Integrated management method and system for mine wireless gateways

Abstract

The present application provides an integrated management method and system for wireless gateways for mines, which relates to the field of wireless gateway technology. The method includes: interactively obtaining the tunnel topology of the target mine and dividing the target mine into a honeycomb area grid; deploying K multimodal sensor arrays; building a communication link between the multimodal sensor array and the edge gateway; the diffusion risk analysis platform performs integrated simulation of the risk diffusion path according to the multimodal time series characteristics, and locates multiple real-time risk partitions; performs directional activation of the relay identification hierarchical topology; awakens multiple real-time relay identification sequences to perform RFID coverage identification on multiple real-time risk partitions, and obtains multiple real-time personnel distribution characteristics; and dynamically allocates rescue resources. This application solves the technical problem that the wireless gateway has poor accuracy in identifying risk sources due to the complex and frequently changing mine environment, which affects the rescue efficiency, and improves the mine rescue scheduling capability and efficiency.

Description

Technical Field

[0001] The present application relates to the field of wireless gateway technology, and in particular to an integrated management method and system for mine-used wireless gateways. Background Art

[0002] Through centralized management and distributed deployment, mining wireless gateways enable seamless connection and efficient collaboration of various sensors, equipment, and communication systems in mining environments. The dynamic and complex nature of the mining environment requires mining wireless gateways to be able to identify and locate multiple risk sources in real time, while also being able to dynamically adjust network architecture and monitoring modes to adapt to the ever-changing working environment. The wireless gateway acquires data from different sensors and equipment in real time and conducts comprehensive analysis to enable monitoring of the mining environment and risk warnings. However, complex factors in the mining environment (such as winding tunnels, numerous obstacles, etc.), limited wireless signal propagation, and uneven signal coverage have resulted in existing mining wireless gateways having low accuracy in identifying personnel and risk sources, making it impossible to respond to sudden risks in a timely manner, thus affecting emergency response and rescue efficiency.

[0003] In summary, the existing technology has a technical problem that due to the complex and frequently changing mining environment, the wireless gateway has poor accuracy in identifying risk sources, which further affects the rescue efficiency. Summary of the Invention

[0004] The purpose of this application is to provide an integrated management method and system for wireless gateways for mines, so as to solve the technical problem in the prior art that the wireless gateway has poor accuracy in identifying risk sources due to the complex and frequently changing mining environment, which further affects the rescue efficiency.

[0005] In view of the above problems, the present application provides an integrated management method and system for mine wireless gateways.

[0006] In a first aspect, the present application provides an integrated management method for wireless gateways for mines, which is implemented through an integrated management system for wireless gateways for mines, wherein the integrated management method for wireless gateways for mines includes: interactively obtaining the tunnel topology of a target mine, and dividing the target mine into honeycomb area grids based on the tunnel topology; deploying K multimodal sensor arrays for K grid partitions in the honeycomb area grid through monitoring coverage fitting; establishing a communication link between the K multimodal sensor arrays and K edge gateways, wherein the edge gateways have a built-in lightweight AI chip; a diffusion risk analysis platform performs integrated simulation of risk diffusion paths based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk partitions, wherein the K edge gateways are connected to the diffusion risk analysis platform; performing directed activation of the relay identification hierarchical topology based on the multiple real-time risk partitions, and outputting multiple real-time relay identification sequences; waking up the multiple real-time relay identification sequences to perform RFID coverage identification on the multiple real-time risk partitions to obtain multiple real-time personnel distribution characteristics; and dynamically allocating rescue resources based on the multiple real-time personnel distribution characteristics.

[0007] Optionally, multi-source data collection and fusion are used to extract the tunnel topology structure, and a weighted tunnel connectivity graph is generated based on the tunnel topology structure; multiple cross-node coordinates and multiple node weight data of multiple tunnel topology nodes are extracted from the weighted tunnel connectivity graph; dynamic grid division is performed based on the multiple cross-node coordinates and multiple node weight data to divide the target mine into the honeycomb area grid.

[0008] Optionally, an initial topological skeleton is generated by analyzing and processing the design phase BIM model of the target mine, wherein the analyzing and processing includes the extraction of the tunnel centerline, intersection coordinates, and support structure parameters; after using an explosion-proof mobile laser scanner to collect point cloud data along the tunnels of the target mine, the collected data is compressed by voxel grid filtering to obtain tunnel laser point cloud data; a tunnel fusion three-dimensional model is obtained by aligning the tunnel laser point cloud data and the initial topological skeleton; the tunnel centerline is extracted from the tunnel fusion three-dimensional model to obtain the tunnel topological structure; and the construction of the weighted tunnel connectivity graph is completed by injecting dynamic and static node weights into the tunnel topological structure.

[0009] Optionally, based on the multiple node spatial positions of the multiple tunnel topology nodes in the tunnel topology structure; performing a lithologic stability analysis on the multiple node spatial positions to obtain multiple node static weights; based on the multiple topological edge spatial positions of the multiple tunnel topology edges in the tunnel topology structure, extracting multiple roof displacement data from the associated geological exploration report; performing deformation rate calculation on the multiple roof displacement data to obtain multiple topological edge dynamic weights; based on the multiple node spatial positions and the multiple topological edge spatial positions, weight injection of the multiple node static weights and the multiple topological edge dynamic weights is performed in the tunnel topology structure mapping to complete the construction of the weighted tunnel connectivity graph.

[0010] Optionally, the associated geological exploration report of the target mine is called locally; multiple rock layer stability coefficients are extracted from the associated geological exploration report based on the spatial positions of the multiple nodes; local accident records are called according to the spatial positions of the multiple nodes to obtain multiple node accident frequencies; and the multiple node static weights are obtained by normalizing the multiple rock layer stability coefficients and the multiple node accident frequencies.

[0011] Optionally, based on the connection relationship between the nodes and the topological edges, multiple groups of topological edge dynamic weights of the multiple tunnel topological nodes are extracted; the multiple node static weights and the multiple groups of topological edge dynamic weights are fused and calculated by the entropy weight method to obtain the multiple node weight data; multiple tunnel topological nodes are used as gridding starting points, and the grid density is dynamically corrected according to the multiple node weight data to divide the target mine into the honeycomb area grids, wherein the grid weight density deviation of the K grid partitions meets the preset deviation scale.

[0012] Optionally, according to the tunnel topology and the K sensor deployment coordinates of the K multimodal sensor arrays, spatiotemporal alignment mapping of the K multimodal time series features is performed to complete the configuration of the spatiotemporal data cube; based on the spatiotemporal data cube, physical-driven modeling and data-driven modeling are performed synchronously to obtain a risk diffusion simulation model; risk diffusion positioning is performed by running the risk diffusion simulation model to obtain the multiple real-time risk partitions, wherein the multiple real-time risk partitions include risk source partitions and M risk diffusion partitions.

[0013] Optionally, the three-dimensional boundaries of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel are extracted from the spatiotemporal data cube; the three-dimensional boundaries of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel are input into the fluid dynamics equation to construct a basic diffusion model, and a dynamic diffusion trajectory set is output; the multimodal time series distribution of the spatiotemporal data cube is processed through a spatiotemporal graph neural network, and a risk probability distribution matrix is ​​output; the dynamic diffusion trajectory set and the risk probability distribution matrix are dynamically weighted fused to generate the risk diffusion simulation model.

[0014] Optionally, the relay identification hierarchical topology is deployed in the target mine through signal coverage fitting; the coverage relationship between the risk source partition and the M risk diffusion partitions is analyzed for identification energy consumption according to the relay identification hierarchical topology to obtain a first real-time relay identification sequence and M real-time relay identification sequences; wherein the first real-time relay identification sequence and the M real-time relay identification sequences constitute the multiple real-time relay identification sequences.

