A method for an intelligent monitoring and early warning system with multi-dimensional integration in a mine

Abstract

The present invention relates to the technical field of coal mine dynamic disaster monitoring and early warning, and discloses an intelligent monitoring and early warning system method for multi-dimensional integration in a mine. The system is an all-time, multi-scale, and multi-parameter coupling monitoring and early warning model and system integrating twelve major modules, namely, the original data acquisition module, mining condition analysis, data transmission module, pre-data preprocessing, expert analysis and demonstration, determination of optimal parameters, basic theory calculation, numerical simulation analysis, laboratory verification, machine learning and neural network optimization, coupling model construction, and on-site application detection. The intelligent monitoring and early warning system method for multi-dimensional integration in a mine proposed by the present invention uses multi-level means, avoiding the limitations of traditional single solutions or the subjectivity of single human interference, and can effectively prevent mine dynamic disasters to a great extent, which is of great significance for reducing the monitoring and early warning of coal-rock-gas compound dynamic disasters and the safe production of mines.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine dynamic disaster monitoring and early warning, and particularly to an intelligent monitoring and early warning system method for multi-dimensional integration in a mine. Background Art

[0002] In-depth research on coal-rock-gas complex dynamic disasters helps to reveal their internal occurrence and development mechanisms, provides a scientific basis for establishing more accurate prediction models and early warning systems, and thus enables the adoption of effective preventive measures in advance to reduce the likelihood of disasters. This can not only ensure the safety of coal mine workers, reduce casualties and property losses, but also improve the mining efficiency and safety of coal resources, and promote the sustainable development of the coal industry.

[0003] Currently, the main monitoring and early warning means for mine dynamic disasters mainly include microseismic method, drill cuttings method, acoustic emission monitoring method, gas content assessment method, CT scanning technology, etc. They can achieve good monitoring effects to a certain extent. However, for mines with complex disaster manifestations, a single early warning means is no longer sufficient to meet the needs of the front line of the mine. Of course, there are also some research personnel who have proposed schemes for integrating two or a few monitoring technologies for monitoring, but there are still large inaccuracies and limitations.

[0004] In view of this, it is urgently necessary to construct a full-time-space, multi-scale, multi-parameter coupled monitoring and early warning model and system from the acquisition of raw data, analysis of mining conditions, preprocessing of data in the early stage, expert analysis, selection of optimal parameters, design of monitoring systems, basic theoretical calculations, optimization of machine learning and neural networks, construction of coupled models, numerical simulation analysis, laboratory verification, on-site application detection to the development of early warning systems, a perfect mine coal-rock-gas complex dynamic disaster monitoring and early warning system that "starts from the beginning to the end, from original parameters to successful early warning" to effectively ensure the safe operation of the front line of the mine. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent monitoring and early warning system and implementation plan for multi-dimensional integration in a mine to solve the technical problems existing in the existing measures. This method intends to cooperate with each other from multiple levels to monitor the possibility of coal-rock-gas complex dynamic disasters through multi-parameter integration, evaluate the risk of combined dynamic disasters, and automatically give early warnings according to the monitoring results, aiming to provide technical support and guarantee for the safe production of coal mines.

[0006] To achieve the above purpose, the technical scheme adopted by the present invention is as follows:

[0007] The intelligent monitoring and early warning system for multi-dimensional integration in mines proposed by the present invention includes twelve major modules: raw data acquisition module, mining condition analysis module, data transmission module, preprocessing module for early-stage data, expert analysis and demonstration, optimal parameter determination module, basic theory calculation, numerical simulation analysis module, experimental verification module, machine learning and neural network optimization module, coupled monitoring and early warning model and system, and on-site verification.

[0008] Preferably, a plurality of sensors and monitoring devices should be deployed for the raw data acquisition to collect environmental data in the mine, such as gas concentration, gas pressure, drill cuttings data, electromagnetic parameters, microseismic data, temperature, humidity, etc., to ensure the accuracy and comprehensiveness of data acquisition, and regularly calibrate the equipment.

