Early warning method and system for coal and gas outburst danger of machine digging face

Abstract

The invention discloses an early warning method and system for coal and gas outburst danger of a mechanical driving face, and belongs to the technical field of coal mine safety, and the method specifically comprises the following steps: collecting data of the working face in real time, constructing a comprehensive early warning model to realize trend prediction and anomaly detection, triggering early warning and evaluating a risk level; a mine GIS is combined, an early warning area is accurately positioned, an intelligent decision support system of a knowledge graph and a rule engine is used, an optimal emergency plan is rapidly matched, and an emergency response plan is generated; according to the system and the method, workers of the heading machine can take refuge or escape measures in time when an accident occurs, so that the mine operation safety and the emergency response efficiency are improved, and the operation effect of the heading machine is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal mine safety, and specifically relates to a method and system for warning of the risk of coal and gas outburst in a mechanized excavation working face. Background Art

[0002] Coal and gas outburst is a serious natural disaster faced in the process of coal mining. It refers to the phenomenon that a large amount of gas and coal suddenly gush out from the coal body into the excavation space in an extremely short time. This kind of disaster not only seriously threatens the safety production of coal mines, but also causes heavy casualties and property losses. Therefore, researching and developing effective methods for warning of the risk of coal and gas outburst is of great significance for improving the safety and efficiency of coal mine production.

[0003] Coal and gas outburst is characterized by strong suddenness, great destructiveness and difficulty in prediction. During the process of coal mining, once a coal and gas outburst occurs, a large amount of gas and coal will instantly rush into the excavation space, resulting in serious consequences such as roadway blockage, ventilation system damage, and sharp rise in gas concentration. This will not only seriously affect the normal production of coal mines, but also may trigger secondary disasters such as gas explosion, posing a great threat to the life safety of underground workers. At present, scholars and engineering and technical personnel at home and abroad have conducted a large number of studies on coal and gas outburst problems and proposed various prediction and warning methods. However, there are still some deficiencies in the actual application of these methods: most of the existing prediction methods are based on empirical formulas or statistical models, which are difficult to accurately reflect the complex mechanism of coal and gas outburst, resulting in limited prediction accuracy; some warning systems rely only on a single monitoring means, such as gas concentration monitoring, ignoring the monitoring of other key parameters and being difficult to comprehensively reflect the precursor information of coal and gas outburst; some warning systems have the problem of lagging data update, unable to reflect the dynamic change process of coal and gas outburst in real time, resulting in poor warning effect.

[0004] For example, the Chinese patent with the authorization announcement number CN110118103B discloses a method for warning of coal mine gas, including: first obtaining an information table configList of gas sensors configured with gas warning parameters, an information table realList of real-time gas data, and an information table alarmList of real-time gas warning data from the gas monitoring system, and then comparing and analyzing through the information table realLis of real-time gas data, the information table configList of gas sensors configured with gas warning parameters, and the information table alarmList of real-time gas warning data to obtain the information table alarmList of real-time gas warning data and an information table of gas historical alarm information. This technical solution solves the defect that the existing coal mine gas monitoring system is prone to cause accidents by only alarming after gas overlimit. This technical solution can predict possible alarms.

[0005] The above existing technologies all have the following problems: lack of real-time performance and trend prediction ability, and lack of spatial positioning ability, unable to detect potential dangers in advance and take emergency measures. Summary of the Invention

[0006] In view of the deficiencies of the existing technologies, the present invention proposes a warning method and system for the risk of coal and gas outburst in a mechanical excavation working face, including: collecting working face data in real time, constructing a comprehensive warning model to achieve trend prediction and anomaly detection, triggering a warning and evaluating the risk level; combining with the mine GIS, accurately positioning the warning area, and using an intelligent decision-making support system based on a knowledge graph and a rule engine to quickly match the optimal emergency plan and generate an emergency response plan; in the present invention, the roadheader operators can take refuge or escape measures in time when an accident occurs, improving the safety of mine operations and the emergency response efficiency, and improving the operation effect of the roadheader.

[0007] To achieve the above object, the present invention provides the following technical solutions: A warning method for the risk of coal and gas outburst in a mechanical excavation working face, including: Step S1: Using a warning component installed on the end face of the roadheader body, real-time collecting the monitoring information of the working face through a wireless data sending and receiving component. The warning component on the end face of the roadheader body includes an installation shell, an installation plate provided on the inner wall of the installation shell, a sensor component provided on the end face of the installation plate, and a real-time data collection component. The wireless data sending and receiving component is used to upload the working state and analysis results of the roadheader and receive the instructions and prompt information from the ground central station; Step S2: Based on the monitoring information of the working face, establish a comprehensive warning model, conduct real-time trend prediction and anomaly detection on the monitoring information of the working face. If data anomalies or potential dangers are found, the electric control warning platform immediately triggers a warning mechanism and automatically evaluates the risk level through a built-in risk assessment algorithm; Step S3: Based on the warning information, combine with the mine geographic information system to locate the warning information, and construct an intelligent emergency decision-making support system based on a knowledge graph and a rule engine. According to the urgency and risk level of the warning information, automatically match the optimal emergency plan. At the same time, based on the emergency plan, execute the emergency response plan through the eight-way control circuit in the power-off control component; Step S4: After receiving the warning information, the roadheader operators enter the refuge or escape mechanism according to the instructions of the warning information and the emergency plan.

