-risk areas. When updating multi-field coupling relationships, the particle swarm optimization algorithm will prioritize reducing the bias in high-risk areas, making the updated target multi-field coupling relationship more accurate in predicting high-risk areas, thereby improving the reliability of subsequent early warning status determination. This method fits the actual working condition of uneven risk distribution in coal mine goaf areas, and can quickly assign weights based on spatial location without complex calculations, balancing scientific rigor and operability.

[0133] Corresponding to the coal mine goaf early warning method in the above embodiment, Figure 4 This is a structural block diagram of a coal mine goaf early warning system provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 4 The coal mine goaf early warning system 20 includes: a data acquisition module 21, a coupling relationship construction module 22, and an early warning module 23.

[0134] Among them, the data acquisition module 21 is used to acquire multi-field monitoring data of the target goaf at the current moment; the multi-field monitoring data includes stress field data, fracture field data, water inrush field data and gas field data;

[0135] The coupling relationship construction module 22 is used to construct multi-field coupling relationships based on multi-field monitoring data. Each coupling relationship is the coupling relationship formed by every two monitoring data, and is used to characterize the mutual influence relationship between the two monitoring data.

[0136] The early warning module 23 is used to make predictions based on multi-field monitoring data and multi-field coupling relationships to obtain target multi-field monitoring data and target early warning status; the target multi-field monitoring data and target early warning status are the multi-field monitoring data and early warning status corresponding to the future target time.

[0137] In one embodiment of this application, the coupling relationship construction module 22, when constructing multi-field coupling relationships based on multi-field monitoring data, is specifically used for:

[0138] The first coupling relationship is constructed based on stress field data and fracture field data; the first coupling relationship is determined by the damage rate coefficient and the rock mass strength threshold.

[0139] A second coupling relationship is constructed based on fracture field data and water inrush field data; the second coupling relationship is determined by the water permeability coefficient and the water-rock softening coefficient.

[0140] A third coupling relationship is constructed based on fracture field data and gas field data; the third coupling relationship is determined by the gas permeability growth coefficient and the gas permeability growth index.

[0141] A fourth coupling relationship is constructed based on water inrush field data and gas field data; the fourth coupling relationship is determined by bound water saturation, residual gas saturation, water relative permeability curve index, and gas relative permeability curve index.

[0142] In one embodiment of this application, the coal mine goaf early warning system 20 further includes a deviation calculation module:

[0143] The deviation calculation module is used to obtain the predicted multi-field monitoring data corresponding to the current moment. The predicted multi-field monitoring data is the target multi-field monitoring data corresponding to the current moment obtained by predicting the multi-field monitoring data corresponding to the historical moment and the multi-field coupling relationship corresponding to the historical moment.

[0144] By comparing the predicted monitoring data with the monitoring data from multiple events, the deviation of each monitoring event is obtained.

[0145] The coupling relationships of each field are updated based on the deviation of the monitoring data of each field to obtain the multi-field coupling relationship of the target.

[0146] Among them, predictions based on multi-field monitoring data and multi-field coupling relationships are used to obtain target multi-field monitoring data and target early warning status, including:

[0147] Prediction is made based on multi-field monitoring data and the multi-field coupling relationship of the target to obtain multi-field monitoring data and early warning status of the target.

[0148] In one embodiment of this application, the deviation calculation module is specifically used for:

[0149] By comparing the predicted monitoring data with the actual monitoring data from multiple events, the deviation of each monitoring event is obtained, including:

[0150] The single-field deviation between the predicted multi-field monitoring data and the multi-field monitoring data is calculated based on the first calculation formula; the single-field deviation includes stress field deviation, fracture field deviation, water inrush field deviation, and gas field deviation; the first calculation formula is:

[0151]

[0152] in, For monitoring data; For X m The single-field deviation of the field, m=1,2,3,4; corresponding to the stress field, fracture field, water inrush field and gas field, respectively; Let m be the predicted value of the field at position i; This represents the actual monitored value of field m at location m; This represents the total number of monitoring points. The range of the actual monitored values ​​of field m is used to normalize the root mean square error. This represents the maximum value among the actual monitored values ​​for field m; This is the minimum value among the actual monitored values ​​of field m; This represents the actual monitoring value for field m.

