Gas coal mine goaf coupling disaster monitoring method, electronic device and storage medium

Abstract

The invention relates to the technical field of coal mine disaster monitoring, in particular to a gas coal mine goaf coupling disaster monitoring method, an electronic device and a storage medium, and the gas coal mine goaf coupling disaster monitoring method comprises the following steps: obtaining comprehensive data of a goaf through a sensor network, and carrying out data preprocessing to obtain standardized data; constructing a digital twinborn model through a 3D modeling and geographic information system technology; performing data synchronization and model correction processing on the digital twinborn model, and optimizing parameters and states of the digital twinborn model; constructing a fluid-solid-heat multi-field coupling model through a computational fluid mechanics and finite element analysis method; constructing a risk assessment model through an analytic hierarchy process and a fuzzy comprehensive evaluation method; training a disaster early warning model by using a machine learning algorithm based on the standardized data and the risk assessment model; a digital twinborn model, standardized data, a risk assessment model and a disaster early warning model are integrated, and a visual interaction platform is constructed. According to the monitoring method, multiple disaster elements can be coupled and dynamically evolved, and the disaster prediction accuracy and timeliness are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine disaster monitoring, and particularly relates to a method for monitoring the coupling disasters in the goaf of a gas coal mine, an electronic device, and a storage medium. Background Art

[0002] As one of the main global energy sources, coal occupies a key position in economic development. However, coupling disasters between gas and the goaf frequently occur during coal mining, seriously threatening coal mine production safety and personnel lives. According to statistics, the proportion of gas accidents in some key coal mining areas in China is quite high. Disasters such as explosions caused by gas accumulation and roof falls and spontaneous combustion related to the goaf have led to a large number of casualties, heavy economic losses, and waste of coal resources, restricting the sustainable development of the coal industry.

[0003] Traditional gas monitoring methods mostly focus on the real-time detection of gas concentration. For example, the common sensor fixed-point monitoring technology can provide local concentration data, but it has insufficient understanding of the gas migration law in the complex environment of the goaf. Limited by the distribution density and monitoring range of sensors, it is difficult to timely capture the source of sudden changes in gas concentration and the diffusion trend, and cannot comprehensively reflect the dynamic gas accumulation situation in the goaf. At the same time, existing goaf monitoring means mostly focus on the determination of single disaster characterization parameters. For example, warning of spontaneous combustion or roof caving by monitoring temperature and pressure changes ignores the internal coupling relationship between gas and other disasters in the goaf. For example, the movement of overlying strata in the goaf causes the evolution of the fracture network, changing the gas seepage channel and accumulation space, and the gas accumulation enhances the explosion risk and the catalytic effect on coal spontaneous combustion, forming a complex disaster chain. Traditional monitoring methods are difficult to effectively monitor and evaluate risks from the perspective of overall coupling and cannot meet the requirements of safe and efficient coal mining, so there is an urgent need to innovate monitoring methods to break the deadlock. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for monitoring the coupling disasters in the goaf of a gas coal mine, an electronic device, and a storage medium to solve the problems mentioned in the above background art.

[0005] The technical solution adopted by the present invention to solve its technical problems is: A method for monitoring the coupling disasters in the goaf of a gas coal mine, the method for monitoring the coupling disasters in the goaf of a gas coal mine includes the following steps:

[0006] S1. Obtain comprehensive data of the goaf through a sensor network and perform data preprocessing to obtain standardized data;

[0007] S2. Construct a digital twin model through 3D modeling and geographic information system technology;

[0008] S3. Perform data synchronization and model correction processing on the digital twin model to optimize the parameters and state of the digital twin model;

[0009] S4. Construct a fluid-structure-thermal multi-field coupling model through computational fluid dynamics and finite element analysis methods;

[0010] S5. Construct a risk assessment model through the analytic hierarchy process and fuzzy comprehensive evaluation method;

[0011] S6. Based on the standardized data and risk assessment model, use machine learning algorithms to train a disaster warning model;

[0012] S7. Integrate the digital twin model, standardized data, risk assessment model and disaster warning model to construct a visual interactive platform.

[0013] Preferably, in step S1, the data preprocessing includes the following steps:

[0014] S11. Precisely amplify the signal obtained by the sensor through a signal conditioning circuit to obtain an analog signal;

[0015] S12. Denoise and filter the analog signal through an active or passive filter to obtain a filtered signal;

[0016] S13. Convert the filtered signal into a digital signal through an analog-to-digital converter;

[0017] S14. Calibrate the digital signal through a standard measuring device to obtain a calibrated signal;

[0018] S15. Normalize the calibrated signal to obtain a standardized signal.