[0009] Preferably, for the mining condition analysis, it is necessary to conduct a detailed analysis of conditions such as the geological structure, mining method, and operation intensity of the mine, clarify the distribution of coal and rock strata structures underground, and identify the areas prone to compound dynamic disasters such as faults and folds during the mining process, so as to consider the influence of mining conditions on monitoring data and provide a basis for subsequent analysis.

[0010] Preferably, the data transmission is a key link connecting the data acquisition points and the data processing center. Select a suitable communication technology, such as wireless communication, wired network, or optical fiber communication. Establish a stable data transmission network to ensure the stability and reliability of the data transmission network, so as to reduce data loss and transmission delay. The terminals of the raw data acquisition module and the mining condition analysis module are connected to the data transmission module.

[0011] Preferably, the preprocessing module for early-stage data is designed to preprocess the collected raw data, such as cleaning, denoising, and standardization. During this process, data loss and information distortion should be avoided to ensure data quality; it is connected to the terminal of the data transmission module, and the data to be processed is transmitted by the communication technology in the data transmission module.

[0012] Preferably, the expert analysis and demonstration refers to inviting industry experts to analyze the data processed by the preprocessing module for early-stage data and provide professional opinions. However, it is necessary to ensure that the opinions and suggestions of the experts are highly objective and popular, so as to ensure the effectiveness of the data analysis results and enable them to be fully understood and applied by system designers.

[0013] Preferably, the determination of the optimal parameters refers to evaluating the influence degree of different parameters on mine safety through methods such as correlation analysis and principal component analysis (PCA), retaining the relevant parameters that can best reflect and monitor the coal-rock-gas composite dynamic disaster in combination with the expert analysis and demonstration module, then conducting sensitivity analysis on the key parameters to understand the impact of parameter changes on the performance of the early warning system, and finally using optimization algorithms (such as genetic algorithm, gradient descent method, etc.) to determine the key optimal parameters, such as microseismic, gas pressure, gas content, in-situ stress and other data, and then transmitting them to the corresponding computer database through another port of the data transmission module. For example, the microseismic data is a, the gas content is b, etc.;

[0014] Preferably, for the basic theoretical calculation, professional theoretical calculation formulas (such as stiffness theory, impact tendency theory, "three-criterion" theory, deformation instability theory, energy theory, strength theory, "rheological hypothesis", "fluid-structure interaction instability theory", "spherical shell instability hypothesis", "three-factor" theory, etc.) are required. The corresponding computer database is retrieved in combination with the theoretical calculation formula and the above computer database code. It should be noted that the corresponding parameters in the above theoretical calculation formula need to be replaced with the data codes corresponding to the database;

[0015] Preferably, for the numerical simulation analysis, the simulation details need to be designed according to the above parameters, including different working conditions, parameter changes, etc., to comprehensively evaluate the safety status of the mine. For example, numerical simulation software such as Comsol, PFC, FLAC3D, etc. is used to conduct single dynamic disaster simulation, and then the secondary development scheme is used to analyze its composite dynamic disaster, identify potential risk points and safety thresholds in the mine, adjust the simulation parameters, and conduct a large number of simulations and corrections;

[0016] Preferably, for the laboratory verification, a gas-solid coupling experimental system can be designed according to the coal-rock-gas composite dynamic disaster, the experimental conditions are set according to the relevant optimal parameters, the potential induction critical value of the composite dynamic disaster is studied, and multiple experiments are carried out. It should be noted that the variable control during the experiment must be ensured;

[0017] Preferably, the machine learning and neural network optimization is carried out on the basis of parameter revision of the data preprocessing module, expert analysis and demonstration, and optimal parameter determination module. First, it is necessary to design a neural network architecture, including the number of layers, the number of neurons, activation functions, etc. Then, methods such as cross-validation and hyperparameter tuning are used to optimize the model performance. Further, ensemble learning methods, such as random forest and gradient boosting machine, are considered to improve the generalization ability of the model. Further, the performance of the model is evaluated using a test set, and indicators such as accuracy, recall rate, and F1 score are concerned. Then, the results obtained from the above-mentioned large amounts of basic theoretical calculations, numerical simulation analyses, and laboratory verifications are placed in the machine learning and neural network optimization module for training and optimization, and finally, the induced critical values and basic models in different situations are obtained, such as theoretical models, simulation models, and experimental models.

