A monitoring system for deformation of surrounding rock in a well

Abstract

The application discloses a kind of for underground surrounding rock deformation monitoring system, it is related to mine safety monitoring technical field, including acquisition module, analysis module and decision module, acquisition module is used to collect three-dimensional space geometry data and real-time data, establishes coding and dynamically expands sample library;Analysis module is based on sample library and establishes hierarchical early warning system and visual model, and the deformation trend is analyzed by machine learning;Decision module predicts deformation development trend and rate, triggers hierarchical early warning and repair measures.The application realizes real-time, accurate monitoring and forward-looking early warning to underground surrounding rock deformation by multi-sensor data fusion, intelligent algorithm and visual display, effectively improves the automation and intelligent level of mine safety production, reduces the risk of accident and the demand of manual intervention.The system has the advantages of fast response, high precision, strong self-adaptation, etc.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mine safety monitoring, and in particular to a monitoring system for underground surrounding rock deformation. BACKGROUND

[0002] In the mining and construction process of underground engineering such as coal mines, the stability of the surrounding rock of the underground roadway directly relates to the life safety of the operating personnel and the smooth progress of production. The surrounding rock will deform under the influence of mining stress, geological structure and other factors, and if it cannot be monitored and warned in time, it may lead to serious accidents such as roadway collapse and roof fall.

[0003] Traditional surrounding rock monitoring methods mostly rely on manual periodic measurement using convergence meters, separation meters and other tools. This method is not only inefficient and data discrete, but also has a monitoring blind area, making it difficult to capture the dynamic whole process of surrounding rock deformation in time. In addition, some existing automatic monitoring systems often focus on the monitoring of a single physical quantity, such as displacement or stress, lack the fusion of multi-source information, cannot construct the overall three-dimensional spatial situation of surrounding rock deformation, the warning method is single, and lack the prediction ability based on historical data, resulting in insufficient accuracy and foresight of the warning.

[0004] At present, the Chinese invention patent with application number CN202510625829.9 discloses a coal mine underground roadway surrounding rock state monitoring and disaster warning method, which constructs a polygonal monitoring network by a self-organizing network seismic pickup to realize real-time sensing of surrounding rock deformation, combines an anchor rod multi-point separation displacement sensor to capture crack development characteristics, and triggers a millimeter wave radar to dynamically scan the abnormal area; a data fusion algorithm is used to analyze the deformation gradient and strain tensor to realize accurate positioning of the disaster location and evolution trend prediction. Its technical effect lies in breaking through the limitations of single monitoring technology, simultaneously improving the disaster positioning accuracy and warning timeliness, and providing multi-dimensional decision support for deep roadway surrounding rock stability evaluation.

[0005] The above-mentioned technology is difficult to judge the danger of the warning, and each warning may cause waste of resources, the prediction result is not verified and adjusted, the corresponding warning method is not reminded for the corresponding warning situation, it is not convenient to distinguish the serious situation of the surrounding rock state, and the signal is poor in the coal mine, the transmission data is slow and easy to lose. SUMMARY

[0006] The technical problem solved by the present application is that the prior art is difficult to judge the danger of the warning, each warning may cause waste of resources, the prediction result is not verified and adjusted, the corresponding warning method is not reminded for the corresponding warning situation, it is not convenient to distinguish the serious situation of the surrounding rock state, and the signal is poor in the coal mine, the transmission data is slow and easy to lose.

[0007] To solve the above technical problems, the application provides the following technical scheme: a monitoring system for deformation of surrounding rock in a mine, comprising a collection module, an analysis module and a decision module:

[0008] The collection module is used for collecting three-dimensional space geometry data, obtaining a three-dimensional model, obtaining real-time data through different sensor nodes, establishing an encoding according to the real-time data, and increasing a sample library according to the encoding;

[0009] The analysis module is used for obtaining sample historical data according to the sample library, establishing a hierarchical early warning system according to the sample historical data, and obtaining a visual model through the three-dimensional model according to the hierarchical early warning system and the real-time data;

[0010] The decision module is used for taking the sample library and the hierarchical early warning system as a first instruction, obtaining a deformation development trend and rate, taking the real-time data, the deformation development trend and the rate as a second instruction, obtaining a prediction result, calling the corresponding prediction result through the encoding, obtaining an early warning level and a position according to the prediction result, and performing maintenance and alarm.

