Intelligent monitoring and early warning system for composite disasters in coal mine goaf

Abstract

The invention provides an intelligent monitoring and early warning system for composite disasters in a coal mine goaf. The intelligent monitoring and early warning system comprises a first step of a comprehensive monitoring module, wherein the comprehensive monitoring module comprises a geological structure monitoring unit, a stress-strain monitoring unit, a displacement monitoring unit, a gas monitoring unit, a hydrological monitoring unit and a temperature monitoring unit; the method is used for obtaining various monitoring data. The intelligent analysis and early warning module is used for conducting real-time analysis on the multi-source heterogeneous data by constructing a goaf safety risk assessment model, then calculating a real-time risk assessment value of a single disaster and a total risk assessment value, and achieving single-disaster and multi-disaster coupling early warning of the hidden danger of the coal mine goaf. The goaf geological structure, stress strain, displacement, gas and temperature can be monitored in real time, potential safety hazards such as rock mass instability, gas accumulation and fire disasters can be found in time, and therefore precautionary measures are taken in advance, accidents are effectively avoided, and the life safety of personnel and normal production of a coal mine are guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal mines, relates to goafs, and specifically relates to an intelligent monitoring and early warning system for compound disasters in coal mine goafs. Background Art

[0002] Traditional monitoring methods for coal mine goafs often have many limitations. For example, relying on manual inspections and simple instrument measurements is not only inefficient but also difficult to obtain comprehensive, real-time, and accurate monitoring data. For the understanding of geological structures, early on, it may mainly rely on limited geological exploration data, and it is impossible to timely grasp the dynamic changes of the geological structure in the goaf, such as the development of faults and folds.

[0003] In terms of stress and strain monitoring, traditional monitoring means may not be able to achieve real-time continuous monitoring, and it is difficult to accurately reflect the changes in rock mass stress and strain, thus making it difficult to early warn of potential rock mass instability risks.

[0004] In terms of displacement monitoring, the accuracy and timeliness of traditional methods are insufficient, and it is impossible to accurately measure the displacements of the goaf surface and key parts, making it difficult to effectively predict disasters such as possible ground collapses.

[0005] In terms of gas monitoring, previous sensors may only be able to detect a few types of gases, and their sensitivity and accuracy are limited. They cannot timely detect abnormal changes in gas concentration and have insufficient early warning capabilities for dangerous situations such as gas explosions in the goaf.

[0006] In terms of temperature monitoring, traditional temperature measurement methods may be difficult to achieve comprehensive and continuous monitoring of the temperature distribution in the goaf and cannot timely detect possible fire hazards.

[0007] In addition, the data transmission and processing capabilities of traditional monitoring systems are weak, unable to quickly analyze a large amount of monitoring data, and difficult to achieve real-time risk assessment and early warning. Summary of the Invention

[0008] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide an intelligent monitoring and early warning system for compound disasters in coal mine goafs to solve the technical problem that the performance of the known monitoring and early warning systems in the existing technology needs to be further improved.

[0009] To solve the above technical problems, the present invention is implemented by adopting the following technical solutions:

[0010] An intelligent monitoring and early warning system for compound disasters in coal mine goafs, the system includes the following modules:

[0011] Step 1, Comprehensive Monitoring Module:

[0012] The described comprehensive monitoring module is used to obtain a variety of monitoring data.

[0013] Step 2, Data Transmission and Processing Module:

[0014] The described data transmission and processing module is used to transmit and process various monitoring data to obtain multi-source heterogeneous data.

[0015] Step 3, Big Data Module:

[0016] The described big data module is used to implement the warehousing, cleaning, classification, and storage management of multi-source heterogeneous data.

[0017] Step 4, Intelligent Analysis and Early Warning Module:

[0018] The described intelligent analysis and early warning module is used to perform real-time analysis on multi-source heterogeneous data by constructing a goaf safety risk assessment model, and then calculate the real-time risk assessment values of single disasters and the total risk assessment value, so as to realize single-disaster and multi-disaster coupling early warning of dangerous hidden dangers in coal mine goafs.