[0015] In the second aspect, the present application also provides an integrated management system for wireless gateways for mining, which is used to execute the integrated management method for wireless gateways for mining as described in the first aspect, wherein the integrated management system for wireless gateways for mining includes: a mine division processing module, which is used to interactively obtain the tunnel topology of the target mine, and divide the target mine into honeycomb area grids according to the tunnel topology; a monitoring deployment processing module, which is used to deploy K multimodal sensor arrays to K grid partitions in the honeycomb area grid through monitoring coverage fitting; a communication link construction module, which is used to construct communication links between the K multimodal sensor arrays and K edge gateways, wherein the edge gateway has a built-in lightweight AI chip; risk A diffusion simulation module is used for the diffusion risk analysis platform to perform integrated simulation of the risk diffusion path based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk partitions, wherein the K edge gateways are connected to the diffusion risk analysis platform; a relay identification activation module is used to perform directional activation of the relay identification hierarchical topology based on the multiple real-time risk partitions and output multiple real-time relay identification sequences; a coverage identification processing module is used to wake up the multiple real-time relay identification sequences to perform RFID coverage identification on the multiple real-time risk partitions to obtain multiple real-time personnel distribution characteristics; a resource allocation processing module is used to dynamically allocate rescue resources based on the multiple real-time personnel distribution characteristics.

[0016] One or more technical solutions provided in this application have at least the following beneficial effects:

[0017] The tunnel topology of the target mine is obtained through interaction, and the target mine is divided into honeycomb area grids according to the tunnel topology; K multimodal sensor arrays are deployed on K grid partitions in the honeycomb area grid through monitoring coverage fitting; a communication link between the K multimodal sensor arrays and K edge gateways is constructed, wherein the edge gateway has a built-in lightweight AI chip; the diffusion risk analysis platform performs integrated simulation of the risk diffusion path based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk partitions, wherein the K edge gateways are connected to the diffusion risk analysis platform; a directed activation of the relay identification hierarchical topology is performed according to the multiple real-time risk partitions, and multiple real-time relay identification sequences are output; the multiple real-time relay identification sequences are awakened to perform RFID coverage identification on the multiple real-time risk partitions to obtain multiple real-time personnel distribution characteristics; and rescue resources are dynamically allocated according to the multiple real-time personnel distribution characteristics. That is to say, by dividing the mine into multiple cellular area grids, deploying a multimodal sensor array to monitor the mine environment in real time, establishing a communication link in the wireless communication gateway to transmit the collected multimodal time series feature data back to the edge gateway, and performing an integrated simulation of the risk diffusion path of the multimodal time series feature data, locating the risk partition, and directional activation of the hierarchical topology through relay identification, waking up the relevant relay equipment, determining the real-time personnel at the risk source and the direction of risk diffusion, and dynamically allocating rescue resources to ensure that in the event of an emergency, rescue resources can be deployed quickly and accurately, thereby improving the rescue dispatch capability and efficiency.

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0020] Figure 1 This is a flowchart of the integrated management method for mine wireless gateways in this application;

[0021] Figure 2This is a structural diagram of the integrated management system for mine wireless gateways in this application.

[0022] Explanation of the accompanying reference numerals: mine division processing module 11, monitoring deployment processing module 12, communication link construction module 13, risk diffusion simulation module 14, relay identification activation module 15, coverage identification processing module 16, resource allocation processing module 17. DETAILED DESCRIPTION

[0023] This application solves the technical problem in the prior art that the wireless gateway has poor accuracy in identifying risk sources due to the complex and frequently changing mine environment, which further affects the rescue efficiency by providing an integrated management method and system for mine wireless gateways. By dividing the mine into multiple cellular area grids, deploying a multimodal sensor array to monitor the mine environment in real time, establishing a communication link in the wireless communication gateway to transmit the collected multimodal time series feature data back to the edge gateway, performing an integrated simulation of the risk diffusion path of the multimodal time series feature data, locating the risk partition, waking up the relevant relay equipment through the directional activation of the relay identification hierarchical topology, determining the real-time personnel at the risk source and the risk diffusion direction, and dynamically allocating rescue resources to ensure that rescue resources can be deployed quickly and accurately in an emergency, thereby improving the rescue scheduling capability and efficiency.

[0024] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0025] For example, see the attached Figure 1 The present application provides an integrated management method for a mine-used wireless gateway, wherein the integrated management method for a mine-used wireless gateway is executed by an integrated management system for a mine-used wireless gateway, and the integrated management method for a mine-used wireless gateway specifically includes the following steps:

[0026] S100: interactively obtaining a tunnel topology structure of a target mine, and dividing the target mine into honeycomb area grids according to the tunnel topology structure.

[0027] Furthermore, the present application S100 includes:

[0028] The tunnel topology structure is extracted through multi-source data collection and fusion, and a weighted tunnel connectivity graph is generated based on the tunnel topology structure; multiple cross-node coordinates and multiple node weight data of multiple tunnel topology nodes are extracted from the weighted tunnel connectivity graph; dynamic grid division is performed based on the multiple cross-node coordinates and multiple node weight data to divide the target mine into the honeycomb area grid.

[0029] Specifically, a fused 3D model of the tunnels is generated using the target mine's design-stage BIM model and point cloud data along the mine's tunnels. The tunnel centerlines are extracted from the fused 3D model to create a complete tunnel topology. A weighted tunnel connectivity graph is generated based on the static weights of multiple tunnel topology nodes and the dynamic weights of multiple tunnel topology edges in the tunnel topology. Nodes represent intersections, endpoints, or connection points in a tunnel, reflecting the spatial layout and structure of the mine's tunnels. Edges represent connections between two nodes, or rather, paths between two tunnel segments. Weights are used to represent properties such as safety and stability of each tunnel segment.

[0030] From the weighted roadway connectivity graph, we extract multiple intersection node coordinates and node weights for multiple roadway topological nodes, i.e., the location of each node and its corresponding weight. The intersection node coordinates represent the spatial location of roadway intersections within the mine, while the node weights are derived from factors such as rock formation stability, accident records, and geological stability, reflecting the safety risks at different locations within the mine.

[0031] According to the importance and risk level of the nodes, the grid density is adjusted to ensure that the grid density can accurately reflect the risk level of different areas. For example, high-risk nodes will be assigned to denser grids for more detailed monitoring; low-risk nodes will be assigned to larger, sparser grids. Through grid density, the target mine is divided into honeycomb area grids. Each honeycomb grid represents an independent management area, which can be managed differently according to the risk characteristics of each area. The shape of each grid may be different, usually a polygon, and the specific shape is closely related to the mine's topography, tunnel layout and risk distribution. Through multi-source data collection and fusion analysis, refined dynamic grid division is performed based on the weighted tunnel connectivity map to achieve efficient identification of mine risks and emergency response. Guided by node weight data, the grid density can reflect the risk differences in different areas of the mine, ensuring more accurate monitoring and intervention in high-risk areas.

[0032] Furthermore, the present application further comprises the following steps:

[0033] An initial topological skeleton is generated by analyzing and processing the design phase BIM model of the target mine, wherein the analysis and processing includes the extraction of tunnel center lines, intersection coordinates, and support structure parameters; after using an explosion-proof mobile laser scanner to collect point cloud data along the tunnels of the target mine, the collected data is compressed by voxel grid filtering to obtain tunnel laser point cloud data; a tunnel fusion three-dimensional model is obtained by aligning the tunnel laser point cloud data and the initial topological skeleton; the tunnel center line is extracted from the tunnel fusion three-dimensional model to obtain the tunnel topological structure; and the construction of the weighted tunnel connectivity graph is completed by injecting dynamic and static node weights into the tunnel topological structure.

[0034] Furthermore, the present application further comprises the following steps:

[0035] According to the multiple node spatial positions of the multiple tunnel topology nodes in the tunnel topology structure; performing lithologic stability analysis on the multiple node spatial positions to obtain multiple node static weights; according to the multiple topological edge spatial positions of the multiple tunnel topology edges in the tunnel topology structure, extracting multiple roof displacement data from the associated geological exploration report; performing deformation rate calculation on the multiple roof displacement data to obtain multiple topological edge dynamic weights; according to the multiple node spatial positions and the multiple topological edge spatial positions, weight injection of the multiple node static weights and the multiple topological edge dynamic weights is performed in the tunnel topology structure mapping to complete the construction of the weighted tunnel connectivity graph.

