Risk monitoring method for coal mine goaf

Abstract

The invention provides a risk monitoring method for a coal mine goaf, and the method comprises the steps: obtaining risk association information provided by a plurality of information collection devices in the coal mine goaf in real time according to a preset encryption communication mode; based on all the risk association information and a pre-trained risk assessment model, determining a current risk index value of the coal mine goaf, the risk assessment model being used for reflecting an association relationship between the risk index value of the coal mine goaf and all the risk association information; determining the current risk level of the coal mine goaf based on the current risk index value of the coal mine goaf and the index weight of the risk index value; and executing a risk early warning strategy corresponding to the current risk level of the coal mine goaf. According to the technical scheme, reliable technical guarantee is provided for safe production of the coal mine goaf.

Description

[0001] The present application relates to the technical field of coal mine safety, and particularly relates to a risk monitoring method for a coal mine goaf.

[0002] Coal mine goaf risk monitoring has always been a key link of coal mine safety production. With the increase of mining depth and width, the geological conditions of the goaf become more and more complex. The traditional monitoring means rely on manual inspection and single-point equipment, which is low in efficiency and limited in data, and it is difficult to fully reflect the goaf conditions. Moreover, the backward data transmission mode in the goaf leads to insufficient real-time and accuracy of safety detection. In a word, the existing safety monitoring method cannot adapt to the influence of complex geological conditions and mining activities, and the early warning mechanism is extensive, which cannot accurately classify and push according to the risk severity and emergency level, seriously restricting the guarantee ability of coal mine safety production.

[0003] Therefore, how to realize comprehensive, real-time and accurate goaf risk monitoring has become a technical problem to be solved at present.

[0004] Embodiments of the present application provide a risk monitoring method for a coal mine goaf, aiming to solve the technical problem that the risk monitoring effect is difficult to meet the actual safety demand due to insufficient risk monitoring capability of the goaf in related technologies.

[0005] In a first aspect, the embodiments of the present application provide a risk monitoring method for a coal mine goaf, comprising:

[0006] Real-time acquisition of risk associated information provided by a plurality of information collection devices in the coal mine goaf according to a predetermined encrypted communication mode;

[0007] Determination of a current risk index value of the coal mine goaf based on all the risk associated information and a pre-trained risk assessment model, wherein the risk index value includes risk severity, risk emergency level, risk hazard range and secondary disaster occurrence probability, and the risk assessment model is used to reflect the correlation between the risk index value of the coal mine goaf and all the risk associated information;

[0008] Determination of a current risk level of the coal mine goaf based on the current risk index value of the coal mine goaf and an index weight of the risk index value;

[0009] Execution of a risk early warning strategy corresponding to the current risk level of the coal mine goaf.

[0010] In an embodiment of the present application, optionally, before the real-time acquisition of risk associated information provided by a plurality of information collection devices in the coal mine goaf, it further comprises: ​​​

[0011] The plurality of information collection devices in the coal mine goaf respectively collect a plurality of risk-related information in real time, wherein the plurality of risk-related information includes roof displacement, stress distribution information, gas concentration, underground water level, temperature, humidity, microseismic activity information, and pore pressure, radioactive material content, rock acoustic emission characteristic information, underground water flow rate and flow direction, soil resistivity, gas composition change information, and rock permeability in the goaf stratum.

[0012] In an embodiment of the present application, optionally, the real-time acquisition of the risk-related information provided by each of the plurality of information collection devices in the coal mine goaf in the predetermined encrypted communication mode comprises:

[0013] The risk-related information provided by each of the plurality of information collection devices is encrypted using a lightweight symmetric encryption algorithm to obtain first encrypted data, and the key of the first encrypted data is updated in real time and dynamically through a quantum key distribution network;

[0014] A timestamp and a device digital signature are set for the first encrypted data to obtain second encrypted data;

[0015] The second encrypted data and a device digital certificate are packaged together as a transaction request, and the transaction request is sent to a verification node of a blockchain for the verification node to verify whether the timestamp, the device digital signature, and the device digital certificate are valid;

[0016] In the case where the verification node determines that the timestamp, the device digital signature, and the device digital certificate are valid, the transaction request that passes the verification is broadcast to the blockchain for inter-node information synchronization, and the second encrypted data is transmitted to a risk monitoring center for determining the current risk index value of the coal mine goaf.

[0017] In an embodiment of the present application, optionally, in the process of transmitting the second encrypted data to the risk monitoring center for determining the current risk index value of the coal mine goaf, further comprising:

[0018] All network devices in the path of the second encrypted data transmitted to the risk monitoring center are taken as topological nodes, and the communication links between the network devices are taken as topological edges to construct a transmission path distribution map;

[0019] Based on the transmission path distribution map and an ant colony algorithm, the selection probability of each transmission path between the second encrypted data and the risk monitoring center is determined, wherein,

[0020]

[0021] p ia selected probability of an ith transmission path between the second encrypted data and the risk monitoring center, a pheromone concentration of the ith transmission path, determined by the communication capability characteristics of each topology node and each topology edge in the ith transmission path, a heuristic function of the ith transmission path, determined by a path length of the ith transmission path, n is a total number of transmission paths, j is a transmission path code, and a and β are weights of the pheromone concentration and the heuristic function, respectively;

[0022] determining the transmission path with the highest selected probability as a target path for transmitting the second encrypted data to the risk monitoring center.

[0023] In an embodiment of the present application, optionally, determining the current risk indicator value of the coal mine goaf based on all the risk correlation information and the pre-trained risk assessment model comprises:

[0024] determining a hidden state of each time period based on the risk correlation information of each time period in a plurality of historical time periods and a current time period by a long short-term memory network, wherein the hidden state is used to reflect a spatiotemporal feature of the risk correlation information in the time period;

[0025] determining an association strength between each of the historical time periods and the current time period based on the hidden state of each time period and a preset parameter matrix, wherein the association strength is used to reflect a spatiotemporal feature change of the risk correlation information from the historical time period to the current time period;

[0026] normalizing all the association strengths based on a Softmax function to obtain a weight of each of the association strengths;

[0027] performing weighted summation processing on the hidden state of the time period corresponding to each of the association strengths according to the weight of each of the association strengths to obtain the risk severity.