[0011] As a preferred scheme of the monitoring system for deformation of surrounding rock in a mine, the three-dimensional model specifically comprises:

[0012] The three-dimensional space geometry data comprises roadway section profile data, surrounding rock surface topography data and borehole peeping data;

[0013] The roadway section profile data comprises an initial shape and size of a roadway, the surrounding rock surface topography data comprises three-dimensional coordinate information of a surrounding rock surface relief and crack distribution after roadway excavation, and the borehole peeping data comprises three-dimensional space information of an internal structure of surrounding rock;

[0014] The roadway section profile data is obtained through a total station and a three-dimensional laser scanner;

[0015] The borehole peeping data is obtained through borehole photography and radar;

[0016] The three-dimensional model is obtained according to the three-dimensional space geometry data.

[0017] As a preferred scheme of the monitoring system for deformation of surrounding rock in a mine, the real-time data specifically comprises:

[0018] The real-time data comprises displacement data, stress data and microseismic data, the displacement data comprises a relative displacement of a top and bottom plate of a coal mine underground roadway, convergence displacement of two sides and three-dimensional coordinate change of a specific point on a roadway surface;

[0019] The stress data includes internal stress of surrounding rock, anchor rod stress, anchor cable stress and hydraulic support working resistance;

[0020] The microseismic data includes energy, position and occurrence time of microseismic events generated by rock mass fracture;

[0021] The displacement data is acquired by the displacement sensor;

[0022] The stress data is acquired by the stress sensor;

[0023] The microseismic data is acquired by the microseismic sensor.

[0024] As a preferred scheme of the monitoring system for deformation of surrounding rock in a mine shaft, the establishing code specifically comprises:

[0025] The underground node and the cloud node are set through the communication bus, the real-time data is transmitted to the underground node, and the historical data range is matched;

[0026] If the real-time data is within the historical data range, the code of the historical data is transmitted to the cloud node;

[0027] If the real-time data is not within the historical data range, a new code is established according to the real-time data, the real-time data is expanded according to a preset expansion range, the historical data range is acquired, saved to the underground node, and then the real-time data and the new code are transmitted to the cloud node; the cloud node expands the real-time data according to the preset expansion range, increases a sample library, and the sample library includes sample historical data, code and prediction result;

[0028] The historical data range is a expansion value interval with the real-time data as a center and the preset expansion range as an interval radius, the real-time data is expanded, sample codes of all virtual data points in the expansion value interval are established, and the virtual data points are regarded as the acquired real-time data;

[0029] The sample historical data is all virtual data points in the expansion value interval, and the virtual data points are sorted according to time.

[0030] As a preferred scheme of the monitoring system for deformation of surrounding rock in a mine shaft, the hierarchical early warning system specifically comprises:

[0031] Sample historical data is acquired according to the sample library, data ranges are divided according to the sample historical data, early warning levels are set according to the data ranges, and the data ranges include a first range, a second range and a third range;

[0032] The setting early warning level is divided according to the real-time data of the deformation degree in the sample historical data, and the data range is the maximum and minimum values of the real-time data of the normal deformation, the maximum and minimum values of the real-time data of the deformation needing to be checked, and the maximum and minimum values of the real-time data of the deformation needing to be repaired.

[0033] The early warning level corresponding to the first range is primary early warning, the early warning level corresponding to the second range is middle early warning, and the early warning level corresponding to the third range is high early warning.

[0034] As a preferred scheme of the monitoring system for deformation of surrounding rock in a well, the visualization model specifically comprises:

[0035] The early warning level is displayed in different colors on the corresponding position on the three-dimensional model to obtain a visualization model, the primary early warning corresponds to a first color, the middle early warning corresponds to a second color, the high early warning corresponds to a third color, and the corresponding position is a color-coded position corresponding to a specific area of the collected real-time data.

