Coal mine underground roadway surrounding rock state monitoring and catastrophe early warning method

Abstract

The invention relates to a coal mine underground roadway surrounding rock state monitoring and catastrophe early warning method, and belongs to the technical field of coal mine safety monitoring. Aiming at the problems of data isolation, response lag and inaccurate catastrophe positioning in the prior art, the invention provides a cooperative monitoring scheme fused with multi-source sensing: constructing a polygon monitoring network through an ad hoc network geophone to perceive surrounding rock deformation in real time, and capturing fracture development characteristics in combination with an anchor rod multi-point separation layer displacement sensor; the millimeter wave radar is triggered to dynamically scan the abnormal area; and a data fusion algorithm is adopted to analyze the deformation gradient and the strain tensor, and accurate positioning of a catastrophe position and evolution trend prediction are realized. The method has the technical effects that the limitation of a single monitoring technology is broken through, the catastrophe positioning precision and the early warning timeliness are synchronously improved, and multi-dimensional decision support is provided for stability evaluation of deep roadway surrounding rocks.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal mine safety monitoring, and relates to a method for monitoring the state of roadway surrounding rock and disaster warning in coal mines. Background Art

[0002] Driven by the continuous development of the global economy and the rigid growth of energy demand, the status of coal as the ballast of the energy system is difficult to change in the short term. At present, the shallow coal seams are on the verge of exhaustion due to long-term high-intensity mining, and the deep coal seams have become the main battlefield for ensuring energy security. With the increase of mining depth, the roadway faces the superimposed effects of high ground stress, high pore water pressure and complex geological structures, resulting in a sharp increase in the risk of non-linear disasters such as large deformation of the surrounding rock and rock burst. However, the existing monitoring technology system has significant defects: the traditional roadway surrounding rock displacement monitor can only detect local deformation and cannot locate the starting point of the disaster; although the microseismic monitoring technology has a wide coverage, it is difficult to identify the type of anomaly due to the interference of the complex underground environment; the non-contact distance measurement sensor is limited by the narrow monitoring area and cannot be analyzed in coordination with other technical data. More critically, the data isolation of the existing technology leads to a lag in the response of the disaster signal and insufficient accuracy in deformation positioning, making it difficult to meet the real-time warning requirements for disasters in deep roadways.

[0003] Therefore, there is an urgent need for a monitoring method that integrates multi-source data to break through the limitations of a single technology and achieve accurate positioning and early warning of roadway surrounding rock disasters. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method for monitoring the state of roadway surrounding rock and disaster warning in coal mines. To solve the problems that the existing non-contact distance measurement sensor only monitors the roadway within the monitoring area, the monitoring area is limited, the data are independent of each other, it is impossible to jointly judge the disaster situation of the roadway, and there are problems such as response lag, difficulty in accurately positioning the roadway deformation and disaster location.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A method for monitoring the state of roadway surrounding rock and disaster warning in coal mines, comprising the following steps:

[0007] Step 1: Install at least three seismographs with self-organizing network functions on the roof and two sides of the roadway bolt 3. The seismographs include a first seismograph 11, a second seismograph 12 and a third seismograph 13, forming a polygon monitoring network to monitor the change of the relative distance between the seismographs in real time;

[0008] Step 2: Install a multi-point separation displacement sensor 4 at the end of each bolt 3 to monitor the displacement data of the roadway surrounding rock in real time;

[0009] Step 3: When the seismometer detects the rock mass rupture vibration signal or the relative distance change of the polygon monitoring network exceeds the threshold, trigger the millimeter-wave radar ranging sensor to perform directional scanning on the abnormal area;

[0010] Step 4: Integrate the deformation data of the polygon monitoring network, the multi-point separation displacement data and the millimeter-wave radar scanning data, and determine the location and evolution trend of the disaster through data fusion analysis;

[0011] Step 5: Generate a hierarchical warning signal according to the coordinates of the disaster location and the evolution trend.