[0019] The present invention also has the following technical features:

[0020] In Step 1, the described comprehensive monitoring module includes a geological structure monitoring unit, a stress and strain monitoring unit, a displacement monitoring unit, a gas monitoring unit, a hydrogeological monitoring unit, and a temperature monitoring unit.

[0021] In Step 101, the described geological structure monitoring unit is used to obtain the geological structure information of the goaf by using geophysical exploration techniques such as seismic exploration and electrical prospecting and drilling exploration techniques; the geological structure information includes faults, folds, and water-rich abnormal bodies.

[0022] In Step 102, the stress and strain monitoring unit is used to monitor the stress and strain changes and deformation changes of rock masses and airtight walls in real time, and stress and strain gauges are arranged.

[0023] In Step 103, the described displacement monitoring unit is based on the Global Navigation Satellite System (GNSS) and Real-Time Kinematic (RTK) technology to monitor the displacement of the goaf surface, and a laser rangefinder is used to measure the relative displacement in the goaf.

[0024] In Step 104, a variety of gas sensors are arranged in the gas monitoring unit, which are automatically calibrated according to environmental conditions and historical data to monitor the gas concentration in the goaf in real time.

[0025] In Step 105, the described hydrogeological monitoring unit monitors the water level, water quality, and drainage volume of the water-bearing aquifer adjacent to the goaf and the goaf water accumulation in real time, establishes a mine water quality database, and uses the monitoring data to realize the identification of the goaf water source and the monitoring and analysis of the water accumulation degree.

[0026] Step 106: The temperature monitoring unit is used to monitor the temperature distribution in the goaf by using a distributed optical fiber temperature sensor, and a computer is used to correct and compensate the temperature, so as to monitor abnormal fires in the goaf.

[0027] In step 102, in the stress and strain monitoring unit, the relationship between stress and resistance change is expressed as:

[0028] σ = K × (ΔR / R).

[0029] In the formula:

[0030] σ represents stress;

[0031] K represents the sensitivity coefficient of the strain gauge;

[0032] ΔR is the change in resistance;

[0033] R is the initial resistance.

[0034] In step 103, in the displacement monitoring unit, the formula for coordinate transformation and displacement calculation is: Displacement = Square root of [(X2 - X1) 2 + (Y2 - Y1) 2 + (Z2 - Z1) 2 .

[0035] In the formula:

[0036] (X1, Y1, Z1) and (X2, Y2, Z2) represent the coordinate values measured at different times.

[0037] Specifically in step 104, the multiple gas sensors include a methane sensor, a carbon monoxide sensor, and a carbon dioxide sensor.

[0038] In step 104, the specific algorithm formula for automatic calibration according to environmental conditions and historical data is:

[0039] Assume that the gas concentration to be monitored is C, and the environmental conditions include temperature T, humidity H, and pressure P.

[0040] Establish a multiple linear regression model through historical data:

[0041] C = a0 + a1T + a2H + a3P + ε

[0042] In the formula:

[0043] a0 represents the intercept;

[0044] a1, a2, and a3 all represent regression coefficients;

[0045] ε represents the error term.

[0046] During actual monitoring, the real-time acquired temperature, humidity, and pressure are T now , P now , H now , respectively. Then the predicted gas concentration C predicted is:

[0047] C predicted = a0 + a1T now + a2H now + a3P now

[0048] The actually measured gas concentration is C measure . Then the calibration coefficient K is:

[0049]

[0050] The finally calibrated gas concentration C calibrated is:

[0051] C calibrated = K × C measured .

[0052] In step 106, the specific method of using a computer to correct and compensate for temperature is:

[0053] Temperature correction formula: Tcor = Tmea + △T.

[0054] In the formula:

[0055] Tcor represents the corrected temperature;

[0056] Tmea represents the measured temperature;

[0057] △T represents the temperature correction value.

[0058] Temperature compensation formula: Tcom = Tcor + f(Tam).

[0059] In the formula:

[0060] Tcom represents the compensated temperature;

[0061] Tcor represents the corrected temperature;

[0062] Tam represents the ambient temperature;

[0063] f(Tam) represents the compensation function of the ambient temperature.

[0064] In step four, the goaf safety risk assessment model includes the following steps:

[0065] Step 40101, set the basic weight values W 水 , W火 , W 瓦斯 and W 顶板 .

