Early warning system for coal seam disaster occurrence based on dynamic physical field digital twin.

Abstract

This invention discloses a coal seam disaster-prone state early warning system based on a digital twin of the dynamic physical field of coal seam disaster-prone conditions. The system displays three dynamic physical fields during the tunneling process of a working face: the coal seam stress field, the gas concentration field, and the coal-rock failure intensity field. It predicts and updates these three dynamic physical fields in real time using the ARIMA algorithm. Furthermore, it uses the ARIMA algorithm and a hazard threshold difference judgment criterion to predict and compare the disturbance states of each hazard indicator in the disaster-prone twin, enabling real-time analysis of the coal seam disaster-prone process. It provides early warning when a coal outburst hazard occurs, marks the disaster-prone location in the three-dimensional digital model of the working face, and provides emergency response suggestions. This invention can generate and monitor anomalies in the digital twin of the physical field of hazard indicators for future coal and gas outbursts, improving the visualization and intelligence level of accident prediction.

Description

Technical Field

[0001] This invention relates to the field of coal mine safety monitoring and early warning technology, and in particular to an early warning system for the state of coal seam disaster based on a digital twin of the dynamic physical field of coal seam disaster. Background Technology

[0002] Coal and gas outbursts, rock bursts, and other underground disasters are extremely serious accidents in coal mines. They can cause not only casualties but also disrupt coal production, deteriorate the safety environment of coal mines, and waste coalbed methane resources, resulting in huge economic losses.

[0003] Currently, existing technologies lack sufficient research on multi-indicator monitoring and early warning fusion technology and hazard monitoring. Their intelligence level is low, their visualization level is poor, and the monitoring of the disaster-prone process is lacking. Summary of the Invention

[0004] This invention provides a disaster-prone state early warning system based on a digital twin of the dynamic physical field of coal seam disaster-prone conditions, in order to solve the technical problems of insufficient research on multi-indicator monitoring and early warning fusion technology and hazard monitoring in existing technologies, low level of intelligence, poor visualization, and lack of monitoring of the disaster-prone process.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] A coal seam disaster-prone state early warning system based on a dynamic physical field digital twin, comprising: downhole sensors, a physical signal mapping module, a data-driven module, a data mapping module, a dynamic physical field inversion module, and a hazard indicator disturbance early warning module; wherein,

[0007] The downhole sensor is used to be configured in the downhole tunneling face to be monitored, so as to monitor a variety of preset monitoring indicators in real time during the tunneling process of the downhole tunneling face to be monitored, and obtain data of each monitoring indicator;

[0008] The physical signal mapping module is used to store the monitoring index data obtained by the downhole sensor into the corresponding data table of each monitoring index, and generate virtual objects of each monitoring index based on the data table of each monitoring index; wherein, the virtual objects include the historical data of the corresponding monitoring index;

[0009] The data-driven module is used to construct the dynamic physical field corresponding to each monitoring indicator, and to embed the virtual objects of each monitoring indicator into the dynamic physical field corresponding to the corresponding indicator to reflect the disaster situation in the mining area at the current moment; wherein, the virtual objects change in real time as the data of the corresponding monitoring indicators change.

[0010] The data mapping module is used to construct a three-dimensional model of the underground tunneling face to be monitored and its mining area at a 1:1 scale to obtain a three-dimensional digital model of the working face; and to map the dynamic physical field corresponding to each monitoring index into the three-dimensional digital model of the working face to obtain a digital twin of the tunneling face.

[0011] The dynamic physical field inversion module is used to invert the digital twin of the tunneling face to obtain a dynamic physical field digital twin of coal seam disaster.

[0012] The danger index disturbance early warning module is used to perform real-time analysis of the coal seam disaster formation process based on the coal seam disaster formation dynamic physical field digital twin, and to issue an early warning when a major danger occurs.

[0013] Furthermore, the preset monitoring indicators include: tunneling progress, gas concentration, stress field at the tunneling face, and coal and rock damage intensity;

[0014] Accordingly, the downhole sensors include: a laser rangefinder, a gas concentration sensor, a stress sensor, and an electromagnetic radiation sensor.