[0012] Furthermore, the seismometer in Step 1 has an electromagnetic wave ranging function, and alternately performs vibration monitoring and adjacent node spacing measurement through time division multiplexing. The shape parameters of the polygon monitoring network include at least one geometric feature parameter such as the side length change rate and the angle change amount of each side.

[0013] Furthermore, the millimeter-wave radar ranging sensor in Step 3 includes a first millimeter-wave radar ranging sensor 21 and a second millimeter-wave radar ranging sensor 22, and adopts a composite scanning method combining mechanical rotation scanning and electronic beam scanning. The scanning range covers a ±45° solid angle range of the azimuth where the abnormal area is located, and the scanning frequency is dynamically adjusted according to the intensity of the disaster signal.

[0014] Furthermore, the data fusion analysis in Step 4 includes:

[0015] Perform spatial difference processing on the deformation data of the seismometer network to establish a roadway surface displacement field;

[0016] Register the millimeter-wave radar point cloud data with the displacement field, and calculate the three-dimensional deformation gradient of the surrounding rock through the iterative closest point algorithm;

[0017] Combine the axial displacement data of the multi-point separation displacement sensor 4 to construct a surrounding rock strain tensor model.

[0018] Furthermore, the calculation formula of the strain tensor model is:

[0019]

[0020] where ε ij represents the strain tensor component in the Cartesian coordinate system, and the subscripts i, j ∈ {1, 2, 3}, corresponding to the three-dimensional space coordinate axes respectively, and u i , u j represent the components in the x i , x j directions respectively.

[0021] A monitoring and disaster warning system for the surrounding rock state of coal mine roadways includes:

[0022] A polygon monitoring network composed of a first seismograph 11, a second seismograph 12, and a third seismograph 13, where each seismograph is interconnected through a wireless communication module, with functions of synchronous vibration monitoring and node spacing measurement;

[0023] Multiple magnetostrictive multi-point separation displacement sensors 4 are installed at the tail end of the bolt 3 through flexible measuring rods, and each sensor integrates no less than three cursor magnetic rings;

[0024] The first millimeter-wave radar ranging sensor 21 and the second millimeter-wave radar ranging sensor 22 have a mechanical rotation mechanism and an electronic beam scanning function, and perform directional scanning in response to the abnormal signals of the polygon monitoring network;

[0025] A data processing unit is configured to execute the disaster analysis algorithm of the method.

[0026] Furthermore, the first seismograph 11, the second seismograph 12, the third seismograph 13 and the multi-point separation displacement sensor 4 are integrated in the same housing to form an integrated sensing node. The bottom of the housing is provided with a threaded interface for connecting to the bolt 3, and the top is integrated with a millimeter-wave reflection enhancement structure.

[0027] Furthermore, the communication module of the integrated sensing node supports dual-mode communication of the Long Range Wide Area Network (LoRaWAN) protocol and the Narrow Band Internet of Things (NB-IoT) protocol, and forms a Mesh network topology structure in the roadway. The network node density is 1-3 nodes deployed per 10-meter roadway length.

[0028] Furthermore, the scanning mechanisms of the first millimeter-wave radar ranging sensor 21 and the second millimeter-wave radar ranging sensor 22 include a pitch-azimuth two-axis pan-tilt head, with an azimuth angle scanning range of 360°, a pitch angle scanning range of -30° to +60°, a distance resolution of up to 5 cm, and a maximum detection distance of 50 meters.

[0029] Furthermore, the data processing unit includes an edge computing module and a cloud disaster deduction module. The edge computing module is deployed in an underground explosion-proof box to process the original sensor data in real time and generate a primary warning; the cloud disaster deduction module constructs a three-dimensional mechanical model of the roadway based on digital twin technology and performs long-term stability prediction analysis.