[0036] As a preferred scheme of the monitoring system for deformation of surrounding rock in a well, the analysis module specifically comprises:

[0037] The sample library and the grading early warning system are input into a machine learning model as a first instruction to perform regression analysis and time series analysis and obtain a deformation development trend and rate, the real-time data, the deformation development trend and rate are input into the machine learning model as a second instruction to obtain a prediction result, and the prediction result is theoretical real-time data, a risk level and position information.

[0038] According to the prediction result, the corresponding early warning level is determined through the color displayed by the visualization model, the corresponding position information is obtained according to the position displayed by the color, and the corresponding early warning mode is triggered according to the early warning level.

[0039] As a preferred scheme of the monitoring system for deformation of surrounding rock in a well, the corresponding early warning mode specifically comprises:

[0040] The early warning mode corresponding to the primary early warning is to display the real-time data through a monitoring center and send a normal message and the real-time data to designated personnel.

[0041] The early warning mode corresponding to the middle early warning is to trigger an audible and light alarm and link a downhole broadcasting system to publish an abnormal data message and display position information.

[0042] The high-level early warning corresponds to an early warning mode of triggering an audible and light alarm, linking an underground broadcasting system to issue evacuation instructions, automatically locking the power supply of equipment and displaying location information.

[0043] As a preferred scheme of the monitoring system for deformation of surrounding rock in a mine shaft, the decision module specifically comprises:

[0044] The theoretical real-time data and the real-time data are subtracted to obtain a difference value, when the difference value is greater than or equal to a first threshold value and less than or equal to a second threshold value, the theoretical real-time data is taken as the real-time data to obtain a new prediction result;

[0045] When the difference value is less than the first threshold value or greater than the second threshold value, the theoretical real-time data is discarded, and a new prediction result is obtained according to the real-time data, a deformation development trend and a rate.

[0046] As a preferred scheme of the monitoring system for deformation of surrounding rock in a mine shaft, the decision module further comprises:

[0047] According to the newly added sample historical data, the grading early warning system is updated, and the corresponding data range is adjusted according to the updated grading early warning system.

[0048] When the historical data range of the sample library covers all expected working conditions of the deformation of the surrounding rock in the mine shaft, real-time data are obtained, an encoding corresponding to the real-time data is sent to a cloud node, and the cloud node directly calls a corresponding prediction result according to the encoding.

[0049] The beneficial effects of the present application: by adopting the multi-sensor fusion technology, the three-dimensional space geometry data including the roadway section contour data, the surrounding rock surface topography data and the borehole peep data, and the real-time data such as displacement, stress and microseismic are collected, which ensures the comprehensiveness and accuracy of data collection, which provides a reliable foundation for building a high-precision three-dimensional model, so as to more truly reflect the deformation state of the surrounding rock, through the establishment of the coding mechanism and the dynamic sample library, the efficient management and expansion of the data are realized, the sample library is intelligently expanded based on the historical data range, which can cover a variety of expected working conditions, improve the adaptability and robustness of the system, reduce the misjudgment risk caused by data loss, the analysis module establishes a hierarchical early warning system based on the sample library, divides the early warning level into primary, intermediate and high levels, and intuitively displays in the visual model through color coding, so that the management personnel can quickly identify the risk area and level, improve the intuitiveness and operability of monitoring, facilitate timely response measures, the decision module uses machine learning model for regression analysis and time series analysis, predicts the deformation trend and rate, and generates prediction results combined with real-time data, realizes forward-looking early warning, and can also automatically trigger the corresponding early warning mode, such as sound and light alarm, broadcast notification and equipment locking, ensures the timeliness and effectiveness of emergency response, finally, has self-optimization ability, dynamically adjusts the prediction model by comparing the difference between the theoretical prediction data and the actual data, and updates the hierarchical early warning system, ensures the accuracy of long-term monitoring, which not only improves the accuracy and efficiency of the deformation monitoring of the surrounding rock in the mine, but also reduces the labor cost, enhances the automation and intelligent level of the mine safety production, provides reliable technical support for preventing accidents, at the same time, through visual display and intelligent decision, improves the overall safety management level. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 A basic flowchart of a monitoring system for deformation of surrounding rock in a mine is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all embodiments.