[0019] Preferably, step S2 includes the following steps:

[0020] S21. Combine the goaf stratum structure data, mining plan and actual production data to construct a three-dimensional geological model of the goaf and a framework of the mining process model. The goaf stratum structure data includes the thickness, dip angle, spacing of the coal seam and the lithology parameters of the roof and floor. The mining plan includes the roadway orientation, cross-sectional dimensions, coal mining method and advancing speed. The actual production data includes the daily coal output, mining progress and equipment layout;

[0021] The goaf stratum structure data includes the thickness, dip angle, spacing of the coal seam and the lithology parameters of the roof and floor;

[0022] The mining plan includes the roadway orientation, cross-sectional dimensions, coal mining method and advancing speed;

[0023] The actual production data includes the daily coal output, mining progress and equipment layout;

[0024] S22. Construct a goaf solid model through 3D modeling software based on coal mine engineering data;

[0025] S23. Combine the three-dimensional geological model of the goaf, the framework of the mining process model and the goaf solid model to construct a digital twin model.

[0026] Preferably, the step S3 includes the following steps:

[0027] S31. Obtain model prediction data through simulation by the digital twin model;

[0028] S32. Use the ensemble Kalman filter algorithm to fuse the standardized data and the model prediction data to obtain the assimilated data;

[0029] S33. Set the dynamic weights of different parameters according to the correlation degree between the types of each data in the standardized data and the parameters in the digital twin model;

[0030] S34. Input the assimilated data into the digital twin model, and inversely solve the key parameters in the digital twin model through the optimization algorithm;

[0031] S35. Calibrate the key parameters according to the spatio-temporal distribution data of gas concentration in the standardized data through the parameter inversion technology, and the spatio-temporal distribution data of gas concentration is the change curve of gas concentration at different positions and different time periods.

[0032] Preferably, in the ensemble Kalman filter algorithm, let the system state vector be x, the observation vector be y, and the model prediction operator Observation operator

[0033] Prediction step:

[0034] In the formula, x a Is the state vector after the analysis step update, and x f Is the predicted state vector;

[0035] Analysis step:

[0036] In the formula, the gain matrix P f Is the predicted error covariance matrix, and R is the observation error covariance matrix.

[0037] Preferably, the step S4 includes the following steps:

[0038] S41. Through simulation by the digital twin model, correlate the gas pressure with the change of the surrounding rock strength in the goaf to construct a gas pressure-stress coupling equation;

[0039] S42. Through simulation by the digital twin model, introduce the correlated change between the surrounding rock strength in the goaf and the temperature to construct a fluid-solid-thermal multi-field coupling model.

[0040] 7. The gas coal mine goaf coupling disaster monitoring method according to claim 1, characterized in that: the step S5 includes the following steps:

[0041] S51. Construct a disaster type library, select indicators for each disaster type in the disaster type library and quantify the indicators.

[0042] The disaster type library includes gas explosion disasters, coal natural disasters and roof accidents.

[0043] The gas explosion disaster indicators include gas concentration, oxygen content, and fire source possibility.

[0044] The coal natural disaster indicators include coal body temperature, carbon monoxide concentration, and coal spontaneous combustion tendency parameter.

[0045] The roof accident indicators include roof separation amount, roof pressure, and surrounding rock integrity coefficient.

[0046] S52. Construct a judgment matrix through the analytic hierarchy process, and combine historical cases and expert experience to establish the relative weights of each indicator.

[0047] S53. Through the fuzzy comprehensive evaluation method, fuzzify the quantified indicators according to the membership function of each indicator, construct a risk assessment fuzzy relation matrix, and establish a risk assessment model through fuzzy operation and combination with relative weights.

[0048] Preferably, the disaster warning model is as follows:

[0049] Let the training sample set

[0050] In the formula, x i is the eigenvector, y i ∈{-1, 1} is the class label.

[0051] The objective function is The constraint conditions are

[0052] In the formula, w is the normal vector of the hyperplane, b is the intercept, ξ i is the slack variable, C is the penalty parameter. is the kernel function mapping.

[0053] An electronic device, the electronic device includes a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface complete mutual communication through the communication bus.

