A large-dip-angle stope coal and rock dynamic disaster monitoring and early warning method and system based on digital twinning

Abstract

The present application provides a kind of big inclination stope coal rock dynamic disaster monitoring and early warning method and system based on digital twinning, comprising: obtaining sensor installation parameters and big inclination stope geological environment information, correction model is established, and the geological exploration data of big inclination stope collected by sensor is corrected;According to the corrected parameter, the digital twin model of big inclination stope is constructed;Based on historical coal rock disaster case data and expert experience, the early warning index system of coal rock dynamic disaster is constructed;Based on machine learning algorithm, the coal rock dynamic disaster early warning model is constructed;The coal rock dynamic disaster early warning model is integrated into the digital twin model, when the digital twin model is updated, the coal rock dynamic disaster early warning model carries out real-time evaluation and early warning to the dynamic disaster risk of big inclination stope.The present application effectively reduces the occurrence risk of coal rock dynamic disaster, guarantees the life safety of stope operating personnel and the normal operation of equipment, improves the safety and economic benefit of coal mining.

Description

Technical Field

[0001] This invention relates to the field of disaster early warning technology in steeply inclined mining areas, specifically to a method and system for monitoring and early warning of coal and rock dynamic disasters in steeply inclined mining areas based on digital twins. Background Technology

[0002] With the increasing depth and intensity of coal mining, the frequency and severity of dynamic disasters in steeply inclined mining areas (such as coal and gas outbursts and rock bursts) are becoming increasingly serious. Traditional monitoring and early warning methods have the following shortcomings:

[0003] 1. Monitoring data is scattered and not intuitive, making it difficult to comprehensively and accurately reflect the actual state of the coal and rock mass in the mining area.

[0004] 2. The accuracy of the early warning model is not high enough to meet the needs of effective monitoring and early warning of coal and rock dynamic disasters in complex environments of steeply inclined mining areas.

[0005] 3. Lacks real-time interactive capabilities, making it impossible to dynamically adjust warning results based on real-time data. Summary of the Invention

[0006] This invention provides a method for monitoring and early warning of coal and rock dynamic disasters in steeply inclined mining areas based on digital twins, enabling the monitoring and early warning of coal and rock dynamic disasters in steeply inclined mining areas.

[0007] A method for monitoring and early warning of dynamic coal and rock disasters in steeply inclined mining areas based on digital twins includes:

[0008] Obtain sensor installation parameters and geological environment information of steep-angle stopes, establish a calibration model, and calibrate the geological exploration data of steep-angle stopes collected by the sensors;

[0009] Based on the corrected geological exploration data and mining design parameters of the steeply inclined mining area, a digital twin model of the steeply inclined mining area is constructed.

[0010] Based on historical coal and rock disaster case data and expert experience, an early warning indicator system for coal and rock dynamic disasters is constructed.

[0011] The early warning indicator system is trained and learned based on machine learning algorithms to construct an early warning model for coal and rock dynamic disasters.

[0012] The coal and rock dynamic disaster early warning model is integrated into the digital twin model. When the digital twin model is updated, the coal and rock dynamic disaster early warning model performs real-time assessment and early warning of dynamic disaster risks in steeply inclined mining areas.

[0013] Preferably, the sensors include stress sensors, strain sensors, gas sensors, displacement sensors, and micro-vibration sensors;

[0014] The sensor installation parameters include the installation angle and installation position; wherein, the installation position includes the coal pillar area, the coal and rock mass in front of the coal mining machine, and the hydraulic support area, and the sensor is deployed in association with the equipment and facilities in the mining area;

[0015] The geological environment information of the steeply inclined mining area includes the dip angle, thickness variation of the coal seam, and distribution of geological structures.

[0016] Preferably, the method for establishing a calibration model for the sensor installation angle and position includes:

[0017] An adaptive array sensor group is used to dynamically adjust the installation attitude according to the dip angle of the coal seam. The installation angle deviation is recorded in real time by laser ranging and inertial navigation unit to build an installation angle deviation compensation model.

[0018] Establish the mapping relationship between sensor installation parameters and rock mass wave velocity anisotropy, use backpropagation correction matrix to compensate for signal attenuation, and construct a wave velocity anisotropy compensation model;

[0019] A non-uniform medium wave field reconstruction technique is introduced, and a propagation path compensation model is constructed by simulating the propagation path deviation of electromagnetic waves in coal-bearing rock fractured media through time-domain finite difference simulation.

[0020] The correction model is obtained based on the installation angle deviation compensation model, the wave velocity anisotropy compensation model, and the propagation path compensation model.

[0021] Preferably, the method for constructing the digital twin model includes:

[0022] The corrected geological exploration data of the steep-angle stope and the stope design parameters are integrated to construct a unified data format and coordinate system, and obtain multi-source fused data;

[0023] Based on the multi-source fusion data, a three-dimensional geometric model of the coal and rock mass is constructed using three-dimensional modeling technology.

[0024] Based on the aforementioned three-dimensional geometric model, and combined with the mechanical properties of coal and rock, the stress-strain law during the mining process, and the gas migration law, the coal and rock mass is endowed with corresponding physical field properties, and physical field models of stress field, displacement field, and gas seepage field are constructed.

[0025] Three-dimensional modeling was performed on the coal mining machine, hydraulic support and scraper conveyor in the mining area to obtain a three-dimensional model of the equipment and facilities.

[0026] By integrating the three-dimensional geometric model, the physical field model, and the three-dimensional model of the equipment and facilities, a digital twin model of the steep-angle mining area is obtained.