[0008] Specifically, the specific steps of the said Step S2 include: S2.1: Receive the monitoring information of the working face and perform preprocessing, extract the features of the preprocessed monitoring information of the working face to generate the working face feature data where, represents theN One set of working face characteristic data N indicating the quantity of the working face characteristic data; the working face characteristic data includes working face gas concentration data, coal seam stress state data, and working face wind speed data; S2.2: Construct a comprehensive early warning model based on machine learning methods and anomaly detection algorithms, train the comprehensive early warning model using historical working face monitoring information, and evaluate the model using a confusion matrix; The confusion matrix is used to display the comparison between the model prediction results and the actual categories, and the elements in the confusion matrix are filled based on the prediction results of the comprehensive early warning model.

[0009] Specifically, the specific steps of step S2 further include: S2.3: Input the working face characteristic data into the trained comprehensive early warning model, and use to perform trend prediction and anomaly detection to obtain the anomaly detection result , where represents the anomaly detection result at the current time point t, g represents a constant term, r represents the order of the autoregressive part, represents the coefficient of the autoregressive part, represents the time point when the anomaly detection result, u represents the order of the moving average part, represents the coefficient of the moving average part, represents the moving average part order of the error term, v represents the number of external variables, represents the external variable coefficient, represents the external variable, z represents the number of periodic patterns, represents the coefficient of the periodic function, represents the periodic function, represents the coefficient of the dummy variable, represents the dummy variable, represents the coefficient of the time trend term, represents the time trend term, represents the error term, represents the anomaly detection result of the Nth set of working face characteristic data.

[0010] Specifically, the specific steps of step S2 further include: S2.4: Set the anomaly detection threshold , where , represents the mean of Y, b represents the slope coefficient, represents the standard deviation of Y; If , it indicates that the working face characteristic data is normal data; If , it indicates that there is abnormal data, and the early warning mechanism is triggered through the electric control early warning platform; S2.5: Set the warning signals as blue, yellow, orange, and red, and automatically evaluate the risk level according to the severity of the warning signals.

[0011] Specifically, the specific steps of step S3 include: S3.1: Receive the warning information in step S2 and preprocess the warning information; S3.2: Use the mine geographic information system to locate the warning information on the mine map, and display the warning location and its surrounding environment through the map display function of GIS; S3.3: Construct a mine safety knowledge graph, extract knowledge from text and images using natural language processing, and store the extracted knowledge in a structured manner in the knowledge graph; S3.4: Design a rule engine for automatically matching the optimal emergency plan according to the urgency and risk level of the warning information; S3.5: Formulate decision rules. When the warning information is received, the intelligent emergency decision support system automatically triggers the rule engine for decision analysis. The rule engine matches the optimal emergency plan according to the attributes of the warning information and the knowledge in the knowledge graph, and generates an emergency response plan according to the emergency plan; If the emergency response plan is triggered, the corresponding power cut and shutdown safety measures are automatically executed through the control loop; S3.6: Send the generated emergency response plan to the staff. At the same time, monitor the emergency response process, collect feedback information in real time, and dynamically adjust the emergency response plan according to the feedback information by the intelligent emergency decision support system; S3.7: Continuously optimize and iterate the intelligent emergency decision support system according to the actual effect and feedback information of the emergency response.

[0012] Specifically, the abnormal detection results in S2.3 include the time, location, type, and severity information of the abnormality; the emergency plans in S3 include evacuating personnel, cutting off the power supply, starting the ventilation equipment, and allocating resources.

[0013] The early warning system for the risk of coal and gas outburst in the heading face includes: a data acquisition module, a comprehensive early warning module, an emergency response module, and a refuge module; The data acquisition module is used to collect the working face monitoring information in real time by using the warning components and wireless data sending and receiving components at the end face of the roadheader body, including gas concentration, coal seam stress state, and wind speed parameters; The comprehensive early warning module is used to evaluate and predict the risk of coal and gas outburst by using machine learning methods based on the working face monitoring information provided by the data acquisition module; The emergency response module is used to start the emergency plan and guide the on-site staff to take corresponding emergency measures after receiving the early warning signal; The risk avoidance module is used to send the information of the safety shelter or the escape route after the early warning information is triggered, and guide the staff to enter the shelter or escape mechanism according to the instructions of the emergency plan.