[0036] Specifically, the design phase BIM model of the target mine is obtained. This refers to the detailed information about the target mine during the initial design phase. The BIM model contains detailed mine design information such as the geometry of the tunnels, the locations of intersections, and the configuration of support structures. The design phase BIM model is parsed to extract key information from the model to generate an initial topological skeleton. Specifically, the parsing process includes extracting tunnel centerlines, intersection coordinates, and support structure parameters.

[0037] By analyzing the geometric data in the BIM model, the centerline of the tunnel is extracted, representing the main channel trajectory of the mine tunnel. The intersection is an important node in the mine tunnel structure, representing the connection point or intersection point of different tunnel branches. Extracting the coordinates of the intersection can clearly mark the key connection positions in the tunnel system. The support structure is an important component of the mine tunnel. It is used to ensure the stability and safety of the tunnel and extract the detailed parameters of the support structure (such as support type, size, material, etc.). The initial topological skeleton is composed of the extracted tunnel centerline, intersection and support structure information, forming the basic framework of the mine tunnel.

[0038] Because mining environments are often accompanied by hazardous gases, extreme temperatures, or high humidity, explosion-proof mobile laser scanners are required to ensure safe operation in this complex and hazardous environment while efficiently collecting three-dimensional spatial data of mine tunnels. Laser scanners emit laser beams and measure their return time to calculate the distance between different points and generate a large amount of point cloud data representing the geometry of the mine tunnel, including its curves, inclination angles, spatial distribution, and surrounding obstacles. Explosion-proof mobile laser scanners can achieve high-precision, all-round scanning of the tunnel's internal structure without contacting the mine surface.

[0039] Voxel grid filtering is used to compress the collected point cloud data. Voxel grid filtering is a commonly used point cloud data dimensionality reduction technique that divides the point cloud space into uniform voxels (i.e., three-dimensional grid cells) and aggregates the points within each voxel into a representative point. Voxel grid filtering is a point cloud data processing technique that divides the point cloud data into many small cubes (voxels) and then counts and processes the points within each voxel to achieve data compression and denoising.

[0040] By aligning the point cloud data with the initial topological skeleton, the tunnel laser point cloud data is matched and fused with the initial topological skeleton in the BIM model to generate a complete three-dimensional fusion model of the tunnel. This integrates the design information from the BIM model and the point cloud data collected from the actual situation, and can provide a more realistic and accurate display of the mine tunnel structure. The core purpose of the registration is to spatially align the laser point cloud data (real data collected by explosion-proof laser scanners) with the initial topological skeleton (tunnel geometric information obtained by parsing the BIM model). Since the laser point cloud data and the initial topological skeleton come from different data sources, one is based on theoretical data in the design stage, and the other is based on point cloud data collected in the actual environment, the two data sets usually have differences in position, scale, direction, etc. Therefore, the registration process is very critical to ensure that the two data sets can be accurately aligned in the same coordinate system.

[0041] During the registration process, a point-to-point registration algorithm (such as the ICP algorithm or the iterative closest point algorithm) or a feature point-based registration method is typically used to align the laser point cloud data with the initial topological skeleton. Feature points in the initial topological skeleton that correspond to the laser point cloud data, such as roadway intersections and endpoints, are automatically identified and used for alignment. If errors are present during this process, the point cloud data is fine-tuned to better align it with the actual roadway spatial layout.

[0042] The registered laser point cloud data and the initial topological skeleton data will be combined to generate a fused three-dimensional model of the tunnel. This model not only retains the design structure of the tunnel in the initial topological skeleton (such as the tunnel centerline, intersection coordinates and support structure, etc.), but also incorporates the actual collected point cloud data, providing more accurate tunnel spatial geometry information and truly reflecting the actual tunnel.

[0043] Extracting the centerline of the tunnel from the fused three-dimensional model can accurately reflect the overall direction, curvature and structural changes of the tunnel. The tunnel centerline extraction usually uses the minimum path algorithm or curve fitting method based on point cloud data to extract the central axis of the tunnel from the point cloud data of the tunnel. The minimum path algorithm determines the centerline by finding the shortest path from the entrance to the exit of the tunnel, usually starting from the starting point in the point cloud data and extending along the main channel of the tunnel to the end of the tunnel. The curve fitting algorithm will try to fit the centerline of the tunnel into a smooth curve, which can more accurately capture the curved part of the tunnel. Spline curves (such as B-spline or Bezier curves) are used to fit the key points in the point cloud data to ensure that the fitted curve is still smooth when transitioning through the curves and conforms to the actual tunnel shape.

[0044] Based on the extracted tunnel centerlines, the tunnel topology is constructed. This tunnel topology uses a node-edge network topology. Nodes represent tunnel intersections, endpoints, or key locations, such as tunnel forks, termini, or connections to other tunnels. Edges represent connected sections of a tunnel, typically straight or curved segments between adjacent nodes, connecting the various sections of the tunnel into a cohesive network. The tunnel topology is supplemented with additional attributes, such as slope, length, and curve radius, to identify the danger or difficulty of different tunnel sections, enabling more accurate modeling of mine tunnel structures.

[0045] By performing lithologic stability analysis and deformation rate calculations on the nodes and edges of the roadway topology, each node and edge is assigned a specific weight, thereby constructing a weighted roadway connectivity graph. Lithologic stability analysis is performed based on the spatial positions of multiple roadway topology nodes within the roadway topology. By locally accessing associated geological exploration reports and accident records, combined with the mine's actual geological conditions and historical accident data, a static weight is assigned to each roadway node, reflecting the safety of each node in the mine.

[0046] Based on the spatial positions of multiple roadway topological edges within the roadway topology, roof displacement data corresponding to each topological edge location is extracted from the associated geological exploration report. Roof displacement refers to the displacement of the rock strata at the top of a roadway during mining. Geological exploration reports typically include a large amount of displacement measurement data, reflecting the deformation of the roadway roof over a certain period of time.

[0047] The deformation rate of the extracted roof displacement data is calculated to obtain the dynamic weight of each topological edge. The deformation rate reflects the deformation speed of the tunnel roof, that is, the displacement of the rock layer per unit time. The roof displacement of the same area at different time points is calculated by difference. The ratio of displacement to time is calculated to obtain the deformation rate (unit is displacement / time). Similar calculations are performed on all tunnel topological edges to obtain the deformation rate of each topological edge. By calculating the deformation rate, a dynamic weight is assigned to each topological edge. For example, displacement data ten days apart are collected, topological edge 1 is 2.5mm and 4.0mm, and topological edge 2 is 1.2mm and 1.8mm. Then the deformation rate of topological edge 1 is 0.15mm / day, and the deformation rate of topological edge 2 is 0.06mm / day.

[0048] The static weights of multiple nodes at multiple node spatial positions and the dynamic weights of multiple topological edges at multiple topological edge spatial positions are mapped to the lane topology structure to obtain a weighted lane connectivity graph, which is used to represent the stability and risk distribution of the lane network and accurately reflect the stability of different lane sections.

[0049] Furthermore, the present application further comprises the following steps:

[0050] Locally call the associated geological exploration report of the target mine; extract multiple rock layer stability coefficients from the associated geological exploration report based on the multiple node spatial positions; perform local accident record call based on the multiple node spatial positions to obtain multiple node accident frequencies; and obtain the multiple node static weights by normalizing the multiple rock layer stability coefficients and the multiple node accident frequencies.

[0051] Specifically, by locally calling the associated geological exploration report of the target mine, the geological exploration information of the target mine is obtained, that is, detailed information on the geological conditions of the target mine, including key geological information such as the rock layer distribution, rock type, and rock layer stability coefficient of the target mine. According to the spatial positions of multiple nodes, that is, the spatial positions of each tunnel topology node in the tunnel topology structure, the rock layer stability coefficient corresponding to each node is extracted from the associated geological exploration report. The rock layer stability coefficient is a numerical value that measures the stability of the rock layer. It is usually calculated based on the physical and mechanical properties of the rock and reflects the ability of the rock layer to remain stable under specific conditions. The rock layer stability coefficient is a quantitative value used to evaluate the strength and deformation potential of the rock layer. A higher stability coefficient indicates that the rock layer in the area is stronger and more stable, while a lower stability coefficient indicates that the rock layer in the area may be more fragile or prone to deformation. Multiple rock layer stability coefficients reflect the geological stability of the locations of multiple nodes.