[0054] The memory is used to store the monitoring program for the coupled disasters in the goaf of the gas coal mine.

[0055] The processor is used to execute the monitoring program for the coupled disasters in the goaf of the gas coal mine. When the monitoring program for the coupled disasters in the goaf of the gas coal mine is executed, the steps of the above-mentioned monitoring method for the coupled disasters in the goaf of the gas coal mine are implemented.

[0056] A computer-readable storage medium stores a monitoring program for coupled disasters in the gob area of a gas coal mine. When the monitoring program for coupled disasters in the gob area of the gas coal mine is executed by a processor, the steps of the monitoring method for coupled disasters in the gob area of the gas coal mine as described above are implemented.

[0057] The beneficial effects of the present invention are as follows:

[0058] The present invention integrates digital twin technology, accurately collects multiple parameters through a sensor network and data preprocessing, drives the digital twin model to accurately reproduce the actual situation and disaster trajectory of the gob area, enables the coupling of disaster elements to evolve dynamically, and greatly improves the accuracy and timeliness of the model for disaster prediction. Specific embodiments

[0059] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0060] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0061] The present invention will be further described in conjunction with specific examples below. The following examples are only for explaining the present invention and do not constitute a limitation to the present invention. The test samples and test processes used in the following examples include the following content (if the specific experimental conditions are not indicated in the examples, they are usually in accordance with conventional conditions or the conditions recommended by the reagent company; the reagents, consumables, etc. used in the following examples can be obtained from commercial sources without special instructions).

[0062] One of the objectives of the present invention is to provide a monitoring method for coupled disasters in the gob area of a gas coal mine. The monitoring method for coupled disasters in the gob area of the gas coal mine includes the following steps:

[0063] S1. Obtain comprehensive data of the gob area through a sensor network and perform data preprocessing to obtain standardized data;

[0064] S2. Construct a digital twin model through 3D modeling and geographic information system technology;

[0065] S3. Perform data synchronization and model calibration processing on the digital twin model to optimize the parameters and states of the digital twin model;

[0066] S4. Construct a fluid-solid-thermal multi-field coupling model through computational fluid dynamics and finite element analysis methods;

[0067] S5. Construct a risk assessment model through the analytic hierarchy process and fuzzy comprehensive evaluation method;

[0068] S6. Based on the standardized data and risk assessment model, use machine learning algorithms to train a disaster warning model;

[0069] S7. Integrate the digital twin model, standardized data, risk assessment model, and disaster warning model to construct a visual interaction platform.

[0070] Among them, in step S1, the data preprocessing includes the following steps:

[0071] S11. Precisely amplify the signal obtained by the sensor through a signal conditioning circuit to obtain an analog signal. This signal conditioning circuit is set at the front end of the acquisition. According to the sensor type and signal characteristics, use an amplifier to precisely adjust the signal amplitude to the appropriate acquisition range, such as amplifying a weak strain signal by a hundred times;

[0072] S12. Denoise and filter the analog signal through an active or passive filter to obtain a filtered signal. This active or passive filter can be selected from low-pass, high-pass, band-pass filters or used in combination, and filter according to the frequency characteristics of the target physical quantity to filter out high-frequency electromagnetic interference and low-frequency mechanical vibration noise, improve the signal quality and stability, and ensure that the change of the monitoring parameter is truly reflected;

[0073] S13. Convert the filtered signal into a digital signal through an analog-to-digital converter. This analog-to-digital converter selects a high-speed analog-to-digital converter, and selects an appropriate resolution of the high-speed analog-to-digital converter according to the sensor range and accuracy requirements (such as 12 - 24 bits) to ensure that the conversion accuracy reaches the microvolt and microstrain levels;

[0074] S14. Calibrate the digital signal through a standard measuring instrument to obtain a calibrated signal. Eliminate the zero drift, temperature drift, and nonlinear error of the sensor through the standard measuring instrument. When collecting data online, regularly conduct on-site calibration and comparison with standard gases, standard pressure sources, standard strain gauges, etc., and correct the collected data in real time according to the calibration results to ensure the accuracy and reliability of the data and provide a credible basis for subsequent analysis;

[0075] S15. Normalize the calibrated signal to obtain a standardized signal.