[0028] In an embodiment of the present application, optionally, determining the current risk indicator value of the coal mine goaf based on all the risk correlation information and the pre-trained risk assessment model further comprises:

[0029] determining an emergency degree feature of each of the sub time periods based on the risk correlation information in each of the sub time periods in the current time period, wherein the emergency degree feature comprises a mutation feature, an extreme value feature and a coupling feature;

[0030] Based on the urgency features of each sub-period and a pre-trained support vector machine model, the risk urgency of the current period is determined, wherein the support vector machine model is used to reflect the correlation between the urgency features of each sub-period in the current period and the risk urgency of the current period.

[0031] In one embodiment of this application, optionally, determining the current risk indicator value of the coal mine goaf based on all the risk association information and the pre-trained risk assessment model further includes:

[0032] Based on all the aforementioned risk-related information, a three-dimensional topological map of the coal mine goaf is constructed, and the three-dimensional topological map is divided into spatial grids.

[0033] Based on the three-dimensional topological map of the coal mine goaf, the ant colony algorithm is used to simulate the first disaster development path of the coal mine goaf.

[0034] The perturbation parameters of the ant colony algorithm are determined by Monte Carlo random perturbation simulation, and the development path of the second disaster in the coal mine goaf is simulated based on the perturbation parameters.

[0035] In the first disaster development path and the second disaster development path, the risk level of each spatial grid is determined, and spatial grids with a risk level higher than a predetermined safety probability are identified as risk grids, wherein the risk level represents the probability that the spatial grid will be affected during disaster development;

[0036] Taking the potential risk occurrence point in the coal mine goaf as the center, the distance between each risk grid and the center is determined as the affected radius, and the risk hazard range of the coal mine goaf is determined based on the largest affected radius.

[0037] In one embodiment of this application, optionally, determining the current risk indicator value of the coal mine goaf based on all the risk association information and the pre-trained risk assessment model further includes:

[0038] Based on predetermined geological feature evaluation rules, the geological features and possible risk types corresponding to the risk association information are determined;

[0039] Based on the possible risk types, the risk association information, and the geological features, a Bayesian causal network is constructed. The input nodes of the Bayesian causal network are the possible risk types and the geological features. The hidden nodes connected to the input nodes in the Bayesian causal network are the risk behaviors caused by the possible risk types. The output nodes connected to the hidden nodes in the Bayesian causal network are the secondary disasters caused by the risk behaviors.

[0040] Based on the historical frequency of occurrence of the possible risk types, the conditional probability of each node in the Bayesian causal network is determined;

[0041] Using the risk association information of the current time period as the input information of the Bayesian causal network, the probability of the occurrence of the secondary disaster is output through the Bayesian causal network.

[0042] In a second aspect, embodiments of this application provide a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the method described in the first aspect above.

[0043] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions for performing the method described in the first aspect above.

[0044] The above technical solution addresses the technical problem of insufficient risk monitoring capabilities in goaf areas, which makes it difficult to meet actual safety requirements. It deploys multiple dedicated sensors to collect multi-dimensional risk data from coal mine goaf areas in real time. Quantum encryption and blockchain technology ensure data transmission security. Furthermore, a risk assessment model integrating multiple intelligent algorithms is used to quantitatively assess the severity, urgency, scope of harm, and probability of secondary disasters from multiple dimensions. Finally, a weighted calculation is used to determine the risk level, and a tiered early warning strategy is implemented. This achieves closed-loop management of the entire process from data collection, secure transmission, intelligent assessment to precise early warning. It solves the systemic problems of single data sources, one-sided assessments, and delayed responses in traditional coal mine goaf monitoring. Multi-source data fusion analysis improves the comprehensiveness and accuracy of risk assessment, intelligent algorithms enable early risk identification and dynamic prediction, and the tiered early warning mechanism ensures timely and targeted emergency response. This significantly improves the intelligence level and early warning effectiveness of coal mine safety monitoring, effectively prevents major accidents, provides reliable technical support for coal mine safety production, and achieves a fundamental shift from passive response to proactive prevention. [Attached Image Description]

[0045] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1A flowchart of a risk monitoring method for coal mine goaf according to an embodiment of this application is shown;

[0047] Figure 2 A flowchart is shown below illustrating a method for encrypted data transmission in risk monitoring of coal mine goaf areas according to an embodiment of this application;

[0048] Figure 3 A block diagram of a computer device according to one embodiment of this application is shown;

[0049] Figure 4 A block diagram of a computer device according to another embodiment of this application is shown.

Detailed Implementation Methods

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Figure 1 A flowchart of a risk monitoring method for coal mine goaf areas according to an embodiment of this application is shown.

[0052] like Figure 1 As shown, a risk monitoring method for coal mine goaf areas according to an embodiment of this application includes:

[0053] Step 102: Obtain risk-related information from multiple information collection devices within the coal mine goaf in real time, according to a predetermined encrypted communication method.

[0054] The predetermined encrypted communication method uses a lightweight symmetric encryption algorithm combined with quantum key distribution technology, such as AES (Advanced Encryption Standard) encryption and a dynamic quantum key update mechanism, to ensure the security of data transmission.

[0055] The risk-related information includes, but is not limited to, one or more of the following: roof displacement, stress distribution information, gas concentration, groundwater level, temperature, humidity, microseismic activity information, pore pressure, radioactive material content, rock acoustic emission characteristics, groundwater flow velocity and direction, soil resistivity, gas composition change information, and rock permeability.

[0056] The information collection device is used to collect risk-related information, and a corresponding information collection device is set up for each risk-related information. Before step 102, multiple risk-related information items are collected in real time by the multiple information collection devices in the coal mine goaf.