[0018] Preferably, the coupling model construction refers to the combination of the theoretical model, simulation model, and experimental model. The parameters of typical dynamic disaster mines are respectively "fed" into the computer database for a large number of verifications to judge the differences among the three. Again, experts are invited to analyze and optimize the three major models, taking the essence and discarding the dross, and finally, a relatively complete full-time and space, multi-scale, multi-parameter coupling monitoring and early warning model and system are obtained.

[0019] On the other hand, the present invention also provides specific design steps for an intelligent monitoring and early warning scheme for multi-dimensional integration of mines:

[0020] S1. Define the monitoring scope and area, and reasonably arrange monitoring devices at multiple levels of points, surfaces, static, and dynamic, such as multiple monitoring devices such as microseismic sensors and gas pressure sensors, so that the entire monitored mine is fully covered to collect complete data within the scope.

[0021] S2. Analyze the specific laws of the mining conditions in the area, clarify the geological structure, mining method, operation intensity, etc. of the mine, and clarify the distribution of the underground coal and rock strata structures.

[0022] S3. Invite experts and scholars in the industry to evaluate and screen effective parameters and input them into the monitoring database, and then determine the number of monitoring points according to the effective parameters of the mine, that is, the number of collection layout points 3 (such as electromagnetic radiation pulses, microseismic numbers, gas pressure, gas concentration, etc.).

[0023] S4. Establish a stable data transmission network to ensure the stability and reliability of the data transmission network to reduce data loss and transmission delay.

[0024] S5. Perform data preprocessing such as cleaning, denoising, and standardization on the collected original data.

[0025] S6. Invite industry experts to analyze the data after the preliminary preprocessing of the data, provide professional opinions, and provide guarantee for screening the best parameter values;

[0026] S7. Evaluate the influence degree of different parameters on mine safety through methods such as correlation analysis and principal component analysis (PCA), retain the relevant parameters that can best reflect and monitor the coal-rock-gas composite dynamic disaster in combination with expert analysis and demonstration, and then conduct sensitivity analysis on the key parameters to determine the key best parameters, and then transmit them to the computer database through another port of the data transmission module, such as the microseismic data is a, the gas content is b, etc.;

[0027] S8. Call out the corresponding computer database in combination with the theoretical calculation formula and the above computer database code, and substitute the parameters into the theoretical calculation formula for a large number of calculation predictions;

[0028] S9. Design simulation details according to the above parameters, including different working conditions, parameter changes, etc., to comprehensively evaluate the safety status of the mine, identify potential risk points and safety thresholds of the mine through a large number of simulations, adjust the simulation parameters, and conduct a large number of analyses;

[0029] S10. Design a reasonable gas-solid coupling experimental system for coal-rock-gas composite dynamic disasters, set experimental conditions according to the relevant best parameters, and conduct multiple experiments;

[0030] S11. Place the results obtained from the above-mentioned large number of theoretical calculation modules, numerical simulation analysis modules and experimental verification modules into the machine learning and neural network optimization module for training and optimization, and obtain the induced critical values and basic models in different situations, such as theoretical models, simulation models and experimental models. Finally, deploy the trained three major models to the monitoring and early warning system;

[0031] S12. Combine the above-mentioned theoretical model, simulation model and experimental model, respectively "feed" the parameters of typical dynamic disaster mines into the optimized database for a large number of verifications, judge the differences among the three, and invite experts to analyze again to optimize the three major models, take the essence and discard the dross, and finally obtain a relatively complete full-time-space, multi-scale, multi-parameter coupling monitoring and early warning model and system;

[0032] S13. Select multiple mines to collect data, input them into the coupling monitoring and early warning model and system for on-site verification, and test the reliability and accuracy of the model.