[0153] In one embodiment of this application, the deviation calculation module, when performing collaborative deviation calculation, is specifically used for:

[0154] The co-occurrence deviation between predicted multi-field monitoring data and multi-field monitoring data is calculated based on the second calculation formula; the second calculation formula is:

[0155]

[0156] in, For the degree of coordination deviation; Let m be the normalized single-field deviation of the m-th field; Let be the weight coefficient of the m-th field, and ;

[0157] The coupling relationships are updated based on the deviation values ​​corresponding to each field monitoring data to obtain the target multi-field coupling relationships, including:

[0158] Based on at least one of the single-field deviation and the cooperative deviation, the multi-field coupling relationship is updated to obtain the target multi-field coupling relationship.

[0159] In one embodiment of this application, when the deviation calculation module updates the multi-field coupling relationship based on at least one of single-field deviation and cooperative deviation to obtain the target multi-field coupling relationship, it is specifically used for:

[0160] In response to the existence of Z single-field deviations greater than a preset single-field deviation, where Z is not greater than 2 and the cooperative deviation is less than or equal to a preset cooperative deviation, the coupling relationship corresponding to the single-field deviation greater than the preset single-field deviation is updated using the first method; the first method is a linear correction method for single-field coupling parameters based on physical empirical formulas; Z is a positive integer;

[0161] In response to the existence of Z single-field deviations greater than the preset single-field deviation, Z being greater than 2, or the cooperative deviation being greater than the preset cooperative deviation, the multi-field coupling relationship is updated using a second method, which is the particle swarm algorithm.

[0162] In one embodiment of this application, when the deviation calculation module updates the multi-field coupling relationship using the second method, it is specifically used for:

[0163] The parameters to be optimized in the multi-field coupling relationship are used as particle dimension parameters in the particle swarm optimization algorithm. The parameters to be optimized include damage rate coefficient, rock mass strength threshold, water permeability coefficient, water-rock softening coefficient, gas permeability growth coefficient, gas permeability growth index, bound water saturation, residual gas saturation, water relative permeability curve index, and gas relative permeability curve index.

[0164] The fitness function is the weighted sum of the deviations between the theoretical monitoring data and the corresponding actual monitoring data of all monitoring points in the target goaf area. The theoretical monitoring data is predicted based on the updated multi-field coupling relationship. The actual monitoring data is the multi-field monitoring data of the target goaf area at the current moment.

[0165] Initialize the position and velocity of the particle swarm, where the position parameter corresponds to the value of the parameter to be optimized, and the velocity parameter corresponds to the parameter adjustment rate;

[0166] Iteratively update the position and velocity of each particle in the particle swarm;

[0167] In response to the number of iterations reaching a preset threshold or the fitness value of the global optimum being less than or equal to a preset deviation threshold, the iteration stops, and the position parameters corresponding to the final global optimum are obtained.

[0168] The position parameters corresponding to the final global optimal solution are used as the target parameter values ​​in the multi-field coupling relationship;

[0169] Update multi-field coupling relationships based on target parameter values;

[0170] The process of updating the particle swarm includes:

[0171] The particle velocity update is determined based on the individual optimal solution and the global optimal solution. The individual optimal solution is the position parameter corresponding to the historical best fitness of a single particle, and the global optimal solution is the position parameter corresponding to the historical best fitness of the entire particle swarm.

[0172] The particle position parameters are adjusted according to the velocity update, and the adjustment range of the position parameters is limited to the physically reasonable range of the parameters to be optimized.