[0027] Preferred methods for constructing an early warning indicator system for coal and rock dynamic disasters include:

[0028] Based on graph convolutional networks, the topological features of the historical disaster case data are extracted, a tilt similarity mapping function is constructed, knowledge transfer is performed on historical disaster case data across tilt angles, and spatiotemporal frequency three-dimensional potential indicators are obtained.

[0029] Based on expert experience, the potential indicators are screened to obtain candidate indicators for the early warning indicator system.

[0030] Using the candidate indicators as input variables and the occurrence and severity of historical disasters as output variables, a machine learning model is constructed.

[0031] Based on the machine learning model, the contribution of the candidate indicators to the prediction of coal and rock dynamic disasters is evaluated;

[0032] Based on the aforementioned contribution level, the final early warning indicators are obtained, and an early warning indicator system for coal and rock dynamic disasters is constructed.

[0033] Preferably, based on the aforementioned early warning indicator system, a coal and rock dynamic disaster early warning model is constructed using a physical information neural network; wherein, the residual term of the coal and rock constitutive equation is embedded in the physical information neural network.

[0034] This invention also provides a digital twin-based monitoring and early warning system for coal and rock dynamic disasters in steeply inclined mining areas, used to implement the method, comprising:

[0035] The data correction module is used to acquire sensor installation parameters and geological environment information of steep-angle stopes, establish a correction model, and correct the geological exploration data of steep-angle stopes collected by the sensors.

[0036] The digital twin model construction module is used to construct a digital twin model of the steeply inclined stope based on the corrected geological exploration data and stope design parameters.

[0037] The early warning indicator system construction module is used to construct an early warning indicator system for coal and rock dynamic disasters based on historical coal and rock disaster case data and expert experience.

[0038] The disaster early warning model construction module is used to train and learn the early warning indicator system based on machine learning algorithms to construct a coal and rock dynamic disaster early warning model.

[0039] The early warning module is used to integrate the coal and rock dynamic disaster early warning model into the digital twin model. When the digital twin model is updated, the coal and rock dynamic disaster early warning model performs real-time assessment and early warning of the dynamic disaster risk in steeply inclined mining areas.

[0040] Preferably, the data correction module includes:

[0041] An angle compensation unit is used to dynamically adjust the installation attitude according to the dip angle of the coal seam using an adaptive array sensor group. It records the installation angle deviation in real time through laser ranging and inertial navigation unit to build an installation angle deviation compensation model.

[0042] The wave velocity compensation unit is used to establish the mapping relationship between sensor installation parameters and rock mass wave velocity anisotropy, and uses a backpropagation correction matrix to compensate for signal attenuation and construct a wave velocity anisotropy compensation model.

[0043] The propagation path compensation unit is used to introduce non-uniform medium wave field reconstruction technology, and to construct a propagation path compensation model by simulating the propagation path deviation of electromagnetic waves in coal-bearing rock fractured medium through time-domain finite difference simulation.

[0044] The correction model construction unit is used to obtain the correction model based on the installation angle deviation compensation model, the wave velocity anisotropy compensation model, and the propagation path compensation model.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] Improved data accuracy: By establishing a calibration model, the geological exploration data collected by sensors can be effectively corrected, improving the accuracy and reliability of the data and providing a higher quality data foundation for subsequent analysis and early warning.

[0047] Improved accuracy of early warnings: By using machine learning algorithms to train and learn the early warning indicator system, the constructed coal and rock dynamic disaster early warning model can more accurately assess and warn of coal and rock dynamic disaster risks, reducing false alarms and missed alarms.

[0048] Real-time monitoring and early warning: By integrating the early warning model into the digital twin model, real-time assessment and early warning of the risk of dynamic disasters in coal and rock in steeply inclined mining areas are realized, potential safety hazards are detected in a timely manner, and time is gained to take effective prevention and control measures.

[0049] Intelligent decision support: Combining the visualization and simulation analysis capabilities of digital twin models, it provides mining site managers with intuitive mining site status information and scientific decision-making basis, assisting in the formulation of reasonable mining plans and disaster prevention strategies.

[0050] Significant safety benefits: It effectively reduces the risk of coal and rock dynamic disasters, protects the lives of workers in the mining area and ensures the normal operation of equipment, and improves the safety and economic benefits of coal mining. Attached Figure Description

[0051] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the 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.

[0052] Figure 1 This is a flowchart of the method for monitoring and early warning of coal and rock dynamic disasters in steeply inclined mining areas based on digital twins, according to an embodiment of the present invention.

[0053] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention;

[0054] Figure 3 A flowchart illustrating the construction of a digital twin model according to an embodiment of the present invention;

[0055] Figure 4 A flowchart illustrating the construction of an early warning indicator system for coal and rock dynamic disasters in an embodiment of the present invention.

[0056] illustrate:

[0057] 1010, Processor; 1020, Memory; 1030, Input / Output Interface; 1040, Communication Interface; 1050, Bus. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by those skilled in the art. The terms "first," "second," and similar terms used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0060] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] Example 1

[0062] like Figure 1 As shown, a method for monitoring and early warning of coal and rock dynamic disasters in steeply inclined mining areas based on digital twins includes:

[0063] S1: Obtain sensor installation parameters and geological environment information of steep-angle stopes, establish a calibration model, and calibrate the geological exploration data of steep-angle stopes collected by the sensors.

[0064] A further embodiment is that the sensor includes a stress sensor, a strain sensor, a gas sensor, a displacement sensor, and a micro-vibration sensor.

[0065] The sensor installation parameters include the installation angle and installation location; the installation location includes the coal pillar area, the coal and rock mass in front of the coal mining machine, and the hydraulic support area, and the sensor is deployed in association with the equipment and facilities in the mining area;

[0066] Geological environment information for steeply inclined mining areas includes the dip angle, thickness variation of coal seams, and distribution of geological structures.