[0033] Compared with the related technologies, the method of the intelligent monitoring and early warning system for multi-dimensional integration of mines proposed by the present invention has the following beneficial effects:

[0034] The present invention proposes a method of an intelligent monitoring and early warning system for multi-dimensional integration of mines:

[0035] 1. The intelligent monitoring and early warning solution for multi-dimensional integration in mines proposed by the present invention integrates means at multiple levels such as theoretical calculation, numerical analysis, experimental verification, big data optimization, and expert professional analysis, avoiding the limitations of traditional single solutions or the subjectivity of single human interference, and can effectively prevent mine dynamic disasters to a great extent, which is of great significance for the monitoring and early warning of reducing coal-rock-gas composite dynamic disasters and the safe production of mines.

[0036] 2. In the intelligent monitoring and early warning solution for multi-dimensional integration in mines proposed by the present invention, three major models (theoretical model, simulation model, and experimental model) are subjected to a large amount of optimization processing in deep learning and neural networks, and through comparative analysis of the three, the full-time-space, multi-scale, multi-parameter coupling monitoring and early warning model and system obtained can cover all regions and time periods of the mine, ensuring no blind spots and providing continuous monitoring data.

[0037] 3. In the intelligent monitoring and early warning solution for multi-dimensional integration in mines proposed by the present invention, multiple data sources and monitoring technologies are integrated, improving the richness and reliability of data, helping to more accurately identify and predict complex phenomena in mines. At the same time, the data transmission module ensures the real-time transmission of data, enabling the monitoring and early warning system to respond quickly and issue early warnings in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a specific step illustration diagram of the intelligent monitoring and early warning system method for multi-dimensional integration in mines proposed by the present invention.

[0039] Figure 2 It is a specific process schematic diagram of the intelligent monitoring and early warning system method for multi-dimensional integration in mines proposed by the present invention.

[0040] Reference numerals in the figure: 1. Raw data acquisition module; 2. Mining condition analysis module; 3. Acquisition layout point; 4. Expert analysis and demonstration; 5. Monitoring equipment; 6. Data transmission module; 7. Data preprocessing module; 8. Optimal parameter determination module; 9. Basic theoretical calculation; 10. Theoretical calculation formula; 11. Numerical simulation analysis module; 12. Laboratory verification; 13. Machine learning and neural network optimization module; 14. Theoretical model; 15. Simulation model; 16. Experimental model; 17. Optimization database; 18. Coupling monitoring and early warning model and system; 19. Field verification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] The present invention will be further described below with reference to the drawings and embodiments.

[0042] Please refer to Figure 1-2 , wherein, Figure 1Structural schematic diagram of a preferred embodiment of the intelligent monitoring and early warning system method for multi-dimensional integration in a mine proposed by the present invention; Figure 2 is Figure 1 The enlarged schematic diagram of part A shown in the figure.

[0043] The present invention proposes an intelligent monitoring and early warning system for multi-dimensional integration in a mine, which includes twelve major modules such as the raw data acquisition module 1, the mining condition analysis module 2, the data transmission module 6, the data preprocessing module 7, the expert analysis and demonstration 4, the optimal parameter determination module 8, the basic theory calculation 9, the numerical simulation analysis module 11, the experimental verification module 12, the machine learning and neural network optimization module 13, the coupled monitoring and early warning model and system 18, and the on-site verification 19.

