Coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion

Abstract

The invention discloses a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion, and relates to the field of mine shaft safety management, and the system comprises a pickup module which is used for uploading attitude information of an internal support structure of a coal mine shaft, constructing a support structure model based on the attitude information, and picking key point positions on the support structure module; the sensing module is used for sensing state information of an internal supporting structure of the coal mine shaft and internal environment information of the coal mine shaft; the evaluation module is used for receiving the state information and the environment information sensed by the sensing module, and evaluating the safety of the internal supporting structure of the coal mine shaft based on the state information and the environment information; multi-dimensional data are fused to construct a coal mine shaft internal supporting structure model, key point positions are accurately captured, parameters such as structure posture, vibration, position deviation and corrosive gas-liquid content are synchronously monitored, the structure safety is evaluated in real time by means of a dynamic calculation model, audio early warning is triggered when data are continuously abnormal, and the safety of a coal mine shaft is improved. And a time window is won for hidden danger investigation.

Description

Technical Field

[0001] The present invention relates to the technical field of mine safety management, and in particular to a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion. Background Art

[0002] The purpose of coal mine shaft structure safety management is to monitor and maintain shaft support, ventilation and other systems, detect structural hazards, prevent accidents such as collapse and water seepage, ensure personnel safety and normal operation of equipment, ensure safe production in coal mines, and avoid major safety risks and economic losses caused by structural problems.

[0003] The invention patent application with application number 202010643666.4 discloses a steel support structure safety monitoring and early warning system, including multiple measuring devices, multiple smart terminals, a management server and a cloud platform, wherein multiple measuring devices are arranged in the area to be monitored, for measuring the monitoring data of the area to be monitored; the smart terminal is communicatively connected with the multiple measuring devices in the sub-area to be monitored, including a data acquisition module, an early warning strategy module, a terminal sound and light alarm and a terminal LoRa communication module, the data acquisition module is used to communicate with the multiple measuring devices in the sub-area to be monitored, and collect the monitoring data measured by the measuring device in real time, the early warning strategy module is used to perform data management, risk assessment and early warning in the area to be monitored according to the monitoring data, and the sound and light alarm is in the early warning strategy module. The cloud platform is connected to the management server for receiving and storing the monitoring data of the management server. The application aims to solve the problem that "the monitoring area is not comprehensive enough, and the integrated design of on-site timely monitoring, result warning, alarm output and event recording cannot be realized. The warning reminder cycle is long and not timely, and the surrounding monitoring points cannot be reminded according to the warning monitoring data. The working environment safety of on-site monitoring personnel is poor."

[0004] However, for the safety monitoring of coal mine shaft structures, most existing technologies use regular inspections to manage the safety of coal mine shaft structures. This method has poor real-time performance and is affected by environmental factors and inspection locations, resulting in low accuracy.

[0005] Therefore, a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion is proposed. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the prior art, the present invention provides a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion, which can effectively solve the problems of the prior art.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] The present invention discloses a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion, comprising:

[0009] The picking module is used to upload the posture information of the internal support structure of the coal mine shaft, build the support structure model based on the posture information, and pick up key points on the support structure module; the perception module is used to perceive the status information of the internal support structure of the coal mine shaft and the internal environment information of the coal mine shaft; the evaluation module is used to receive the status information and environment information perceived by the perception module during operation, and evaluate the safety of the internal support structure of the coal mine shaft based on the status information and environment information; the monitoring module is used to receive the safety of the internal support structure of the coal mine shaft evaluated by the evaluation module in real time, set the early warning trigger threshold, and compare the early warning trigger threshold with the safety evaluation result of the internal support structure of the coal mine shaft to determine whether the internal support structure of the coal mine shaft is safe; the early warning module is used to issue a preset audio early warning prompt when the monitoring module determines that the internal support structure of the coal mine shaft is unsafe; the visualization module is used to mark the structural risk level of each area on the support structure model.

[0010] Furthermore, the posture information of the internal support structure of the coal mine shaft uploaded by the picking module includes: the structural size of the support structure, the distribution position of the support structure, and after the support structure model is built, all sub-model connection positions on the support structure model are captured, and the positions of the designed number are picked from all the captured sub-model connection positions and recorded as key points;

[0011] Among them, in the support structure model construction stage, independent model construction operations are performed on all components that make up the support structure based on the structural dimensions of the support structure in the support structure posture information, that is, the sub-models of the support structure model. Then, based on the distribution position of the support structure in the support structure posture information, each independently constructed model is placed in the corresponding distribution position and combined to obtain the support structure model.