[0014] Specifically, the comprehensive early warning module includes: an early warning model construction unit and a risk assessment unit; The early warning model construction unit is used to construct a comprehensive early warning model according to the historical working face monitoring information and expert knowledge, including a trend prediction model and an anomaly detection model; The risk assessment unit is used to perform real-time analysis on the working face monitoring information by using the comprehensive early warning model, evaluate the risk level of the danger, and trigger the corresponding early warning mechanism.

[0015] Specifically, the emergency response module includes: a positioning unit and an emergency response execution unit; The positioning unit is used to combine the early warning information with the mine spatial data to position the early warning information; The emergency response execution unit is used to automatically select and start the corresponding emergency plan and execute the emergency response measures according to the early warning information and the risk assessment result.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. The present invention proposes a warning system for the danger of coal and gas outburst in the mechanized excavation working face, and has optimized and improved the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production cost.

[0017] 2. The present invention proposes a method for warning the danger of coal and gas outburst in the mechanized excavation working face. Through the acquisition of working face monitoring information, a comprehensive early warning model and an intelligent emergency decision-making support system, a comprehensive and real-time warning of the danger of coal and gas outburst in the mechanized excavation working face is realized. It can not only detect potential dangers in advance and trigger the early warning mechanism, but also automatically evaluate the risk level and match the optimal emergency plan, thus significantly improving the accuracy and timeliness of the early warning, accelerating the emergency response speed, reducing the risk of coal and gas outburst accidents, ensuring the safety of personnel, and improving the safety and efficiency of coal mine production.

[0018] 3. The present invention proposes a method for warning of the danger of coal and gas outburst in the machine-driven working face. Through real-time monitoring and warning, the roadheader can more accurately judge the geological conditions of the working face, thereby adjusting the roadheader parameters and avoiding high-risk operations in the areas prone to coal and gas outburst. This not only reduces the failure rate and maintenance cost of the roadheader, but also improves the tunneling efficiency and coal output. At the same time, the warning system can also provide real-time safety guidance for the roadheader to ensure that the tunneling operation is carried out under safe conditions, further protecting the lives of the roadheader workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic diagram of the method for warning of the danger of coal and gas outburst in the machine-driven working face of the present invention; Figure 2 is a principle flow chart of the method for warning of the danger of coal and gas outburst in the machine-driven working face of the present invention; Figure 3 is a risk level assessment flow chart of the method for warning of the danger of coal and gas outburst in the machine-driven working face of the present invention; Figure 4 is a system architecture diagram of the warning system for the danger of coal and gas outburst in the machine-driven working face of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] Example 1

[0021] Please refer to Figures 1 - 3 , an embodiment provided by the present invention: a method for warning of the danger of coal and gas outburst in the machine-driven working face, including the following steps: Step S1: Using the warning component installed on the end face of the roadheader body, the monitoring information of the working face is collected in real time through the wireless data sending and receiving component. The warning component on the end face of the roadheader body includes an installation shell, an installation plate provided on the inner wall of the installation shell, a sensor component provided on the end face of the installation plate, and a real-time data acquisition component. The wireless data sending and receiving component is used to upload the working state and analysis results of the roadheader and receive the instructions and prompt information from the ground central station; Among them, the monitoring information of the working face includes the environmental information, warning information, location of the staff, working state and distribution of the personnel, analysis, warning prompt, and control instruction of the ground central station; The process of obtaining the monitoring information of the working face includes: (1) Deploy microseismic sensors, gas sensors, and wind speed sensors in the working area of the roadheader and connect them to the monitoring system in a wired or wireless manner; (2) Install a camera capable of real-time monitoring of the change of physical parameters of the coal seam in the working face and an accurate personnel positioning system to realize real-time tracking of the location, working state and distribution of the personnel.

[0022] Step S2: Based on the working face monitoring information, establish a comprehensive early warning model to conduct real-time trend prediction and anomaly detection on the working face monitoring information. If data anomalies or potential dangers are found, the electric control early warning platform immediately triggers the early warning mechanism and automatically evaluates the risk level through the built-in risk assessment algorithm; Step S3: Based on the early warning information, combined with the mine geographic information system, locate the early warning information, and construct an intelligent emergency decision-making support system based on the knowledge graph and rule engine. According to the urgency and risk level of the early warning information, automatically match the optimal emergency plan. At the same time, based on the emergency plan, execute the emergency response plan through the eight-way control loop in the power-off control component; Furthermore, the emergency plan in S3 includes but is not limited to evacuating personnel, cutting off the power supply, starting ventilation equipment, and allocating resources; Step S4: After receiving the early warning information, the roadheader operator enters the refuge or escape mechanism according to the instructions of the early warning information and the emergency plan.