[0030] The beneficial effects of the present invention are as follows: By integrating multi-source sensing data and a collaborative analysis mechanism, the limitations of a single monitoring method are effectively overcome, and all-round three-dimensional monitoring of the disaster-causing changes in the surrounding rock of the roadway is realized. A dynamic geometric monitoring network is constructed using self-organizing seismic sensors, and combined with the active scanning ability of millimeter-wave radar, the initial position and expansion path of the deformation of the surrounding rock are accurately captured, significantly improving the accuracy of disaster-causing positioning. At the same time, through the spatio-temporal correlation analysis of multi-sensor data, the problem of data islands in traditional monitoring technologies is broken through, and ultra-early identification of abnormal surrounding rock states is realized. In addition, a two-layer processing architecture of edge computing and cloud models is adopted. While ensuring real-time early warning response, it supports the prediction of the long-term stability evolution trend of the surrounding rock, providing multi-dimensional decision-making support for the safety control of deep roadways.

[0031] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on an investigation and study of the following text, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be described in detail preferably with reference to the accompanying drawings, where:

[0033] Figure 1 is the schematic diagram of the present invention.

[0034] Reference numerals: 11 - first seismic sensor, 12 - second seismic sensor, 13 - third seismic sensor, 21 - first millimeter-wave radar ranging sensor, 22 - second millimeter-wave radar ranging sensor, 3 - bolt, 4 - multi-point separation displacement sensor. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The following specific examples illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the drawings provided in the following embodiments only illustrate the basic concept of the present invention schematically, and the following embodiments and the features in the embodiments can be combined with each other without conflict.

[0036] Among them, the accompanying drawings are only for illustrative purposes, showing only schematic diagrams rather than physical diagrams, and should not be construed as a limitation on the present invention; in order to better illustrate the embodiments of the present invention, some components in the accompanying drawings will be omitted, enlarged or reduced, which do not represent the dimensions of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the accompanying drawings may be omitted.

[0037] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc. indicating the orientation or positional relationship, they are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the accompanying drawings are only for illustrative purposes and should not be construed as a limitation on the present invention. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0038] Please refer to Figure 1 , a method for monitoring the surrounding rock state and disaster warning of underground coal mine roadways, including a first seismometer, a second seismometer 12, a third seismometer 13, a first millimeter-wave radar ranging sensor 21, a second millimeter-wave radar ranging sensor 22, a bolt 3, and a multi-point separation displacement sensor 4.

[0039] The seismometers have self-organizing network and electromagnetic wave ranging functions, and the number is not less than 3, which are respectively set at Figure 1 points a, b, and c in [the figure], and the seismometers communicate with each other to form a virtual polygon. By monitoring the change in the relative distance between two seismometers, disasters such as the settlement of the vault and the displacement of the roof of the underground roadway are monitored. The seismometers monitor rock mass fracture events and the stability of the roadway through the vibration signals of the rock formation. The multi-point separation displacement sensor monitors events such as the separation change of the roadway roof, the development of cracks in the surrounding rock of the roadway, and the settlement of the roof.

[0040] The millimeter-wave radar ranging sensor is used to continuously scan the roadway sidewalls around the sensors where the surrounding rock disaster signals of the roadway appear when the wireless seismometers and the multi-point separation displacement sensors monitor such signals, and continuously monitor the state of the surrounding rock in the area around the disaster signals.

[0041] Further, the wireless seismograph and the multi-point separation displacement sensor are integrated sensors, which are installed at the end of the bolt. A number of wireless seismographs and multi-point separation displacement integrated sensors form a virtual polygon through self-networking. When the spatial position of the integrated sensor changes, the virtual polygon is damaged, and the multi-point separation displacement sensor starts to work, collects the displacement of the surrounding rock of the roadway, locates the integrated sensor with abnormal displacement of the surrounding rock by comparing with the initial value, and issues an early warning. When the seismograph monitors abnormal events such as rock mass rupture, the seismograph that monitors the abnormal vibration signal issues an early warning.