[0052] The embodiment of the present application provides a kind of for monitoring system of deformation of surrounding rock in well, system can be applied to including but not limited to coal mine, metal mine and so on underground safety monitoring platform, and in including but not limited to when carrying out roadway surrounding rock deformation real-time monitoring and early warning, it is suitable for mine exploitation, tunnel engineering and other underground engineering safety monitoring scene.Face the technical problems of traditional technology in well surrounding rock deformation monitoring data, early warning lag, decision support is insufficient, the inventor proposes the underground surrounding rock deformation monitoring system of the embodiment of the present application, the core idea of the embodiment of the present application is: by multi-sensor acquisition three-dimensional space geometry data and real-time data, establish coding and sample library, based on sample library construction hierarchical early warning system and visual model, utilize machine learning analysis and predict deformation trend, realize accurate early warning and automation response, to improve the safety and reliability of underground operation.

[0053] Embodiment 1, refer to Figure 1 , Figure 1 The module schematic diagram of a kind of for monitoring system of deformation of surrounding rock in well provided by the embodiment of the present application is as shown in Figure 1 As shown in the embodiment, the system includes but is not limited to acquisition module, analysis module and decision module:

[0054] In an embodiment, the acquisition module is used to acquire three-dimensional space geometry data, obtain three-dimensional model, obtain real-time data by different sensor nodes, establish coding according to real-time data, and increase sample library according to the coding;

[0055] The acquisition module provides original input for surrounding rock deformation monitoring by multi-source data acquisition. The roadway section profile data is obtained by total station and three-dimensional laser scanner.

[0056] The roadway section profile data acquisition unit is based on geometric measurement principle, and a typical coal mine roadway is taken as a prototype to establish a three-dimensional geometric model of the roadway. The key parameters of the roadway are defined as an arch-shaped section, a width of 4.5 meters, and a height of 3.2 meters. The key point coordinates of the roadway, such as the roof, floor, and two sides, are measured by a total station. The total station uses Leica TS60 model, with a measurement accuracy of ±1 millimeter and a scanning rate of 1000 points per second. The initial shape and size data are obtained. High-density scanning is performed by a three-dimensional laser scanner, such as Faro Focus S350, to generate point cloud data. The point cloud density is 1000 points per square meter, and the point cloud accuracy is ±2 millimeters. The scanning range covers the full length of 100 meters of the roadway. The output roadway section profile data includes roadway contour line, section area, and geometric size. When implemented, data registration and three-dimensional reconstruction are performed by point cloud processing software, such as CloudCompare, to ensure that the model is consistent with the actual roadway.

[0057] Drill hole peeping data is obtained by drill hole camera and radar.

[0058] The borehole peeping data acquisition unit is based on optical and electromagnetic wave detection principles, drills a borehole in the surrounding rock of the roadway, the borehole has a diameter of 50 mm and a depth of 5 m, captures images and videos inside the surrounding rock through borehole camera equipment such as an endoscope camera, has a resolution of 1920x1080 and a frame rate of 30 fps, identifies cracks and cavities, transmits electromagnetic waves through a geological radar such as a GSSI SIR-4000, has a frequency of 100 MHz, detects the internal structure of the surrounding rock, obtains three-dimensional spatial information such as crack position, depth and strike, and outputs borehole peeping data including internal structure images, radar waveforms and three-dimensional coordinates; when implemented, the optical and radar data are integrated through a data fusion algorithm to generate a surrounding rock internal structure model.