[0044] A plurality of sensors and monitoring devices 5 should be deployed in the raw data acquisition module 1 to collect environmental data in the mine, such as gas concentration, gas pressure, drill cuttings data, electromagnetic parameters, microseismic data, temperature, humidity, etc., to ensure the accuracy and comprehensiveness of data acquisition, and regularly calibrate the equipment;

[0045] The mining condition analysis means that it is necessary to conduct a detailed analysis of the geological structure, mining method, operation intensity and other conditions of the mine, clarify the distribution of underground coal and rock strata structures, and clarify the range of areas prone to compound dynamic disasters such as faults and folds that may occur during the mining process, so as to consider the influence of mining conditions on monitoring data and provide a basis for subsequent analysis;

[0046] The data transmission is a key link connecting the data acquisition point and the data processing center. Select a suitable communication technology, such as wireless communication, wired network or optical fiber communication. Establish a stable data transmission network to ensure the stability and reliability of the data transmission network, so as to reduce data loss and transmission delay. The terminals of the raw data acquisition module 1 and the mining condition analysis module 2 are connected to the data transmission module 6;

[0047] The data preprocessing in the early stage aims to perform preprocessing such as cleaning, denoising, and standardization on the collected raw data. During this process, data loss and information distortion should be avoided to ensure data quality; it is connected to the terminal of the data transmission module 6, and the processed data are all transmitted by the communication technology in the data transmission module 6;

[0048] The expert analysis and demonstration 4 means inviting industry experts to analyze the data processed by the data preprocessing in the early stage and provide professional opinions, but it is necessary to ensure that the opinions and suggestions of the experts are highly objective and popular, so as to ensure the effectiveness of the data analysis results and can be fully understood and applied by the system designers;

[0049] The determination of the optimal parameters refers to evaluating the influence degree of different parameters on mine safety through methods such as correlation analysis and principal component analysis (PCA), retaining the relevant parameters that can best reflect and monitor the coal-rock-gas composite dynamic disaster in combination with expert analysis and demonstration, then conducting sensitivity analysis on the key parameters to understand the influence of parameter changes on the performance of the early warning system, and finally using optimization algorithms (such as genetic algorithm, gradient descent method, etc.) to determine the key optimal parameters, such as microseismic, gas pressure, gas content, in-situ stress and other data, and then transmitting them to the computer database, such as the microseismic data is a, the gas content is b, etc.;

[0050] The basic theoretical calculation needs to use professional theoretical calculation formulas (such as stiffness theory, impact tendency theory, "three criteria" theory, deformation instability theory, energy theory, strength theory, "rheological hypothesis", "fluid-structure interaction instability theory", "spherical shell instability hypothesis", "three-factor" theory, etc.), and call out the corresponding computer database according to the theoretical calculation formula and the above computer database code. It should be noted that the corresponding parameters in the above theoretical calculation formula need to be replaced with the data codes corresponding to the computer database;

[0051] The numerical simulation analysis needs to design simulation details according to the above parameters, including different working conditions, parameter changes, etc., to comprehensively evaluate the safety status of the mine. For example, single dynamic disaster simulations are carried out using numerical simulation software such as Comsol, PFC, FLAC3D, etc., and then the composite dynamic disaster is analyzed using the secondary development scheme to identify potential risk points and safety thresholds in the mine, adjust the simulation parameters, and conduct a large number of simulations and corrections;

[0052] The laboratory verification can design a gas-solid coupling experimental system according to the coal-rock-gas composite dynamic disaster, set the experimental conditions according to the relevant optimal parameters, study the potential induced critical values of the composite dynamic disaster, and conduct multiple experiments. It should be noted that variable control during the experiment must be ensured;

[0053] The machine learning and neural network optimization are carried out on the basis of parameter revision of the data preprocessing module 7, expert analysis and demonstration 4, and optimal parameter determination module 8. First, the neural network architecture needs to be designed, including the number of layers, the number of neurons, activation functions, etc., and then methods such as cross-validation and hyperparameter tuning are used to optimize the model performance. Then, ensemble learning methods such as random forest and gradient boosting machine are considered to improve the generalization ability of the model; further, the performance of the model is evaluated using the test set, and indicators such as accuracy, recall rate, and F1 score are concerned. Then, the results obtained from the above large number of basic theoretical calculations, numerical simulation analyses, and laboratory verifications are placed in the machine learning and neural network optimization module 13 for training and optimization, and finally the induced critical values and basic models in different situations are obtained, such as the theoretical model 14, the simulation model 15, and the experimental model 16;