[0015] Furthermore, the arrangement of the downhole sensors is as follows:

[0016] The laser rangefinder is positioned at the entrance of the tunnel, pointing towards the tunneling face;

[0017] The stress sensors are multiple and are inserted into the bottom roadway in front of the tunnel to be monitored in the underground working face through drill holes, with one stress sensor arranged every 30m.

[0018] The gas concentration sensors are arranged at multiple points behind the tunneling head, one every 50m.

[0019] The electromagnetic radiation sensor is located at the tunnel head.

[0020] Furthermore, the physical signal mapping module generates virtual objects for each monitoring indicator in the following way:

[0021] The stress field in front of the tunnel face is displayed using a stress field contour map;

[0022] The gas concentration field behind the tunneling face is shown using a gas concentration contour map;

[0023] The degree of damage to the coal and rock around the tunneling face is shown by using a dynamic curve of electromagnetic radiation.

[0024] The tunneling speed and total progress are displayed using a tunneling gauge.

[0025] Furthermore, the three-dimensional digital model of the working face includes: a geological unit of the working face, a production unit of the tunneling machine, and a sensor unit.

[0026] Furthermore, the dynamic physical field inversion module is specifically used for:

[0027] The ARIMA algorithm is used to predict the three dynamic physical fields—stress field, gas concentration field, and coal and rock failure intensity field—in the digital twin of the tunneling face at the current moment, so as to obtain the prediction results of the three dynamic physical fields at future moments. The prediction results of the three dynamic physical fields at future moments are then imported into the digital twin of the coal seam disaster-prone dynamic physical field to reflect the disaster-prone situation in the mining area at future moments.

[0028] Furthermore, the danger indicator disturbance early warning module is specifically used for:

[0029] The ARIMA algorithm is used to predict the disturbances of three monitoring indicators in the digital twin of the dynamic physical field of coal seam disaster-prone area: gas concentration, stress field at the tunnel face, and coal and rock failure intensity.

[0030] Based on the preset danger threshold difference judgment criteria, the coal seam disaster-inducing process is analyzed in real time according to the disturbance prediction results of the monitoring indicators, and an early warning is issued when a sudden danger occurs. At the same time, emergency response suggestions are provided when an early warning is issued, and the disaster-inducing location is marked in the three-dimensional digital model of the working face.

[0031] Furthermore, the criterion for judging the difference in danger thresholds includes:

[0032] The disturbance range of three monitoring indicators—gas concentration, stress field at the tunnel face, and coal and rock failure intensity—is used as the monitoring object for danger. The warning level is classified according to the preset disturbance range threshold and the danger state interpolation.

[0033] The beneficial effects of the technical solution provided by this invention include at least the following:

[0034] 1. This invention realizes the display of coal seam stress field, gas concentration field, and coal and rock failure intensity field during the tunneling process of the tunneling face to be monitored. It predicts and updates the three physical fields in real time through the ARIMA algorithm, and performs real-time analysis of the coal seam disaster initiation process through the danger index disturbance early warning module, and issues an early warning when a sudden danger occurs, thereby achieving accurate early warning of coal seam disaster initiation.

[0035] 2. This invention breaks through the traditional function of digital twins in coal mine production, which is limited to a single visualized working condition. It solves the problem that existing technologies cannot predict the danger of production conditions at future moments. It proposes a functional processing iteration technology between multiple digital twins, integrating coal and gas outburst monitoring, prediction, and early warning in coal mine production.

[0036] 3. This invention proposes the concept of a dynamic physical field for hazard indicators, which can innovatively solve the problems of traditional hazard indicator values ​​being difficult to integrate and visualize in layers.

[0037] 4. The early warning function of this invention is based on the prediction of the disturbance state of the dynamic physical field and provides early warning based on the fluctuation of the disturbance state, which makes up for the shortcomings of the traditional threshold method, which can only make a single judgment by comparing the numerical results at the current moment. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a structural block diagram of the disaster-prone status early warning system based on the dynamic physical field digital twin of coal seam disaster-prone area provided in this embodiment of the invention;

[0040] Figure 2 This is a schematic diagram illustrating the implementation process of the coal seam disaster-prone state early warning system based on a dynamic physical field digital twin provided in this embodiment of the invention.