[0173] Calculate the fitness value of each particle after the update, and update the individual optimal solution and the global optimal solution.

[0174] See Figure 5 , Figure 5 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 5 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 4 The functions of the data acquisition module 21, the coupling relationship construction module 22, and the early warning module 23 are shown.

[0175] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0176] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0177] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0178] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the coal mine goaf early warning method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0179] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0180] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0181] This application provides a computer program product, which includes computer-executable instructions or a computer program. The computer-executable instructions or computer program are stored in a computer-readable storage medium. The processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to execute the coal mine goaf early warning method described in this application embodiment.

[0182] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0183] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0184] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules / units, or it may be an electrical, mechanical, or other form of connection.

[0185] The modules / units described as separate components may or may not be physically separate. Similarly, the components shown as modules / units may or may not be physical modules / units; they may be located in one place or distributed across multiple network modules / units. Some or all of the modules / units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0186] Furthermore, the functional modules / units in the various embodiments of this application can be integrated into one processing module / unit, or each module / unit can exist physically separately, or two or more modules / units can be integrated into one module / unit. The integrated modules / units described above can be implemented in hardware or in the form of software functional modules / units.

[0187] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for early warning of coal mine goaf areas, characterized in that, include: Acquire multiple monitoring data points of the target goaf area at the current moment; The multi-field monitoring data includes stress field data, fracture field data, water inrush field data, and gas field data; Based on the multi-field monitoring data, a multi-field coupling relationship is constructed. Each coupling relationship is the coupling relationship formed by two fields of monitoring data and is used to characterize the mutual influence relationship between the two fields of monitoring data. Based on the multi-field monitoring data and the multi-field coupling relationship, prediction is made to obtain the target multi-field monitoring data and the target early warning status; The target multi-field monitoring data and the target early warning status are the multi-field monitoring data and early warning status corresponding to the future target time. The construction of multi-field coupling relationships based on the multi-field monitoring data includes: A first coupling relationship is constructed based on the stress field data and the fracture field data; the first coupling relationship is determined by the damage rate coefficient and the rock mass strength threshold. A second coupling relationship is constructed based on the fracture field data and the water inrush field data; the second coupling relationship is determined by the water permeability coefficient and the water-rock softening coefficient. A third coupling relationship is constructed based on the fracture field data and the gas field data; the third coupling relationship is determined by the gas permeability growth coefficient and the gas permeability growth index. A fourth coupling relationship is constructed based on the water inrush field data and the gas field data; the fourth coupling relationship is determined by the bound water saturation, residual gas saturation, water relative permeability curve index, and gas relative permeability curve index. The expression for the third coupling relationship is: , The gas permeability growth coefficient; The initial gas permeability growth coefficient; The density of the fracture; The degree of crack opening / closing; For gas pressure; Used to characterize the intensity of the effect of fracture density on gas permeability. Used to characterize the intensity of the effect of fracture opening degree on gas permeability. Used to characterize the degree of influence of gas pressure on gas permeability; a, b, and c represent the gas permeability growth index; The process of constructing the fourth coupling relationship includes: defining the saturation relationship and constructing the relative permeability curve; The defined saturation relationship is expressed as follows: ; Water saturation can be calculated using the fracture opening degree and pore water pressure, reflecting the degree to which water occupies the fracture space. Gas saturation can be calculated from fracture density and gas pressure, reflecting the degree to which gas occupies the fracture space; To bind water saturation; The construction of the relative permeability curve includes the relative permeability of water: Relative gas permeability: , The relative permeability of water increases monotonically with the increase of the fracture opening degree; The index of the relative permeability curve of water; The relative permeability of gas is positively correlated with fracture density. denoted as residual gas saturation, and σ is the exponent of the relative gas permeability curve.