[0054] The construction of the coupling model refers to the combination of the theoretical model 14, the simulation model 15, and the experimental model 16. The parameters of typical dynamic disaster mines are respectively "fed" into the optimization database 17 for a large number of verifications to judge the differences among the three. Then, experts are invited to analyze and optimize the three major models, taking the essence and discarding the dross, and finally obtaining a relatively complete full-time-space, multi-scale, and multi-parameter coupling monitoring and early warning model and system 18.

[0055] In addition, the present invention also proposes an intelligent monitoring and early warning method for multi-dimensional integration of mines, which specifically includes the following steps:

[0056] S1. Define the monitoring scope and area, and reasonably arrange monitoring devices at multiple levels of points, surfaces, static, and dynamic, such as multiple monitoring devices including microseismic sensors, gas pressure sensors, etc., so as to comprehensively cover the entire monitored mine and collect data within the complete range.

[0057] S2. Analyze the specific laws of the mining conditions in the area, clarify the geological structure, mining method, operation intensity, etc. of the mine, and clarify the distribution of the underground coal and rock strata structures.

[0058] S3. Invite industry experts and scholars to evaluate and screen effective parameters and input them into the monitoring database, and then determine the number of monitoring points according to the effective parameters of the mine, that is, the number of collection layout points 3 (such as electromagnetic radiation pulses, microseismic numbers, gas pressure, gas concentration, etc.).

[0059] S4. Establish a stable data transmission network to ensure the stability and reliability of the data transmission network, so as to reduce data loss and transmission delay.

[0060] S5. Perform data preprocessing such as cleaning, denoising, and standardization on the collected original data.

[0061] S6. Invite industry experts to analyze the data after the above data preprocessing and provide professional opinions to ensure the selection of the best parameter values.

[0062] S7. Evaluate the influence degree of different parameters on mine safety through methods such as correlation analysis and principal component analysis (PCA). Combine the expert analysis and demonstration to retain the relevant parameters that can best reflect and monitor the coal-rock-gas composite dynamic disasters, and then conduct sensitivity analysis on the key parameters to determine the key best parameters, and then transmit them to the computer database through another port of the data transmission module 6, such as the microseismic data is a, the gas content is b, etc.

[0063] S8. Call out the corresponding computer database in combination with the theoretical calculation formula and the above computer database code, and substitute the parameters into the theoretical calculation formula for a large number of calculation predictions.

[0064] S9. Design simulation details based on the above parameters, including different working conditions, parameter changes, etc., to comprehensively evaluate the safety status of the mine. Identify potential risk points and safety thresholds in the mine through a large number of simulations, adjust the simulation parameters, and conduct a large number of analyses;

[0065] S10. Design a reasonable experimental system for gas-solid coupling of coal-rock-gas composite dynamic disasters. Set experimental conditions according to relevant optimal parameters and conduct multiple experiments;

[0066] S11. Place the results obtained from the above-mentioned large number of theoretical calculation modules 10, numerical simulation analysis modules 11, and experimental verification modules 12 into the machine learning and neural network optimization module 13 for training and optimization to obtain the induced critical values and basic models in different situations, such as theoretical model 14, simulation model 15, and experimental model 16. Finally, deploy the trained three major models into the monitoring and early warning system;

[0067] S12. Combine the theoretical model 14, simulation model 15, and experimental model 16. Feed the parameters of typical dynamic disaster mines into the optimization database 17 respectively for a large number of verifications, judge the differences among the three, and invite experts to analyze again to optimize the three major models, taking the essence and discarding the dross. Finally, obtain a relatively complete all-time, all-space, multi-scale, multi-parameter coupling monitoring and early warning model and system 18;

[0068] S13. Select multiple mines to collect data and input it into the coupling monitoring and early warning model and system 18 for on-site verification 19 to test the reliability and accuracy of the model.