[0023] It should be noted that the overall implementation process of the present invention includes: (1) The roadheader starts, and each system conducts an initial inspection to ensure that the equipment is in good working condition. At the same time, the sensors built in the roadheader, such as vibration sensors and gas concentration sensors, start to work and are ready to receive data; (2) Use the sensors and cameras on the early warning component at the end face of the roadheader body to collect real-time monitoring information of the geological structure, coal seam thickness, gas concentration, temperature, humidity, etc. of the working face to form a comprehensive working face monitoring data set; (3) The computer processing system built in the roadheader receives and analyzes the monitoring data, conducts real-time trend prediction and anomaly detection based on the pre-set comprehensive early warning model. If data anomalies are found, such as a sharp rise in gas concentration or a decrease in coal seam stability, or potential dangers exist, immediately trigger the early warning mechanism and automatically evaluate the risk level through the risk assessment algorithm. At the same time, the early warning information is sent to the roadheader operator and the ground control center through the display screen or wireless communication device of the roadheader. Among them, the early warning information includes the risk level, early warning type, and recommended measures; (4) The roadheader uses the mine geographic information system to accurately locate the early warning information, determine the specific location and scope of the early warning area, and construct an intelligent emergency decision-making support system based on the knowledge graph and rule engine. According to the urgency and risk level of the early warning information, automatically match the optimal emergency plan; (5) Generate a detailed emergency response plan, including the personnel evacuation route, the shutdown position of the roadheader, the usage guide of emergency equipment, etc., and send it to the roadheader operator through the display screen or wireless communication device of the roadheader; (6) After receiving the early warning information and the emergency response plan, the roadheader operators immediately stop the roadheader operation, shut down the main systems of the roadheader, and enter the refuge or escape mechanism according to the instructions of the early warning information and the emergency plan, including wearing protective equipment, evacuating to a safe area along the designated route, and starting the emergency ventilation system. At the same time, the roadheader operators keep in touch with the ground control center through wireless communication equipment, report their positions and status, and receive further guidance and support; (7) On the premise of ensuring safety, the ground control center organizes a professional team to investigate and analyze the cause of the accident, and based on the investigation results, formulates a plan for resuming operations, repairs and strengthens the roadheader and the working face as necessary, and after confirming that all potential safety hazards have been eliminated, restarts the roadheader operation.

[0024] The specific steps of step S2 include: S2.1: Receive the working face monitoring information and perform preprocessing, extract features from the preprocessed working face monitoring information, and generate working face feature data , where represents the N th working face feature data, N represents the number of working face feature data; the working face feature data includes working face gas concentration data, coal seam stress state data, and working face wind speed data; S2.2: Construct a comprehensive early warning model based on machine learning methods and anomaly detection algorithms, train the comprehensive early warning model using historical working face monitoring information, and evaluate the model using a confusion matrix; The confusion matrix is used to show the comparison between the model prediction results and the actual categories, and the elements in the confusion matrix are filled based on the prediction results of the comprehensive early warning model; Furthermore, the specific steps of constructing the comprehensive early warning model include: S2.21: Define the application scenario and specific requirements of the early warning model, and set the expected goals of the model, such as early warning accuracy, early warning speed, and system stability; S2.22: Collect historical working face monitoring information from the data source, including data in normal and abnormal states, and perform preprocessing on the historical working face monitoring information, including: 1) data cleaning, such as removing noise, duplicate data, and filling missing values, 2) data transformation, such as normalization and standardization, 3) data partitioning, such as dividing the data set into a training set, a validation set, and a test set; S2.23: Extract features from the preprocessed historical working face monitoring information, where these features should be able to reflect the characteristics and changes of the target state, and perform feature selection to remove redundant or irrelevant features, reduce the complexity of the model, and improve the prediction performance; S2.24: Select a machine learning method based on decision trees and an anomaly detection algorithm based on local outlier factors according to the characteristics of the problem and the data, and design the architecture and parameters of the comprehensive early warning model, such as the number of layers, nodes, and activation functions of the neural network. Among them, the machine learning method based on decision trees and the anomaly detection algorithm based on local outlier factors are both prior art content in this field and not the creative solutions of this application, so they will not be elaborated here; S2.25: Use the training set data to train the comprehensive early warning model to enable the comprehensive early warning model to learn the patterns and rules in the data. During the training process, use the validation set data to evaluate the comprehensive early warning model, and adjust the parameters and architecture of the comprehensive early warning model according to the evaluation results to optimize the performance of the comprehensive early warning model; S2.26: Use the test set data to conduct a final evaluation of the trained comprehensive early warning model, verify the early warning accuracy rate of the comprehensive early warning model, and analyze the confusion matrix evaluation indicators; S2.27: Deploy the trained comprehensive early warning model to the actual working environment and integrate it with the monitoring system; S2.28: Configure the interfaces for the real-time input data and output early warning results of the comprehensive early warning model to ensure that the comprehensive early warning model can work properly and respond to abnormal situations in a timely manner, and regularly maintain and update the comprehensive early warning model.