[0076] The above sensor network distribution method is as follows:

[0077] Inside the goaf, gas concentration sensors are layered at key positions according to different coal seam heights, strikes, and dips, such as near the coal seam roof, floor, and around coal pillars, to accurately capture the gas concentration gradient changes; near the goaf edge and coal wall, high-precision pressure sensors and strain sensors are deployed to monitor the dynamic stress and strain of the surrounding rock. The spacing is determined according to the geological complexity, generally at intervals of 10-20 meters; liquid level sensors are installed in areas where water may accumulate; at key nodes of the ventilation roadway, wind speed and direction sensors, temperature and humidity sensors, and dust concentration sensors are installed to ensure no dead spots in the ventilation system monitoring. A wide-coverage microseismic monitoring network is constructed around the entire goaf. Multiple microseismic sensors are used to monitor the microseismic signals generated by coal and rock fractures to locate potential dangerous areas; an atmospheric environment monitoring station is set up at the ground wellhead and its surrounding areas to monitor the air quality indicators and meteorological parameters related to the coal mine in real time, forming an all-round sensor network that integrates the sky and the ground and takes into account both the inside and the outside to ensure no key parameters are missed in monitoring.

[0078] After the data of each sensor is collected, it is connected to the data acquisition terminal through a dedicated cable or wireless transmission module (selected according to the environment and distance, such as using optical fiber or LoRa wireless module for long distance and complex electromagnetic interference). This terminal integrates a high-performance microprocessor and a large-capacity storage chip, and has a real-time clock function to accurately timestamp the collected data, and synchronously collects the data of multiple sensors at a fixed high-frequency sampling rate (such as 1-5 seconds per time for gas concentration, 10-30 seconds per time for stress and strain) to ensure the consistency and integrity of the data time series.

[0079] Step S2 includes the following steps:

[0080] S21. Combining the goaf stratigraphic structure data, mining plan, and actual production data, construct a three-dimensional geological model and a mining process model framework of the goaf.

[0081] The goaf stratigraphic structure data includes the thickness, dip angle, spacing of the coal seam, and the lithology parameters of the roof and floor. The lithology parameters of the roof and floor include elastic modulus, Poisson's ratio, and compressive strength.

[0082] The mining plan includes the roadway strike, cross-sectional dimensions, coal mining method, and advancing speed.

[0083] The actual production data includes the daily coal output, mining progress, and equipment layout.

[0084] S22. Through three-dimensional modeling software (such as Bentley MicroStation, Dassault Systèmes Catia, etc.), construct a goaf solid model based on the coal mine engineering data.

[0085] S23. Combining the three-dimensional geological model and the mining process model framework of the goaf and the goaf solid model, construct a digital twin model.

[0086] After the modeling is completed, material properties and mechanical characteristics are assigned to coal seams and rock strata according to lithological differences; roadways, chambers, and coal mining faces are accurately modeled according to the design, and detailed features (support structures, equipment external dimensions, and installation positions) are added; the boundaries of goafs are determined according to the theory and measured data of caving zones, fissure zones, and bending subsidence zones, and the physical entity spatial form and topological structure of the goaf are accurately reproduced.

[0087] Step S3 includes the following steps:

[0088] S31. Obtain model prediction data through simulation using the digital twin model;

[0089] S32. Use the Ensemble Kalman Filter algorithm to fuse the standardized data and the model prediction data to obtain the assimilated data;

[0090] S33. Set the dynamic weights of different parameters according to the type of each data in the standardized data and the correlation degree of the parameters in the digital twin model. For example, when the gas concentration changes suddenly, increase its correction weight for gas migration parameters in model update;

[0091] S34. Input the assimilated data into the digital twin model, and inversely solve the key parameters in the digital twin model through optimization algorithms (such as genetic algorithms, simulated annealing algorithms) to drive the update of the model state variables, so that the model closely tracks the changes in the goaf working conditions and accurately reflects the real-time state of the physical entity. The key parameters include permeability, porosity, and strength parameters, and the model state variables include gas distribution, stress-strain field, and temperature field;

[0092] S35. Based on the Continuous Discontinuous Element Method (CDEM), build a simulation environment by combining the GDEM numerical simulation software with the digital twin model. According to the spatio-temporal distribution data of gas concentration in the standardized data, calibrate the key parameters through parameter inversion technology. The spatio-temporal distribution data of gas concentration is the change curve of gas concentration at different positions and different time periods. For example, set a gas concentration error objective function at the key monitoring points in the goaf, and adjust parameters such as permeability and diffusion coefficient through the optimization algorithm to make the fitting error between the simulated gas concentration and the measured value within the allowable range (such as the average relative error is less than 10%), ensuring that the model accurately simulates the gas migration and accumulation laws and providing a reliable basis for gas disaster early warning.