[0069] The intelligent monitoring and early warning system method for multi-dimensional integration of mines proposed by the present invention has significant progress compared with the related technologies:

[0070] First of all, this method integrates multi-level means such as theoretical calculation, numerical analysis, experimental verification, big data optimization, and expert professional analysis, overcomes the limitations of traditional single solutions and the subjectivity of human interference, effectively prevents mine dynamic disasters, and is of great significance for reducing coal-rock-gas composite dynamic disasters and ensuring the safe production of mines;

[0071] Secondly, through deep learning and neural network optimization of the three major models and comparative analysis, the all-time, all-space, multi-scale, multi-parameter coupling monitoring and early warning model and system obtained can comprehensively cover all areas and time periods of the mine without blind spots and provide continuous monitoring data;

[0072] Finally, integrating multiple data sources and monitoring technologies improves the richness and reliability of data, helps to more accurately identify and predict complex phenomena in the mine, and the data transmission module ensures the real-time transmission of data, enabling the monitoring and early warning system to respond quickly and issue early warnings in a timely manner.

[0073] The above are only embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. An intelligent monitoring and early warning system method for multi-dimensional integration in a mine, characterized in that It includes the following steps: S1. Define the monitoring scope and area, and reasonably arrange monitoring devices at multiple levels of points, surfaces, static and dynamic, such as multiple monitoring devices including microseismic sensors and gas pressure sensors, so as to comprehensively cover the entire monitored mine and collect data within the complete range; S2. Analyze the specific laws of the mining conditions in the area, clarify the geological structure, mining method, and operation intensity conditions of the mine, and sort out the distribution of the underground coal and rock strata structures; S3. Invite industry experts and scholars to evaluate and screen effective parameters and input them into the monitoring database, and then determine the number of monitoring points according to the effective parameters of the mine, that is, the number of acquisition layout points such as electromagnetic radiation pulses, microseismic numbers, gas pressure, and gas concentration; S4. Establish a stable data transmission network to ensure the stability and reliability of the data transmission network, so as to reduce data loss and transmission delay; S5. Perform preliminary preprocessing on the collected raw data, such as data cleaning, denoising, and standardization; S6. Invite industry experts to analyze the data after the above-mentioned preliminary data preprocessing, and provide professional opinions to ensure the selection of the best parameter values; Expert analysis and demonstration means inviting industry experts to analyze the data after the above-mentioned preliminary data preprocessing and provide professional opinions, but it is necessary to ensure that the opinions and suggestions of the experts are highly objective and popular, and can ensure the effectiveness of the data analysis results and can be fully understood and applied by the system designers; S7. Evaluate the influence degree of different parameters on the mine safety through correlation analysis and principal component analysis methods, retain the relevant parameters that can best reflect and monitor the coal-rock-gas composite dynamic disasters in combination with expert analysis and demonstration, and then conduct sensitivity analysis on the key parameters to determine the key optimal parameters, and then transmit them to the computer database through another port of the data transmission module, such as the microseismic data is a and the gas content is b; The determination of the optimal parameters means evaluating the influence degree of different parameters on the mine safety through correlation analysis and principal component analysis, retaining the relevant parameters that can best reflect and monitor the coal-rock-gas composite dynamic disasters in combination with expert analysis and demonstration, and then conducting sensitivity analysis on the key parameters to understand the influence of parameter changes on the performance of the early warning system, and finally using an optimization algorithm to determine the key optimal parameters, such as microseismic, gas pressure, gas content, and in-situ stress data, and then transmitting them to the computer database, such as the microseismic data is a and the gas content is b; S8. Call out the corresponding computer database in combination with the theoretical calculation formula and the above-mentioned computer database code, and substitute the parameters into the theoretical calculation formula for a large number of calculation predictions; Basic theoretical calculations need to use professional theoretical calculation formulas, such as stiffness theory, impact tendency theory, "three-criterion" theory, deformation instability theory, energy theory, strength theory, "rheological hypothesis", "fluid-structure coupling instability theory", "spherical shell instability hypothesis", "three-factor" theory. Call out the corresponding computer database in combination with the theoretical calculation formula and the above-mentioned computer database code. It should be noted that the corresponding parameters in the above-mentioned theoretical calculation formula need to be replaced with the data codes corresponding to the corresponding computer database; S9. Design simulation details based on the above parameters, including different working conditions and parameter changes, to comprehensively evaluate the safety status of the mine. Identify potential risk points and safety thresholds in the mine through a large number of simulations, adjust the simulation parameters, and conduct a large number of analyses. Numerical simulation analysis needs to design simulation details based on the above parameters, including different working conditions and parameter changes, to comprehensively evaluate the safety status of the mine. For example, use numerical simulation software such as Comsol, PFC, and FLAC3D to conduct single dynamic disaster simulations, and then use the secondary development scheme to analyze its compound dynamic disasters, identify potential risk points and safety thresholds in the mine, adjust the simulation parameters, and conduct a large number of simulations and corrections. S10. Design a reasonable gas-solid coupling experimental system for coal-rock-gas compound dynamic disasters, set experimental conditions according to relevant optimal parameters, and conduct multiple experiments. Laboratory verification can design a gas-solid coupling experimental system for coal-rock-gas compound dynamic disasters, set experimental conditions according to relevant optimal parameters, study the potential induction critical values of compound dynamic disasters, conduct multiple experiments, and note that variable control during the experiment must be ensured. S11. Place the results obtained from the above large number of theoretical calculation modules, numerical simulation analysis modules, and experimental verification modules into the machine learning and neural network optimization module for training and optimization to obtain induction critical values and basic models under different conditions, such as theoretical models, simulation models, and experimental models. Finally, deploy the trained three major models to the monitoring and early warning system. S12. Combine the above theoretical model, simulation model, and experimental model, respectively "feed" the parameters of typical dynamic disaster mines into the optimized database for a large number of verifications, judge the differences among the three, and invite experts to analyze again to optimize the three major models, take the essence and discard the dross, and finally obtain a relatively complete full-time and space, multi-scale, multi-parameter coupling monitoring and early warning model and system. S13. Select multiple mines to collect data, input it into the coupling monitoring and early warning model and system for on-site verification, and test the reliability and accuracy of the model.