[0059] Real-time data is obtained through displacement sensors, stress sensors and microseismic sensors;

[0060] The real-time data acquisition unit deploys multiple sensor nodes including displacement sensors such as laser displacement sensors installed on the roof and floor and the two sides of the roadway to measure the relative convergence of the roof and floor and the convergence displacement of the two sides with an accuracy of ±0.1 mm and a sampling frequency of 10 Hz; stress sensors such as resistance strain gauges embedded in the surrounding rock or installed on anchor rods and anchor cables to measure the internal stress of the surrounding rock, anchor rod stress and anchor cable stress with a range of 0-50 MPa and an accuracy of ±0.5%; microseismic sensors such as accelerometers arranged around the roadway to capture microseismic events with an energy detection range of 10⁻ 6 ⁻³J and a positioning accuracy of ±1 m; output real-time data including displacement data such as three-dimensional coordinate changes, stress data such as hydraulic support working resistance and microseismic data such as event energy and occurrence time; when implemented, the data is transmitted to the underground node through a wireless sensor network such as the ZigBee protocol to ensure real-time and stability.

[0061] The acquisition module is also used to establish encoding and add a sample library;

[0062] The coding and sample library management unit sets the underground node and the cloud node through a communication bus, such as industrial Ethernet, the underground node is deployed in the well and is responsible for data temporary storage, and the cloud node is located on the ground server; after real-time data is transmitted to the underground node, the real-time data is matched with a historical data range, the historical data range is a numerical interval generated by taking the real-time data value as the center and expanding the interval radius by ±5%, if the real-time data is within the historical data range, the system transmits the coding of the historical data to the cloud node, if the real-time data is out of the historical data range, the system generates a new coding, expands the new coding according to a preset expansion range with the real-time data as the center, generates a new historical data range, saves the new historical data range to the underground node, and transmits the real-time data and the new coding to the cloud node, the cloud node expands according to the preset expansion range according to the real-time data, increases the sample library, and the sample library includes sample historical data, coding and prediction results, the sample historical data is all virtual data points in the expanded numerical interval, and the virtual data points are sorted by time to simulate a historical sequence; in implementation, the sample library is stored and updated through a database management system, such as MySQL, to ensure that data is traceable and expandable.

[0063] According to the multi-source data fusion principle, the three-dimensional geometric data and real-time data are cooperatively collected, the deformation state of surrounding rock is comprehensively captured, the coding and sample library management utilize data mining and dynamic expansion technology, data loss and working condition changes are compensated, the three-dimensional model is used as the basis, the real-time data is used as the input, and the sample library is used as the support, a unified data foundation is formed, the integration of the total station, the scanner and the sensor is used, the collection module accurately describes the change of the internal structure and the geometry of the roadway, especially the real-time evolution of displacement and stress, which enhances the reliability of monitoring, because the multi-sensor data can cross-verify deformation information, thereby providing accurate input for subsequent analysis and reducing the risk of false positives.

[0064] In an embodiment, the analysis module is configured to obtain sample historical data from the sample library, establish a hierarchical early warning system, and obtain a visual model from the three-dimensional model according to the hierarchical early warning system and real-time data.

[0065] The analysis module extracts data from the sample library and constructs early warning and visual output.

[0066] The analysis module is configured to establish a hierarchical early warning system.

[0067] The hierarchical early warning system construction unit divides the data range according to the sample historical data in the sample library, and the sample historical data includes time sequence information of displacement, stress and microseismic parameters; the data range is divided into three levels according to the deformation degree: the first range corresponds to the real-time data with normal deformation, for example, the displacement change is 0-10 mm, and the stress change is 0-5 MPa; the second range corresponds to the real-time data that needs to be checked, for example, the displacement change is 10-20 mm, and the stress change is 5-10 MPa; the third range corresponds to the real-time data that needs to be repaired, for example, the displacement change is more than 20 mm, and the stress change is more than 10 MPa; accordingly, the early warning levels are set: the primary early warning corresponds to the first range, the intermediate early warning corresponds to the second range, and the high-level early warning corresponds to the third range; the threshold is set based on historical statistics and engineering experience, for example, through a machine learning clustering algorithm such as K-means to automatically optimize the threshold; when implemented, the sample historical data is processed by a data analysis software such as Python pandas to ensure that the classification is scientific and reasonable.