[0041] Figure 3 This is a schematic diagram of the workflow of the coal seam disaster-prone state early warning system based on the dynamic physical field digital twin of coal seam disaster-prone area provided in the embodiments of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0043] This embodiment provides a disaster-prone state early warning system based on a digital twin of the dynamic physical field of coal seam disaster-prone conditions. Combining digital twin technology, it proposes a new concept of dynamic physical field of coal seam disaster-prone indicators, and uses multiple digital twin generation and processing technology to predict the risk of coal and gas outbursts in tunneling faces. It conceptualizes and digitally twins the physical index field of coal seam disaster-prone conditions, and proposes a practical twin prediction system that can realize the monitoring and early warning of the disaster-prone state of coal seams in tunneling faces, thereby providing strong support for safe coal mine production.

[0044] like Figure 1 As shown, the early warning system includes: downhole sensors, a physical signal mapping module, a data-driven module, a data mapping module, a dynamic physical field inversion module, and a hazard indicator disturbance early warning module.

[0045] The underground sensors are configured in the underground tunneling face to be monitored, enabling real-time monitoring of various preset monitoring indicators during the tunneling process, and obtaining data for each indicator. These preset monitoring indicators include: tunneling progress, gas concentration, tunneling face stress field, and coal and rock failure strength. Accordingly, the underground sensors include: a laser rangefinder, a gas concentration sensor, a stress sensor, and an electromagnetic radiation sensor. The arrangement of each sensor is as follows:

[0046] The laser rangefinder is positioned at the entrance of the tunnel, pointing towards the tunneling face;

[0047] The stress sensors are multiple and are inserted into the bottom roadway in front of the tunnel to be monitored in the underground working face through drill holes, with one stress sensor arranged every 30m.

[0048] The gas concentration sensors are arranged at multiple points behind the tunneling head, one every 50m.

[0049] The electromagnetic radiation sensor is located at the tunnel head.

[0050] Each sensor transmits data to the server's database of various hazard indicators based on the downhole ring network.

[0051] The physical signal mapping module is used to store the monitoring index data obtained by the downhole sensors into the corresponding data tables (stress table, gas table, electromagnetic radiation intensity table) in the database, and generate virtual objects for each monitoring index based on the data tables. The virtual objects are virtual objects of each hazard index field, including stress field virtual objects, gas concentration virtual objects, electromagnetic radiation virtual objects, and progress scales. Each virtual object contains historical data collected by its corresponding sensor.

[0052] Furthermore, the physical signal mapping module generates virtual objects for each monitoring indicator in the following way:

[0053] The stress field in front of the tunnel face is displayed using a stress field contour map;

[0054] The gas concentration field behind the tunneling face is shown using a gas concentration contour map;

[0055] The degree of damage to the coal and rock around the tunneling face is shown by using a dynamic curve of electromagnetic radiation.

[0056] The tunneling speed and total progress are displayed using a tunneling gauge.

[0057] The data-driven module is used to construct dynamic physical fields corresponding to each monitoring indicator, and to embed virtual objects of each monitoring indicator into the corresponding dynamic physical fields to reflect the current disaster-prone situation in the mining area. Specifically, the stress field contour map, gas concentration contour map, electromagnetic radiation dynamic curve, and tunneling gauge are all updated in real time according to the data-driven module, and the numerical simulation results are assigned to the dynamic physical fields corresponding to each virtual object. Further, the dynamic physical fields are generated from virtual physical objects produced by sensor signals and then processed by the ARIMA (Autoregressive Integrated Moving Average) algorithm. The ARIMA algorithm processes the dataset of the virtual object itself, outputting the budget values ​​of each indicator and assigning them to the coal seam disaster-prone dynamic physical field. The dynamic physical fields include: stress field, gas concentration field, and coal and rock failure intensity field; these three dynamic physical fields can reflect the current disaster-prone situation in the mining area.

[0058] The data mapping module is used to construct a 1:1 scale 3D model of the underground tunneling face to be monitored and its surrounding mining area to obtain a 3D digital model of the working face. The module then maps the dynamic physical fields corresponding to each monitoring indicator into this 3D digital model, resulting in a digital twin of the tunneling face. This 3D digital model is a scaled-down 3D visualization model of the working face and its surrounding mining area, containing the geometric model of the tunneling face to be monitored. It includes geological units, production units such as tunneling machines, supports, sensors, and rangefinders, as well as sensor units, simulating the actual production conditions of the working face. The digital twin of the tunneling face incorporates a virtual object of dynamic physical fields, integrating three hazardous field indicators: gas, stress, and coal and rock damage intensity. This enables the monitoring and digital twinning of the coal seam's disaster-prone physical field at the current moment, providing a realistic basis for constructing the dynamic physical field of coal seam disaster-prone areas in the future.