[0093] In the above Ensemble Kalman Filter algorithm, let the system state vector be x, the observation vector be y, and the model prediction operator Observation operator

[0094] Prediction step:

[0095] In the formula, x a is the state vector after the analysis step update, xf is the predicted state vector;

[0096] Analysis steps:

[0097] In the formula, the gain matrix P f is the predicted error covariance matrix, and R is the observation error covariance matrix.

[0098] Step S4 includes the following steps:

[0099] S41. Through the digital twin model, simulate the stress and strain evolution of the surrounding rock in the goaf during the mining process, analyze the mechanical responses such as overlying rock movement, coal pillar deformation, and roof caving, correlate the gas pressure with the change in the strength of the surrounding rock in the goaf, and construct a gas pressure-stress coupling equation. Among them, the gas pressure exacerbates the weakening and deformation of the surrounding rock strength. This gas pressure-stress coupling equation is used to simulate the influence of gas occurrence and migration on the stability of the surrounding rock;

[0100] S42. Through the digital twin model simulation, introduce the correlated change between the strength of the surrounding rock in the goaf and temperature (such as the thermal stress generated by coal spontaneous combustion), and construct a fluid-solid-thermal multi-field coupling model.

[0101] S43. Verify the model based on the data of the surrounding rock displacement (measured by total station and multi-point displacement meter) and stress (monitored by stress meter) on site. After adjusting the model parameters and boundary conditions, make the simulation results fit well with the measured displacement and stress curves (such as the displacement error is within ±5 mm and the stress error is within ±0.5 MPa).

[0102] Step S5 includes the following steps:

[0103] S51. Construct a disaster type library, select indicators for each disaster type in the disaster type library and quantify the indicators.

[0104] The disaster type library includes gas explosion disasters, coal natural disasters, and roof accidents.

[0105] The gas explosion disaster indicators include gas concentration (risk levels are divided according to the concentration range), oxygen content (lack of oxygen or rich oxygen exacerbates the explosion risk), and the possibility of ignition source (evaluated according to the distribution of electrical equipment and the probability of friction heat sources).

[0106] The coal natural disaster indicators include coal body temperature (risk is judged according to the heating rate and critical spontaneous combustion temperature), carbon monoxide concentration (early warning of the concentration threshold of the marker gas), and the spontaneous combustion tendency parameter of coal (determined in the laboratory).

[0107] The roof accident indicators include roof separation (quantified according to the data of monitoring sensors), roof pressure (comparing the pressure change rate with the threshold), and surrounding rock integrity coefficient (evaluated by acoustic wave detection). According to the physical meanings and disaster mechanisms of each indicator, the quantification method and grading standard are determined, and a risk assessment index system with clear levels and comprehensive systems is constructed to accurately depict the characteristics of the goaf disaster risk state;

[0108] S52. Construct a judgment matrix through the analytic hierarchy process. Combining historical cases and expert experience, determine the relative weights of each indicator. For example, through expert scoring and data statistical analysis, it is determined that the weight of gas concentration for gas explosion risk is 0.4, oxygen content 0.3, and the possibility of ignition source 0.3; the weight of coal body temperature for coal spontaneous combustion risk is 0.5, carbon monoxide concentration 0.3, and spontaneous combustion tendency 0.2, etc.;

[0109] S53. Through the fuzzy comprehensive evaluation method, the quantified indicators are fuzzified according to the membership function of each indicator, a risk assessment fuzzy relation matrix is constructed, and through fuzzy operation and synthesis with the relative weight, a risk assessment model is established.

[0110] In step S5, the application method of the machine learning algorithm is as follows: Collect a large amount of historical standardized data and the corresponding disaster occurrence situations (labeled samples), and use supervised learning algorithms (such as support vector machines, random forests, neural networks) to train the disaster warning model. Use the multi-parameter standardized data as the input feature vector and whether the disaster occurs as the output label to train the disaster warning model to learn the association between the disaster occurrence pattern and characteristics in the data. For example, the neural network optimizes the weights through the backpropagation algorithm to explore the triggering relationship between the combination characteristics of the gas concentration change trend, abnormal temperature rise, and sudden change in roof pressure and disasters; the support vector machine maps the data to a high-dimensional space according to the kernel function, finds the optimal classification hyperplane to distinguish between disaster and normal state data, and constructs a disaster warning model with high accuracy and strong generalization ability to realize the automatic identification mapping from standardized data to disaster risks.