[0042] Further, when the wireless seismograph and the multi-point separation displacement sensor are integrated sensors and an early warning signal appears, it means that there are abnormalities around the sensor that issues the early warning signal, but it is difficult to accurately locate the surrounding rock where the abnormal event occurs.

[0043] The millimeter-wave radar ranging sensor continuously scans the roadway sidewall around the sensor with a disaster signal, continuously monitors the state of the surrounding rock in the area around the disaster signal, and facilitates early warning of surrounding rock disasters.

[0044] Further, the millimeter-wave radar ranging sensor can be either hung on the relatively stable roadway sidewall or installed in the roadway with a tripod, can rotate 360°, has a wireless communication function, and after receiving the signals of the integrated sensors of the wireless seismograph and the multi-point separation displacement sensor, automatically adjusts its orientation, continuously scans the surrounding rock around the warning sensor, and monitors the disaster situation of the surrounding rock.

[0045] Further, the multi-point separation displacement sensor is a displacement sensor based on the magnetostrictive principle, and the measuring rod is a flexible measuring rod, and more than three cursor magnetic rings can be used according to actual needs.

[0046] Example 1: Cooperative monitoring and disaster location of multi-source sensors

[0047] 1. Sensor deployment and initialization

[0048] Three self-networking seismographs are arranged in an equilateral triangle on the roadway roof (the vertex spacing is 8 meters), and the installation height is 2.5 meters from the bottom plate, and are respectively marked as the first seismograph (coordinates X = K12 + 300, Y = 3.2), the second seismograph (X = K12 + 308, Y = 0), and the third seismograph (X = K12 + 300, Y = -3.2).

[0049] A magnetostrictive multi-point separation displacement sensor is installed at the end of the bolt under each seismograph. The length of the measuring rod is 4 meters, and five cursor magnetic rings are set (depths 0.5m, 1.2m, 2.0m, 2.8m, 3.5m).

[0050] Install two sets of millimeter-wave radar ranging sensors symmetrically on both sides of the roadway, 1.8 meters from the floor, and align the initial azimuth angle of the scanning head with the roadway direction.

[0051] 2. Dynamic data acquisition

[0052] The seismograph network executes alternately with a 20ms time window:

[0053] a) Collect microseismic signals in the first 10ms (frequency band 50Hz - 5kHz, dynamic range 140dB);

[0054] b) Transmit 77GHz frequency-modulated continuous wave (FMCW) in the next 10ms to measure the distance between adjacent nodes (accuracy ±1mm).

[0055] The displacement sensor collects the displacement of each magnetic ring every 10 seconds, with a resolution of 0.01mm.

[0056] 3. Abnormal event trigger mechanism

[0057] When the following composite conditions are detected, a three-level response is initiated:

[0058] a) The second seismograph records 3 microseismic events with energy > 1e×4J within 3 seconds;

[0059] b) The shortening rate of the distance between the first and the third seismographs reaches 2mm / s;

[0060] c) The displacement of the magnetic ring at a depth of 1.2m suddenly increases by 0.8mm.

[0061] Trigger the first millimeter-wave radar to perform spiral scanning on the west side roadway wall (radius 5m, angular velocity 30° / s).

[0062] 4. Multimodal data fusion

[0063] Use the improved ICP algorithm to register the radar point cloud (2000 points per second) with the deformation field of the seismograph network, and establish a coordinate transformation matrix:

[0064]

[0065] Among them, θ = 12.7° is the deflection angle of the roadway direction, and (Δx, Δy) = (0.3m, -0.15m) is the coordinate offset.

[0066] Calculate the main components of the strain tensor ε1 = 1.2e-3, ε2 = -0.9e-3, and determine that the west side roadway wall has undergone shear-tensile composite failure.