2. The coal mine goaf early warning method as described in claim 1, characterized in that, The method further includes: Obtain the predicted multi-field monitoring data corresponding to the current moment. The predicted multi-field monitoring data is the target multi-field monitoring data corresponding to the current moment obtained by predicting the multi-field monitoring data corresponding to the historical moment and the multi-field coupling relationship corresponding to the historical moment. The predicted multi-field monitoring data is compared with the multi-field monitoring data to obtain the deviation degree corresponding to each field monitoring data. The coupling relationships corresponding to each field are updated based on the deviation of the monitoring data of each field to obtain the target multi-field coupling relationship; The step of predicting based on the multi-field monitoring data and the multi-field coupling relationship to obtain the target multi-field monitoring data and the target early warning status includes: Based on the multi-field monitoring data and the multi-field coupling relationship of the target, predictions are made to obtain the multi-field monitoring data of the target and the target early warning status.

3. The coal mine goaf early warning method as described in claim 2, characterized in that, The deviation includes single-field deviation; The step of comparing the predicted multi-field monitoring data with the multi-field monitoring data to obtain the deviation degree corresponding to each field monitoring data includes: The single-field deviation between the predicted multi-field monitoring data and the multi-field monitoring data is calculated based on the first calculation formula; the single-field deviation includes stress field deviation, fracture field deviation, water inrush field deviation, and gas field deviation; the first calculation formula is: in, For monitoring data; Let Xm be the single-field deviation, where m = 1, 2, 3, 4; corresponding to the stress field, fracture field, water inrush field, and gas field, respectively. Let m be the predicted value of the field at position i; This represents the actual monitored value of field m at location m; This represents the total number of monitoring points. The range of the actual monitored values ​​of field m is used to normalize the root mean square error. This represents the maximum value among the actual monitored values ​​for field m; This is the minimum value among the actual monitored values ​​of field m; This represents the actual monitoring value for field m.

4. The coal mine goaf early warning method as described in claim 3, characterized in that, The method also includes: The coordination deviation between the predicted multi-field monitoring data and the multi-field monitoring data is calculated based on the second calculation formula; the second calculation formula is: in, For the degree of coordination deviation; Let m be the normalized single-field deviation of the m-th field; Let be the weight coefficient of the m-th field, and ; The step of updating the corresponding coupling relationship based on the deviation degree corresponding to each field monitoring data to obtain the target multi-field coupling relationship includes: Based on at least one of the single-field deviation and the cooperative deviation, the multi-field coupling relationship is updated to obtain the target multi-field coupling relationship.

5. The coal mine goaf early warning method as described in claim 4, characterized in that, The step of updating the multi-field coupling relationship based on at least one of the single-field deviation and the cooperative deviation to obtain the target multi-field coupling relationship includes: In response to the existence of Z single-field deviations greater than a preset single-field deviation, where Z is not greater than 2, and the cooperative deviation is less than or equal to a preset cooperative deviation, the coupling relationship corresponding to the single-field deviation greater than the preset single-field deviation is updated using a first method; the first method is a linear correction method for single-field coupling parameters based on physical empirical formulas; Z is a positive integer; In response to the existence of Z single-field deviations greater than a preset single-field deviation, Z being greater than 2, or the cooperative deviation being greater than a preset cooperative deviation, the multi-field coupling relationship is updated using a second method, which is a particle swarm optimization algorithm.