[0066] Step 40102: For the cases where the water, fire, gas and roof disasters in the goaf occur separately, determine the quantitative score S according to the abnormal degree of a single disaster factor 单 , then the risk assessment value R of a single disaster 单 = W 单 × S 单 , where W 单 is the basic weight value of this kind of disaster.

[0067] Step 40103: For the cases where the water, fire, gas and roof disasters in the goaf are coupled in pairs or multiple disasters are coupled, the risk assessment value R of the coupled disasters 耦合 is:

[0068]

[0069] In the formula:

[0070] i and j respectively represent different disaster types;

[0071] W i represents the basic weight value of the i disaster type;

[0072] W j represents the basic weight value of the j disaster type;

[0073] S i represents the abnormal score of the i disaster type;

[0074] S j represents the abnormal score of the j disaster type;

[0075] C ij represents the coupling coefficient between the i disaster type and the j disaster type.

[0076] Step 40104: Obtain the total risk assessment value R 总 = ∑R 单 + R 耦合 .

[0077] In Step 4, the specific implementation steps of the intelligent analysis and early warning module are as follows:

[0078] Step 401: Establish a goaf safety risk assessment model:

[0079] Step 402: Real-time analysis:

[0080] The multi-source heterogeneous data under real-time monitoring is analyzed in real time through the goaf safety risk assessment model described in step 401 to obtain the risk assessment values of single disasters in real time and the total risk assessment value.

[0081] Step 403, compound disaster warning:

[0082] The compound disasters mentioned above include single disasters and multi-disaster couplings of water, fire, gas and roof disasters in the goaf.

[0083] Step 40301, according to the risk assessment values of single disasters in real time obtained in step 402, conduct single-disaster warnings for water, fire, gas and roof disasters in the goaf.

[0084] Step 40302, according to the total risk assessment value in real time obtained in step 402, conduct multi-disaster coupling warnings for the two-by-two couplings or multi-disaster couplings of water, fire, gas and roof disasters in the goaf.

[0085] Step 404, multi-level warning:

[0086] For the single-disaster warnings and multi-disaster coupling warnings in step 403, set warning signals at different levels respectively, and the warning information is conveyed to the staff in a timely manner through SMS, APP push or audible and visual alarm methods.

[0087] Compared with the prior art, the present invention has the following technical effects:

[0088] (Ⅰ) The present invention realizes the real-time monitoring of the geological structure, stress and strain, displacement, gas and temperature of the goaf, can timely discover potential safety hazards, such as rock mass instability, gas accumulation, fire, etc., so as to take preventive measures in advance, effectively avoid accidents, and ensure the safety of personnel's lives and the normal production of coal mines.

[0089] (Ⅱ) The intelligent analysis and warning module of the present invention based on big data and cloud computing combines historical data to build an accurate risk assessment model, quickly analyzes the real-time monitoring data, can accurately evaluate the safety status of the goaf, and timely notifies relevant personnel through multi-level warning methods to ensure a rapid response in case of danger and reduce losses.

[0090] (Ⅲ) The present invention adopts a data transmission network of 5G network or industrial Ethernet, and a data processing center of cloud computing and big data technology, can realize fast and stable data transmission and efficient processing, ensure the timeliness and accuracy of monitoring data, and provide a reliable basis for decision-making.

[0091] (Ⅳ) The advanced technologies and equipment adopted in the comprehensive monitoring module of the present invention, such as three-dimensional seismic exploration technology, distributed optical fiber temperature sensors, high-precision stress and strain monitoring equipment, etc., can provide more accurate monitoring data, reduce errors and misjudgments.

[0092] (Ⅴ) The gas monitoring unit of the present invention introduces intelligent algorithms for automatic calibration, which can adapt to factors such as environmental condition changes and equipment aging, ensuring the accuracy of gas monitoring data; the correction and compensation calculations of the temperature monitoring unit improve the accuracy of temperature monitoring.

[0093] (Ⅵ) The intelligent monitoring and warning system of the present invention reduces the need for manual inspections, lowering labor costs; at the same time, by promptly detecting problems and taking measures, it reduces production interruptions and equipment damage caused by accidents, improving the production efficiency and economic benefits of the coal mine.