[0052] Based on the spatial locations of multiple nodes, local accident records are retrieved to obtain historical accident data, including the types, frequencies, and areas involved in the target mine's past accidents over different time periods. Accident frequencies for multiple nodes corresponding to these spatial locations are obtained to understand the historical number of accidents within the node area. Areas with higher accident frequencies generally indicate greater potential risks, which may be caused by poor rock conditions, poor ventilation, or other factors.

[0053] Through normalization, the rock formation stability coefficient and accident frequency are converted into comparable values. Normalization is to convert data of different dimensions into the same standard scale, which can eliminate the dimensional differences between different data and enable them to be comprehensively evaluated under the same standard. The normalized rock formation stability coefficient and accident frequency will give each node a unified standardized value to ensure that these two factors have a reasonable influence when calculating the static weight. The static weights of multiple nodes represent the safety of each node in the tunnel topology. Normalization is to return the data scale to a similar value range and then remove the data unit. The weight is to obtain the normalized value of all nodes, use the node normalized value as the numerator, and the sum of the normalized values ​​of all nodes as the denominator to calculate the static weight of each node.

[0054] For example, assuming that the rock formation stability coefficient and accident frequency of two nodes A and B are obtained from the geological exploration report, the static weights of nodes A and B are calculated as shown in Table 1:

[0055] Table 1 Node static weight

[0056] node A B Rock formation stability coefficient 0.8 0.6 Accident frequency 3 1 Normalized value of rock formation stability coefficient 0.8 0.6 Normalized value of accident frequency 1.5 0.5 Node static weight 0.68 0.32

[0057] According to the data in the table, the normalized value of node A is 2.3, and the normalized value of node B is 1.1. Therefore, the static weights of node A are 2.3 / 3.4, and the static weights of node B are 1.1 / 3.4. Through normalization, multiple rock formation stability coefficients and multiple node accident frequencies are converted into comparable static weights, which are used to assess the risk level of each node under static conditions.

[0058] Furthermore, the present application further comprises the following steps:

[0059] Based on the connection relationship between the nodes and the topological edges, the dynamic weights of multiple groups of topological edges of the multiple tunnel topological nodes are extracted; the static weights of the multiple nodes and the dynamic weights of the multiple groups of topological edges are fused and calculated by the entropy weight method to obtain the weight data of the multiple nodes; the multiple tunnel topological nodes are used as the gridding starting points, and the grid density is dynamically corrected according to the multiple node weight data to divide the target mine into the honeycomb area grids, wherein the grid weight density deviation of the K grid partitions meets the preset deviation scale.

[0060] Specifically, based on the connection between nodes and topological edges in the roadway topology structure, multiple sets of dynamic weights for topological edges are extracted for multiple roadway topological nodes. In the entropy weighting method, the entropy value of each indicator is first calculated, and then the weight distribution of each indicator is determined based on the entropy value. Finally, the static and dynamic weights are combined to derive a comprehensive risk weight for each node, i.e., the weight data of multiple nodes. The entropy weighting method is an objective weighting method that calculates weights based on the degree of variation between indicator data. In information theory, entropy is a measure of information uncertainty, and the entropy weighting method uses this principle to assign weights.

[0061] Using multiple tunnel topology nodes as the starting point for gridding, the grid density is dynamically corrected based on multiple node weight data, and the target mine is divided into honeycomb area grids. The density of the grid is adjusted according to the node weight data to ensure that the grid can accurately reflect the risk level of different areas. Generally, the grid density corresponding to higher-risk areas will be increased accordingly, while the grid density will be reduced in lower-risk areas, allowing high-risk areas to receive more detailed monitoring and response. Based on the corrected grid density, the target mine is divided into multiple polygonal areas of inconsistent shapes, namely honeycomb area grids. The shape and size of the grid are dynamically adjusted according to the risk weight of the area. It is not necessarily a regular polygon, but is determined according to the actual mine topology and risk distribution.

[0062] To ensure the rationality and consistency of meshing, a preset mesh density deviation scale is established. Within this scale, the density deviation of all mesh areas must meet certain standards. This deviation scale control ensures that the mine's meshing not only accurately reflects the risk distribution but also avoids excessive concentration or sparseness of mesh density, ensuring the rational allocation of monitoring resources. Through dynamic mesh density correction and honeycomb area grid division, the risk level of different areas in the target mine can be accurately assessed, thereby improving the accuracy of risk management.

[0063] S200: Deploy K multimodal sensor arrays to K grid partitions in the cellular area grid by monitoring coverage fitting.

[0064] Specifically, the goal of monitoring coverage fitting is to ensure that each grid section within the honeycomb grid effectively collects environmental monitoring data, enabling real-time monitoring and identification of mine risks. Monitoring coverage fitting involves performing a regional coverage analysis of each honeycomb grid within the mine to ensure that the monitoring requirements of each grid section are met. Based on the actual conditions of the mine, the monitoring requirements of each grid section are rationally determined to ensure coverage of potential risk sources within each area. The appropriate sensor type, quantity, and location are configured based on the risk characteristics of each area to achieve optimal monitoring results.

[0065] Within each grid zone, a corresponding multimodal sensor array is deployed, including but not limited to laser methane sensors, infrared thermal imagers, and microseismic monitoring nodes. Laser methane sensors are used to detect methane gas concentrations in mine tunnels, providing early warning signals for incidents such as gas leaks and fires. Infrared thermal imagers are used to detect heat sources in the mining environment, particularly areas with abnormal temperature fluctuations. Microseismic monitoring nodes are used to monitor small vibrations and geological activity in the mine, especially during mining operations, where the risk of geological vibrations or mine collapse cannot be ignored.

[0066] By deploying a multimodal sensor array, the diverse monitoring needs within each grid area are met, enabling comprehensive monitoring of the mine environment. Due to the diverse sensor types, each sensor can work independently or collaboratively to provide a variety of data types, such as gas concentration, temperature, and vibration, covering all aspects of the mine environment.

[0067] S300: Build communication links between the K multimodal sensor arrays and K edge gateways, wherein the edge gateways have built-in lightweight AI chips.

[0068] Specifically, K multimodal sensor arrays are deployed in different areas of the mine. Each array collects mine environmental data using different types of sensors (such as laser sensors, gas detection sensors, and temperature sensors). A communication link is established between each multimodal sensor array and its corresponding edge gateway to ensure data reception and rapid processing using an AI chip. The edge gateway is a network device located between the sensor array and the central monitoring system, responsible for collecting sensor data and performing preliminary processing and analysis. A lightweight AI chip, integrating artificial intelligence algorithms, enables real-time data processing and analysis on edge devices. It performs pre-processing operations such as filtering and feature extraction on raw data, such as calculating the gradient change rate of gas concentration, and only uploads key indicators to the central platform, reducing bandwidth pressure. For example, by calculating the gradient change rate of gas concentration, the AI ​​chip can analyze gas diffusion trends in real time and extract relevant key data (such as the rate of change of gas concentration, temperature changes, and microseismic events). By establishing an efficient communication link between the edge gateway and the multimodal sensor array, real-time monitoring, analysis, and rapid response to the mine environment are achieved.

[0069] S400: The diffusion risk analysis platform performs an integrated simulation of the risk diffusion path based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk partitions, wherein the K edge gateways are connected to the diffusion risk analysis platform.

[0070] Furthermore, the present application S400 includes:

[0071] According to the tunnel topology and the K sensor deployment coordinates of the K multimodal sensor arrays, spatiotemporal alignment mapping of the K multimodal time series features is performed to complete the configuration of the spatiotemporal data cube; based on the spatiotemporal data cube, physical-driven modeling and data-driven modeling are synchronously executed to obtain a risk diffusion simulation model; risk diffusion positioning is performed by running the risk diffusion simulation model to obtain the multiple real-time risk partitions, wherein the multiple real-time risk partitions include risk source partitions and M risk diffusion partitions.