[0067] A further implementation method involves establishing a correction model for the sensor mounting angle and position, including:

[0068] An adaptive array sensor group is adopted, and the installation attitude is dynamically adjusted according to the dip angle of the coal seam. The installation angle deviation is recorded in real time by laser ranging and inertial navigation unit to construct an installation angle deviation compensation model. Among them, the laser ranging array adopts an 8-point ring layout, and the inertial navigation unit adopts a 100Hz sampling rate. The least squares method is used to fit the installation surface equation by laser ranging data, calculate the angle deviation between the actual normal vector and the ideal normal vector, and establish a Lie group SE(3) optimization model based on the theoretical installation point and the actual measurement point. Based on the optimization model, the angle deviation is optimized and dynamic compensation is implemented. Combined with the real-time deviation, the attitude of each sensor in the sensor group is adjusted by PID controller.

[0069] It should be noted that wave velocity anisotropy refers to the different wave velocity characteristics of elastic waves (such as P-waves and S-waves) in different propagation directions, which is usually caused by geological structures such as bedding, fissures, and stress fields of rock masses.

[0070] There is a close relationship between the correction of sensor data and wave velocity anisotropy, especially in complex geological environments (such as steeply dipped coal seams), where the anisotropic characteristics of the rock mass can significantly affect the accuracy and reliability of sensor data.

[0071] In coal seams, wave velocity anisotropy is mainly manifested as follows:

[0072] Stratification plane direction: Waves propagating along the stratification plane have a faster speed, while waves propagating perpendicular to the stratification plane have a slower speed.

[0073] Fracture distribution: Fracture density and directionality lead to spatial variations in wave velocity.

[0074] Stress field: Non-uniform stress distribution can change the elastic modulus of rock mass, which in turn affects wave velocity.

[0075] Furthermore, anisotropy causes varying degrees of signal attenuation in different directions, potentially leading to underestimation or overestimation of the signal strength received by the sensor. For example, signals propagating perpendicular to bedding planes experience greater attenuation, which may result in lower displacement or stress measurements. Wave velocity anisotropy causes deviations in signal propagation time from theoretical values, affecting the accuracy of microseismic event location. For instance, signals propagating along bedding planes may arrive in a shorter time than expected, leading to location errors. In anisotropic media, the frequency components and waveform of signals may be distorted, affecting the resolution of acoustic emission or microseismic data. Wave velocity anisotropy has a significant impact on sensor data, making correction necessary.

[0076] Therefore, this invention establishes a mapping relationship between sensor installation parameters and rock mass wave velocity anisotropy, employs a backpropagation correction matrix to compensate for signal attenuation, and constructs a wave velocity anisotropy compensation model. Specifically, four sets of P-wave transducers and eight sets of S-wave receivers are arranged, and the three-dimensional wave velocity distribution is calculated using the time-of-flight difference to obtain an orthogonal elastic wave excitation-receiving array. Based on the orthogonal elastic wave excitation-receiving array, sensor Euler angles, and horizontal stress, a tensor mapping of wave velocity to installation angle is established to dynamically invert rock mass parameters. Based on the direction-dependent attenuation coefficient and the angle between the wave propagation direction and the bedding plane, anisotropy attenuation compensation equation is obtained. Then, the original signal received by the sensor is subjected to wavelet transform, and the direction-sensitive attenuation factor is calculated using the wave velocity tensor eigenvalues ​​and eigenvectors. Based on the direction-sensitive factor and the anisotropy attenuation compensation equation, a backpropagation correction matrix is ​​constructed. The original wavelet-transformed signal is then subjected to inverse wavelet transform to obtain the reconstructed signal, completing the construction of the wave velocity anisotropy compensation model.

[0077] A non-uniform medium wavefield reconstruction technique is introduced, and a propagation path compensation model is constructed by simulating the propagation path deviation of electromagnetic waves in coal-bearing fractured media using finite-difference time-domain (FDTD). Specifically, a non-uniform medium model of coal-bearing fractured media is established based on the physical parameters and fracture development of the coal-bearing medium. The coal-bearing mass is divided into multiple small units, each with different electromagnetic parameters and fracture characteristics to reflect the non-uniformity and complexity of the coal-bearing medium. Appropriate FDTD simulation software is selected, and the initial and boundary conditions of the FDTD simulation are set according to the coal-bearing medium model and electromagnetic wave monitoring data. This includes defining the size and mesh of the simulation region, setting the source and receiver locations of the electromagnetic waves, and specifying the simulation time step and total duration. The FDTD simulation is run to calculate the propagation process of electromagnetic waves in coal-bearing fractured media. The simulation yields information such as the electric and magnetic field distributions, propagation paths, and propagation times of electromagnetic waves in the coal-bearing medium. The reflection, refraction, and scattering phenomena of electromagnetic waves at fractures, as well as the propagation path deviation caused by the non-uniformity of the coal-bearing medium, are analyzed. The electromagnetic wave propagation path obtained from FDTD simulation is compared with the propagation path in an ideal homogeneous medium to calculate the deviation between the actual and ideal paths. This deviation can be expressed as differences in path length, offsets in propagation direction, etc. Simultaneously, the relationship between propagation path deviation and coal-rock medium parameters and fracture characteristics is analyzed to identify the main influencing factors and patterns. Based on the calculation results and analysis of propagation path deviation, a propagation path compensation model is constructed. This model involves collecting a large amount of propagation path deviation data and corresponding coal-rock medium parameters to train a neural network model. Using the coal-rock medium parameters as input and the propagation path compensation amount as output, the propagation path compensation model is constructed to achieve automatic compensation and prediction of propagation path deviation.