[0094] The following further elaborates on the specific content of the present invention in conjunction with embodiments. Specific Embodiments

[0095] It should be noted that all modules, units, technologies, equipment, networks, centers, and servers in the present invention, unless otherwise specified, all adopt the modules, units, technologies, equipment, networks, centers, and servers known in the prior art.

[0096] With the continuous progress of technology, the coal mining industry has increasingly high requirements for the safety monitoring of goafs. There is a need for a system that can comprehensively, real - time, and accurately monitor various parameters of goafs and can perform intelligent analysis and warning to ensure the safe production of coal mines, reduce accidents, and improve production efficiency and economic benefits. Therefore, the intelligent monitoring and warning system for compound disasters in coal mine goafs of the present invention emerges as the times require.

[0097] The following provides specific embodiments of the present invention. It should be noted that the present invention is not limited to the following specific embodiments, and all equivalent transformations made on the basis of the technical solutions of this application fall within the protection scope of the present invention.

[0098] Embodiment:

[0099] This embodiment provides an intelligent monitoring and warning system for compound disasters in coal mine goafs, which includes the following modules:

[0100] Step 1, Comprehensive Monitoring Module:

[0101] The comprehensive monitoring module is used to obtain a variety of monitoring data.

[0102] In step 1, the comprehensive monitoring module includes a geological structure monitoring unit, a stress - strain monitoring unit, a displacement monitoring unit, a gas monitoring unit, a hydrogeological monitoring unit, and a temperature monitoring unit.

[0103] Step 101: The geological structure monitoring unit is used to obtain the geological structure information of the goaf by using geophysical exploration techniques such as seismic exploration and electrical prospecting and drilling exploration techniques. The geological structure information includes faults, folds, and water-rich anomalies.

[0104] Step 102: The stress and strain monitoring unit is used to monitor the stress and strain changes and deformation changes of the rock mass and the airtight wall in real time, and stress and strain gauges are arranged.

[0105] In Step 102, in the stress and strain monitoring unit, the relationship between stress and resistance change is expressed as:

[0106] σ = K×(ΔR / R), where σ represents stress, K represents the sensitivity coefficient of the strain gauge, ΔR is the resistance change amount, and R is the initial resistance.

[0107] Step 103: The displacement monitoring unit, based on the Global Navigation Satellite System (GNSS) and Real-Time Kinematic (RTK) technology, monitors the displacement of the goaf surface and measures the relative displacement of key parts in the goaf by using a laser rangefinder. In this embodiment, the key parts refer to the known and commonly used key parts in the goaf in the art.

[0108] In Step 103, in the displacement monitoring unit described above, the formula for coordinate transformation and displacement calculation is: Displacement = Square root of [(X2 - X1) 2 +(Y2 - Y1) 2 +(Z2 - Z1) 2 .

[0109] In the formula:

[0110] (X1, Y1, Z1) and (X2, Y2, Z2) represent the coordinate values measured at different times.

[0111] Step 104: A variety of gas sensors are installed in the gas monitoring unit, which are automatically calibrated according to environmental conditions and historical data, and the gas concentration in the goaf is monitored in real time.

[0112] Specifically in Step 104, the variety of gas sensors include methane sensors, carbon monoxide sensors, and carbon dioxide sensors.

[0113] In Step 104, further, the specific algorithm formula for automatic calibration according to environmental conditions and historical data is:

[0114] Assume that the gas concentration to be monitored is C, and the environmental conditions include temperature T, humidity H, and pressure P.

[0115] A multiple linear regression model is established through historical data:

[0116] C = a0 + a1T + a2H + a3P + ∈

[0117] In the formula:

[0118] a0 represents the intercept;

[0119] a1, a2, and a3 all represent regression coefficients;

[0120] ε represents the error term.

[0121] Specifically in this embodiment, the values of the coefficients in the above multiple linear regression model are obtained through training with historical data.