[0072] The three-dimensional boundaries of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel are extracted from the spatiotemporal data cube; the three-dimensional boundaries of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel are input into the fluid dynamics equation to construct a basic diffusion model, and a dynamic diffusion trajectory set is output; the multimodal time series distribution of the spatiotemporal data cube is processed through a spatiotemporal graph neural network, and a risk probability distribution matrix is ​​output; the dynamic diffusion trajectory set and the risk probability distribution matrix are dynamically weighted fused to generate the risk diffusion simulation model.

[0073] Specifically, the Diffusion Risk Analysis Platform monitors, analyzes, and locates risks in the mine environment in real time based on data transmitted from multiple edge gateways. By integrating K multimodal time series features transmitted from K edge gateways into a simulation of risk diffusion paths, the platform aims to quickly and accurately identify and locate potential risk zones within the mine. Based on these simulation results, the Diffusion Risk Analysis Platform identifies multiple areas within the mine that may be at risk and designates these areas as real-time risk zones.

[0074] Based on the tunnel topology and the K sensor deployment coordinates of the K multimodal sensor arrays, the multimodal time series features collected by each sensor array are matched in spatial position and time through spatiotemporal alignment mapping. By merging the time series data at each time point and each sensor location, all data are integrated into a spatiotemporal data cube, including time, space, and modal dimensions. For example, the gas concentration (0.8%), temperature (35°C), and vibration acceleration (2.5g) at time t in a certain area are integrated into the vector [0.8, 35, 2.5], which, together with its corresponding timestamp and spatial coordinates, forms part of the spatiotemporal data cube.

[0075] The three-dimensional boundaries of the tunnels, the tunnel wind speed distribution, and the tunnel gas concentration gradient distribution are extracted from the spatiotemporal data cube. The three-dimensional boundaries of the tunnels represent the spatial form and structure of the mine tunnels and are crucial for simulating the gas diffusion path and the effectiveness of the ventilation system. The spatial data portion of the spatiotemporal data cube allows the extraction of the tunnel geometry, including the tunnel width, height, and overall spatial layout. The tunnel wind speed distribution is an important factor affecting the diffusion rate and path of gases (such as gas) within the tunnel. Data collected by sensors (such as wind speed sensors) can reflect the airflow pattern within the tunnel, thereby affecting the gas diffusion path. The tunnel gas concentration gradient distribution reflects the spatial variation of the gas concentration within the tunnel. Gas concentration data typically comes from gas sensors or gas detection equipment to assess the risk of gas leakage or accumulation. This data exists in a time series format within the spatiotemporal data cube.

[0076] The three-dimensional tunnel boundary, tunnel wind speed distribution, and tunnel gas concentration gradient are input into the fluid dynamics equations to construct a basic diffusion model. The fluid dynamics equations are used to simulate the diffusion behavior of gases (such as methane) and output a set of dynamic diffusion trajectories that describe the gas diffusion process in a mine tunnel. The basic diffusion model takes into account the tunnel geometry, wind speed and direction, and gas concentration and gradient to simulate the gas diffusion process in the tunnel. The initial conditions are the initial distribution of gas concentrations in the tunnel. Typically, these initial concentrations are derived from concentration data at gas leak points. Areas with higher concentrations are often the starting points of diffusion, and gas diffusion will originate from these areas. Boundary conditions require setting the gas flow rate and concentration at the tunnel outlet (ventilation opening) and inlet (external air input point). Based on these initial and boundary conditions, the fluid dynamics equations are numerically solved. Over time, the gas concentration distribution, flow rate, and diffusion trajectory will continuously change. Through diffusion simulation, the temporal evolution of gas concentration at various locations within the tunnel is determined, and dynamic gas diffusion trajectories are generated.

[0077] The dynamic diffusion trajectory set includes time series, diffusion paths, and concentration changes. The time series represents the spatial distribution of gas at each time point and describes the spatiotemporal evolution of gas diffusion. The diffusion path represents the propagation path of gas within the tunnel, showing how gas diffuses to different areas of the tunnel over time. The concentration change represents the change in gas concentration at each location, helping to identify high-risk areas.

[0078] A spatiotemporal graph neural network is a deep learning model that combines graph neural networks (GNNs) with spatiotemporal data. The relationship between data is represented through a graph structure (graph nodes and graph edges), while taking into account changes in time series data. In mine risk assessment, a spatiotemporal graph neural network can perform risk prediction and anomaly detection by capturing the spatiotemporal relationships between nodes (such as different locations in a tunnel) and between edges (such as the spatial dependencies between sensors). The multimodal time series data of the mine is obtained through a spatiotemporal data cube, that is, each data point represents the sensor value at a specific time, specific location, and specific mode. Based on the topological structure of the mine, the sensor locations in the tunnel are regarded as nodes of the graph, and the spatial relationships between sensors are regarded as edges of the graph. Each sensor node will have a spatiotemporal data associated with it.

[0079] The convolutional layers in the graph neural network capture the spatial relationships between nodes. For each node, the model updates its own state based on the states of its neighboring nodes. The spatiotemporal graph neural network combines temporal and spatial information, effectively propagating information through the graph structure, thereby capturing potential patterns in spatiotemporal changes. After processing by the multi-layer spatiotemporal graph neural network, the output is a high-risk probability distribution matrix, representing the risk probability at different times and locations, specifically expressed as the risk value for each grid or node. For example, the risk probability distribution matrix is ​​shown in Table 2:

[0080] Table 2 Risk probability distribution matrix

[0081]

[0082] The dynamic diffusion trajectory set is based on a fluid dynamics model of the mining environment, specifically a diffusion model for hazardous substances such as gas or methane. By inputting environmental parameters (such as the three-dimensional boundaries of the tunnel, wind speed distribution, and gas concentration), the set calculates diffusion trajectories under different temporal and spatial conditions. The output of the dynamic diffusion trajectory set represents the propagation path and changes of hazardous substances in the mining environment.

[0083] Based on the risk probability distribution matrix generated by the spatiotemporal graph neural network, each region and time period is assigned a risk probability weight. A higher risk probability indicates a greater risk in that region and therefore warrants a higher weight. Each trajectory in the dynamic diffusion trajectory set represents the spatial propagation path of gas or other risk sources. A larger diffusion range or higher concentration variation may indicate a higher risk in that region, so a corresponding weight can be assigned based on the scale and speed of diffusion. For example, if a region has a high gas concentration risk and the diffusion trajectory indicates that it is the core area of ​​the risk source, the risk weight for that region will be higher. The specific weighted fusion formula is R(t,x) = α·P(t,x)+β·E(t,x), where R(t,x) is the combined risk value at time t and location x, P(t,x) is the risk probability at time t and location x, E(t,x) is the diffusion trajectory at time t and location x, and α and β are the weighting coefficients for the risk probability and diffusion trajectory.

[0084] After dynamic weighted fusion, the final risk diffusion simulation model will simultaneously consider the influence of multiple factors such as gas concentration, wind speed, airflow, etc., and can accurately predict how the risk will spread and which areas will become potential high-risk areas under different time and space conditions.

[0085] Run the risk diffusion simulation model to dynamically simulate each location in the tunnel, simulating the diffusion path and changes of risk sources. Risk diffusion positioning involves calculating and simulating the diffusion path and impact range of risk sources to identify and locate different risk areas in a mine or other industrial environment in real time.

[0086] Based on the risk values ​​(such as gas concentration, fire hazard index, temperature, etc.) and diffusion paths of the operation results, the target mine is divided into multiple dangerous areas, including risk source zones and multiple risk diffusion zones. Risk source zones refer to the origin areas of risk events. In the scenario of gas leakage, these areas are the source of gas leakage. Generally, these areas have higher risk levels and stronger diffusion potential, so they need to be given priority for protection and emergency treatment. Risk diffusion zones are parts of the risk that expand from risk source zones to other areas over time. According to the diffusion trajectory, the risk will spread to other areas with factors such as airflow and tunnel morphology. The simulation model divides these areas according to the size of the risk value and marks them as M risk diffusion zones.