[0012] Furthermore, when picking the key points, the number of picked designs follows: the larger the volume of the supporting structure model space, the more the number of picked designs; the more complex the supporting structure model structure, the more the number of picked designs; and the number of picked key points is not less than three;

[0013] The complexity of the support structure model is calculated by the following formula:

[0014]

[0015] Where: C is the complexity of the supporting structure model; V max 、E max 、F max The maximum number of vertices, edges, and faces in the support structure model; V min 、E min 、F min The minimum number of vertices, edges, and faces required to construct the model in the supporting structure model; L avg is the average connection length of the upper edge of the supporting structure model; L max is the diagonal length of the bounding box of the supporting structure model; V′ is the bounding box volume of the supporting structure model; V is the spatial volume of the supporting structure model;

[0016] in,

[0017] Where: v i 、v j are the coordinates of the two vertices of edge i; ||·||2 represents the Euclidean distance.

[0018] Furthermore, after the number of key point design picks is determined, the criticality of each captured sub-model connection position is calculated synchronously, and the sub-model connection positions are arranged in descending order based on the criticality of the sub-model connection positions, and a corresponding number of sub-model connection positions are picked up at the front positions of the sub-model connection positions arranged in descending order as key points;

[0019] K(a)=N a ×α+D a ×β;

[0020] Where: K(a) is the criticality of the sub-model connection position a; N a 、D a is the neighborhood connection contribution and spatial distribution contribution of the sub-model connection position a; α and β are weight coefficients;

[0021] Among them, the weight coefficients α and β are both non-zero positive numbers, and the sum of the weight coefficients α and β is 1. After the complexity of the sub-model connection position source sub-model is calculated based on the complexity calculation logic of the supporting structure model, the higher the complexity of the sub-model connection position source sub-model, the larger the value of the weight coefficient β.

[0022] Furthermore, the N a 、D a The calculation formulas are:

[0023]

[0024] Where: EdgeCount(a) is the number of edges connected to the sub-model connection position a; EdgeCount max 、EdgeCount min is the maximum and minimum number of edges connecting all points of the sub-model at the sub-model connection position a; StructuralFactor(a) is the structural factor; Distance(a,Centroid) is the Euclidean distance from the sub-model connection position a to the centroid of its source sub-model; MaxDistance is the maximum distance from all points on the sub-model at the sub-model connection position a to the centroid; SparsityFactor(a) is the sparsity factor;

[0025] Among them, if the sub-model connection position a is located at a sharp corner or edge of the model, StructuralFactor(a) = 1.5; if it is located in a smooth surface area of ​​the model, StructuralFactor(a) = 1; if the point density in the neighborhood of the sub-model connection position a is less than half of the average point density of the model, SparsityFactor(a) = 1.2; if the point density in the neighborhood is higher than twice the average point density of the model, SparsityFactor(a) = 0.8.

[0026] Furthermore, the number of the sensing modules is set based on the number of key points picked up by the picking module, so that each key point is deployed with a group of sensing modules, each group of the sensing modules is integrated with a position sensor, a vibration sensor, and a corrosive gas and liquid content sensor, and each group of the sensing modules operates synchronously and continuously based on a preset cycle;

[0027] The perception module is internally provided with a recording unit, and the recording unit is used to store state information and environmental information perceived by the perception module during operation.

[0028] Furthermore, the safety evaluation logic of the internal support structure of the coal mine shaft in the evaluation module is expressed as follows:

[0029]

[0030] Where: Q is the safety performance value of the internal support structure of the coal mine shaft; is the similarity quantization value corresponding to the two vibration signals with the smallest similarity in the historical vibration signals perceived by the vibration sensor; x is the total number of position sensors; u y is the total amount of historical position information sensed by the yth position sensor; L(d v ,d v+1 ) is the offset value between the vth sensing position coordinate and the v+1th sensing position coordinate of the yth position sensor; MAX ρThe maximum corrosive gas and liquid content historically sensed by the corrosive gas and liquid content sensor;

[0031] Among them, the monitoring module continuously receives the safety evaluation results of the internal supporting structure of the coal mine shaft. When the latest three evaluation results decline continuously, the early warning module is triggered to run synchronously.

[0032] Furthermore, a segmentation unit is provided inside the visualization module, and the segmentation unit is used to segment the bounding box of the support structure model. The number of segmentations is subject to the following: the higher the accuracy of the system end user monitoring requirement, the more segmentations are required, and vice versa, the fewer segmentations are required. The segmentation result is: the volume of each sub-bounding box is equal, and the length, width and height are consistent. At the same time, the number of sub-bounding boxes in the length, width and height directions is equal;

[0033] The incomplete sub-model contained in the sub-bounding box still belongs to the sub-bounding box.