[0025] Furthermore, the specific steps for using the confusion matrix to evaluate the model include: (1) Define the positive and negative classes. For example, the prominent danger is the positive class and the normal state is the negative class; (2) Obtain the prediction results of the comprehensive early warning model; (3) Construct an empty 2×2 matrix and fill the matrix; If the predicted class of the comprehensive early warning model and the actual class of the sample are both positive classes, a true positive example is obtained. For example, the actual gas concentration at the working face monitoring point exceeds the standard, and the comprehensive early warning model also predicts that the gas concentration at this monitoring point exceeds the standard; If the predicted class of the comprehensive early warning model is the positive class, but the actual class of the sample is the negative class, a false positive example is obtained. For example, the actual gas concentration at the working face monitoring point is within the normal range, but the comprehensive early warning model predicts that the gas concentration at this monitoring point exceeds the normal range; If the predicted class of the comprehensive early warning model is the negative class, but the actual class of the sample is the positive class, a false negative example is obtained; If the predicted class of the comprehensive early warning model and the actual class of the sample are both negative classes, a true negative example is obtained; (4) Obtain the confusion matrix by taking the true positive and false negative examples as the elements of the first row of the matrix and the false positive and true negative examples as the elements of the second row of the matrix; (5) Calculate evaluation metrics using a confusion matrix, where the evaluation metrics include accuracy, precision, and recall, and the calculation formulas for accuracy, precision, and recall are the prior art content in this field and are not the creative solutions of this application, so they will not be elaborated here.

[0026] S2.3: Input the working face feature data into the trained comprehensive early warning model and use for trend prediction and anomaly detection to obtain the anomaly detection result , where represents the anomaly detection result at the current time point t, g represents the constant term, r represents the order of the autoregressive part, represents the coefficient of the autoregressive part, represents the time point when the anomaly detection result, u represents the order of the moving average part, represents the coefficient of the moving average part, represents the moving average part order of the error term, v represents the number of external variables, represents the external variable coefficient, represents the external variable, z represents the number of periodic patterns, represents the periodic function coefficient, represents the periodic function, represents the dummy variable coefficient, represents the dummy variable, represents the time trend term coefficient, represents the time trend term, represents the error term, represents the anomaly detection result of the Nth working face feature data; Further, the anomaly detection result includes information on the time, location, type, and severity of the anomaly occurrence.

[0027] It should be noted that in the present invention, external variables, periodic patterns, dummy variables, and time trend terms are added. These additional parameters and variables enable the model to consider more dimensional information during prediction, can more accurately reflect the impact of seasonal fluctuations on the predicted value. At the same time, consider the impact of sudden events on the time series and take into account the basic development trend of the data during prediction. By comprehensively considering the above various factors, the modified model can more comprehensively reflect the complexity and dynamics of time series data during prediction, enhance the flexibility, accuracy, and adaptability of the model, and reduce the prediction error.

[0028] S2.4: Set the anomaly detection threshold , where , represents the mean of Y, and b represents the slope coefficient. represents the standard deviation of Y; If , it indicates that the working face characteristic data is normal data; If , it indicates that there are abnormal data, and the early warning mechanism is triggered through the electric control early warning platform; S2.5: Set the early warning signals as blue, yellow, orange, and red, and automatically evaluate the risk level according to the severity of the early warning signals.

[0029] Further, when the audible and visual alarm is green, it represents no outburst danger, and the working face is under normal construction. When the audible and visual alarm is blue, it represents that the outburst danger reaches the threat value. At this time, the cutting section speed needs to be slowed down, and the intermittent operation mode is adopted to reduce the aggregation degree of concentrated stress and weaken the outburst danger. When the audible and visual alarm is orange, it represents that the outburst danger reaches the dangerous value. At this time, the cutting section operation needs to be stopped, the power supply of the cutting head motor of the roadheader is cut off, and the already very tense concentrated stress is transferred to the deep part of the working face by stopping tunneling to reduce the outburst danger; when the audible and visual alarm is red, it represents that the outburst danger reaches the critical value. At this time, the audible and visual voice prompt needs to be turned on, and an order to stop work and evacuate people is issued to each operator on the working face, and the power supply of all equipment except the early warning platform on the working face is cut off.