[0111] The disaster warning model is as follows:

[0112] Let the training sample set

[0113] where x i is the feature vector, y i ∈{-1,1} is the class label,

[0114] The objective function is The constraint conditions are

[0115] where w is the normal vector of the hyperplane, b is the intercept, ξ i is the slack variable, C is the penalty parameter, is the kernel function mapping. By solving this optimization problem, the classification decision function is determined to achieve intelligent early warning of disaster risks, and the model is updated according to the new sample incremental learning.

[0116] The design method of the visualization interaction platform is as follows:

[0117] The visualization interaction platform is designed with a hierarchical architecture, including a data layer, a model layer, a service layer, and an application layer from bottom to top. The data layer integrates standardized data, historical data, and external relevant data (such as geological data and meteorological data) to build a unified data management system to ensure efficient data storage, retrieval, and update; the model layer integrates digital twin models, simulation analysis models, and risk assessment models to provide model call, operation, and management interfaces; the service layer develops data processing, analysis, visualization rendering, and decision support service components to encapsulate business logic; the application layer constructs user-oriented interaction interfaces and functional modules to realize functions such as goaf state monitoring, disaster early warning, and decision simulation. Each layer communicates and cooperates according to standardized interfaces to ensure the flexibility and scalability of the platform architecture and adapt to the complex business needs of coal mines.

[0118] The second object of the present invention is to provide an electronic device, which includes a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete mutual communication through the communication bus;

[0119] The memory is used to store the coupled disaster monitoring program for goafs in gas coal mines;

[0120] The processor is used to execute the coupled disaster monitoring program for goafs in gas coal mines. When the coupled disaster monitoring program for goafs in gas coal mines is executed, the steps of the above-mentioned coupled disaster monitoring method for goafs in gas coal mines are realized.

[0121] The above-mentioned electronic device can be selected as a notebook computer, a stand-alone assistant, a smart tablet, etc. with intelligent computing capabilities; the processor can be selected as a CPU or other final execution units with information processing and program running capabilities; the memory can be selected as a device such as a memory, a hard disk, or a storage card with storage and program reading capabilities.

[0122] The third object of the present invention is to provide a computer-readable storage medium, in which a coupled disaster monitoring program for goafs in gas coal mines is stored. When the coupled disaster monitoring program for goafs in gas coal mines is executed by a processor, the steps of the above-mentioned coupled disaster monitoring method for goafs in gas coal mines are realized.

[0123] The above-mentioned computer-readable storage medium can be selected as a device such as a USB flash drive, a mobile hard disk, or an optical disc.

[0124] In the embodiments described in this specification, a progressive approach is adopted. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0125] The above has introduced in detail a method for monitoring coupling disasters in the gob area of a gas coal mine, an electronic device, and a storage medium provided by the present invention. Specific examples are used herein to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. A method for monitoring coupled disasters in gas coal mine goaf, characterized in that: The method for monitoring coupled disasters in gas coal mine goafs comprises the following steps: S1, obtain comprehensive data of the goaf through the sensor network, and perform data preprocessing to obtain standardized data; S2. Build digital twin models through 3D modeling and geographic information system technology; S3. Perform data synchronization and model correction on the digital twin model to optimize the parameters and status of the digital twin model; S4. Construct a fluid-solid-thermal multi-field coupling model through computational fluid dynamics and finite element analysis methods; S5. Construct a risk assessment model through analytic hierarchy process and fuzzy comprehensive evaluation method; S6. Use machine learning algorithms to train disaster warning models based on standardized data and risk assessment models; S7. Integrate digital twin models, standardized data, risk assessment models and disaster warning models to build a visual interactive platform.

2. The method for monitoring coupled disasters in gas coal mine goaf according to claim 1, characterized in that: In step S1, the data preprocessing includes the following steps: S11, accurately amplifying the signal obtained by the sensor through a signal conditioning circuit to obtain an analog signal; S12, performing noise reduction filtering on the analog signal through an active or passive filter to obtain a filtered signal; S13, converting the filtered signal into a digital signal through an analog-to-digital converter; S14, calibrating the digital signal by a standard meter to obtain a calibration signal; S15. Perform normalization processing on the calibration signal to obtain a standardized signal.