[0067] 5. Hierarchical early warning output

[0068] Generate a secondary early warning message containing the following elements:

[0069] "Catastrophe type": "Hanging wall shear slip",

[0070] "Central coordinate": "K12+304W2.1m",

[0071] "Influence radius": "8.3m",

[0072] "Evolution trend": "The displacement is expected to reach 15mm in the next 2 hours",

[0073] "Disposal suggestions": ["Strengthen the bolt support of W3-W7", "Suspend the mining operation in this area"]

[0074] It is pushed to the dispatching center and on-site handheld terminals synchronously through the industrial ring network and the underground broadcasting system.

[0075] Embodiment 2: Integrated sensor node networking and real-time analysis

[0076] 1. High-density node deployment

[0077] Integrated sensor nodes (size Φ120×300mm) are arranged every 8 meters along the roadway. The node housing adopts a 304 stainless steel explosion-proof structure and is internally equipped with:

[0078] Triaxial MEMS accelerometer (range ±50g, noise density 100μg / √Hz)

[0079] Magnetostrictive displacement sensing module (range 4m, non-linear error <0.05% FS)

[0080] Dual-frequency millimeter-wave radar front end (24GHz+77GHz, bandwidth 4GHz)

[0081] The nodes form a self-healing Mesh network through 2.4GHz ZigBee, and the network delay <50ms.

[0082] 2. Adaptive sampling mechanism

[0083] In the basic mode:

[0084] The accelerometer sampling rate is 500Hz, and the displacement sensor samples every 30 seconds

[0085] The node power consumption is maintained at 15mW, and the battery life is 6 months

[0086] When any node detects that the vibration energy > 1e3J:

[0087] Activate 5 surrounding nodes to enter the high-precision mode (the accelerometer sampling rate is increased to 2kHz)

[0088] Start the radar module to perform a fan-shaped scan on the vibration source direction (azimuth angle ±60°, frame rate 10Hz)

[0089] 3. Edge intelligence processing

[0090] The on-node FPGA executes real-time feature extraction:

[0091] a) Perform wavelet packet decomposition on the acceleration signal (db4 wavelet, 5-layer decomposition), and extract the energy ratio in the frequency band of 3 - 5 kHz;

[0092] b) Perform Kalman filtering on the displacement data (process noise Q = 1e-6, observation noise R = 1e-5);

[0093] c) Use an SVM classifier to determine the type of anomaly (the training set contains 300 groups of historical disaster data).

[0094] When the classification confidence > 85%, trigger adjacent nodes to synchronously store the original waveform data (sampling rate 2 kHz, duration 30 s).

[0095] 4. Cloud digital twin modeling

[0096] The edge node uploads the compressed feature vectors to the cloud every 5 minutes, and the cloud executes:

[0097] a) Update the 3D mechanical model of the roadway based on FEM (element size 0.5 m, material parameters dynamically corrected);

[0098] b) Run the LSTM time series prediction network (256 nodes in the hidden layer, prediction step 60 minutes);

[0099] c) Generate a heat map to visualize the surrounding rock stability index (range 0 - 1, values above 0.7 are marked in red for early warning).

[0100] 5. Closed-loop control response

[0101] When the cloud model predicts that the safety factor of section K12+400 < 1.5:

[0102] a) Automatically adjust the pressure of the hydraulic props in this area (increase by 25%, maintain for 2 hours);

[0103] b) Start the directional pressure relief drilling robot to perform 3 groups of Φ50mm drills on the roof (depth 3 m, spacing 1.2 m);

[0104] c) Adjust the ventilation system to increase the wind speed in the abnormal area to 3 m / s and reduce the risk of gas accumulation.

[0105] Example 3: Adaptive disaster tracking with millimeter-wave radar

[0106] 1. Multi-target tracking and scanning

[0107] When the second millimeter-wave radar (operating frequency 79 GHz, bandwidth 4 GHz) detects abnormal echoes:

[0108] a) Initial scanning mode: The mechanical pan-tilt performs omnidirectional scanning (rotation speed 10° / s, range resolution 5 cm);

[0109] b) After detecting a suspicious target, switch to the electronic scanning mode (phased array beam, scanning rate 1000 beams / s);

[0110] c) Perform TOF ranging on 5 key areas (accuracy ±1 mm, update rate 50 Hz).