[0078] A correction model is obtained based on the installation angle deviation compensation model, the wave velocity anisotropy compensation model, and the propagation path compensation model.

[0079] S2: Based on the corrected geological exploration data and stope design parameters, construct a digital twin model of the steeply inclined stope. For example... Figure 3 As shown. Compared to near-horizontal coal seams, the mining of steeply dipped coal seams (dip angle between 35° and 55°) studied in this invention faces many unique challenges, such as gravity-dip angle effects, anisotropic gas migration, and insufficient adaptability of the support system. Specific solutions include using unstructured mesh refinement in areas with drastic dip angle changes (such as fault intersections) when constructing the three-dimensional geometric model, employing gravity field vectorization modeling in the physical field calculations, and performing anisotropic seepage field corrections. The adaptability of the support system is reflected in the early warning mechanism.

[0080] A further implementation method involves constructing a digital twin model, including:

[0081] The corrected geological exploration data and mining design parameters of the steeply inclined mining area are integrated to construct a unified data format and coordinate system, obtaining multi-source fused data. Specifically, corrected geological exploration data of the steeply inclined mining area are collected, including multi-parameter data such as stress, strain, gas concentration, and displacement of the coal and rock mass, as well as mining design parameters such as the geometric dimensions of the mining area, the dip angle of the coal seam, the model and parameters of the coal mining machine, and the model and parameters of the hydraulic support. This data is systematically organized and a database is established. Through data consistency checks, significant differences in stress data measured at the same location by different sensors are identified and corrected; through data integrity checks, missing data points are supplemented or reasonable interpolation processing is performed.

[0082] Based on multi-source fusion data, a three-dimensional geometric model of the coal and rock mass is constructed using 3D modeling technology. Specifically, during the modeling process, the shape, size, and spatial location of the coal and rock mass are accurately reproduced to ensure that the model is highly consistent with the actual coal and rock mass structure in the mining area. Simultaneously, considering the complexity and irregularity of the coal and rock mass, the mesh density and orientation of the 3D geometric model are dynamically adjusted based on changes in the coal seam dip angle. In areas with drastic dip angle changes (geological structures such as folds and faults), unstructured mesh refinement is used to ensure detailed modeling of stress concentration zones and gas-rich areas, facilitating subsequent physical field simulation and mechanical analysis. In particular, this embodiment provides a detailed process for constructing the 3D geometric model:

[0083] A deep neural network (DNN) is constructed, taking into input parameters including coal seam dip angle and thickness, stress gradient heatmaps, gas concentration fields, and spatial clustering data of microseismic events. The output is a dynamic mesh generation strategy. The network is trained through reinforcement learning, aiming to minimize the residuals in subsequent physical field simulations. It prioritizes generating unstructured, denser meshes (side length ≤ 0.5m) in areas of abrupt dip angle changes (e.g., >40°) and areas with dense microseismic events, while employing sparse, structured meshes (side length ≤ 2m) in stable regions. A real-time feedback mechanism updates the mesh configuration every 30 minutes based on the latest sensor data, ensuring the model dynamically adapts to changes in geological conditions.

[0084] Based on the inversion of the three-dimensional topology of the fracture network using microseismic monitoring data, a fractal geometry algorithm is employed to generate a statistically equivalent fracture model, which is then embedded into the geometric model of the coal and rock mass. For the bedding planes of steeply dipping coal seams, a dip-dip tensor field is defined to force the bedding planes to be orthogonal to the coal seam normal vector during modeling. The geometric morphology of the bedding planes is then fitted using non-uniform rational B-spline (NURBS) surfaces. At fault intersections, a hybrid modeling method combining discrete fracture networks (DFN) and a continuous medium model is used. Virtual joint elements connect macroscopic faults and microscopic fractures, achieving cross-scale mechanical behavior coupling.

[0085] The mesh quality evaluation function (using the Jacobian matrix condition number in this embodiment) is transformed into a quadratic unconstrained binary optimization (QUBO) problem, and the optimal node position is solved using the quantum annealing algorithm. To address the cell distortion problem at the boundary of the dense mesh, a local optimization strategy based on the quantum tunneling effect is introduced, improving mesh smoothness by 42% while maintaining tilt-related characteristics. The principle of this quantum tunneling-based local optimization strategy is as follows: during quantum annealing, a transverse magnetic field is applied to introduce quantum fluctuations, enabling the system to overcome energy barriers. When the algorithm gets stuck in a local optimum (such as distortion at mesh boundary nodes due to abrupt tilt changes), the quantum tunneling effect allows the system to probabilistically "traverse" classically insurmountable high-energy states, exploring a better solution space. For example, at the boundary between dense and sparse meshes, traditional gradient descent may stall due to abrupt changes in cell aspect ratio, while quantum tunneling can overcome such geometric constraints. The tunneling intensity is adaptively adjusted based on local mesh characteristics (such as dip gradient and stress concentration factor): in high-distortion regions (Jacobi condition number > 10), the tunneling probability is increased to accelerate the escape from local optima; in smooth regions (condition number < 3), the tunneling weight is reduced, and classical optimization is prioritized to improve convergence speed. This strategy achieves a balance between global exploration and local refinement through quantum-classical hybrid optimization.

[0086] By using mixed reality (MR) devices, 3D geometric models are superimposed onto the real mining environment, allowing engineers to adjust mesh density and orientation in real time via gestures. The system automatically detects manually modified areas and compares them with physical field simulation results (such as maximum principal stress error >15%). If they are inconsistent, adaptive mesh regeneration is triggered, forming a closed loop of "human-machine collaborative modeling".