3. The method for monitoring coupled disasters in gas coal mine goaf according to claim 1, characterized in that: The step S2 comprises the following steps: S21. Combine the goaf area stratigraphic structure data, mining planning and actual production data to build a three-dimensional geological model of the goaf area and a mining process model framework. The goaf stratigraphic structure data include the thickness, inclination, spacing and lithology parameters of the coal seams, and the mining plan includes the direction of the tunnel, the cross-section size, the coal mining method and the advancement speed. The actual production data include daily coal production, mining progress and equipment layout; S22. Using 3D modeling software and based on coal mine engineering data, construct a physical model of the goaf; S23. Construct a digital twin model by combining the three-dimensional geological model of the goaf with the mining process model framework and the goaf entity model.

4. The method for monitoring coupled disasters in gas coal mine goaf according to claim 1, characterized in that: The step S3 comprises the following steps: S31. Simulating the digital twin model to obtain model prediction data; S32, using an ensemble Kalman filter algorithm to fuse the standardized data and the model prediction data to obtain assimilated data; S33. Setting dynamic weights of different parameters according to the correlation between the type of each data in the standardized data and the parameters in the digital twin model; S34, inputting the assimilated data into the digital twin model, and reversely solving the key parameters in the digital twin model through the optimization algorithm; S35. Calibrate key parameters through parameter inversion technology according to the spatiotemporal distribution data of gas concentration in the standardized data, wherein the spatiotemporal distribution data of gas concentration is a variation curve of gas concentration at different locations and different time periods.

5. The method for monitoring coupled disasters in gas coal mine goaf according to claim 4 is characterized in that: In the ensemble Kalman filter algorithm, let the system state vector x, observation vector y, model prediction operator Observation Operator Prediction Steps: In the formula, x a is the updated state vector after the analysis step, x f is the predicted state vector; Analysis steps: In the formula, the gain matrix P f is the prediction error covariance matrix, and R is the observation error covariance matrix.

6. The method for monitoring coupled disasters in gas coal mine goaf according to claim 1, characterized in that: The step S4 comprises the following steps: S41. Through digital twin model simulation, the gas pressure is correlated with the change in surrounding rock strength in the goaf, and the gas pressure-stress coupling equation is constructed; S42. Through digital twin model simulation, the correlation between the strength and temperature of the surrounding rock in the goaf is introduced to construct a fluid-solid-heat multi-field coupling model.

7. The method for monitoring coupled disasters in gas coal mine goaf according to claim 1, characterized in that: The step S5 comprises the following steps: S51, construct a disaster category library, select indicators for each disaster category in the disaster category library and quantify the indicators, wherein the disaster category library includes gas explosion disasters, coal natural disasters and roof accidents, The gas explosion hazard indicators include gas concentration, oxygen content, and fire source possibility. The coal natural disaster indicators include coal body temperature, carbon monoxide concentration, and coal spontaneous combustion tendency parameters; the roof accident indicators include roof delamination, roof pressure, and surrounding rock integrity coefficient; S52. Construct a judgment matrix through the analytic hierarchy process, combine historical cases with expert experience, and establish the relative weights of each indicator; S53. Through the fuzzy comprehensive evaluation method, the quantitative indicators are fuzzified according to the membership functions of each indicator, and the risk assessment fuzzy relationship matrix is ​​constructed. After fuzzy operation and relative weight synthesis, a risk assessment model is established.

8. A method for monitoring coupled disasters in gas coal mine goaf, characterized in that: The disaster warning model is as follows: Assume that the training sample set In the formula, x i is the feature vector, y i ∈{-1,1} is the category label, The objective function is The constraints are Where w is the normal vector of the hyperplane, b is the intercept, ξ i is the slack variable, C is the penalty parameter, is the kernel function mapping.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store the gas coal mine goaf area coupling disaster monitoring program; The processor is used to execute the gas coal mine goaf area coupling disaster monitoring program, and when the gas coal mine goaf area coupling disaster monitoring program is executed, the steps of the gas coal mine goaf area coupling disaster monitoring method as described in any one of claims 1-8 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a gas coal mine goaf area coupling disaster monitoring program. When the gas coal mine goaf area coupling disaster monitoring program is executed by the processor, the steps of the gas coal mine goaf area coupling disaster monitoring method as described in any one of claims 1-8 are implemented.

Images