[0122] During actual monitoring, the temperature, humidity, and pressure obtained in real time are T now , P now , H now , respectively, then the predicted gas concentration C predicted is:

[0123] C predicted = a0 + a1T now + a2H now + a3P now

[0124] The actually measured gas concentration is C measure , then the calibration coefficient K is:

[0125]

[0126] The finally calibrated gas concentration C calibrated is:

[0127] C calibrated = K × C measured .

[0128] Step 105, the hydrographic monitoring unit monitors the water level, water quality, and drainage volume of the water - filled aquifer adjacent to the goaf and the water accumulation in the goaf in real time, establishes a mine water quality database, and uses the monitoring data to realize the identification of the goaf water source and the monitoring and analysis of the water accumulation degree.

[0129] Step 106, the temperature monitoring unit is used to monitor the temperature distribution in the goaf by using a distributed optical fiber temperature sensor, and a computer is used to correct and compensate the temperature, so as to monitor the abnormal fire in the goaf.

[0130] Step 106, the specific method of using a computer to correct and compensate the temperature is:

[0131] Temperature correction formula: Tcor = Tmea + △T.

[0132] In the formula:

[0133] Tcor represents the corrected temperature;

[0134] Tmea represents the measured temperature;

[0135] △T represents the temperature correction value.

[0136] Temperature compensation formula: Tcom = Tcor + f(Tam).

[0137] In the formula:

[0138] Tcom represents the compensated temperature;

[0139] Tcor represents the corrected temperature;

[0140] Tam represents the ambient temperature;

[0141] f(Tam) represents the compensation function of the ambient temperature.

[0142] Step two, data transmission and processing module:

[0143] The data transmission and processing module is used to transmit and process various monitoring data to obtain multi-source heterogeneous data.

[0144] As a specific solution of this embodiment, in step two, the data transmission and processing module includes a data acquisition terminal, a data transmission network, and a data center connected in sequence. Among them:

[0145] No. 201, the acquisition terminal transmits the data collected by each monitoring device in the comprehensive monitoring module to the data center through the data transmission network.

[0146] No. 202, the data communication network of the data transmission network adopts 5G, WIFI network or industrial Ethernet.

[0147] No. 203, the data processing center can use cloud computing and big data technologies to quickly process and analyze the monitoring data to obtain multi-source heterogeneous data.

[0148] Step three, big data module:

[0149] The big data module is used to realize the warehousing, cleaning, classification, and storage management of multi-source heterogeneous data.

[0150] In this embodiment, the multi-source heterogeneous data is: unstructured data including CAD drawings, videos, and images, and structured data of online monitoring and manual measurement; the multi-source heterogeneous data is assigned attribute information according to different time dimensions and geographical dimensions.

[0151] Step four, intelligent analysis and warning module:

[0152] Intelligent analysis and early warning module, which is used to construct a goaf safety risk assessment model to conduct real-time analysis on multi-source heterogeneous data, and then calculate the real-time risk assessment value of a single type of disaster and the total risk assessment value, so as to realize the single-disaster and multi-disaster coupling early warning of the dangerous hidden dangers in the coal mine goaf.

[0153] As a specific solution of this embodiment, in step four, the goaf safety risk assessment model includes the following steps:

[0154] Step 40101, set the basic weight values W 水 , W 火 , W 瓦斯 and W 顶板 respectively for water, fire, gas and roof disasters.

[0155] Step 40102, for the case where water, fire, gas and roof disasters in the goaf occur alone, determine the quantitative score S 单 according to the abnormal degree of single-disaster factors. Then the risk assessment value R 单 =W 单 ×S 单 , where W 单 is the basic weight value of this type of disaster.

[0156] In this embodiment, the scoring range of S 单 is from 0 to 10 points. The higher the abnormal degree, the higher the score. The greater the proportion of the gas concentration exceeding the normal range, the higher the score of the gas disaster.

[0157] Step 40103, for the case of pairwise coupling or multi-disaster coupling of water, fire, gas and roof disasters in the goaf, the risk assessment value R 耦合 of the coupling disaster is:

[0158]

[0159] In the formula:

[0160] i and j respectively represent different disaster types;

[0161] W i represents the basic weight value of the i disaster type;

[0162] W j represents the basic weight value of the j disaster type;

[0163] S i represents the abnormal score of the i disaster type;

[0164] S j represents the abnormal score of the j disaster type;

[0165] C ijDenote the coupling coefficient between the i-th disaster type and the j-th disaster type; the coupling coefficient reflects the degree of mutual enhancement or weakening when the two disasters occur simultaneously.