[0087] Based on a three-dimensional geometric model, and combining the mechanical properties of coal and rock, the stress-strain laws during mining, and the gas migration laws, corresponding physical field properties are assigned to the coal and rock mass. Physical field models of stress field, displacement field, and gas seepage field are constructed. In the physical field calculations, gravitational acceleration is decomposed into normal and tangential components, which are coupled to the stress field and displacement field solvers respectively, accurately simulating the asymmetric load distribution caused by the dip angle. Based on real-time dip angle data (from the inertial navigation unit), the weight of the gravity component is dynamically adjusted to achieve adaptive characterization of the mechanical response during mining. Specifically, through laboratory tests and in-situ field tests, mechanical property parameters of the coal and rock mass, such as elastic modulus, Poisson's ratio, compressive strength, and shear strength, are obtained. These parameters form the basis for constructing the physical field model of the coal and rock mass, reflecting its mechanical response during mining. Numerical simulation methods were used to construct stress and displacement field models of the coal and rock mass. Reasonable boundary and load conditions were set, including constraints on the roof and floor of the mining face and mining pressure, to simulate the stress distribution and displacement changes of the coal and rock mass during mining. Based on the gas migration patterns of the coal and rock mass and gas concentration distribution information from geological exploration data, combined with parameters such as permeability of the coal and rock mass, a gas seepage field model was constructed. Considering the diffusion and convection migration mechanisms of gas in the coal and rock mass, as well as the influence of coal seam deformation on gas seepage paths and pressures during mining, the seepage distribution and dynamic changes of gas in the coal and rock mass were simulated. Specifically, a dip angle correction coefficient was embedded in the gas seepage model to quantify the inhibitory effect of dip angle on permeability; the angle between the coal seam dip and the main seepage direction was inverted in real time using a digital twin model, and the anisotropic tensor in the seepage equation was dynamically adjusted to improve the prediction accuracy of gas-enriched areas.

[0088] In particular, in this embodiment, considering the asymmetric stress characteristics of the roof and floor of a steeply inclined mining area, a boundary constraint equation related to the dip angle is introduced into the physical field model to simulate the interaction between the coal seam slip trend and the support structure.

[0089] Three-dimensional modeling was performed on the coal mining machine, hydraulic supports, and scraper conveyors within the mining area to obtain 3D models of the equipment and facilities. Specifically, based on the actual dimensions, shape, and performance parameters of the equipment, precise models of the equipment were created using 3D modeling software and placed in their corresponding positions within the 3D geometric model of the coal and rock mass, ensuring accurate spatial relationships between the equipment and the coal and rock mass. Simultaneously, corresponding kinematic and dynamic properties were added to the equipment models, such as the coal cutting motion of the coal mining machine and the lifting motion of the hydraulic supports, enabling the equipment models to dynamically simulate the operating states during the actual mining process.

[0090] A digital twin model of a steeply inclined mining area is obtained by integrating a 3D geometric model, a physical field model, and a 3D model of equipment and facilities. Specifically, during the integration process, the data interfaces and communication protocols between the various sub-models are ensured to be compatible, enabling seamless data transmission and sharing. The calculation results of the physical field model are combined with the 3D geometric model of the coal and rock mass, allowing the geometry of the coal and rock mass to be updated in real time according to changes in the physical field. The operational status data of the equipment and facilities are coupled with the physical field model of the coal and rock mass to simulate the impact of equipment operation on the coal and rock mass and the feedback effect of changes in the state of the coal and rock mass on equipment operation. Combined with microseismic monitoring data, the fracture topology in the digital twin model is updated in real time, and the correlation between fracture propagation and coal and rock mass instability is simulated using the discrete element method (DEM).

[0091] In this embodiment, the real-time data collected by the sensors interacts with the constructed virtual models in the following ways:

[0092] Stress, strain, and gas sensors are networked using a hybrid 5G / Industrial Ethernet architecture, employing a Time Stamping Protocol (PTP) to ensure data timing consistency, with a sampling frequency of 100Hz–1kHz. Embedded edge servers are deployed in the mining area to run lightweight calibration models (such as installation angle deviation compensation models) to filter, denoise, and normalize the raw data, compressing the data volume to 30% of its original size.

[0093] Preprocessed data is pushed to the cloud via the MQTT protocol, and key parameters (such as microseismic event waveforms and sudden changes in gas concentration) are accelerated via UDP channels, with end-to-end latency of <50ms.

[0094] Adopting a "hot and cold tiered" storage strategy:

[0095] Hot storage: Real-time data is stored in a time-series database (such as InfluxDB), retaining the most recent 72 hours of data and supporting millisecond-level queries;

[0096] Cold storage: Historical data is transferred to a distributed file system (such as HDFS), categorized and archived, which facilitates model training and backtracking analysis.

[0097] Regarding the injection of real-time data, sensor data streams are connected to the digital twin platform via RESTful API, and Kafka message queues are used to achieve high-concurrency data buffering, ensuring a stable throughput of tens of thousands of data points per second.