[0087] By simulating diffusion trajectories and predicting future risk dynamics, emergency response preparations can be made in advance based on the risk diffusion simulation model, effectively reducing the probability of disasters and losses, comprehensively improving mine safety, and optimizing resource allocation to ensure the sustainable operation of mines and the safety of workers.

[0088] S500: Performing directed activation of a relay identification hierarchical topology according to the multiple real-time risk partitions, and outputting multiple real-time relay identification sequences.

[0089] Furthermore, the present application S500 includes:

[0090] Through signal coverage fitting, the relay identification hierarchical topology is deployed in the target mine; according to the relay identification hierarchical topology, the coverage relationship between the risk source partition and the M risk diffusion partitions is analyzed for identification energy consumption to obtain a first real-time relay identification sequence and M real-time relay identification sequences; wherein, the first real-time relay identification sequence and the M real-time relay identification sequences constitute the multiple real-time relay identification sequences.

[0091] Specifically, the relay identification hierarchical topology is activated in a targeted manner based on multiple real-time risk zones. Based on known risk sources and diffusion directions, combined with the relay device's coverage capabilities, location, and communication link status, a relay identification transfer sequence is generated, specifying the activation sequence for each relay device. This ensures the network can provide timely coverage of critical areas and maintain stable communication connections in a dynamic environment. Following this sequence, relay devices are activated one by one to perform RFID identification of risk sources and risk diffusion directions.

[0092] Through signal coverage fitting, a relay identification hierarchical topology is deployed in the target mine to determine which areas are more critical for relay node deployment, and a hierarchical topology is constructed based on the actual communication needs of the mine. In other words, it is determined which areas require the deployment of relay equipment and the optimal deployment location of the relay equipment. When deploying the relay identification hierarchical topology, key risk areas in the mine are identified, such as gas leakage sources, fire sources, and areas with unstable airflow. A deployment plan for relay equipment is developed through a comprehensive analysis of the signal propagation characteristics and environmental factors in these areas. The hierarchical topology is determined based on the mine tunnel structure and layout, signal coverage capabilities, equipment power consumption limitations, etc. in the target mining area. Each relay device is divided into different levels according to its deployment location, coverage area, and signal strength to ensure uniform coverage and efficient use of equipment.

[0093] The relay identification hierarchical topology may include primary relay nodes, secondary relay nodes and auxiliary relay nodes. The primary relay nodes are located in the core areas of the mine, such as the main tunnels or risk source areas, and are responsible for handling important communication tasks; the secondary relay nodes are located in the peripheral areas of the mine or diffusion zones, and are responsible for supplementing the signal coverage of the primary nodes and enhancing the breadth of the network; the auxiliary relay nodes are deployed in areas with poor communication or signal blind spots to provide temporary signal coverage support.

[0094] Based on the location information of the risk source zone and the risk diffusion zone, the relay identification hierarchical topology is used to perform identification energy consumption analysis. Risk source areas (such as gas leakage sources, fire sources, etc.) are areas with higher risks in mines, and it is necessary to ensure that these areas are always under effective signal coverage. The energy consumption analysis will take into account the signal strength and communication requirements between the risk source area and the relay equipment to ensure that the relay equipment can provide optimal signal coverage with the lowest power consumption. The risk diffusion area is a potential dangerous area that spreads from the risk source area. During the risk diffusion process, the signal coverage requirements will continue to adjust with time and environmental changes. The energy consumption analysis takes into account the direction, speed and coverage area of ​​the risk diffusion, helping to optimize the scheduling of relay equipment to achieve optimal energy efficiency.

[0095] By calculating the relationship between each relay device and the risk zone, the signal transmission strength and energy consumption under different circumstances are evaluated. Based on the results of the energy consumption analysis, a real-time relay identification sequence is generated, which determines the order in which relay devices are activated to ensure effective signal coverage throughout the mine area, especially in the risk source and risk diffusion areas. The first real-time relay identification sequence is typically the sequence of relay devices that are activated with the highest priority in the risk source area of ​​the mine. The M real-time relay identification sequences are relay device activation sequences generated based on the risk diffusion area.

[0096] The first real-time relay identification sequence is combined with M real-time relay identification sequences to form multiple real-time relay identification sequences, which are used to guide the operation of relay nodes during risk identification and transmission. By deploying a hierarchical relay identification topology and performing identification energy consumption analysis, the use of relay nodes is optimized, communication efficiency is improved, and network lifespan is extended.

[0097] S600: Waking up the multiple real-time relay identification sequences to perform RFID coverage identification on the multiple real-time risk zones to obtain multiple real-time personnel distribution features.

[0098] S700: Dynamically allocate rescue resources according to the multiple real-time personnel distribution characteristics.

[0099] Specifically, within the mine, all personnel will wear devices or cards with RFID tags. When a worker enters a risk zone, their RFID tag is scanned by the RFID reader / writer on the relay node. The activated relay node transmits an RFID signal and scans the RFID tags within the mine. The distance between the tag and the reader determines the transmission time and accuracy of the information, enabling precise personnel location. Relay identification devices are activated based on changes in the risk source and risk diffusion zones to ensure coverage and identification of the required risk areas.

[0100] RFID coverage identification uses radio frequency identification (RFID) technology to equip underground personnel with RFID tags, allowing for rapid scanning to determine the personnel composition of a specific area. RFID typically consists of an RFID tag (worn by personnel), an RFID reader (installed at key locations in the mine), and a backend data management system. When a person enters the reader's signal coverage area, the reader automatically identifies the tag and reads the stored information, such as the individual's ID, department, and time of entry. This data is then transmitted to the backend for analysis and display.

[0101] Once the relay identification device is activated, it uses RFID technology to identify and locate the target area, using radio waves for contactless data transmission. By wearing RFID tags on mine workers, the distribution of personnel in the mine can be identified in real time. Each relay device performs RFID identification on the area it covers and reports the personnel's location data. Through the combined operation of RFID technology and relay devices, the distribution of personnel within each real-time risk zone in the mine is obtained, and the number, location, and activity of personnel in each zone are monitored. Real-time personnel distribution characteristics are generated, including personnel location, personnel density, personnel flow trajectory, and personnel status. This accurately identifies the number and distribution of personnel within the risk zone, as well as the location of each person.

[0102] Generate rescue routes based on personnel location and status, dynamically allocate rescue resources, and ensure that resources are delivered on demand. First, evaluate the distribution of personnel in each risk zone and identify areas of emergency need. If there are many staff in the area, and there is excessively high gas concentration or an unstable leak source, prioritize gas detectors, ventilation system repairers, and emergency evacuation teams. Prioritize rescue resources based on the risk area, risk level, and health status of the personnel. Analyze the resource needs of each area in real time, calculate the required amount of resources, and automatically dispatch the corresponding rescue teams and equipment. Use AR navigation to guide the rescue team's actions to ensure a response time of less than 5 minutes.

[0103] Multimodal sensors deployed (such as thermal imagers, microseismic monitoring nodes, and gas concentration detectors) capture real-time on-site environmental data. This data is fed back to a central platform and combined with real-time personnel distribution patterns to optimize resource allocation. During the rescue process, as the personnel's condition and the environment change, rescue resources are dynamically adjusted and optimized. Once trapped personnel are rescued, rescue resources from that area are redeployed to other affected areas.

[0104] Before actual rescue operations, different resource allocation scenarios are simulated and evaluated based on historical and real-time data, including time-cost analysis and risk assessment, to ensure optimal rescue results in the shortest possible time. By accurately analyzing real-time personnel distribution patterns and dynamically scheduling rescue resources, the mine emergency response system minimizes casualties and ensures the safety of personnel in the mine area during disasters.