[0057] Specifically, roof displacement is acquired using laser rangefinders or displacement sensors; stress distribution information is obtained using resistance strain gauge sensors or fiber optic stress sensors; methane concentration is monitored using catalytic combustion methane sensors or infrared methane sensors; groundwater level is measured using submersible level sensors or ultrasonic level sensors; temperature is detected using thermocouples or resistance temperature sensors; humidity is acquired using capacitive or resistive humidity sensors; microseismic activity information is obtained using microseismic monitoring instruments based on acceleration sensors; pore pressure inside the goaf rock strata is monitored using pore pressure sensors; radioactive material content is measured using radioactive detectors such as Geiger counters; acoustic emission characteristics of rocks are acquired using acoustic emission sensors; groundwater flow velocity and direction are obtained using electromagnetic or ultrasonic velocimeters combined with flow direction sensors; soil resistivity is detected using resistivity meters; gas composition changes are monitored using gas chromatographs or infrared gas analyzers; and rock permeability is measured using permeability meters.

[0058] Therefore, by obtaining multi-dimensional risk correlation information, a comprehensive data foundation is provided for subsequent analysis.

[0059] This step solves the problem of data being easily tampered with or leaked in traditional monitoring by using encryption, overcomes the lag in manual inspections, and provides a guarantee for the accuracy and timeliness of risk monitoring.

[0060] Step 104: Based on all the risk association information and the pre-trained risk assessment model, determine the current risk index value of the coal mine goaf.

[0061] The risk index value reflects the quantitative assessment result of the current overall safety status of the coal mine goaf. The risk assessment model is used to reflect the correlation between the risk index value of the coal mine goaf and all the risk-related information. The risk assessment model here integrates multiple networks or models, and each network or model can be used to calculate a risk index value.

[0062] In one possible design, risk index values ​​include, but are not limited to, four types: risk severity, risk urgency, risk hazard range, and probability of secondary disasters. Risk severity reflects the potential extent and depth of damage caused by the current risk event; risk urgency reflects the imminent occurrence of the risk event and the urgent need for emergency measures; risk hazard range reflects the spatial area and scope of impact that the risk event may affect; and the probability of secondary disasters reflects the likelihood of triggering a chain reaction of disasters under the current risk situation.

[0063] By integrating multiple intelligent algorithms into a risk assessment model, a multi-dimensional and precise quantitative assessment of the safety status of coal mine goaf areas can be achieved. This model dynamically assesses four key dimensions: severity, urgency, hazard range, and probability of secondary disasters, comprehensively reflecting the risk status of the goaf area. This multi-indicator collaborative assessment mechanism overcomes the limitations of traditional single-risk assessments, considering both the degree of damage and the urgency of emergency response, while also predicting the possible scope of impact and chain reactions. This provides a more scientific and comprehensive basis for decision-making in coal mine safety production. Through the intuitive presentation of quantitative indicators, managers can quickly grasp the risk situation and take timely and targeted prevention and control measures, effectively improving the accuracy and foresight of coal mine safety management.

[0064] Step 106: Determine the current risk level of the coal mine goaf based on the current risk index value and the index weight of the risk index value.

[0065] Risk indicator values ​​are calculated using a preliminary risk assessment model, reflecting the risk characteristics of the goaf in different dimensions. The indicator weights reflect the varying contributions of each factor to the overall risk. By using weighted calculations to synthesize multi-dimensional indicator values ​​into a unified risk level, the problems of strong subjectivity and inconsistent standards in traditional risk assessments are solved, making risk level determination more objective and accurate, and providing a scientific basis for subsequent early warning responses. Simultaneously, through quantitative level classification, managers can quickly identify risk levels and promptly activate corresponding emergency plans.

[0066] Step 108: Execute the risk warning strategy corresponding to the current risk level of the coal mine goaf.

[0067] The risk warning strategy sets differentiated response measures for different levels, such as triggering a mine-wide evacuation for particularly serious risks and initiating a partial shutdown for major risks. The warning content includes key information such as the risk location, characteristics, and handling recommendations, for example, displaying the risk area distribution through 3D visualization. This step achieves precise warning response by intelligently matching risk levels with warning strategies, solving the problems of delayed or over-reacting responses in traditional warning methods. This tiered warning mechanism significantly improves the targeting and timeliness of emergency response, effectively reduces accident losses, avoids unnecessary resource waste, and provides strong protection for safe coal mine production.

[0068] In addition, early warning information can be pushed out in real time through various channels, such as SMS, radio, and smart terminals, to ensure that relevant personnel receive it in a timely manner.

[0069] The above technical solution deploys multiple dedicated sensors to collect multi-dimensional risk data from coal mine goaf areas in real time. Quantum encryption and blockchain technology ensure data transmission security. Furthermore, a risk assessment model integrating multiple intelligent algorithms is used to quantitatively assess the severity, urgency, scope of harm, and probability of secondary disasters from multiple dimensions. Finally, a weighted calculation is used to determine the risk level and implement a tiered early warning strategy. This achieves closed-loop management of the entire process from data collection, secure transmission, intelligent assessment to precise early warning, solving systemic problems in traditional coal mine goaf monitoring such as single data sources, incomplete assessments, and delayed responses. Multi-source data fusion analysis improves the comprehensiveness and accuracy of risk assessment, intelligent algorithms enable early risk identification and dynamic prediction, and the tiered early warning mechanism ensures timely and targeted emergency response. This significantly improves the intelligence level and early warning effectiveness of coal mine safety monitoring, effectively preventing major accidents and providing reliable technical support for coal mine safety production, achieving a fundamental shift from passive response to proactive prevention.

[0070] Figure 2 A flowchart of a data encryption transmission method in risk monitoring of coal mine goaf areas according to an embodiment of this application is shown.

[0071] like Figure 2 As shown, a data encryption transmission method for risk monitoring of coal mine goaf areas according to an embodiment of this application specifically includes:

[0072] Step 1022: Use a lightweight symmetric encryption algorithm to encrypt the risk association information provided by each of the multiple information acquisition devices to obtain the first encrypted data, and dynamically update the key of the first encrypted data in real time through a quantum key distribution network.