[0098] For physical quantities such as stress field and displacement field, a local recalculation of the finite element model is performed every 10 seconds, updating only the mesh in regions with a change rate > 5%; when the microseismic energy > 10 3When the gas concentration gradient changes by more than 20%, a full model iteration is immediately triggered to ensure accurate mapping of disaster precursors. The stress distribution predicted by the digital twin model is compared with measured data; if the mean square error (MSE) is greater than 15%, sensor calibration or model parameter recalibration is automatically triggered. Support adjustment commands output by the early warning model are sent to the hydraulic support controller via the OPC UA protocol, while the execution results are recorded and fed back to the digital twin model, forming a closed-loop verification. Using HoloLens2 devices, real-time sensor data (such as displacement vectors and gas concentration cloud maps) are overlaid onto the actual mining scene in AR format, supporting gesture interaction to retrieve historical data trends at any location. Based on WebGL technology, dynamic 3D rendering of the coal and rock fracture network and equipment operating status is achieved in the digital twin platform, with a data update latency of less than 200ms, ensuring frame synchronization between the virtual model and the physical world.

[0099] S3: Based on historical coal and rock disaster case data and expert experience, construct an early warning indicator system for coal and rock dynamic disasters. For example... Figure 4 As shown.

[0100] A further implementation method involves constructing an early warning indicator system for coal and rock dynamic disasters, including:

[0101] Based on graph convolutional networks, topological features of historical disaster case data are extracted, and a dip similarity mapping function is constructed to perform knowledge transfer on historical disaster case data across dip angles, obtaining three-dimensional potential indicators in the spatiotemporal and frequency domains. These indicators include: temporal indicators such as displacement acceleration rate and stress change rate; spatial indicators such as stress gradient and bedding plane angle; and frequency indicators such as acoustic emission dominant frequency band energy and microseismic event b-value. In this embodiment, auxiliary indicators are also included: coal seam dip angle, burial depth, and fracture density; groundwater pressure; and geothermal temperature.

[0102] In particular, this embodiment also introduces the following potential indicators based on collected historical disaster case data and the unique disaster patterns of steeply inclined mining areas:

[0103] Dip Angle-Stress Coupling Factor: This factor quantifies the contribution of the dip angle to stress redistribution by calculating the cosine of the angle between the coal seam dip angle and the principal stress direction. A threshold is set at [value missing]. Where n is the normal vector of the bedding plane;

[0104] Tangential displacement abrupt change rate: Monitor the change in displacement gradient along the dip of the coal seam, use wavelet transform to extract singular points of the displacement signal, and identify precursors of slip instability;

[0105] Gas migration tilt angle effect coefficient: Based on the modified formula of Darcy's law, a tilt angle correction term is introduced to characterize the gas permeability decay law caused by the increase of tilt angle;

[0106] Support structure inclination adaptation: The adaptability of the support system to steeply inclined coal seams is assessed by measuring the real-time deviation between the hydraulic support force direction and the coal seam normal. An early warning is triggered when the deviation exceeds 5°. The implementation process is as follows: The digital twin model calculates the ideal support force direction of the hydraulic support based on the real-time changes in the coal seam normal vector (measured by a micro inertial navigation system), generates control commands, and sends them to the support electro-hydraulic system. A support force-displacement coupling feedback mechanism is embedded in the model. If the deviation between the actual support direction and the coal seam normal is detected to be >5°, an early warning is immediately triggered and a correction procedure is initiated.

[0107] Based on expert experience, potential indicators are screened to obtain candidate indicators for the early warning indicator system.

[0108] A machine learning model is constructed by using candidate indicators as input variables and historical disaster occurrence and severity as output variables.

[0109] Based on machine learning models, the contribution of candidate indicators to the prediction of coal and rock dynamic disasters is evaluated.

[0110] Based on the contribution level, the final early warning indicators are obtained, and an early warning indicator system for coal and rock dynamic disasters is constructed.

[0111] S4: A coal and rock dynamic disaster early warning model is constructed by training and learning the early warning indicator system based on machine learning algorithms. A further implementation involves using a physical information neural network (PIN) to construct the model, embedding residual terms of the coal and rock constitutive equation within the PSN. Specifically, a deep neural network structure is designed, with the input layer receiving early warning indicator data (such as stress, strain, and gas concentration), the hidden layer employing an appropriate activation function (such as ReLU), and the output layer outputting the probability or risk level of the coal and rock dynamic disaster. The coal and rock constitutive equation describes the relationship between coal and rock stress and strain, in the form:

[0112] σ = f(∈, coal and rock parameters),

[0113] Where σ represents stress, ∈ represents strain, and coal and rock parameters include elastic modulus, Poisson's ratio, etc. In the neural network, in addition to the data-driven loss term, a residual term from the constitutive equation is introduced as a physical constraint. The residual term is defined as the difference between the stress predicted by the network and the stress calculated by the constitutive equation:

[0114] R = σ 预测 -f(∈ 预测 (coal and rock parameters)

[0115] The residual term R is incorporated as part of the network optimization to ensure that the network's prediction results conform to the physical properties of coal and rock.

[0116] S5: The coal and rock dynamic disaster early warning model is integrated into the digital twin model. When the digital twin model is updated, the coal and rock dynamic disaster early warning model performs real-time assessment and early warning of dynamic disaster risks in steeply inclined mining areas. Specifically, the early warning mechanism constructed in this invention achieves accurate response in steeply inclined mining areas through the following innovations:

[0117] 1. Based on real-time data from a digital twin model, a spatiotemporal graph neural network (STGNN) is used to model an angle-sensitive disaster chain of "microseismic event → crack propagation → stress transfer → macroscopic instability" to predict the disaster propagation path;

[0118] 2. By using fuzzy logic algorithms to integrate expert experience with real-time data, the warning threshold is adaptively adjusted, thereby reducing the false alarm rate;

[0119] 3. High-risk areas in the digital twin model are superimposed onto the actual mining field view using mixed reality (MR) equipment, with the slip risk level marked by the dip gradient color band, and the disaster avoidance route is dynamically displayed;

[0120] 4. After the early warning signal is triggered, the cutting trajectory of the coal mining machine and the support parameters of the hydraulic support are automatically adjusted to form a closed loop of "monitoring-early warning-control" to suppress dip angle-induced dynamic disasters.