[0034] Furthermore, the visualization module applies the evaluation module to perform a security evaluation on the sub-model to which each sub-bounding box belongs, and sorts the sub-bounding boxes from small to large based on the evaluation results. The sorted sub-bounding boxes are then assigned serial numbers so that the sub-bounding box with the smallest evaluation result value is numbered 1. The serial numbers of the sub-bounding boxes are used as risk levels, i.e., the smaller the risk level value, the higher the risk.

[0035] Among them, the operation of marking the structural risk level of each area on the supporting structure model in the visualization module is the operation of marking each sub-bounding box. When marking each sub-bounding box, each sub-bounding box is marked in the form of a text information pop-up window, and the content of the text information pop-up window is the risk level of the sub-bounding box.

[0036] Furthermore, the picking module is interactively connected to the perception module through a wireless network, the perception module is interactively connected to a recording unit through a wireless network, the perception module is interactively connected to the evaluation module and the monitoring module through a wireless network, the monitoring module is interactively connected to the early warning module and the visualization module through a wireless network, and the visualization module is interactively connected to a segmentation unit through a wireless network.

[0037] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0038] The present invention provides a coal mine shaft structural safety monitoring and early warning system based on multi-parameter fusion. During operation, the system integrates multi-dimensional data to construct a model of the internal support structure of the coal mine shaft and accurately captures key points. It can simultaneously monitor multiple parameters such as structural posture, vibration, position offset, and corrosive gas and liquid content. Relying on a dynamic calculation model, it assesses structural safety in real time and triggers an audio warning when the data is continuously abnormal, thus creating a time window for hidden danger investigation.

[0039] The system also intelligently determines the number of monitoring points based on model complexity and spatial volume, quantifying the criticality of each point by combining neighborhood connectivity contribution, spatial distribution characteristics, and structural morphology to ensure monitoring coverage of key areas. The visualization module divides the model bounding box into equal volumes, provides a refined safety rating for each sub-area, and annotates the risk level with text pop-ups, visually presenting structural weaknesses and assisting managers in quickly locating high-risk areas. This enables multi-level safety monitoring from global to local levels, effectively improving the scientific nature, accuracy, and timeliness of coal mine shaft structural safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] To more clearly illustrate the embodiments of the present invention or the technical solutions in 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 only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0041] Figure 1 This is a structural diagram of a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion. DETAILED DESCRIPTION

[0042] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] The present invention will be further described below with reference to the embodiments.

[0044] Example:

[0045] This embodiment is a coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion, such as Figure 1 As shown, including:

[0046] The picking module is used to upload the posture information of the internal support structure of the coal mine shaft, build the support structure model based on the posture information, and pick key points on the support structure module;

[0047] The internal support structure posture information of the coal mine shaft uploaded in the picking module includes: the structural dimensions of the support structure, the distribution position of the support structure. After the support structure model is built, all sub-model connection positions on the support structure model are captured. Among all the captured sub-model connection positions, the designed number of positions are picked and recorded as key points.

[0048] In the support structure model construction stage, all components constituting the support structure are independently modeled based on the structural dimensions of the support structure in the support structure posture information, i.e., sub-models of the support structure model. Based on the distribution positions of the support structures in the support structure posture information, the independently constructed models are placed at corresponding distribution positions and combined to obtain the support structure model.

[0049] When picking key points, the number of picked design points follows: the larger the volume of the support structure model, the more design picks are needed; the more complex the support structure model, the more design picks are needed. The number of picked key points should be no less than three.

[0050] The complexity of the supporting structure model is calculated using the following formula:

[0051]

[0052] Where: C is the complexity of the supporting structure model; V max 、E max 、F max The maximum number of vertices, edges, and faces in the support structure model; V min 、E min 、F min The minimum number of vertices, edges, and faces required to construct the model in the supporting structure model; L avg is the average connection length of the upper edge of the supporting structure model; L max is the diagonal length of the bounding box of the supporting structure model; V′ is the bounding box volume of the supporting structure model; V is the spatial volume of the supporting structure model;

[0053] in,

[0054] Where: v i 、v j are the coordinates of the two vertices of edge i; ||·||2 represents the Euclidean distance;

[0055] The complexity of the supporting structure model is calculated through the above logical formula to provide support for the subsequent module operation of the system in this embodiment;

[0056] After the number of key point design picks is determined, the criticality of each captured sub-model connection position is calculated synchronously, and the sub-model connection positions are sorted in descending order based on the criticality of the sub-model connection positions. The corresponding number of sub-model connection positions are picked up at the front of the sub-model connection positions in descending order as key points;

[0057] K(a)=N a ×α+D a ×β;

[0058] Where: K(a) is the criticality of the sub-model connection position a; N a 、D a is the neighborhood connection contribution and spatial distribution contribution of the sub-model connection position a; α and β are weight coefficients;

[0059] Among them, the weight coefficients α and β are both non-zero positive numbers, and the sum of the weight coefficients α and β is 1. Based on the complexity calculation logic of the supporting structure model, after the complexity of the sub-model connection position source sub-model is calculated, the higher the complexity of the sub-model connection position source sub-model, the larger the value of the weight coefficient β;

[0060] The above logic formula is used to define the logic of the picking module picking up key points, so as to provide support for the deployment of the perception module in the system.