[0073] Lightweight symmetric encryption algorithms employ efficient encryption methods to encrypt various types of risky data collected by sensors, forming the first layer of encrypted data to ensure confidentiality during transmission. Quantum key distribution networks dynamically update the encryption keys in real time using quantum communication principles, such as a key distribution mechanism based on the BB84 protocol, effectively preventing key cracking. Thus, through dual encryption protection, the problem of traditional encryption methods' fixed and easily cracked keys is solved, significantly improving the security level of data transmission and providing reliable assurance for subsequent processing.

[0074] Step 1024: Set a timestamp and device digital signature for the first encrypted data to obtain the second encrypted data.

[0075] By setting timestamps, data timeliness can be ensured and replay attacks can be prevented. Device digital signatures can verify the authenticity of data sources. This solves the problem of data being easily forged or tampered with in traditional monitoring and lays a credible foundation for blockchain verification.

[0076] Step 1026: Package the second encrypted data and the device digital certificate together into a transaction request, and send the transaction request to the blockchain verification node so that the verification node can verify whether the timestamp, the device digital signature and the device digital certificate are valid.

[0077] The device digital certificate contains the device's public key and identity information, reflecting the device's security level. Transaction requests package secondary encrypted data, certificates, and timestamps into standardized data packets, such as those using JSON or Protocol Buffers. Verification nodes automatically check the validity of the timestamps and the legitimacy of the signatures and certificates through smart contracts. Thus, through the distributed verification mechanism of blockchain, the single point of trust problem in centralized systems is solved, ensuring that only data from legitimate devices can enter the system, providing access assurance for data synchronization.

[0078] Step 1028: If the verification node determines that the timestamp, the device digital signature, and the device digital certificate are valid, the verified transaction request is broadcast to the blockchain for inter-node information synchronization, and the second encrypted data is transmitted to the risk monitoring center for determining the current risk indicator value of the coal mine goaf.

[0079] Inter-node information synchronization is achieved through a blockchain consensus algorithm, ensuring data consistency across all nodes; for example, each transaction requires confirmation from a majority of nodes. The risk monitoring center, as the final data recipient, possesses decryption and analysis capabilities. Thus, the blockchain broadcast mechanism ensures the accuracy and full traceability of safety monitoring data for coal mine goaf areas, avoiding the data loss or omission issues common in traditional monitoring, and providing a complete and reliable data source for risk assessment of coal mine goaf areas.

[0080] Optionally, the information collection methods and calculation formulas for each risk-related information are as follows.

[0081] a. Top plate displacement:

[0082] Data acquisition method: using a laser rangefinder or displacement sensor;

[0083] Formula: Change in displacement = Measured value - Initial value.

[0084] b. Stress distribution:

[0085] Data acquisition method: stress sensor, such as: resistance strain gauge sensor or fiber optic stress sensor;

[0086] Formula: Stress = Strain × Elastic modulus, where strain is measured by a sensor and elastic modulus is a material constant.

[0087] c. Gas concentration:

[0088] Data acquisition method: gas sensor, such as catalytic combustion gas sensor or infrared gas sensor; formula: gas concentration = sensor output signal × calibration coefficient.

[0089] d. Groundwater level:

[0090] Data acquisition method: Water level sensor, such as: submersible water level sensor, ultrasonic water level sensor; Formula: Water level height = Measurement distance - Sensor installation height.

[0091] e. Temperature:

[0092] Data acquisition method: Temperature sensor such as thermocouple, resistance temperature detector;

[0093] Formula: Temperature = Sensor output voltage or resistance × Temperature coefficient.

[0094] f. Humidity:

[0095] Data acquisition method: Humidity sensor, such as capacitive humidity sensor or resistive humidity sensor;

[0096] Formula: Humidity = Sensor output capacitance or resistance × Humidity conversion coefficient.

[0097] g. Microseismic activity:

[0098] Data acquisition method: The microseismic monitoring instrument is based on an accelerometer.

[0099] Formula: Vibration energy = Integral (acceleration² × time).

[0100] h. Pore pressure within the rock strata:

[0101] Data acquisition method: pore pressure sensor;

[0102] Formula: Pore pressure = Sensor output value × Calibration coefficient.

[0103] i. Content of radioactive materials:

[0104] Data acquisition method: Radioactive detectors, such as Geiger counters;

[0105] Formula: Radioactivity = Count rate ÷ Detection efficiency.

[0106] j. Acoustic emission characteristics of rocks:

[0107] Data acquisition method: Acoustic emission sensor;

[0108] Formula: Acoustic emission energy = integral (acoustic emission signal amplitude 2 × time).

[0109] k. Groundwater flow velocity and direction:

[0110] Data acquisition method: The flow meter uses an electromagnetic flow meter or an ultrasonic flow meter and a flow direction sensor;

[0111] Flow velocity formula: Flow velocity = Sensor output frequency × Flow velocity coefficient;

[0112] Flow direction formula: Flow direction angle = Sensor output angle value.

[0113] l. Soil resistivity:

[0114] Data acquisition method: resistivity meter;

[0115] Formula: Resistivity = (Measured voltage ÷ Measured current) × Electrode coefficient.

[0116] m. Changes in gas composition:

[0117] Data acquisition method: Gas analyzer (such as gas chromatograph, infrared gas analyzer, etc.);

[0118] Formula: Component concentration = Detection signal × Calibration curve.

[0119] n. Rock permeability:

[0120] Data collection method: Permeability meter;

[0121] Formula: Permeability = Flow rate × Fluid viscosity × Length ÷ (Area × Pressure difference).

[0122] In addition, during the process of transmitting the second encrypted data to the risk monitoring center used to determine the current risk index value of the coal mine goaf, the optimal transmission path can be selected through the ant colony algorithm to achieve load balancing of data transmission.

[0123] Specifically, a transmission path distribution map is constructed using all network devices along the path from the second encrypted data to the risk monitoring center as topology nodes and the communication links between network devices as topology edges. Based on the transmission path distribution map and the ant colony algorithm, the probability of each transmission path between the second encrypted data and the risk monitoring center being selected is determined. Wherein:

[0124]

[0125] p i Let be the probability that the i-th transmission path between the second encrypted data and the risk monitoring center is selected. The pheromone concentration of the i-th transmission path is determined by the communication capability characteristics of each topological node and each topological edge in the i-th transmission path. The heuristic function for the i-th transmission path is determined by the path length of the i-th transmission path, n is the total number of transmission paths, j is the transmission path code, and α and β are the weights of the pheromone concentration and the heuristic function, respectively.