[0068] for obtaining a visualization model;

[0069] The visualization model generation unit obtains and the hierarchical early warning system from the acquisition module based on the three-dimensional model, displays the early warning levels on the three-dimensional model in color coding: the primary early warning corresponds to the first color, such as green, the intermediate early warning corresponds to the second color, such as yellow, and the high-level early warning corresponds to the third color, such as red; the position of the color coding corresponds to the specific area of the real-time data acquisition, for example, the displacement sensor detection point or the stress measurement point; when implemented, three-dimensional rendering is performed through computer graphics software such as OpenGL or Unity, the model can be colored on a line segment or a curved surface, and rotation, scaling and section view are supported, so that the management personnel can intuitively view the risk distribution on the display screen of the monitoring center.

[0070] The analysis module is also used to obtain the deformation development trend and rate through a machine learning model;

[0071] The machine learning analysis unit inputs the sample library and the hierarchical early warning system as a first instruction into a machine learning model such as a long short-term memory network LSTM or a random forest for regression analysis and time series analysis; the regression analysis is used to fit the displacement or stress data trend to predict future deformation parameters; the time series analysis is used to identify the periodicity or mutation point of the data to obtain the deformation development trend and rate, for example, to predict the displacement change and average rate within 1 hour in the future; then, the real-time data, the deformation development trend and the rate are input as a second instruction into the same machine learning model to obtain the prediction results, including theoretical real-time data, predicted values, risk levels and position information; the risk level is determined based on the hierarchical early warning system, and the position information comes from the sensor coordinates; when implemented, the model is trained through the TensorFlow or Scikit-learn framework, and the training data comes from the sample library, and the verification accuracy requirement is ≥ 90% to ensure the reliability of the prediction.

[0072] for obtaining the prediction result and triggering the early warning;

[0073] The prediction result processing unit calls the prediction result through coding, because the mapping relationship between the coding and the prediction result is stored in the sample library; for example, when the real-time data matches a certain coding, the system directly calls the prediction result corresponding to the coding, including the theoretical real-time data, the risk level and the position information; according to the prediction result, the decision module obtains the early warning level and the position, and triggers the corresponding early warning mode: the primary early warning corresponds to displaying the real-time data through the monitoring center, and sending the all normal message and the real-time data to the designated personnel, such as the inspector, the message being pushed through the short message or the special APP; the intermediate early warning corresponds to triggering the sound and light alarm, such as the buzzer and the LED lamp installed in the roadway, and linking the underground broadcast system to publish the data abnormal message and display the position information, reminding the personnel to check; the advanced early warning corresponds to triggering the sound and light alarm, linking the underground broadcast system to publish the evacuation instruction, automatically locking the power supply of the equipment, such as cutting off the regional power supply and displaying the position information, and ensuring the safe evacuation; when the implementation, the early warning action is executed through the control logic circuit and the communication protocol, such as Modbus, and the response time is less than 5 seconds.

[0074] According to the data analysis and machine learning principle, the embodiment of the application realizes intelligent monitoring of the deformation state through hierarchical early warning and visual display; the hierarchical system uses the statistical learning principle to simplify complex data into an operable early warning level; the visual model is based on the graphics rendering technology, which enhances the information density and readability; the sample historical data is directly input into the machine learning model and real-time output prediction result; through color coding and trend analysis, the analysis module identifies the abnormal increase of the roof displacement and the stress concentration area, which enhances the sensitivity of fault detection; through the control theory and adaptive learning principle, the system realizes intelligent decision-making through early warning triggering and model optimization; the early warning mode uses multi-modal alarm technology to ensure comprehensive emergency response; the model optimization is based on the error feedback principle to improve the prediction accuracy; because the multi-parameter cooperation can early detect the risk, it provides a basis for the decision module to improve the practicability and response speed of the system.

[0075] In an embodiment, the decision module is used to take the sample library and the hierarchical early warning system as the first instruction to obtain the deformation development trend and rate, take the real-time data, the deformation development trend and the rate as the second instruction to obtain the prediction result, call the corresponding prediction result through coding, obtain the early warning level and the position according to the prediction result, and perform maintenance and alarm;

[0076] The decision module triggers the early warning and maintenance action based on the prediction result.