[0059] The dynamic physical field inversion module is used to invert the digital twin of the tunneling face to obtain a dynamic physical field digital twin of coal seam disaster occurrence. This digital twin includes the stress field, gas concentration field, and coal-rock failure intensity field processed by the ARIMA algorithm. Specifically, the dynamic physical field inversion module performs ARIMA algorithm inversion based on the digital twin of the tunneling face to generate a dynamic physical field digital twin of coal seam disaster occurrence containing future coal seam disaster occurrence physical field information. The implementation process is as follows: the ARIMA algorithm is used to predict the current stress field, gas concentration field, and coal-rock failure intensity field in the digital twin of the tunneling face to obtain prediction results for the three dynamic physical fields at future times. These prediction results are then imported into the dynamic physical field digital twin of coal seam disaster occurrence to reflect the disaster occurrence situation in the mining area at future times.

[0060] The hazardous indicator disturbance early warning module is used to monitor the physical field objects in the digital twin of the dynamic physical field of coal seam disaster formation, predict and judge the disturbance state of hazardous indicators, and issue a hazardous warning message when the disturbance changes abnormally, indicating the disaster location and providing corresponding emergency response suggestions; thereby realizing real-time analysis of the coal seam disaster formation process and thus realizing the early warning of coal and gas outburst hazards.

[0061] Specifically, the warning principle of the danger index disturbance warning module is as follows:

[0062] The ARIMA algorithm is used to predict the fluctuations of three monitoring indicators—gas concentration, tunneling face stress field, and coal and rock failure intensity—in the digital twin of the dynamic physical field of coal seam disaster generation. It should be noted that the ARIMA algorithm is a method for predicting time series data and cannot predict physical fields. Therefore, to achieve the above technical solution, this embodiment proposes the following approach to applying the ARIMA algorithm to the digital twin system: The stress field, gas concentration field, and coal and rock failure intensity field are detected using three parameters: stress value, gas concentration value, and electromagnetic radiation value. The detection results are considered the values ​​of these three fields at a certain point. Then, the values ​​of these three parameters are predicted, and the prediction results are considered the values ​​of the three physical fields that will appear soon, thereby achieving the goal of real-time updating of the three physical fields.

[0063] Based on the preset danger threshold difference judgment criteria, the coal seam disaster-inducing process is analyzed in real time according to the disturbance prediction results of the monitoring indicators, and an early warning is issued when a sudden danger occurs. At the same time, emergency response suggestions are provided when an early warning is issued, and the disaster-inducing location is marked in the three-dimensional digital model of the working face.

[0064] The prediction process involves the following steps: the current indicator state is X. t The predicted value is X t+1 Compare the predicted values ​​with the measured values. If the difference is small, it indicates that the environmental change is small and the environment is safe; otherwise, it indicates that the environment is unsafe.

[0065] The criteria for judging the difference in danger thresholds include: taking the range of disturbance of danger indicators as the object of danger monitoring, and classifying the warning level according to the disturbance amplitude threshold and danger state interpolation; wherein, danger indicators include stress field anomalies, gas concentration anomalies, and electromagnetic radiation intensity anomalies; the "danger" can reflect changes in environmental disturbances, respectively corresponding to common disaster datasets such as drilling, opening of fracture channels, and encountering gas bags, as well as environmental safety status datasets. The dataset in which the predicted value of the danger indicator is located represents the production status at a future moment.

[0066] Based on the above, the implementation process of the coal seam disaster-prone state early warning system based on the dynamic physical field digital twin of coal seam disaster-prone conditions in this embodiment is as follows: Figure 2As shown, it includes the following steps:

[0067] Step 1: Deploy sensors on the tunneling face to be monitored.

[0068] Among them, a laser rangefinder is placed at the entrance of the tunnel, pointing towards the tunneling face; a camera is placed inside the tunnel, and the monitoring range can cover the entire tunnel; a stress sensor is inserted into the bottom tunnel in front of the tunneling face to be monitored through a drill hole, and one is placed every 30m; a gas concentration sensor is placed behind the tunneling face, and one is placed every 50m; an electromagnetic radiation sensor is placed at the tunneling face.