[0111] 2. Dynamic trajectory prediction

[0112] Establish a Kalman filter to track the target motion:

[0113]

[0114] where p x , p y represents the horizontal position coordinates of the target in the roadway coordinate system; v x , v y represents the motion speeds of the target in the x and y directions; Q represents the process noise covariance matrix; P k|k-1 represents the predicted state covariance; P k-1|k-1 represents the corrected state covariance at the previous moment; the state transition matrix F includes roadway constraint conditions (the velocity component v y is limited to ±0.5 m / s).

[0115] When the overlap degree between the predicted position of the target and the deformation area detected by the seismometer network is >70%, it is determined as an effective disaster point.

[0116] 3. Multi-sensor data association

[0117] Construct a joint probabilistic data association (JPDA) model:

[0118] a) The millimeter-wave radar provides target coordinates (σ = 0.1 m);

[0119] b) The seismometer network provides strain distribution (grid accuracy 0.2 m);

[0120] c) The displacement sensor provides the depth displacement gradient.

[0121] Calculate the matching probability of each target with the disaster characteristics, and eliminate false alarm targets with a confidence level <60%.

[0122] 4. Adaptive early warning strategy

[0123] Dynamically adjust the early warning level according to the target evolution characteristics as shown in Table 1.

[0124] Table 1

[0125] Disaster parameter Level 3 warning Level 2 warning Level 1 warning Displacement rate (mm / min) 1～3 3～5 >5 <![CDATA[Strain energy density (kJ / m 3 )]]> 50～100 100～200 >200 Influence range diameter (m) 2～5 5～10 >10

[0126] When two of the three parameters reach the upgrade threshold, a cross-level warning is triggered.

[0127] 5. Emergency resource scheduling

[0128] After the first-level warning is triggered, the following actions are taken:

[0129] a) Automatically dispatch an inspection robot (travel speed 0.8 m / s) equipped with a thermal imager and a gas sensor to approach and conduct reconnaissance;

[0130] b) Activate the laser methane telemetry system to perform a concentration distribution scan within a 20 m range around the disaster point;

[0131] c) Dispatch an emergency material transport vehicle to load quick-setting cement and U-shaped steel supports to the preparatory position (the refuge chamber at K12+350).

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the purpose and scope of the present technical solution, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for monitoring the surrounding rock state of roadways in coal mines and early warning of disasters, characterized in that: Including the following steps: Step 1: Install at least three seismographs with self - networking function on the roof and two sides of the roadway bolt (3). The seismographs include a first seismograph (11), a second seismograph (12) and a third seismograph (13), forming a polygon monitoring network to monitor the relative distance change between seismographs in real time; Step 2: Install multi - point separation displacement sensors (4) at the tail ends of each bolt (3) to monitor the displacement data of the surrounding rock of the roadway in real time; Step 3: When the seismograph detects a rock mass rupture vibration signal or the relative distance change of the polygon monitoring network exceeds the threshold, trigger the millimeter - wave radar ranging sensor to perform directional scanning on the abnormal area; Step 4: Based on the deformation data of the polygon monitoring network, multi - point separation displacement data and millimeter - wave radar scanning data, determine the location and evolution trend of the disaster through data fusion analysis; Step 5: Generate a hierarchical warning signal according to the disaster location coordinates and evolution trend.

2. The method for monitoring the surrounding rock state of underground roadways in coal mines and disaster warning according to claim 1, wherein: In Step 1, the seismograph has an electromagnetic wave ranging function, and alternately performs vibration monitoring and adjacent node spacing measurement through time - division multiplexing. The shape parameters of the polygon monitoring network include at least one geometric characteristic parameter such as the side length change rate and angle change amount of each side.