[0126] Based on this, the transmission path with the highest selection probability is determined as the target path for transmitting the second encrypted data to the risk monitoring center.

[0127] In this process, the transmission path distribution map abstracts network devices as topology nodes and communication links as topology edges to construct the network topology structure for data transmission, such as a hybrid network composed of underground fiber optic nodes and wireless relay devices.

[0128] Ant colony optimization (ACO) simulates the foraging behavior of ants in nature, dynamically evaluating path quality through pheromone concentration and a heuristic function. In one possible design, pheromone concentration reflects the historical communication quality of the path; for example, high-bandwidth links accumulate pheromone concentration faster. The heuristic function considers the physical length of the path, prioritizing shorter paths with fewer hops. Furthermore, the probability of each path being selected is calculated using a probability formula, ensuring that high-quality paths are more likely to be selected while retaining the possibility of exploring new paths. This dynamic path selection mechanism solves the problem of uneven network load in the complex environment of underground coal mines. It fully utilizes high-bandwidth links to improve transmission efficiency while automatically avoiding congested or faulty nodes to ensure communication reliability. By optimizing data transmission paths in real time, it significantly reduces data transmission latency and packet loss rate, providing stable and timely data support for the risk monitoring center, thereby ensuring the real-time performance and accuracy of the entire monitoring system and making risk assessment results more reliable. Simultaneously, this adaptive routing strategy reduces the workload of manual network maintenance and improves the system's autonomous operation capability.

[0129] exist Figure 1 and Figure 2 Based on the illustrated embodiment, the calculation methods for each risk indicator value are as follows.

[0130] In one possible design, based on the risk association information of each of multiple historical time periods and the current time period, a hidden state of each time period is determined using a Long Short-Term Memory (LSTM) network. The hidden state reflects the spatiotemporal characteristics of the risk association information within that time period. Based on the hidden state of each time period and a preset parameter matrix, the association strength between each historical time period and the current time period is determined. The association strength reflects the spatiotemporal changes in the risk association information from the historical time period to the current time period. All association strengths are normalized using a Softmax function to obtain the weight of each association strength. The hidden states of the time periods corresponding to each association strength are weighted and summed according to their respective weights to obtain the risk severity.

[0131] Long Short-Term Memory (LSTM) networks capture the temporal characteristics of risk data through their unique memory unit structure. For example, they can identify gradual trends in roof displacement or abrupt patterns in gas concentration, and the generated hidden states effectively integrate spatiotemporal information. A pre-defined parameter matrix stores feature weights set by expert experience, used to calculate the correlation strength between historical and current periods. For example, changes in rock permeability can be assigned a higher weight in the pre-defined parameter matrix. The correlation strength quantifies the continuity of risk evolution across different periods. Normalization using the Softmax function ensures a reasonable allocation of weights for each period, preventing a single period from dominating the assessment results.

[0132] The weighted summation output by this calculation method considers both the timeliness of recent data and the preservation of long-term evolution patterns, ensuring that the risk severity assessment reflects both the immediate situation and development trends. This assessment method, which integrates temporal characteristics and expert knowledge, overcomes the shortcomings of traditional static assessments that ignore the time dimension. It significantly improves the ability to capture the evolution patterns of risks in goaf areas, making the severity judgment more consistent with the actual risk accumulation process and providing a precise basis for implementing tiered prevention and control measures. Furthermore, this method possesses adaptive learning capabilities, continuously optimizing the assessment results as data accumulates.

[0133] In one possible design, based on the risk association information within each sub-period of the current time period, the urgency characteristics of each sub-period are determined, wherein the urgency characteristics include mutation characteristics, extreme value characteristics, and coupling characteristics; based on the urgency characteristics of each sub-period and a pre-trained support vector machine model, the risk urgency of the current time period is determined, wherein the support vector machine model is used to reflect the correlation between the urgency characteristics exhibited by each sub-period of the current time period and the risk urgency of the current time period.

[0134] Sub-time periods are broken down into smaller time units, such as 10-second intervals, to facilitate the capture of rapid changes in risk parameters. Abrupt change features within the urgency profile are used to identify sudden fluctuations in parameters, such as a surge in gas concentration within 5 seconds; extreme value features detect situations where parameters exceed safety thresholds, such as roof displacement reaching warning levels; and coupling features are used to analyze the coordinated changes of multiple parameters, such as a rise in groundwater level accompanied by a sudden change in rock stress. Based on this, a pre-trained support vector machine model learns feature patterns from historical data to establish a mapping relationship between features and urgency levels.

[0135] Therefore, by using multi-feature joint analysis, the problem of slow response to sudden risks in traditional methods is solved, enabling accurate identification of emergency situations requiring immediate action. The nonlinear classification capability of support vector machines effectively handles the interactions between complex features, allowing urgency assessment to consider both anomalies in single parameters and the interconnected effects of multiple parameters, significantly improving the timeliness and accuracy of risk warnings and buying valuable time for emergency response. Furthermore, the model's adaptive learning capability continuously optimizes the assessment results with new data.

[0136] In one possible design, a three-dimensional topological map of the coal mine goaf is constructed based on all the aforementioned risk-related information, and the three-dimensional topological map is divided into spatial grids. Based on the three-dimensional topological map of the coal mine goaf, an ant colony algorithm is used to simulate the first disaster development path of the coal mine goaf. The perturbation parameters of the ant colony algorithm are determined through Monte Carlo random perturbation simulation, and the second disaster development path of the coal mine goaf is simulated based on the perturbation parameters. In the first disaster development path and the second disaster development path, the risk level of each spatial grid is determined, and the spatial grids with a risk level higher than a predetermined safety probability are identified as risk grids, wherein the risk level represents the probability that the spatial grid will be affected during disaster development. Taking the possible risk occurrence point in the coal mine goaf as the center, the distance between each risk grid and the center is determined as the affected radius, and the risk hazard range of the coal mine goaf is determined based on the largest affected radius.