2. The method of the intelligent monitoring and early warning system for multi-dimensional integration in a mine according to claim 1, characterized in that, The machine learning and neural network optimization is carried out on the basis of the parameter revision of the above data preprocessing, expert analysis and demonstration, and best parameter determination. First, the neural network architecture needs to be designed, including the number of layers, the number of neurons, and the activation function. Then, cross-validation and hyperparameter tuning methods are used to optimize the model performance. Further, ensemble learning methods such as random forest and gradient boosting machine are considered to improve the generalization ability of the model. Further, use the test set to evaluate the performance of the model, pay attention to accuracy, recall rate, and F1 score indicators, and then place the results obtained from the above large number of theoretical calculations, numerical simulation analyses, and experimental verifications into the machine learning and neural network optimization module for training and optimization, and finally obtain induction critical values and basic models under different conditions, such as theoretical models, simulation models, and experimental models.

3. The method of the intelligent monitoring and early warning system for multi-dimensional integration in a mine according to claim 1, characterized in that, Coupling model construction refers to the combination of the theoretical model, simulation model, and experimental model. The parameters of typical dynamic disaster mines are respectively "fed" into the optimized database for a large number of verifications to judge the differences among the three. Then, experts are invited again for analysis to optimize the three major models, taking the essence and discarding the dross, and finally obtaining a relatively complete full-time-space, multi-scale, and multi-parameter coupling monitoring and warning model and system.

Images