[0077] for optimizing the prediction model and updating the hierarchical early warning system;

[0078] The model optimization unit corrects itself by comparing the difference between the theoretical real-time data, the predicted value and the actual real-time data: calculate the absolute value of the difference, if the difference is greater than or equal to the first threshold value, for example 5% error and less than or equal to the second threshold value, for example 10% error, the theoretical real-time data is considered valid and used to update the prediction result; if the difference is less than the first threshold value or greater than the second threshold value, discard the theoretical real-time data, and generate a new prediction result according to the real-time data, the deformation development trend and the rate; at the same time, the decision module updates the graded warning system according to the new sample historical data, for example, redivides the data range threshold to adapt to the geological changes; when the historical data range of the sample library covers all the expected working conditions, the system optimization process: after obtaining the real-time data, its code is sent to the cloud node, the cloud node retrieves the pre-stored prediction result according to the code, without repeated calculation; when, through the iterative algorithm and the database update mechanism, ensure that the system continues to learn.

[0079] In the embodiment of the application, the prediction result directly drives the warning action, and the efficiency is improved by coding retrieval, the decision module dynamically adjusts the output through difference and threshold comparison, avoids model drift, and the warning grading and position display make the measures accurate, which enhances the reliability and safety of the system, because the automated response reduces human delay, thereby improving the overall monitoring performance.

[0080] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (or computer- readable storage media) having computer-usable program code embodied in the medium. The medium can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-usable storage media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other storage medium(s) that can be used to carry or store desired computer program code in the form of instructions or data structures and that can be accessed by a computer. Also, the present application can be embodied in a computer program product that can be traded as goods or merchandise, through the storage medium described above or any other suitable medium. Accordingly, the computer medium can be any entity or device containing, or Figure 1 the functions specified in the flow or flows and / or blocks Figure 1 the functions specified in the flow or flows and / or blocks

[0081] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A monitoring system for deformation of surrounding rock in underground mines, characterized in that, It includes a data acquisition module, an analysis module, and a decision-making module: The acquisition module is used to acquire three-dimensional spatial geometric data, obtain a three-dimensional model, acquire real-time data through different sensor nodes, establish codes based on the real-time data, and add samples to the database based on the codes. The analysis module is used to obtain historical sample data from the sample library, establish a tiered early warning system based on the historical sample data, and obtain a visualization model through a 3D model based on the tiered early warning system and real-time data. The decision module is used to take the sample library and the hierarchical early warning system as the first instruction to obtain the deformation development trend and rate, take the real-time data, deformation development trend and rate as the second instruction to obtain the prediction result, retrieve the corresponding prediction result through the code, obtain the early warning level and location based on the prediction result, and carry out maintenance and alarm. The three-dimensional spatial geometric data includes tunnel cross-sectional contour data, surrounding rock surface morphology data, and borehole observation data; The tunnel cross-sectional profile data includes the initial shape and size of the tunnel; the surrounding rock surface morphology data includes three-dimensional coordinate information of the undulations and fissure distribution of the surrounding rock surface after tunnel excavation; and the borehole inspection data includes three-dimensional spatial information of the internal structure of the surrounding rock. The cross-sectional contour data of the tunnel was obtained using a total station and a 3D laser scanner; The borehole observation data is obtained through borehole cameras and radar; Based on the three-dimensional spatial geometric data, obtain a three-dimensional model; The real-time data includes displacement data, stress data, and microseismic data. The displacement data includes the relative convergence of the roof and floor of the underground coal mine roadway, the convergence displacement of the two sides, and the three-dimensional coordinate changes of specific points on the roadway surface. The stress data includes the internal stress of the surrounding rock, the stress of the anchor bolts, the stress of the anchor cables, and the working resistance of the hydraulic supports. The microseismic data includes the energy, location, and timing of microseismic events generated by rock mass fracturing. The displacement data is acquired using a displacement sensor; The stress data is acquired using a stress sensor; The microseismic data is acquired using a microseismic sensor; By setting up underground nodes and cloud nodes through a communication bus, the real-time data is transmitted to the underground nodes and matched with the historical data range; If the real-time data is within the range of the historical data, then the encoding of the historical data is transmitted to the cloud node; If the real-time data is not within the range of the historical data, a new code is established based on the real-time data, the real-time data is expanded according to a preset expansion range, the range of historical data is obtained, and it is saved to the underground node. Then, the real-time data and the new code are transmitted to the cloud node. The cloud node expands the sample library according to the real-time data and the preset expansion range, and the sample library includes sample historical data, codes and prediction results. The historical data range is defined by taking real-time data as the center, using a preset expansion range as the interval radius, determining an expanded numerical interval, expanding the real-time data, establishing sample codes for all virtual data points within the expanded numerical interval, and treating the virtual data points as acquired real-time data. The historical data of the sample consists of all virtual data points within the expanded numerical range, and these virtual data points are sorted according to time.