[0137] Three-dimensional topology maps, by integrating spatial data collected from various sensors, can construct three-dimensional models of goaf areas. For example, parameters such as rock strata structure and gas distribution can be visualized in three dimensions. Spatial grid division decomposes the model into standardized evaluation units, facilitating refined analysis. Ant colony algorithms simulate the natural spread of disasters. For example, they can simulate the chain reaction path of roof collapse. The first disaster development path reflects the most likely disaster spread trend. Monte Carlo random perturbation introduces uncertainties, such as the random distribution of rock strata fissures, and can generate a second disaster development path to assess various unexpected situations in the most likely disaster spread trend.

[0138] Furthermore, the probability of each grid cell being affected can be quantified using risk level calculations; for example, the closer to the epicenter, the higher the risk level. The affected radius radiates outward from the risk source, and the boundary of the hazard range is defined by the maximum radius. This boundary can be used to determine the area requiring evacuation.

[0139] This technical solution overcomes the limitations of traditional methods for disaster range prediction through dual-path simulation and probabilistic assessment. It considers both deterministic patterns and random factors, making hazard range prediction more comprehensive and reliable. Dynamic gridded assessment enables precise characterization of the risk space, providing a scientific basis for emergency response plan development. Simultaneously, visual display facilitates managers' rapid understanding of the disaster's impact range, effectively improving the pertinence and timeliness of emergency decision-making.

[0140] In one possible design, based on predetermined geological feature evaluation rules, the geological features and possible risk types corresponding to the risk association information are determined; based on the possible risk types, the risk association information, and the geological features, a Bayesian causal network is constructed, wherein the input nodes of the Bayesian causal network are the possible risk types and the geological features, the hidden nodes connected to the input nodes in the Bayesian causal network are the risk behaviors brought about by the possible risk types, and the output nodes connected to the hidden nodes in the Bayesian causal network are the secondary disasters brought about by the risk behaviors; based on the historical occurrence frequency of the possible risk types, the conditional probability of each node in the Bayesian causal network is determined; using the risk association information of the current time period as the input information of the Bayesian causal network, the probability of occurrence of the secondary disaster is output through the Bayesian causal network.

[0141] Geological feature evaluation rules transform monitoring data into assessable geological features by analyzing parameters such as rock strata structure and hydrogeology, providing a professional basis for risk identification. For example, high pore pressure is identified as a sign of rockburst risk.

[0142] Bayesian causal networks construct multi-level causal chains. Input nodes receive raw risk data, such as gas outburst risk types and fault geological features. Hidden nodes simulate the risk evolution process, such as a gas outburst triggering a chain reaction. Output nodes predict the final secondary disasters, such as gas explosions or roof collapses. These conditional probabilities are set based on historical accident statistics, such as the probability that a certain type of geological structure will cause a secondary disaster. The causal reasoning function of Bayesian causal networks can reveal potential disaster paths, for example, by analyzing major risk triggers through backpropagation, providing targeted guidance for preventative measures.

[0143] This probability-based prediction method considers both deterministic patterns and quantifies uncertainty, significantly improving the foresight and accuracy of secondary disaster early warning. It solves the problem of inaccurate predictions of secondary disasters using traditional methods, dynamically assesses the evolutionary possibilities of multiple disaster chains, and shifts safety management from passive response to proactive prevention, effectively reducing losses caused by disaster chain reactions. Furthermore, the network's continuous learning capability allows for ongoing optimization of the prediction model with new data.

[0144] In one embodiment of this application, a method for monitoring the risk of coal mine goaf based on the Internet of Things is also proposed, including the following steps:

[0145] S1. Deploy a distributed monitoring network composed of intelligent sensors. The intelligent sensors are used to monitor roof displacement, stress distribution, gas concentration, groundwater level, temperature, humidity and microseismic activity. The intelligent sensors also include real-time acquisition of parameters such as pore pressure, radioactive material content, rock acoustic emission characteristics, groundwater flow velocity and direction, soil resistivity, gas composition changes and rock permeability parameters inside the goaf.

[0146] S2 employs an IoT communication protocol that combines quantum encryption technology, blockchain distributed ledger technology, and traditional encryption algorithms. This protocol transmits collected multi-source data in a highly secure and tamper-proof encrypted form to a remote monitoring center in real time via a multi-mode heterogeneous transmission network consisting of satellite communication, wired broadband, wireless narrowband, and dedicated underground communication frequency bands. During data transmission, data compression, error correction coding, and data packet reassembly technologies are used to ensure data integrity and accuracy. Furthermore, based on network load balancing, intelligent routing strategies, and congestion control mechanisms, the data transmission path is dynamically optimized to cope with the complex, variable, and harsh underground communication environment of coal mines.

[0147] S3. In the remote monitoring center, a powerful processing system based on a big data analysis framework and cloud computing platform is constructed. It comprehensively utilizes deep learning neural networks, genetic algorithms, ant colony algorithms, support vector machines, and Monte Carlo simulation intelligent algorithms, combined with fuzzy mathematics theory, uncertainty analysis methods, and probabilistic statistical models, to deeply mine, fuse, analyze, and predict trends in the received data. It accurately assesses the risk level of the goaf area and establishes a dynamic adaptive risk assessment model to update the risk indicator weights and assessment model parameters in real time to adapt to the complex and ever-changing geological conditions of the goaf area, the impact of mining activities, and interference from external environmental factors.

[0148] S4. When the risk level exceeds the preset multi-level threshold, an early warning mechanism with intelligent classification and precise push functions is immediately triggered. The early warning level is strictly divided according to the severity, urgency, potential scope of harm, and potential secondary disaster risks of the risk. Highly customized and detailed alarm notifications are sent to the handheld terminal devices of front-line workers at the coal mine, the command and dispatch system of the coal mine management department, and the comprehensive supervision platform of the superior regulatory agency. The notification includes a description of the risk location with precise coordinates, a comprehensive and accurate analysis of the risk characteristics and severity, actionable emergency response suggestions, reference for response measures based on historical big data and similar cases, activation instructions for emergency plans preset for different risk levels, and risk scenario simulations based on virtual reality and augmented reality technologies to help relevant personnel understand the risk situation more intuitively.