[0121] Specifically, regarding the dynamic updating and real-time feedback mechanism of the digital twin model as it changes with the mining site status:

[0122] This embodiment achieves model-driven closed-loop control through the interaction between the real-time data collected by the aforementioned sensors and the constructed virtual models. In the early warning section, this embodiment also involves feedback delay compensation: a Kalman filter is used to fuse sensor data streams and model prediction results to compensate for network transmission and computation delays (typically 50ms), ensuring strict synchronization between the virtual model and the physical world. Based on the advanced simulation capabilities of the digital twin model, the effects of different control strategies (such as a 10% increase or decrease in support force) are simulated one minute in advance, and the optimal strategy is selected for execution, avoiding control lag caused by feedback delay.

[0123] After each control command is executed, actual effect data (such as the displacement change rate after the support force is adjusted) is collected. The parameters of the early warning model are updated through reinforcement learning (RL). A loss function is designed to comprehensively consider safety (such as stress mutation suppression), efficiency (such as the advance of the coal mining machine) and energy consumption (such as the power of the hydraulic system). Pareto optimal control is achieved using the NSGA-II algorithm.

[0124] To ensure the accuracy of disaster early warning, this embodiment employs human-machine collaborative intervention:

[0125] Dynamic permission allocation: In low-risk scenarios (disaster probability <5%), the system operates fully automatically; in medium-to-high-risk scenarios (5% to 30%), early warning information is pushed to the manual monitoring interface, and engineers can modify control commands by overlaying them with AR gestures.

[0126] Traceability and auditing: All automatically generated instructions and manual intervention records are stored on the blockchain (based on Hyperledger Fabric) to ensure that operations are traceable and responsibilities are clear.

[0127] It should be noted that the method of this embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this embodiment, and the multiple devices will interact with each other to complete the method described.

[0128] It should be noted that some embodiments of the present invention have been described above. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The actions or steps recorded in the claims can be performed in a different order than that in the above embodiments and can still achieve the desired result. In addition, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] Example 2

[0130] Based on the same inventive concept, and corresponding to any of the above embodiments, this invention also provides a digital twin-based monitoring and early warning system for coal and rock dynamic disasters in steeply inclined mining areas, used to implement the method, including:

[0131] The data correction module is used to acquire sensor installation parameters and geological environment information of steep-angle stopes, establish a correction model, and correct the geological exploration data of steep-angle stopes collected by the sensors.

[0132] The digital twin model building module is used to build a digital twin model of a steeply inclined stope based on the corrected geological exploration data and stope design parameters.

[0133] The early warning indicator system construction module is used to construct an early warning indicator system for coal and rock dynamic disasters based on historical coal and rock disaster case data and expert experience.

[0134] The disaster early warning model construction module is used to train and learn the early warning indicator system based on machine learning algorithms to construct a coal and rock dynamic disaster early warning model.

[0135] The early warning module is used to integrate the coal and rock dynamic disaster early warning model into the digital twin model. When the digital twin model is updated, the coal and rock dynamic disaster early warning model performs real-time assessment and early warning of dynamic disaster risks in steeply inclined mining areas.

[0136] A further implementation wherein the data correction module includes:

[0137] An angle compensation unit is used to dynamically adjust the installation attitude according to the dip angle of the coal seam using an adaptive array sensor group. It records the installation angle deviation in real time through laser ranging and inertial navigation unit to build an installation angle deviation compensation model.

[0138] The wave velocity compensation unit is used to establish the mapping relationship between sensor installation parameters and rock mass wave velocity anisotropy, and uses a backpropagation correction matrix to compensate for signal attenuation and construct a wave velocity anisotropy compensation model.

[0139] The propagation path compensation unit is used to introduce non-uniform medium wave field reconstruction technology, and to construct a propagation path compensation model by simulating the propagation path deviation of electromagnetic waves in coal-bearing rock fractured medium through time-domain finite difference simulation.

[0140] The calibration model construction unit is used to obtain the calibration model based on the installation angle deviation compensation model, the wave velocity anisotropy compensation model, and the propagation path compensation model.

[0141] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0142] It should be noted that the above system is embodied in the form of functional units. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0143] For example, a "module" can be a software program, hardware circuit, or a combination of both that implements the above functions. Hardware circuits may include application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0144] Example 3

[0145] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any of the above embodiments.

[0146] Figure 2 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0147] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0148] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0149] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0150] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0151] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0152] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0153] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0154] Example 4

[0155] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the methods described in any of the above embodiments.

[0156] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0157] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the methods described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0158] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of the invention as described above, which are not provided in the details for the sake of brevity.

[0159] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of the invention, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of the invention, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of the invention will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of the invention, it will be apparent to those skilled in the art that the embodiments of the invention may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0160] Although the invention has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0161] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0162] The embodiments of this invention are intended to cover all such substitutions, modifications, and variations falling within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this invention should be included within the protection scope of this invention.