[0069] Step 2: Construct a 3D model of the tunneling face to be monitored using digital modeling software, and add sensor models to build a three-dimensional digital model of the tunneling face.

[0070] Step 3: Store the sensor data into the hazard index tables in the server database, create program object instances based on each table, and each program object contains the historical data and characteristic information of its corresponding hazard index to realize numerical simulation of each type of sensor.

[0071] Step 4: Construct a dynamic physical field based on the hazard indicator object generator and update and display the corresponding contour map and cloud map in real time through the data-driven module. The dynamic physical field is subdivided into stress field, gas concentration field, and coal and rock failure intensity field.

[0072] Step 5: Map the dynamic physical field into the three-dimensional digital model of the working face to construct a visualized digital twin of the tunneling working face at the current moment, which includes the visualized dynamic physical field of each hazard indicator.

[0073] Step 6: Use the ARIMA algorithm to invert the digital twin of the tunneling face and present the inversion results in the digital twin of the disaster-prone dynamic physical field, so as to realize the visualization, informatization and intelligentization of the disaster-prone physical field of the tunneling face in future moments.

[0074] Step 7: Using the ARIMA algorithm and the hazard threshold difference judgment criterion, predict and judge the disturbance state of the dynamic physical field of each hazard indicator, issue intelligent hazard warning when it exceeds the specified hazard range, and provide emergency response suggestions.

[0075] Furthermore, such as Figure 3 As shown, the process by which the early warning system in this embodiment implements the early warning function is as follows:

[0076] Numerical simulation of downhole sensor signal volume and measured information is used to generate dynamic physical fields of hazard indicators;

[0077] The dynamic physical field of hazard indicators is mapped into the three-dimensional digital model of the working face to generate a digital twin of the tunneling working face that can reflect the disaster-prone area at the current moment.

[0078] By inverting the digital twin of the tunneling face, a dynamic physical field digital twin of the disaster-prone area can be obtained, which can reflect the disaster-prone area at future moments.

[0079] The hazard indicator disturbance early warning module monitors, predicts, and alarms the dynamic physical field digital twin of the disaster-prone area, realizing the monitoring, early warning, and emergency response prompts for coal and gas outburst hazards.

[0080] Using the aforementioned early warning system in this embodiment, global monitoring of the coal mine tunneling face can be carried out. Using sensor and laser rangefinder data as environmental data, and through multiple digital twin generation and monitoring methods, the data values ​​and disturbance states of coal and gas outburst index parameters of the working face at the next moment can be predicted. Based on the danger threshold judgment, an early warning of coal and gas outburst danger zone can be made for the tunneling face.

[0081] In summary, this embodiment provides a disaster-prone status early warning system based on a dynamic physical field digital twin of coal seam disaster-prone conditions. Combining digital twin technology, it proposes a new concept of a dynamic physical field for coal seam disaster-prone indicators, and concretizes, digitizes, and objectifies the physical fields of various virtual disaster-prone indicators. Integrating the ARIMA algorithm, it achieves prediction and early warning of future production status, constructing a novel dynamic physical field digital twin of coal seam disaster-prone conditions. This effectively improves the visualization and intelligence level of prediction and early warning technologies for dynamic disasters such as coal and gas outbursts and rock bursts. Further development of mine digital twin construction will form a comprehensive, continuous, and accurate new digital twin early warning system for coal seam disaster-prone conditions, providing strong support for safe coal mine production.