3. The method for monitoring the surrounding rock state of underground coal mine roadways and disaster warning according to claim 1, characterized in that: In Step 3, the millimeter - wave radar ranging sensor includes a first millimeter - wave radar ranging sensor (21) and a second millimeter - wave radar ranging sensor (22), adopting a composite scanning method combining mechanical rotation scanning and electronic beam scanning. The scanning range covers a ±45° solid angle range of the azimuth where the abnormal area is located, and the scanning frequency is dynamically adjusted according to the intensity of the disaster signal.

4. The method for monitoring the surrounding rock state and disaster warning of underground roadways in coal mines according to claim 1, characterized in that: The data fusion analysis in Step 4 includes: Perform spatial difference processing on the deformation data of the seismograph network to establish a roadway surface displacement field; Register the millimeter - wave radar point cloud data with the displacement field, and calculate the three - dimensional deformation gradient of the surrounding rock through the iterative closest point algorithm; Combine the axial displacement data of the multi - point separation displacement sensor (4) to construct a surrounding rock strain tensor model.

5. The method for monitoring the surrounding rock state of underground coal mine roadways and disaster warning according to claim 4, characterized in that: The calculation formula of the strain tensor model is: where ε ij represents the components of the strain tensor in the Cartesian coordinate system, with subscripts i, j ∈ {1, 2, 3}, corresponding to the three-dimensional space coordinate axes respectively, and u i , u j represent the components in the x i , x j directions respectively.

6. A monitoring system for the surrounding rock state of underground roadways in coal mines and a disaster warning system, characterized in that: Including: A polygon monitoring network composed of a first seismograph (11), a second seismograph (12) and a third seismograph (13). Each seismograph is interconnected through a wireless communication module and has functions of synchronous vibration monitoring and node spacing measurement; Multiple magnetostrictive multi - point separation displacement sensors (4), installed at the tail ends of the bolts (3) through flexible measuring rods, and each sensor integrates no less than three cursor magnetic rings; A first millimeter - wave radar ranging sensor (21) and a second millimeter - wave radar ranging sensor (22), having a mechanical rotation mechanism and an electronic beam scanning function, and performing directional scanning in response to the abnormal signal of the polygon monitoring network; A data processing unit, configured to execute the disaster analysis algorithm of the method described in any one of claims 1 - 5.

7. The monitoring system for the surrounding rock state of underground coal mine roadways and the disaster warning system according to claim 6, characterized in that: The first seismograph (11), the second seismograph (12), the third seismograph (13) and the multi - point separation displacement sensor (4) are integrated into the same housing to form an integrated sensing node. The bottom of the housing is provided with a threaded interface for connecting with the bolt (3), and the top is integrated with a millimeter - wave reflection enhancement structure.

8. The monitoring system for surrounding rock state of underground roadway in coal mine and disaster warning system according to claim 7, characterized in that: The communication module of the integrated sensing node supports dual-mode communication of the Long Range Wide Area Network (LoRaWAN) protocol and the Narrow Band Internet of Things (NB-IoT) protocol, forming a Mesh network topology in the roadway, with a network node density of 1 to 3 nodes deployed per 10-meter roadway length.

9. The monitoring system for surrounding rock state and disaster warning in underground coal mine roadways according to claim 6, characterized in that: The scanning mechanisms of the first millimeter-wave radar ranging sensor (21) and the second millimeter-wave radar ranging sensor (22) include a pitch-azimuth two-axis pan-tilt head, with an azimuth angle scanning range of 360° and a pitch angle scanning range of -30° to +60°, a distance resolution of up to 5 cm, and a maximum detection distance of 50 meters.

10. The monitoring system for surrounding rock state of roadway in coal mine and disaster warning system according to claim 6, characterized in that: The data processing unit includes an edge computing module and a cloud disaster deduction module. The edge computing module is deployed in an underground explosion-proof box and is used to process raw sensor data in real time and generate primary warnings. The cloud disaster deduction module constructs a three-dimensional mechanical model of the roadway based on digital twin technology and performs long-term stability prediction and analysis.

Images