[0105] In summary, the integrated management method for mine wireless gateways provided by this application has the following beneficial effects:

[0106] The tunnel topology of the target mine is obtained through interaction, and the target mine is divided into honeycomb area grids according to the tunnel topology; K multimodal sensor arrays are deployed on K grid partitions in the honeycomb area grid through monitoring coverage fitting; a communication link between the K multimodal sensor arrays and K edge gateways is constructed, wherein the edge gateway has a built-in lightweight AI chip; the diffusion risk analysis platform performs integrated simulation of the risk diffusion path based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk partitions, wherein the K edge gateways are connected to the diffusion risk analysis platform; a directed activation of the relay identification hierarchical topology is performed according to the multiple real-time risk partitions, and multiple real-time relay identification sequences are output; the multiple real-time relay identification sequences are awakened to perform RFID coverage identification on the multiple real-time risk partitions to obtain multiple real-time personnel distribution characteristics; and rescue resources are dynamically allocated according to the multiple real-time personnel distribution characteristics. That is to say, by dividing the mine into multiple cellular area grids, deploying a multimodal sensor array to monitor the mine environment in real time, establishing a communication link in the wireless communication gateway to transmit the collected multimodal time series feature data back to the edge gateway, and performing an integrated simulation of the risk diffusion path of the multimodal time series feature data, locating the risk partition, and directional activation of the hierarchical topology through relay identification, waking up the relevant relay equipment, determining the real-time personnel at the risk source and the direction of risk diffusion, and dynamically allocating rescue resources to ensure that in the event of an emergency, rescue resources can be deployed quickly and accurately, thereby improving the rescue dispatch capability and efficiency.

[0107] Example 2: Based on the same inventive concept as the integrated management method for wireless gateways for mines in Example 1, this application also provides an integrated management system for wireless gateways for mines, see the attached Figure 2 , the mine wireless gateway integrated management system includes:

[0108] The mine division processing module 11 is used to interactively obtain the tunnel topology of the target mine and divide the target mine into honeycomb area grids according to the tunnel topology; the monitoring deployment processing module 12 is used to deploy K multimodal sensor arrays to K grid partitions in the honeycomb area grid by monitoring coverage fitting; the communication link construction module 13 is used to construct a communication link between the K multimodal sensor arrays and K edge gateways, wherein the edge gateways have built-in lightweight AI chips; the risk diffusion simulation module 14 is used to diffuse the risk analysis platform according to the K multimodal The risk diffusion path is integratedly simulated based on the timing characteristics to locate multiple real-time risk partitions, wherein the K edge gateways are connected to the diffusion risk analysis platform; the relay identification activation module 15 is used to perform directional activation of the relay identification hierarchical topology according to the multiple real-time risk partitions, and output multiple real-time relay identification sequences; the coverage identification processing module 16 is used to wake up the multiple real-time relay identification sequences to perform RFID coverage identification on the multiple real-time risk partitions to obtain multiple real-time personnel distribution characteristics; the resource allocation processing module 17 is used to dynamically allocate rescue resources according to the multiple real-time personnel distribution characteristics.

[0109] Furthermore, the mine division processing module 11 in the integrated management system of the mine wireless gateway is also used to: extract the tunnel topology structure through multi-source data collection and fusion, and generate a weighted tunnel connectivity graph based on the tunnel topology structure; extract multiple cross-node coordinates and multiple node weight data of multiple tunnel topology nodes from the weighted tunnel connectivity graph; perform dynamic grid division based on the multiple cross-node coordinates and multiple node weight data to divide the target mine into the cellular area grid.

[0110] Furthermore, the mine division processing module 11 in the integrated management system of the mine wireless gateway is also used to: generate an initial topological skeleton by analyzing and processing the design stage BIM model of the target mine, wherein the analysis and processing includes the extraction of the tunnel centerline, intersection coordinates, and support structure parameters; after using an explosion-proof mobile laser scanner to collect point cloud data along the tunnel of the target mine, the collected data is compressed by voxel grid filtering to obtain tunnel laser point cloud data; by aligning the tunnel laser point cloud data and the initial topological skeleton, a tunnel fusion three-dimensional model is obtained; the tunnel centerline of the tunnel fusion three-dimensional model is extracted to obtain the tunnel topological structure; and the construction of the weighted tunnel connectivity graph is completed by injecting dynamic and static node weights into the tunnel topological structure.

[0111] Furthermore, the mine division processing module 11 in the integrated management system of the mine wireless gateway is also used for: performing lithologic stability analysis on the multiple node spatial positions of the multiple tunnel topology nodes in the tunnel topology structure to obtain multiple node static weights; extracting multiple roof displacement data from the associated geological exploration report according to the multiple topological edge spatial positions of the multiple tunnel topology edges in the tunnel topology structure; obtaining multiple topological edge dynamic weights by calculating the deformation rate of the multiple roof displacement data; and performing weight injection of the multiple node static weights and the multiple topological edge dynamic weights in the tunnel topology structure mapping according to the multiple node spatial positions and the multiple topological edge spatial positions to complete the construction of the weighted tunnel connectivity graph.

[0112] Furthermore, the mine division processing module 11 in the integrated management system of the mine wireless gateway is also used to: locally call the associated geological exploration report of the target mine; extract multiple rock layer stability coefficients from the associated geological exploration report based on the spatial positions of the multiple nodes; perform local accident record calls based on the spatial positions of the multiple nodes to obtain multiple node accident frequencies; and obtain the static weights of the multiple nodes by normalizing the multiple rock layer stability coefficients and the multiple node accident frequencies.

[0113] Furthermore, the mine division processing module 11 in the integrated management system of the mine wireless gateway is also used to: extract multiple groups of topological edge dynamic weights of the multiple tunnel topology nodes based on the connection relationship between the nodes and the topological edges; calculate the multiple node static weights and multiple groups of topological edge dynamic weights by the entropy weight method to obtain the multiple node weight data; multiple tunnel topology nodes are used as gridding starting points, and the grid density is dynamically corrected according to the multiple node weight data to divide the target mine into the honeycomb area grids, wherein the grid weight density deviation of the K grid partitions meets the preset deviation scale.

[0114] Furthermore, the risk diffusion simulation module 14 in the integrated management system of the mine wireless gateway is also used to: perform spatiotemporal alignment mapping of the K multimodal time series features according to the tunnel topology structure and the K sensor deployment coordinates of the K multimodal sensor arrays, and complete the configuration of the spatiotemporal data cube; based on the spatiotemporal data cube, synchronously execute physical-driven modeling and data-driven modeling to obtain a risk diffusion simulation model; and perform risk diffusion positioning by running the risk diffusion simulation model to obtain the multiple real-time risk partitions, wherein the multiple real-time risk partitions include risk source partitions and M risk diffusion partitions.

[0115] Furthermore, the risk diffusion simulation module 14 in the integrated management system of the mine wireless gateway is also used to: extract the three-dimensional boundary of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel from the spatiotemporal data cube; input the three-dimensional boundary of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel into the fluid dynamics equation to construct a basic diffusion model, and output a dynamic diffusion trajectory set; process the multimodal time series distribution of the spatiotemporal data cube through the spatiotemporal graph neural network, and output a risk probability distribution matrix; dynamically weightedly fuse the dynamic diffusion trajectory set with the risk probability distribution matrix to generate the risk diffusion simulation model.

[0116] Furthermore, the relay identification activation module 15 in the integrated management system of the mine wireless gateway is also used to: deploy the relay identification hierarchical topology in the target mine through signal coverage fitting; perform identification energy consumption analysis on the coverage relationship between the risk source partition and the M risk diffusion partitions according to the relay identification hierarchical topology to obtain a first real-time relay identification sequence and M real-time relay identification sequences; wherein the first real-time relay identification sequence and the M real-time relay identification sequences constitute the multiple real-time relay identification sequences.

[0117] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The integrated management method and specific examples of the mine wireless gateway in Example 1 are also applicable to the integrated management system of the mine wireless gateway in this embodiment. Through the above detailed description of the integrated management method of the mine wireless gateway, those skilled in the art can clearly understand the integrated management system of the mine wireless gateway in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0118] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0119] Obviously, for those skilled in the art, several improvements and modifications can be made to the present application without departing from the principles of the present application, and these improvements and modifications also fall within the scope of protection of the present application.