[0030] The specific steps of step S3 include: S3.1: Receive the early warning information in step S2 and preprocess the early warning information; S3.2: Use the mine geographic information system to locate the early warning information on the mine map, and through the map display function of GIS, visually display the early warning location and its surrounding environment; S3.3: Construct a mine safety knowledge graph, extract knowledge from text and images using natural language processing, and store the extracted knowledge in a structured manner in the knowledge graph; Further, the specific steps of S3.3 include: S3.31: Define the application scenarios of the knowledge graph, such as mine safety monitoring, accident prevention, and emergency response, and define the schema layer of the knowledge graph, including entities, relationships, and attributes, such as mine, equipment, accident types, safety specification entities, and their associated relationships; S3.32: Obtain mine safety data, and perform cleaning, denoising, and formatting processing on the mine safety data. The mine safety data includes: 1) structured data, such as database records, 2) semi-structured data, such as web pages, XML files, 3) unstructured data, such as text, images; S3.33: (1) Text knowledge extraction: Use NLP techniques for text tokenization, part-of-speech tagging, named entity recognition, and relationship extraction to identify mine safety entities, attributes, and relationships in the text. Among them, the entities include: equipment name, accident type, personnel distribution, emergency plan, historical cases; the attributes include: equipment model, accident level; the relationships include: equipment - failure, accident - cause; (2) Image knowledge extraction: Apply image recognition methods to identify mine safety elements in the image, such as equipment status, safety hazards, and extract text information in the image, such as safety signs, equipment labels; S3.34: Integrate the knowledge extracted from text knowledge extraction and image knowledge extraction, solve entity alignment and relationship conflict problems, and store the integrated knowledge in the graph database in the form of Neo4j for efficient query and reasoning; S3.35: Continuously update and maintain the knowledge graph to ensure the timeliness and accuracy of the data.

[0031] S3.4: Design a rule engine to automatically match the optimal emergency plan according to the urgency and risk level of the warning information. Among them, the rule engine is implemented based on conditional judgment, and the emergency plans are divided into four types: A, B, C, and D in descending order according to the urgency of the warning information; For example, if the urgency of the warning information is "relatively high", the risk level is 4, and the emergency plan A is matched; If the urgency of the warning information is "high", the risk level is 3, and the emergency plan B is matched; If the urgency of the warning information is "medium", the risk level is 2, and the emergency plan C is matched; If the urgency of the warning information is "low", the risk level is 1, and the default emergency plan D is matched.

[0032] S3.5: Formulate decision rules. When receiving warning information, the intelligent emergency decision support system automatically triggers the rule engine for decision analysis. The rule engine matches the optimal emergency plan according to the attributes of the warning information and the knowledge in the knowledge graph, and generates an emergency response plan according to the emergency plan; If the emergency response plan is triggered, corresponding power-off and shutdown safety measures are automatically executed through the control loop; Furthermore, the specific steps of S3.5 include: S3.51: Formulate decision rules to clarify under what conditions which emergency plan should be triggered. Among them, the decision rules can be based on the attributes of the warning information, entity relationships and attributes in the knowledge graph; S3.52: Obtain the rule engine, integrate the rule engine with the early warning system, and ensure that when the early warning system receives new early warning information, it can automatically trigger the rule engine for decision-making analysis; S3.53: The rule engine matches the optimal emergency plan according to the attributes of the early warning information and the knowledge in the knowledge graph, and automatically generates a detailed emergency response plan according to the matched emergency plan, including response measures, responsibility assignment, time nodes, and rescue routes; S3.54: Test the entire system to ensure that the rule engine can be correctly triggered, the emergency plan can be matched, and an effective emergency response plan can be generated under various circumstances, and optimize and adjust the system according to the test results;

[0033] S3.55: Deploy the system to the production environment, perform continuous operation and maintenance management, and regularly maintain and update the system to adapt to new early warning information and emergency plans.

[0034] S3.6: Send the generated emergency response plan to the staff for execution. At the same time, monitor the emergency response process, collect feedback information in real time, and dynamically adjust the emergency response plan according to the feedback information by the intelligent emergency decision support system; S3.7: Continuously optimize and iterate the intelligent emergency decision support system according to the actual effect and feedback information of the emergency response.

[0035] Embodiment 2

[0036] Please refer to Figure 4 , another embodiment provided by the present invention: a coal and gas outburst risk early warning system for a mechanized excavation working face, including: A data acquisition module, a comprehensive early warning module, an emergency response module, and an emergency shelter module; The data acquisition module is used to collect the working face monitoring information in real time by using the early warning component and the wireless data sending and receiving component at the end face of the roadheader body, including gas concentration, coal seam stress state, and wind speed parameters; The comprehensive early warning module is used to evaluate and predict the risk of coal and gas outburst by using machine learning methods according to the working face monitoring information provided by the data acquisition module; The emergency response module is used to start the emergency plan and guide the on-site staff to take corresponding emergency measures after receiving the warning signal; The emergency shelter module is used to send the information of the safety shelter or the emergency escape route after the early warning information is triggered, and guide the staff to enter the shelter or escape mechanism according to the instructions of the emergency plan to ensure that the personnel can quickly reach a safe area when the danger occurs.