[0082] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0083] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0086] Finally, it should be noted that the above description represents a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make various improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A disaster-prone state early warning system based on a digital twin of a dynamic physical field of coal seam disaster-prone conditions, characterized in that, The disaster-prone state early warning system includes: downhole sensors, a physical signal mapping module, a data-driven module, a data mapping module, a dynamic physical field inversion module, and a hazard indicator disturbance early warning module; wherein, The downhole sensor is used to be configured in the downhole tunneling face to be monitored, so as to monitor a variety of preset monitoring indicators in real time during the tunneling process of the downhole tunneling face to be monitored, and obtain data of each monitoring indicator; The physical signal mapping module is used to store the monitoring index data obtained by the downhole sensor into the corresponding data table of each monitoring index, and generate virtual objects of each monitoring index based on the data table of each monitoring index; wherein, the virtual objects include the historical data of the corresponding monitoring index; The data-driven module is used to construct the dynamic physical field corresponding to each monitoring indicator, and to embed the virtual objects of each monitoring indicator into the dynamic physical field corresponding to the corresponding indicator to reflect the disaster situation in the mining area at the current moment; wherein, the virtual objects change in real time as the data of the corresponding monitoring indicators change. The data mapping module is used to construct a three-dimensional model of the underground tunneling face to be monitored and its mining area at a 1:1 scale to obtain a three-dimensional digital model of the working face; and to map the dynamic physical field corresponding to each monitoring index into the three-dimensional digital model of the working face to obtain a digital twin of the tunneling face. The dynamic physical field inversion module is used to invert the digital twin of the tunneling face to obtain a dynamic physical field digital twin of coal seam disaster. The danger index disturbance early warning module is used to perform real-time analysis of the coal seam disaster formation process based on the coal seam disaster formation dynamic physical field digital twin, and to issue an early warning when a major danger occurs. The preset monitoring indicators include: tunneling progress, gas concentration, stress field at the tunneling face, and coal and rock damage intensity. Accordingly, the downhole sensors include: a laser rangefinder, a gas concentration sensor, a stress sensor, and an electromagnetic radiation sensor; The danger indicator disturbance early warning module is specifically used for: The ARIMA algorithm is used to predict the disturbances of three monitoring indicators in the digital twin of the dynamic physical field of coal seam disaster-prone area: gas concentration, stress field at the tunnel face, and coal and rock failure intensity. Based on the preset danger threshold difference judgment criteria, the coal seam disaster-inducing process is analyzed in real time according to the disturbance prediction results of the monitoring indicators, and an early warning is issued when a sudden danger occurs. At the same time, emergency response suggestions are provided when an early warning is issued, and the disaster-inducing location is marked in the three-dimensional digital model of the working face.

2. The early warning system for coal seam disaster-prone status based on a dynamic physical field digital twin as described in claim 1, characterized in that, The arrangement of the downhole sensors is as follows: The laser rangefinder is positioned at the entrance of the tunnel, pointing towards the tunneling face; The stress sensors are multiple in number and are inserted into the bottom roadway in front of the working face to be monitored in the underground mine through drill holes, with one stress sensor arranged every 30m; The gas concentration sensors are arranged at multiple points behind the tunneling head, one every 50m. The electromagnetic radiation sensor is located at the tunnel head.

3. The early warning system for coal seam disaster-prone status based on a dynamic physical field digital twin as described in claim 1, characterized in that, The physical signal mapping module generates virtual objects for each monitoring indicator in the following way: The stress field in front of the tunnel face is displayed using a stress field contour map; The gas concentration field behind the tunneling face is shown using a gas concentration contour map; The degree of damage to the coal and rock around the tunneling face is shown by using a dynamic curve of electromagnetic radiation. The tunneling speed and total progress are displayed using a tunneling gauge.

4. The early warning system for coal seam disaster-prone status based on a dynamic physical field digital twin as described in claim 1, characterized in that, The on-site three-dimensional digital model of the working face includes: working face geological unit, tunneling machine production unit, and sensor unit.

5. The early warning system for coal seam disaster-prone status based on a dynamic physical field digital twin as described in claim 1, characterized in that, The dynamic physical field inversion module is specifically used for: The ARIMA algorithm is used to predict the three dynamic physical fields—stress field, gas concentration field, and coal and rock failure intensity field—in the digital twin of the tunneling face at the current moment, so as to obtain the prediction results of the three dynamic physical fields at future moments. The prediction results of the three dynamic physical fields at future moments are then imported into the digital twin of the coal seam disaster-prone dynamic physical field to reflect the disaster-prone situation in the mining area at future moments.

6. The early warning system for coal seam disaster-prone status based on a dynamic physical field digital twin as described in claim 1, characterized in that, The criteria for judging the difference in danger thresholds include: The disturbance range of three monitoring indicators—gas concentration, stress field at the tunnel face, and coal and rock failure intensity—is used as the monitoring object for danger. The warning level is classified according to the preset disturbance range threshold and the danger state interpolation.

Images