[0149] S5. Periodically perform self-calibration and self-diagnosis of the monitoring system. Through preset standard calibration sources and diagnostic procedures, automatically detect the accuracy deviation of sensors, the stability of communication links, and the accuracy of data processing algorithms, promptly identify and repair potential faults, and ensure the long-term reliable operation of the entire monitoring system.

[0150] S6. Establish a long-term storage and traceability mechanism for monitoring data, and use a large-capacity distributed storage system and data archiving strategy to save historical monitoring data for subsequent data analysis, model verification and accident tracing.

[0151] Optionally, the risk level can be calculated as follows: Risk level R = a × Severity S + b × Urgency U + c × Hazard range H + d × Potential secondary disaster risk P.

[0152] Where a, b, c, and d are the weights of each factor, and a+b+c+d=1; the values ​​of severity S, urgency U, hazard range H, and potential secondary disaster risk P can be between 0 and 1, such as: severity: 0 means slight, 1 means extremely serious; urgency: 0 means not urgent, 1 means extremely urgent.

[0153] When the calculated risk level R exceeds the preset multi-level threshold, such as threshold 1 or threshold 2, the corresponding level of early warning mechanism is triggered, and notifications are sent to different objects according to the set rules.

[0154] Optionally, the rules for the periodic self-calibration and self-diagnosis of the monitoring system include:

[0155] A. Set a fixed period T for self-calibration and self-diagnosis, such as daily, weekly, or monthly; B. For sensor accuracy deviation detection, compare the current measurement value with the theoretical value of a standard calibration source; C. Communication link stability is evaluated by monitoring packet loss rate, latency, and jitter; D. Data processing algorithm accuracy is assessed by applying known input data to the algorithm and comparing the output result with the expected result.

[0156] Meanwhile, the sensor accuracy deviation D = (measured value - standard value) / standard value * 100%.

[0157] The communication link packet loss rate L = (number of lost packets / total number of sent packets) * 100%. When the packet loss rate exceeds the set threshold, the communication link is considered unstable.

[0158] The communication link delay time T = reception time - transmission time. If the delay time exceeds the preset maximum allowable delay, it is marked as abnormal.

[0159] The accuracy of the data processing algorithm is calculated as A = (number of correct outputs / total number of tests) * 100%. If the accuracy is lower than the set minimum requirement, the algorithm is considered to have a problem.

[0160] In another embodiment, this application provides a computer device, which may be a server, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it can implement the methods described in any of the above embodiments.

[0161] In one embodiment, this application also provides a computer device, which can be a client, and its internal structure diagram can be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it can implement the methods described in any of the above embodiments.

[0162] Any of the computer devices described in the embodiments of this application exist in various forms, including but not limited to:

[0163] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily aim to provide voice and data communication. These terminals include smartphones, multimedia phones, feature phones, and low-end phones.

[0164] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access features. These terminals include PDAs, MIDs, and UMPCs, etc.

[0165] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players, handheld game consoles, e-books, as well as smart toys, wearable devices, and portable car navigation devices.

[0166] (4) Server: A device that provides computing services. The components of a server include a processor, hard disk, memory, system bus, etc. Servers are similar to general computer architectures, but because they need to provide highly reliable services, they have higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0167] (5) Other electronic devices with data interaction functions.

[0168] Additionally, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which are used to perform the following steps:

[0169] According to the predetermined encrypted communication method, risk-related information provided by multiple information collection devices in the coal mine goaf area is obtained in real time.

[0170] Based on all the aforementioned risk-related information and the pre-trained risk assessment model, the current risk index values ​​of the coal mine goaf are determined. The risk index values ​​include the severity of the risk, the urgency of the risk, the scope of the risk hazard, and the probability of secondary disasters. The risk assessment model is used to reflect the correlation between the risk index values ​​of the coal mine goaf and all the aforementioned risk-related information.

[0171] Based on the current risk index values ​​and the index weights of the coal mine goaf, the current risk level of the coal mine goaf is determined.

[0172] Implement the risk warning strategy corresponding to the current risk level of the coal mine goaf.

[0173] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0174] The technical solution of this application has been described in detail above with reference to the accompanying drawings. This technical solution deploys multiple dedicated sensors to collect multi-dimensional risk data of coal mine goaf areas in real time. Quantum encryption and blockchain technology are used to ensure data transmission security. Furthermore, a risk assessment model integrating multiple intelligent algorithms is used to quantitatively assess the severity, urgency, scope of harm, and probability of secondary disasters from multiple dimensions. Finally, a risk level is determined based on weighted calculation, and a tiered early warning strategy is implemented. This achieves closed-loop management of the entire process from data collection, secure transmission, intelligent assessment to precise early warning, solving systemic problems in traditional coal mine goaf monitoring such as single data sources, one-sided assessments, and delayed responses. Multi-source data fusion analysis improves the comprehensiveness and accuracy of risk assessment, intelligent algorithms enable early risk identification and dynamic prediction, and the tiered early warning mechanism ensures timely and targeted emergency response. This significantly improves the intelligence level and early warning effectiveness of coal mine safety monitoring, effectively prevents major accidents, provides reliable technical support for coal mine safety production, and achieves a fundamental shift from passive response to proactive prevention and control.

[0175] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0176] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0178] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0179] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0180] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A risk monitoring method for coal mine goaf areas, characterized in that, include: According to the predetermined encrypted communication method, risk-related information provided by multiple information collection devices in the coal mine goaf area is obtained in real time. Based on all the aforementioned risk-related information and the pre-trained risk assessment model, the current risk index values ​​of the coal mine goaf are determined. The risk index values ​​include the severity of the risk, the urgency of the risk, the scope of the risk hazard, and the probability of secondary disasters. The risk assessment model is used to reflect the correlation between the risk index values ​​of the coal mine goaf and all the aforementioned risk-related information. Based on the current risk index values ​​and the index weights of the coal mine goaf, the current risk level of the coal mine goaf is determined. Implement the risk warning strategy corresponding to the current risk level of the coal mine goaf.