[0037] The comprehensive early warning module includes: a data processing unit, an early warning model construction unit, and a risk assessment unit; A data processing unit for cleaning, transforming, and storing the monitored information of the working face to ensure data quality; An early warning model construction unit for constructing a comprehensive early warning model based on historical monitored information of the working face and expert knowledge, including a trend prediction model and an anomaly detection model; A risk assessment unit for using the comprehensive early warning model to perform real-time analysis on the monitored information of the working face, evaluate the risk level of hazards, and trigger corresponding early warning mechanisms.

[0038] The emergency response module includes: a positioning unit, an emergency plan library unit, and an emergency response execution unit; The positioning unit for combining the early warning information with the mine spatial data to achieve precise positioning of the early warning information; The emergency plan library unit for storing multiple emergency plans, including response measures under different risk levels and emergency degrees; The emergency response execution unit for automatically selecting and activating the corresponding emergency plan according to the early warning information and the risk assessment result, and executing emergency response measures, where the emergency response measures include: shutting down the ventilation system, stopping mechanical equipment, turning on emergency lighting and communication equipment.

[0039] The risk avoidance module includes: an early warning information release unit, a risk avoidance guidance unit, and a safety monitoring unit; The early warning information release unit for timely releasing early warning information to the roadheader workers through means such as sound and light alarms and communication equipment; The risk avoidance guidance unit for providing clear evacuation or escape routes and operation methods for workers according to the instructions of the emergency plan; The safety monitoring unit for continuously monitoring the safety of personnel during the risk avoidance process to ensure the effective implementation of risk avoidance measures.

[0040] The above describes the embodiments of the present invention in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present invention and without departing from the spirit and scope of the present invention, can also make changes, modifications, substitutions, and variations to the above embodiments, and these all fall within the protection scope of the present invention.

[0041] If the disclosed technical solution involves personal information, the product using the disclosed technical solution has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the disclosed technical solution involves sensitive personal information, the product using the disclosed technical solution has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A method for early warning of coal and gas outburst danger in a machine-digger face, characterized in that: include: Step S1: using the early warning component installed on the end face of the tunnel boring machine body to collect working face monitoring information in real time through the wireless data sending and receiving component, the early warning component on the end face of the tunnel boring machine body includes a mounting shell, a mounting plate arranged on the inner wall of the mounting shell, a sensor component arranged on the end face of the mounting plate, and a real-time data collection component, and the wireless data sending and receiving component is used to upload the working status and analysis results of the tunnel boring machine and receive instructions and prompt information from the ground center station; Step S2: Based on the working face monitoring information, a comprehensive early warning model is established to perform real-time trend prediction and anomaly detection on the working face monitoring information. If data anomalies or potential dangers are found, the electronic control early warning platform immediately triggers the early warning mechanism and automatically evaluates the risk level through the built-in risk assessment algorithm; Step S3: Based on the warning information, combined with the mine geographic information system, the warning information is located, and an intelligent emergency decision support system based on the knowledge graph and rule engine is constructed. According to the urgency and risk level of the warning information, the optimal emergency plan is automatically matched. At the same time, based on the emergency plan, the emergency response plan is executed through the eight-way control loop in the power failure control component; Step S4: After receiving the warning information, the tunnel boring machine staff enters the refuge or escape mechanism according to the warning information and the instructions of the emergency plan.

2. The method for early warning of coal and gas outburst danger in a machine-digger face according to claim 1, characterized in that: The specific steps of step S2 include: S2.1: Receive and preprocess the working face monitoring information, extract features from the preprocessed working face monitoring information, and generate working face feature data ,in, Indicates N Working surface characteristic data, N Indicates the number of working face characteristic data; the working face characteristic data includes working face gas concentration data, coal seam stress state data, and working face wind speed data; S2.2: Build a comprehensive early warning model based on machine learning methods and anomaly detection algorithms, use historical working face monitoring information to train the comprehensive early warning model, and use confusion matrix to evaluate the model; The confusion matrix is ​​used to show the comparison between the model prediction results and the actual categories, and the elements in the confusion matrix are filled based on the prediction results of the comprehensive early warning model.