Claims

1. The integrated management method of mine wireless gateway is characterized by: include: interactively obtaining a tunnel topology structure of a target mine, and dividing the target mine into honeycomb area grids according to the tunnel topology structure; Deploying K multimodal sensor arrays on K grid partitions in the cellular area grid by monitoring coverage fitting; Establishing communication links between the K multimodal sensor arrays and K edge gateways, wherein the edge gateways have built-in lightweight AI chips; The diffusion risk analysis platform performs an integrated simulation of risk diffusion paths based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk zones, wherein the K edge gateways are connected to the diffusion risk analysis platform; performing directed activation of a relay identification hierarchical topology according to the multiple real-time risk partitions, and outputting multiple real-time relay identification sequences; Waking up the multiple real-time relay identification sequences to perform RFID coverage identification on the multiple real-time risk zones to obtain multiple real-time personnel distribution features; Rescue resources are dynamically allocated according to the multiple real-time personnel distribution characteristics.

2. The integrated management method for mine wireless gateways according to claim 1, characterized in that: Interactively obtaining a tunnel topology of a target mine, and dividing the target mine into honeycomb area grids according to the tunnel topology, including: By collecting and fusing multi-source data, the lane topology structure is extracted, and a weighted lane connectivity graph is generated based on the lane topology structure; Extracting a plurality of intersection node coordinates and a plurality of node weight data of a plurality of lane topology nodes from the weighted lane connectivity graph; Dynamic grid division is performed according to the multiple cross-node coordinates and multiple node weight data to divide the target mine into the honeycomb area grids.

3. The integrated management method for mine wireless gateways according to claim 2, characterized in that: The tunnel topology structure is extracted by multi-source data collection and fusion, and a weighted tunnel connectivity graph is generated based on the tunnel topology structure, including: Generating an initial topological skeleton by analytically processing the design phase BIM model of the target mine, wherein the analytical processing includes extracting the centerline of the roadway, the coordinates of the intersection, and the parameters of the support structure; After collecting point cloud data along the tunnel of the target mine using an explosion-proof mobile laser scanner, the collected data is compressed by voxel grid filtering to obtain tunnel laser point cloud data; A fused three-dimensional model of the lane is obtained by registering the lane laser point cloud data and the initial topological skeleton; Extracting the lane centerline from the lane fusion three-dimensional model to obtain the lane topology structure; The construction of the weighted lane connectivity graph is completed by injecting dynamic and static node weights into the lane topology structure.

4. The integrated management method for mine wireless gateways according to claim 3, characterized in that: The weighted lane connectivity graph is constructed by injecting dynamic and static node weights into the lane topology structure, including: According to a plurality of node spatial positions of the plurality of lane topology nodes in the lane topology structure; Performing lithologic stability analysis on the spatial positions of the multiple nodes to obtain static weights of the multiple nodes; extracting a plurality of roof displacement data from an associated geological exploration report according to a plurality of topological edge spatial positions of a plurality of tunnel topological edges in the tunnel topological structure; By calculating the deformation rate of the plurality of top plate displacement data, a plurality of topological edge dynamic weights are obtained; According to the spatial positions of the multiple nodes and the spatial positions of the multiple topological edges, weight injection of the multiple node static weights and the multiple topological edge dynamic weights is performed in the lane topology structure mapping to complete the construction of the weighted lane connectivity graph.

5. The integrated management method for mine wireless gateways according to claim 1, characterized in that: The diffusion risk analysis platform performs integrated simulation of risk diffusion paths based on the K multimodal time series features transmitted back by the K edge gateways to locate multiple real-time risk zones, including: Performing spatiotemporal alignment mapping of the K multimodal time series features according to the lane topology and the K sensor deployment coordinates of the K multimodal sensor arrays to complete the configuration of the spatiotemporal data cube; Based on the spatiotemporal data cube, physics-driven modeling and data-driven modeling are performed simultaneously to obtain a risk diffusion simulation model; The risk diffusion simulation model is run to locate the risk diffusion, thereby obtaining the multiple real-time risk partitions, wherein the multiple real-time risk partitions include risk source partitions and M risk diffusion partitions.

6. The integrated management method for mine wireless gateways according to claim 5, characterized in that: Based on the spatiotemporal data cube, physical-driven modeling and data-driven modeling are performed simultaneously to obtain a risk diffusion simulation model, including: Extracting the three-dimensional boundary of the roadway, the wind speed distribution of the roadway, and the gas concentration gradient distribution of the roadway from the spatiotemporal data cube; Input the three-dimensional boundary of the tunnel, the wind speed distribution of the tunnel, and the gas concentration gradient distribution of the tunnel into the fluid dynamics equation to construct a basic diffusion model, and output a dynamic diffusion trajectory set; Processing the multimodal time series distribution of the spatiotemporal data cube through a spatiotemporal graph neural network to output a risk probability distribution matrix; The dynamic diffusion trajectory set and the risk probability distribution matrix are dynamically weighted and fused to generate the risk diffusion simulation model.

7. The integrated management method for mine wireless gateways according to claim 4, characterized in that: Performing lithologic stability analysis on the spatial positions of the multiple nodes to obtain multiple node static weights, including: Locally call the relevant geological exploration report of the target mine; extracting a plurality of rock formation stability coefficients from the associated geological exploration report using the plurality of node spatial positions as a guide; Calling local accident records according to the spatial positions of the multiple nodes to obtain accident frequencies of the multiple nodes; The static weights of the multiple nodes are obtained by normalizing the multiple rock formation stability coefficients and the multiple node accident frequencies.

8. The integrated management method for mine wireless gateways according to claim 4, characterized in that: Dynamically dividing the target mine into the honeycomb area grids according to the plurality of intersection node coordinates and the plurality of node weight data, including: Extracting multiple groups of topological edge dynamic weights of the multiple lane topological nodes based on the connection relationship between the nodes and the topological edges; Calculating the plurality of node static weights and the plurality of groups of topological edge dynamic weights by fusing them through an entropy weight method to obtain the plurality of node weight data; Multiple tunnel topology nodes are used as gridding starting points, and grid density is dynamically corrected according to the multiple node weight data to divide the target mine into the honeycomb area grids, wherein the grid weight density deviation of the K grid partitions meets the preset deviation scale.

9. The integrated management method for mine wireless gateways according to claim 5, characterized in that: Directed activation of a relay identification hierarchical topology is performed according to the multiple real-time risk zones, and multiple real-time relay identification sequences are output, including: Deploying the relay identification hierarchical topology in the target mine through signal coverage fitting; Performing identification energy consumption analysis on the coverage relationship between the risk source partition and the M risk diffusion partitions according to the relay identification hierarchical topology to obtain a first real-time relay identification sequence and M real-time relay identification sequences; The first real-time relay identification sequence and M real-time relay identification sequences constitute the multiple real-time relay identification sequences.

10. The integrated management system of mine wireless gateway is characterized by: Steps for implementing the integrated management method for mine wireless gateways according to any one of claims 1 to 9, wherein the integrated management system for mine wireless gateways comprises: A mine division processing module, configured to interactively obtain a tunnel topology structure of a target mine and divide the target mine into honeycomb area grids according to the tunnel topology structure; A monitoring deployment processing module is used to deploy K multimodal sensor arrays on K grid partitions in the cellular area grid by monitoring coverage fitting; A communication link construction module, configured to construct a communication link between the K multimodal sensor arrays and the K edge gateways, wherein the edge gateways have built-in lightweight AI chips; a risk diffusion simulation module, configured for the diffusion risk analysis platform to perform integrated simulation of risk diffusion paths based on the K multimodal time series features transmitted back by the K edge gateways, so as to locate multiple real-time risk zones, wherein the K edge gateways are connected to the diffusion risk analysis platform; a relay identification activation module, configured to perform a directed activation of a relay identification hierarchical topology according to the plurality of real-time risk zones, and output a plurality of real-time relay identification sequences; A coverage identification processing module is used to wake up the multiple real-time relay identification sequences to perform RFID coverage identification on the multiple real-time risk zones to obtain multiple real-time personnel distribution features; The resource allocation processing module is used to dynamically allocate rescue resources according to the multiple real-time personnel distribution characteristics.

Images