[0166] Step 40104, obtain the total risk assessment value R 总 = ∑R 单 + R 耦合 .

[0167] Specifically in this embodiment, the system regularly dynamically adjusts and optimizes the basic weight value and the coupling coefficient according to new monitoring data and the actual occurrence of disasters, so as to continuously improve the accuracy of disaster compound assessment and early warning. For example, when it is found that the frequency and harm degree of the coupling occurrence of a certain disaster increase within a certain period of time, the relevant weight value and coupling coefficient are appropriately increased.

[0168] Specifically in this embodiment, the specific construction process of the goaf safety risk assessment model adopts the construction process of the goaf safety risk assessment model known in the art.

[0169] Specifically in this embodiment, a goaf safety risk assessment model is constructed by combining historical data, fully considering the mutual influence relationship between water, fire, gas and roof disasters, as well as the possibility and influence degree of the coupling occurrence of disasters, and incorporating the coupling disaster factors into the model index system.

[0170] Specifically in this embodiment, a goaf safety risk assessment model is established. During the operation of the system, the model is trained by using big data through neural networks, multivariate programming, and dynamic rule algorithms to optimize the early warning identification method.

[0171] As a specific solution of this embodiment, in step four, the specific implementation steps of the intelligent analysis and early warning module are as follows:

[0172] Step 401, establish a goaf safety risk assessment model:

[0173] Step 402, real-time analysis:

[0174] The multi-source heterogeneous data monitored in real time is analyzed in real time through the goaf safety risk assessment model obtained in step 401 to obtain the real-time risk assessment value of a single disaster and the total risk assessment value.

[0175] Step 403, compound disaster early warning:

[0176] The compound disasters mentioned above include single disasters and multi-disaster couplings of water, fire, gas and roof disasters in the goaf.

[0177] Step 40301, according to the real-time risk assessment value of a single disaster obtained in step 402, conduct single-disaster early warning on the water, fire, gas and roof disasters in the goaf.

[0178] Specifically, in this embodiment, for any single disaster such as water, fire, gas and roof disasters in the goaf, the warning method is to set the relevant disaster warning threshold range. When the single monitoring data exceeds the limit, a warning is issued according to the relevant threshold setting.

[0179] Step 40302: According to the real-time total risk assessment value obtained in step 402, conduct multi-disaster coupling warning for the coupling of any two or more disasters among water, fire, gas and roof disasters in the goaf.

[0180] Specifically, in this embodiment, if the total risk value exceeds the preset high-risk threshold, a warning signal of high risk is issued; if the total risk value is within the medium-risk threshold range, a warning signal of medium risk is issued, and according to the risk contribution ratio of different disasters, the main disaster factors and coupling relationships are clearly pointed out in the warning information.

[0181] Step 404: Multi-level warning:

[0182] For the single-disaster warning and multi-disaster coupling warning in step 403, different levels of warning signals are set respectively, and the warning information is promptly conveyed to the staff through text messages, APP push or sound and light alarms.

[0183] In this embodiment, different levels of warning signals are distinguished by red, orange, yellow and blue.

[0184] Specifically, in this embodiment, the development and change of roof rock fissures and other conditions are monitored in real time through microseismic and roof displacement sensors, and the roof deformation and fissure development conditions are obtained through data inversion; First, start the blue warning of gas and conduct corresponding warning and forecasting according to the gas content; Secondly, when the roof fissures develop to a certain distance from the aquifer, start the blue warning of water disaster and conduct corresponding warning and forecasting according to the monitoring of the water level of goaf water accumulation; If fissure development, water and gas are warned at the same time, the warning level is raised; Combine parameters such as OC and temperature in the goaf to warn of fire; Among them, for the multi-dimensional coupling warning of water disaster, if the water accumulation in the goaf rises and there are obvious changes in the water-bearing aquifer involved in the goaf, a warning is triggered; Combine the drainage volume monitoring data with the water level data to raise or lower the warning level; At the same time, couple with the drainage system data to provide data support for the regulation of the drainage system. And compare with the water quality monitoring data and database parameters to identify the water source.