3. The method for early warning of coal and gas outburst danger in a machine-digger face according to claim 2, characterized in that: The specific steps of step S2 also include: S2.3: Work surface feature data Input the trained comprehensive early warning model and use Perform trend prediction and anomaly detection to obtain anomaly detection results ,in, represents the anomaly detection result at the current time point t, g represents the constant term, r represents the order of the autoregressive part, represents the coefficient of the autoregressive part, Indicates time point The anomaly detection result when u represents the order of the moving average part. represents the coefficient of the moving average part, Represents the moving average part The error term of order , v represents the number of external variables, represents the external variable coefficient, represents the external variable, z represents the number of periodic patterns, represents the periodic function coefficient, represents a periodic function, represents the coefficient of the dummy variable, represents a dummy variable, represents the time trend term coefficient, represents the time trend term, represents the error term, Indicates the anomaly detection result of the Nth working surface feature data.

4. The method for early warning of coal and gas outburst danger in a machine-digger face according to claim 3, characterized in that: The specific steps of step S2 also include: S2.4: Setting anomaly detection thresholds ,in, , represents the mean of Y, b represents the slope coefficient, represents the standard deviation of Y; like , it means that the working surface feature data is normal data; like , it means that there is abnormal data, and the early warning mechanism is triggered through the electronic control early warning platform; S2.5: Set the warning signals to blue, yellow, orange, and red, and automatically assess the risk level based on the severity of the warning signal.

5. The method for early warning of coal and gas outburst danger in a machine-digger face according to claim 4, characterized in that: The specific steps of step S3 include: S3.1: receiving the warning information in step S2 and preprocessing the warning information; S3.2: Use the mine geographic information system to locate the warning information on the mine map, and use the map display function of GIS to display the warning location and its surrounding environment; S3.3: Build a mine safety knowledge graph, extract knowledge from text and images using natural language processing, and store the extracted knowledge in a structured manner in the knowledge graph; S3.4: Design a rule engine to automatically match the optimal emergency plan based on the urgency and risk level of the warning information; S3.5: Formulate decision rules. When receiving warning information, the intelligent emergency decision support system automatically triggers the rule engine to perform decision analysis. The rule engine matches the optimal emergency plan based on the attributes of the warning information and the knowledge in the knowledge graph, and generates an emergency response plan based on the emergency plan. If the emergency response plan is triggered, the corresponding power-off and shutdown safety measures will be automatically executed through the control loop; S3.6: Send the generated emergency response plan to the staff, monitor the emergency response process, collect feedback information in real time, and dynamically adjust the emergency response plan based on the feedback information by the intelligent emergency decision support system; S3.7: Continuously optimize and iterate the intelligent emergency decision support system based on the actual effects and feedback information of the emergency response.

6. The method for early warning of coal and gas outburst danger in a machine-digger face according to claim 5, characterized in that: The abnormality detection result in S2.3 includes the time, location, type and severity of the abnormality; the emergency plan in S3 includes evacuating personnel, cutting off power, starting ventilation equipment, and allocating resources.

7. A coal and gas outburst hazard warning system for a machine-digged working face, which is used to implement the coal and gas outburst hazard warning method for a machine-digged working face as described in any one of claims 1 to 6, characterized in that: include: Data collection module, comprehensive warning module, emergency response module, and risk avoidance module; The data acquisition module is used to collect working face monitoring information in real time, including gas concentration, coal seam stress state, and wind speed parameters, using the early warning component and wireless data sending and receiving component on the end face of the tunnel boring machine body; The comprehensive early warning module is used to evaluate and predict the risk of coal and gas outburst using machine learning methods based on the working face monitoring information provided by the data acquisition module; The emergency response module is used to activate the emergency plan after receiving the early warning signal and guide the on-site staff to take corresponding emergency measures; The risk avoidance module is used to send information about safe shelters or risk avoidance passages after the early warning information is triggered, and guide the staff to enter the shelter or escape mechanism according to the instructions of the emergency plan.

8. The coal and gas outburst hazard warning system for a machine-digger face according to claim 7, characterized in that: The comprehensive early warning module includes: an early warning model building unit and a risk assessment unit; The early warning model building unit is used to build a comprehensive early warning model based on historical working face monitoring information and expert knowledge, including a trend prediction model and an anomaly detection model; The risk assessment unit is used to use a comprehensive early warning model to perform real-time analysis on the working face monitoring information, assess the risk level of the hazard, and trigger a corresponding early warning mechanism.

9. The coal and gas outburst hazard warning system for a machine-digger face according to claim 8, characterized in that: The emergency response module includes: a positioning unit and an emergency response execution unit; The positioning unit is used to combine the warning information with the mine spatial data to locate the warning information; The emergency response execution unit is used to automatically select and start the corresponding emergency plan and execute emergency response measures according to the early warning information and risk assessment results.

Images