2. The method according to claim 1, characterized in that, Before acquiring the risk association information provided by multiple information acquisition devices within the coal mine goaf in real time, the method further includes: Multiple information acquisition devices within the goaf of the coal mine collect various risk-related information in real time. These risk-related information include: roof displacement, stress distribution, gas concentration, groundwater level, temperature, humidity, microseismic activity, as well as pore pressure, radioactive material content, rock acoustic emission characteristics, groundwater flow velocity and direction, soil resistivity, gas composition changes, and rock permeability within the goaf rock strata.

3. The method according to claim 1, characterized in that, The method of acquiring risk-related information from multiple information collection devices within the coal mine goaf in real time, according to a predetermined encrypted communication method, includes: The risk association information provided by each of the multiple information acquisition devices is encrypted using a lightweight symmetric encryption algorithm to obtain first encrypted data, and the key of the first encrypted data is dynamically updated in real time through a quantum key distribution network. Set a timestamp and device digital signature for the first encrypted data to obtain the second encrypted data; The second encrypted data and the device digital certificate are packaged together into a transaction request, and the transaction request is sent to the verification node of the blockchain so that the verification node can verify whether the timestamp, the device digital signature and the device digital certificate are valid. Once the verification node determines that the timestamp, the device digital signature, and the device digital certificate are valid, the verified transaction request will be broadcast to the blockchain for inter-node information synchronization, and the second encrypted data will be transmitted to the risk monitoring center for determining the current risk indicator value of the coal mine goaf.

4. The method according to claim 3, characterized in that, The process of transmitting the second encrypted data to the risk monitoring center used to determine the current risk indicator value of the coal mine goaf also includes: A transmission path distribution map is constructed using all network devices in the path from the second encrypted data to the risk monitoring center as topology nodes and the communication links between network devices as topology edges. Based on the transmission path distribution map and the ant colony algorithm, the probability of each transmission path between the second encrypted data and the risk monitoring center being selected is determined, wherein... p i Let be the probability that the i-th transmission path between the second encrypted data and the risk monitoring center is selected. The pheromone concentration of the i-th transmission path is determined by the communication capability characteristics of each topological node and each topological edge in the i-th transmission path. The heuristic function for the i-th transmission path is determined by the path length of the i-th transmission path, n is the total number of transmission paths, j is the transmission path code, and α and β are the weights of the pheromone concentration and the heuristic function, respectively. The transmission path with the highest selection probability is determined as the target path for transmitting the second encrypted data to the risk monitoring center.

5. The method according to any one of claims 1 to 4, characterized in that, The determination of the current risk indicator value of the coal mine goaf based on all the aforementioned risk association information and the pre-trained risk assessment model includes: Based on the risk association information of each of the multiple historical time periods and the current time period, the hidden state of each time period is determined by a long short-term memory network, wherein the hidden state is used to reflect the spatiotemporal characteristics of the risk association information in the time period; Based on the hidden state and preset parameter matrix of each time period, the correlation strength between each historical time period and the current time period is determined, wherein the correlation strength is used to reflect the spatiotemporal characteristics of risk correlation information from the historical time period to the current time period; The weight of each association strength is obtained by normalizing all the association strengths using the Softmax function. The hidden states of each time period corresponding to each association strength are weighted and summed according to their respective weights to obtain the severity of the risk.

6. The method according to claim 5, characterized in that, The step of determining the current risk index value of the coal mine goaf based on all the aforementioned risk association information and the pre-trained risk assessment model also includes: Based on the risk association information within each sub-period of the current time period, the urgency characteristics of each sub-period are determined, wherein the urgency characteristics include mutation characteristics, extreme value characteristics, and coupling characteristics; Based on the urgency features of each sub-period and a pre-trained support vector machine model, the risk urgency of the current period is determined, wherein the support vector machine model is used to reflect the correlation between the urgency features of each sub-period in the current period and the risk urgency of the current period.

7. The method according to claim 6, characterized in that, The step of determining the current risk index value of the coal mine goaf based on all the aforementioned risk association information and the pre-trained risk assessment model also includes: Based on all the aforementioned risk-related information, a three-dimensional topological map of the coal mine goaf is constructed, and the three-dimensional topological map is divided into spatial grids. Based on the three-dimensional topological map of the coal mine goaf, the ant colony algorithm is used to simulate the first disaster development path of the coal mine goaf. The perturbation parameters of the ant colony algorithm are determined by Monte Carlo random perturbation simulation, and the development path of the second disaster in the coal mine goaf is simulated based on the perturbation parameters. In the first disaster development path and the second disaster development path, the risk level of each spatial grid is determined, and spatial grids with a risk level higher than a predetermined safety probability are identified as risk grids, wherein the risk level represents the probability that the spatial grid will be affected during disaster development; Taking the potential risk occurrence point in the coal mine goaf as the center, the distance between each risk grid and the center is determined as the affected radius, and the risk hazard range of the coal mine goaf is determined based on the largest affected radius.

8. The method according to claim 6, characterized in that, The step of determining the current risk index value of the coal mine goaf based on all the aforementioned risk association information and the pre-trained risk assessment model also includes: Based on predetermined geological feature evaluation rules, the geological features and possible risk types corresponding to the risk association information are determined; Based on the possible risk types, the risk association information, and the geological features, a Bayesian causal network is constructed. The input nodes of the Bayesian causal network are the possible risk types and the geological features. The hidden nodes connected to the input nodes in the Bayesian causal network are the risk behaviors caused by the possible risk types. The output nodes connected to the hidden nodes in the Bayesian causal network are the secondary disasters caused by the risk behaviors. Based on the historical frequency of occurrence of the possible risk types, the conditional probability of each node in the Bayesian causal network is determined; Using the risk association information of the current time period as the input information of the Bayesian causal network, the probability of the occurrence of the secondary disaster is output through the Bayesian causal network.

9. A computer device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being configured to cause the processor to perform the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The device stores computer-executable instructions configured to perform the method as described in any one of claims 1 to 8.

Images