[0185] Specifically, in this embodiment, when water disaster is coupled with roof or floor disasters, the water level and water volume in the goaf and the change of the water level of the water-bearing aquifer are combined with the stress and strain changes of the roof or floor and the surface settlement conditions to identify the water disaster accident in the goaf, trigger a warning and guide the prevention and control of water disasters.

[0186] Specifically in this embodiment, the combination of water disaster and airtight monitoring triggers an early warning when the water level and water volume in the goaf increase, and there are stress changes or displacement changes in the airtight wall of the goaf.

Claims

1. An intelligent monitoring and early warning system for complex disasters in coal mine goafs, characterized in that, The system includes the following modules: Step 1, Comprehensive Monitoring Module: The Comprehensive Monitoring Module includes a geological structure monitoring unit, a stress and strain monitoring unit, a displacement monitoring unit, a gas monitoring unit, a hydrogeological monitoring unit, and a temperature monitoring unit; Step 101, The geological structure monitoring unit is used to obtain the geological structure information of the goaf by using geophysical exploration techniques such as seismic exploration and electrical prospecting and drilling exploration techniques; The geological structure information includes faults, folds, and water-rich abnormal bodies; Step 102, The stress and strain monitoring unit is used to monitor the stress and strain changes and deformation changes of the rock mass and the airtight wall in real time, and stress and strain gauges are arranged; Step 103, The displacement monitoring unit monitors the displacement of the goaf surface based on the Global Navigation Satellite System and Real-Time Kinematic (RTK) technology, and measures the relative displacement in the goaf by using a laser rangefinder; Step 104, A variety of gas sensors are arranged in the gas monitoring unit, which are automatically calibrated according to environmental conditions and historical data, and the gas concentration in the goaf is monitored in real time; Step 105, The hydrogeological monitoring unit monitors the water level, water quality, and drainage volume of the water-filled aquifer adjacent to the goaf and the accumulated water in the goaf in real time, establishes a mine water quality database, and uses the monitoring data to realize the identification of the goaf water source and the monitoring and analysis of the accumulated water degree; Step 106, The temperature monitoring unit is used to monitor the temperature distribution of the goaf by using a distributed fiber optic temperature sensor, and a computer is used to correct and compensate the temperature, so as to monitor the abnormal fire in the goaf.

2. The intelligent monitoring and early warning system for compound disasters in coal mine goafs according to claim 1, characterized in that, In Step 102, in the stress and strain monitoring unit, the relationship between stress and resistance change is expressed as: σ = K×(ΔR / R); In the formula: σ represents stress; K represents the sensitivity coefficient of the strain gauge; ΔR is the change in resistance; R is the initial resistance.

3. The intelligent monitoring and early warning system for compound disasters in coal mine goafs according to claim 1, characterized in that, In step 103, in the displacement monitoring unit, the formulas for coordinate transformation and displacement calculation are: displacement amount = square root of [(X2 - X1) 2 +(Y2 - Y1) 2 +(Z2 - Z1) 2 ; In the formula: (X1, Y1, Z1) and (X2, Y2, Z2) represent the coordinate values measured at different times.

4. The intelligent monitoring and early warning system for complex disasters in coal mine goafs according to claim 1, characterized in that, Specifically in Step 104, the variety of gas sensors include a methane sensor, a carbon monoxide sensor, and a carbon dioxide sensor.

5. The intelligent monitoring and early warning system for complex disasters in coal mine goafs as claimed in claim 1, wherein In Step 104, the specific algorithm formula for automatic calibration according to environmental conditions and historical data is: Assume that the gas concentration to be monitored is C, and the environmental conditions include temperature T, humidity H, and pressure P; A multiple linear regression model is established through historical data: C = a0 + a1T + a2H + a3P + ∈ In the formula: a0 represents the intercept; a1, a2, and a3 all represent regression coefficients; ε represents the error term; During actual monitoring, the real-time obtained temperature, humidity and pressure are T now , P now , H now , respectively. Then the predicted gas concentration C predicted is: C predicted = a0 + a1T now + a2H now + a3P now The actually measured gas concentration is C measure , then the calibration coefficient K is as follows: The finally calibrated gas concentration C calibrated is as follows: C calibrated = K × C measured .