6. The coal mine goaf early warning method as described in claim 5, characterized in that, The second method for updating the multi-field coupling relationship includes: The parameters to be optimized in the multi-field coupling relationship are used as particle dimension parameters in the particle swarm optimization algorithm; the parameters to be optimized include damage rate coefficient, rock mass strength threshold, water permeability coefficient, water-rock softening coefficient, gas permeability growth coefficient, gas permeability growth index, bound water saturation, residual gas saturation, water relative permeability curve index, and gas relative permeability curve index. The fitness function is the weighted sum of the deviations between the theoretical monitoring data and the corresponding actual monitoring data of all monitoring points within the target goaf. The theoretical monitoring data is predicted based on the updated multi-field coupling relationship. The actual monitoring data is the multi-field monitoring data of the target goaf at the current moment. Initialize the position and velocity of the particle swarm, where the position parameter corresponds to the value of the parameter to be optimized, and the velocity parameter corresponds to the parameter adjustment rate; Iteratively update the position and velocity of each particle in the particle swarm; In response to the number of iterations reaching a preset threshold or the fitness value of the global optimum being less than or equal to a preset deviation threshold, the iteration stops, and the position parameters corresponding to the final global optimum are obtained. The position parameter corresponding to the final global optimal solution is taken as the target parameter value in the multi-field coupling relationship; The multi-field coupling relationship is updated based on the target parameter values; The process of updating the particle swarm includes: The particle velocity update amount is determined based on the individual optimal solution and the global optimal solution. The individual optimal solution is the position parameter corresponding to the historical best fitness of a single particle, and the global optimal solution is the position parameter corresponding to the historical best fitness of the entire particle swarm. The particle position parameters are adjusted according to the velocity update, and the adjustment range of the position parameters is limited to the physically reasonable range of the parameters to be optimized. Calculate the fitness value of each particle after the update, and update the individual optimal solution and the global optimal solution.

7. A coal mine goaf early warning system, characterized in that, include: The data acquisition module is used to acquire multiple monitoring data of the target goaf area at the current moment; The multi-field monitoring data includes stress field data, fracture field data, water inrush field data, and gas field data; The coupling relationship construction module is used to construct multi-field coupling relationships based on the multi-field monitoring data. Each coupling relationship is the coupling relationship formed by every two monitoring data, and is used to characterize the mutual influence relationship between the two monitoring data. The early warning module is used to make predictions based on the multi-field monitoring data and the multi-field coupling relationship to obtain the target multi-field monitoring data and the target early warning status; The target multi-field monitoring data and the target early warning status are the multi-field monitoring data and early warning status corresponding to the future target time. The coupling relationship construction module is specifically used to construct multi-field coupling relationships based on multi-field monitoring data for: The first coupling relationship is constructed based on stress field data and fracture field data; the first coupling relationship is determined by the damage rate coefficient and the rock mass strength threshold. A second coupling relationship is constructed based on fracture field data and water inrush field data; The second coupling relationship is determined by the water permeability coefficient and the water-rock softening coefficient; A third coupling relationship is constructed based on fracture field data and gas field data; The third coupling relationship is determined by the gas permeability growth coefficient and the gas permeability growth index; A fourth coupling relationship is constructed based on water inrush field data and gas field data; the fourth coupling relationship is determined by bound water saturation, residual gas saturation, water relative permeability curve exponent, and gas relative permeability curve exponent. The expression for the third coupling relationship is: , The gas permeability growth coefficient; The initial gas permeability growth coefficient; The density of the fracture; The degree of crack opening / closing; For gas pressure; Used to characterize the intensity of the effect of fracture density on gas permeability. Used to characterize the intensity of the effect of fracture opening degree on gas permeability. Used to characterize the degree of influence of gas pressure on gas permeability; a, b, and c represent the gas penetration rate growth index; The process of constructing the fourth coupling relationship includes: defining the saturation relationship and constructing the relative permeability curve; The defined saturation relationship is expressed as follows: ; Water saturation can be calculated using the fracture opening degree and pore water pressure, reflecting the degree to which water occupies the fracture space. Gas saturation can be calculated from fracture density and gas pressure, reflecting the degree to which gas occupies the fracture space; To bind water saturation; The construction of the relative permeability curve includes the relative permeability of water: Relative gas permeability: , The relative permeability of water increases monotonically with the increase of the fracture opening degree; The index of the relative permeability curve of water; The relative permeability of gas is positively correlated with fracture density. denoted as residual gas saturation, and σ is the exponent of the relative gas permeability curve.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images