2. The monitoring system for downhole surrounding rock deformation as described in claim 1, characterized in that, The tiered early warning system specifically includes: Based on the sample library, historical sample data is obtained; based on the historical sample data, data ranges are divided; based on the data ranges, warning levels are set; the data ranges include a first range, a second range, and a third range. The warning level is set based on the real-time data of the degree of deformation in the historical data of the sample. The data range is the maximum and minimum value of the real-time data of normal deformation, the maximum and minimum value of the real-time data of deformation that needs to be checked, and the maximum and minimum value of the real-time data of deformation that needs to be repaired. The warning level corresponding to the first range is a primary warning, the warning level corresponding to the second range is a medium warning, and the warning level corresponding to the third range is a high warning.

3. A monitoring system for downhole surrounding rock deformation as described in claim 2, characterized in that, The visualization model specifically includes: The warning levels are displayed in different colors at corresponding positions on the 3D model to obtain a visualization model. The primary warning corresponds to the first color, the intermediate warning corresponds to the second color, and the advanced warning corresponds to the third color. The corresponding position is a color-coded position that corresponds to a specific area of ​​the collected real-time data.

4. A monitoring system for downhole surrounding rock deformation as described in claim 3, characterized in that, The analysis module specifically includes: The sample library and the hierarchical early warning system are used as the first instruction and input into the machine learning model to perform regression analysis and time series analysis to obtain the deformation development trend and rate. Real-time data, deformation development trend and rate are used as the second instruction and input into the machine learning model to obtain the prediction results. The prediction results are theoretical real-time data, risk level and location information. Based on the prediction results, the corresponding warning level is determined by the color displayed by the visualization model, the corresponding location information is obtained based on the position of the color display, and the corresponding warning method is triggered based on the warning level.

5. A monitoring system for downhole surrounding rock deformation as described in claim 4, characterized in that, The corresponding early warning methods specifically include: The warning method corresponding to the primary warning is to display the real-time data through the monitoring center and send a message that everything is normal and the real-time data to designated personnel. The intermediate-level early warning method is to trigger an audible and visual alarm, and link the downhole broadcasting system to release data anomaly messages and display location information. The advanced early warning system uses a warning method that triggers an audible and visual alarm, links the underground broadcasting system to issue evacuation instructions, automatically locks the equipment power supply, and displays location information.

6. A monitoring system for downhole surrounding rock deformation as described in claim 5, characterized in that, The decision-making module specifically includes: The difference between the theoretical real-time data and the real-time data is obtained. If the difference is greater than or equal to the first threshold and less than or equal to the second threshold, the theoretical real-time data is used as the real-time data to obtain a new prediction result. If the difference is less than the first threshold or greater than the second threshold, the theoretical real-time data is discarded, and a new prediction result is obtained based on the real-time data, deformation development trend and rate.

7. A monitoring system for downhole surrounding rock deformation as described in claim 6, characterized in that, The decision-making module also includes: The tiered early warning system is updated based on the newly added historical sample data, and the corresponding data range is adjusted based on the updated tiered early warning system. Once the historical data range of the sample library covers all expected working conditions of downhole surrounding rock deformation, real-time data is acquired, and the code corresponding to the real-time data is sent to the cloud node. The cloud node directly retrieves the corresponding prediction result based on the code.

Images