6. The intelligent monitoring and early warning system for compound disasters in coal mine goafs according to claim 1, characterized in that In Step 106, the specific method for the computer to correct and compensate the temperature is: Temperature correction formula: Tcor = Tmea + △T; In the formula: Tcor represents the corrected temperature; Tmea represents the measured temperature; △T represents the temperature correction value; Temperature compensation formula: Tcom = Tcor + f(Tam); In the formula: Tcom represents the compensated temperature; Tcor represents the corrected temperature; Tam represents the ambient temperature; f(Tam) represents the compensation function of the ambient temperature.

7. The intelligent monitoring and early warning system for complex disasters in coal mine goafs according to claim 1, characterized in that, The system also includes the following modules: Step 2, Data Transmission and Processing Module: The described data transmission and processing module is used to transmit and process various monitoring data to obtain multi-source heterogeneous data; Step 3. Big data module: The described big data module is used to implement the storage, cleaning, classification, and storage management of multi-source heterogeneous data.

8. The intelligent monitoring and early warning system for compound disasters in coal mine goafs according to claim 1, characterized in that The system further includes the following modules: Step 4, Intelligent analysis and early warning module: The described intelligent analysis and early warning module is used to perform real-time analysis on multi-source heterogeneous data by constructing a goaf safety risk assessment model, and then calculate the real-time risk assessment value of a single disaster and the total risk assessment value, so as to realize single-disaster and multi-disaster coupling early warning of dangerous hidden dangers in the coal mine goaf.

9. The intelligent monitoring and early warning system for compound disasters in coal mine goafs as described in claim 8, characterized in that, In Step 4, the goaf safety risk assessment model includes the following steps: Step 40101, set the basic weight values W for water, fire, gas and roof disasters respectively 水 , W 火 , W 瓦斯 and W 顶板 ; Step 40102: For the cases where the disasters of goaf water, fire, gas and roof occur separately, determine the quantitative score S according to the abnormal degree of a single disaster factor 单 , then the risk assessment value R of a single disaster 单 = W 单 × S 单 , where W 单 is the basic weight value of this kind of disaster; Step 40103. For the case of two - fold coupling or multi - hazard coupling of goaf water, fire, gas and roof disasters, the risk assessment value R of the coupled disasters 耦合 is as follows: In the formula: i and j respectively represent different disaster types; W i Represents the basic weight value of the i-th disaster type; W j Represents the basic weight value of the j disaster type; S i Indicates the anomaly score for the i-th disaster type; S j Indicates the anomaly score for the jth disaster type; C ij Denotes the coupling coefficient between the i-th disaster type and the j-th disaster type; Step 40104, obtain the total risk assessment value R 总 = ∑R 单 + R 耦合 .

10. The intelligent monitoring and early warning system for compound disasters in coal mine goafs as described in claim 8, characterized in that, In Step 4, the specific implementation steps of the intelligent analysis and early warning module are as follows: Step 401, Establish a goaf safety risk assessment model: Step 402, Real-time analysis: Perform real-time analysis on the real-time monitored multi-source heterogeneous data through the goaf safety risk assessment model described in Step 401 to obtain the real-time risk assessment value of a single disaster and the total risk assessment value; Step 403, Composite disaster early warning: The described composite disasters include single disasters and multi-disaster couplings of water, fire, gas, and roof disasters in the goaf; Step 40301, According to the real-time risk assessment value of a single disaster obtained in Step 402, perform single-disaster early warning on water, fire, gas, and roof disasters in the goaf; Step 40302, According to the real-time total risk assessment value obtained in Step 402, perform multi-disaster coupling early warning on the two-by-two coupling or multi-disaster coupling of water, fire, gas, and roof disasters in the goaf; Step 404, Multi-level early warning: For the single-disaster early warning and multi-disaster coupling early warning in Step 403, set different levels of early warning signals respectively, and the early warning information is timely conveyed to the staff through text messages, APP push, or audible and visual alarm methods.

Images