Claims

1. A method for monitoring and early warning of dynamic disasters in coal and rock in steeply inclined mining areas based on digital twins, characterized in that, include: Obtain sensor installation parameters and geological environment information of steep-angle stopes, establish a calibration model, and calibrate the geological exploration data of steep-angle stopes collected by the sensors; Based on the corrected geological exploration data and mining design parameters of the steeply inclined mining area, a digital twin model of the steeply inclined mining area is constructed. Based on historical coal and rock disaster case data and expert experience, an early warning indicator system for coal and rock dynamic disasters is constructed. The early warning indicator system is trained and learned based on machine learning algorithms to construct an early warning model for coal and rock dynamic disasters. The coal and rock dynamic disaster early warning model is integrated into the digital twin model. When the digital twin model is updated, the coal and rock dynamic disaster early warning model performs real-time assessment and early warning of dynamic disaster risks in steeply inclined mining areas. The sensors include stress sensors, strain sensors, gas sensors, displacement sensors, and micro-vibration sensors; The sensor installation parameters include the installation angle and installation position; wherein, the installation position includes the coal pillar area, the coal and rock mass in front of the coal mining machine, and the hydraulic support area, and the sensor is deployed in association with the equipment and facilities in the mining area; The geological environment information of the steeply inclined mining area includes the dip angle, thickness variation of the coal seam, and distribution of geological structures. Methods for establishing a calibration model for sensor installation angle and position include: An adaptive array sensor group is used to dynamically adjust the installation attitude according to the dip angle of the coal seam. The installation angle deviation is recorded in real time by laser ranging and inertial navigation unit to build an installation angle deviation compensation model. Establish the mapping relationship between sensor installation parameters and rock mass wave velocity anisotropy, use backpropagation correction matrix to compensate for signal attenuation, and construct a wave velocity anisotropy compensation model; A non-uniform medium wave field reconstruction technique is introduced, and a propagation path compensation model is constructed by simulating the propagation path deviation of electromagnetic waves in coal-bearing rock fractured media through time-domain finite difference simulation. The correction model is obtained based on the installation angle deviation compensation model, the wave velocity anisotropy compensation model, and the propagation path compensation model.

2. The method according to claim 1, characterized in that, The method for constructing the digital twin model includes: The corrected geological exploration data of the steep-angle stope and the stope design parameters are integrated to construct a unified data format and coordinate system, and obtain multi-source fused data; Based on the multi-source fusion data, a three-dimensional geometric model of the coal and rock mass is constructed using three-dimensional modeling technology. Based on the aforementioned three-dimensional geometric model, and combined with the mechanical properties of coal and rock, the stress-strain law during the mining process, and the gas migration law, the coal and rock mass is endowed with corresponding physical field properties, and physical field models of stress field, displacement field, and gas seepage field are constructed. Three-dimensional modeling was performed on the coal mining machine, hydraulic support and scraper conveyor in the mining area to obtain a three-dimensional model of the equipment and facilities. By integrating the three-dimensional geometric model, the physical field model, and the three-dimensional model of the equipment and facilities, a digital twin model of the steep-angle mining area is obtained.

3. The method according to claim 1, characterized in that, Methods for constructing an early warning indicator system for coal and rock dynamic disasters include: Based on graph convolutional networks, the topological features of the historical disaster case data are extracted, a tilt similarity mapping function is constructed, knowledge transfer is performed on historical disaster case data across tilt angles, and spatiotemporal frequency three-dimensional potential indicators are obtained. Based on expert experience, the potential indicators are screened to obtain candidate indicators for the early warning indicator system. Using the candidate indicators as input variables and the occurrence and severity of historical disasters as output variables, a machine learning model is constructed. Based on the machine learning model, the contribution of the candidate indicators to the prediction of coal and rock dynamic disasters is evaluated; Based on the aforementioned contribution level, the final early warning indicators are obtained, and an early warning indicator system for coal and rock dynamic disasters is constructed.

4. The method according to claim 1, characterized in that, Based on the aforementioned early warning indicator system, a coal and rock dynamic disaster early warning model is constructed using a physical information neural network; wherein, the residual term of the coal and rock constitutive equation is embedded in the physical information neural network.

5. A monitoring and early warning system for coal and rock dynamic disasters in steeply inclined mining areas based on digital twins, used to implement the method described in any one of claims 1-4, characterized in that, include: The data correction module is used to acquire sensor installation parameters and geological environment information of steep-angle stopes, establish a correction model, and correct the geological exploration data of steep-angle stopes collected by the sensors. The digital twin model construction module is used to construct a digital twin model of the steeply inclined stope based on the corrected geological exploration data and stope design parameters. The early warning indicator system construction module is used to construct an early warning indicator system for coal and rock dynamic disasters based on historical coal and rock disaster case data and expert experience. The disaster early warning model construction module is used to train and learn the early warning indicator system based on machine learning algorithms to construct a coal and rock dynamic disaster early warning model. The early warning module is used to integrate the coal and rock dynamic disaster early warning model into the digital twin model. When the digital twin model is updated, the coal and rock dynamic disaster early warning model performs real-time assessment and early warning of the dynamic disaster risk in steeply inclined mining areas.

6. The system according to claim 5, characterized in that, The data correction module includes: An angle compensation unit is used to dynamically adjust the installation attitude according to the dip angle of the coal seam using an adaptive array sensor group. It records the installation angle deviation in real time through laser ranging and inertial navigation unit to build an installation angle deviation compensation model. The wave velocity compensation unit is used to establish the mapping relationship between sensor installation parameters and rock mass wave velocity anisotropy, and uses a backpropagation correction matrix to compensate for signal attenuation and construct a wave velocity anisotropy compensation model. The propagation path compensation unit is used to introduce non-uniform medium wave field reconstruction technology, and to construct a propagation path compensation model by simulating the propagation path deviation of electromagnetic waves in coal-bearing rock fractured medium through time-domain finite difference simulation. The correction model construction unit is used to obtain the correction model based on the installation angle deviation compensation model, the wave velocity anisotropy compensation model, and the propagation path compensation model.

Images