[0061] N a 、D a The calculation formulas are:

[0062]

[0063] Where: EdgeCount(a) is the number of edges connected to the sub-model connection position a; EdgeCount max 、EdgeCount min is the maximum and minimum number of edges connecting all points of the sub-model at the sub-model connection position a; StructuralFactor(a) is the structural factor; Distance(a,Centroid) is the Euclidean distance from the sub-model connection position a to the centroid of its source sub-model; MaxDistance is the maximum distance from all points on the sub-model at the sub-model connection position a to the centroid; SparsityFactor(a) is the sparsity factor;

[0064] If the sub-model connection position a is located at a sharp corner or edge of the model, StructuralFactor(a) = 1.5; if it is located on a smooth surface of the model, StructuralFactor(a) = 1; if the point density of the neighborhood where the sub-model connection position a is located is less than half of the average point density of the model, SparsityFactor(a) = 1.2; if the point density of the neighborhood where the sub-model connection position a is located is more than twice the average point density of the model, SparsityFactor(a) = 0.8;

[0065] Through the above logical formula, the parameter values ​​used in the calculation process of K(a) are limited;

[0066] A perception module is used to perceive the status information of the internal support structure of the coal mine shaft and the internal environment information of the coal mine shaft;

[0067] The number of sensing modules is set based on the number of key points picked up by the picking module, so that each key point is deployed with a set of sensing modules. Each set of sensing modules is integrated with a position sensor, a vibration sensor, and a corrosive gas and liquid content sensor. Each set of sensing modules runs synchronously and continuously based on a preset cycle.

[0068] The perception module is internally provided with a recording unit, which is used to store the state information and environmental information perceived by the perception module during operation;

[0069] An evaluation module is used to receive the state information and environmental information sensed by the perception module and evaluate the safety of the internal support structure of the coal mine shaft based on the state information and environmental information;

[0070] The safety evaluation logic of the internal support structure of the coal mine shaft in the evaluation module is expressed as follows:

[0071]

[0072] Where: Q is the safety performance value of the internal support structure of the coal mine shaft; is the similarity quantization value corresponding to the two vibration signals with the smallest similarity in the historical vibration signals perceived by the vibration sensor; x is the total number of position sensors; u y is the total amount of historical position information sensed by the yth position sensor; L(d v ,d v+1 ) is the offset value between the vth sensing position coordinate and the v+1th sensing position coordinate of the yth position sensor; MAX ρ The maximum corrosive gas and liquid content historically sensed by the corrosive gas and liquid content sensor;

[0073] The safety of the internal support structure of the coal mine shaft is evaluated through the above logical formula;

[0074] The monitoring module continuously receives safety evaluation results of the internal support structure of the coal mine shaft. When the latest three evaluation results decrease continuously, the early warning module is triggered to run synchronously.

[0075] The monitoring module is used to receive the safety of the internal support structure of the coal mine shaft in real time from the cloud evaluation module, set the early warning trigger threshold, and compare the early warning trigger threshold with the safety evaluation results of the internal support structure of the coal mine shaft to determine whether the internal support structure of the coal mine shaft is safe;

[0076] The early warning module is used to issue a preset audio early warning prompt when the monitoring module determines that the internal support structure of the coal mine shaft is unsafe;

[0077] A visualization module is used to mark the structural risk level of each area on the supporting structure model;

[0078] A segmentation unit is set up inside the visualization module. The segmentation unit is used to segment the bounding box of the supporting structure model. The number of segmentations follows the following rules: the higher the monitoring accuracy required by the system end user, the more segmentations are required, and vice versa. The segmentation result is: the volume of each sub-bounding box is equal, and the length, width and height are consistent. At the same time, the number of sub-bounding boxes in the length, width and height directions is equal;

[0079] Among them, the incomplete sub-model contained in the sub-bounding box still belongs to the sub-bounding box;

[0080] The visualization module uses the evaluation module to evaluate the security of the sub-model to which each sub-bounding box belongs, and sorts the sub-bounding boxes from small to large based on the evaluation results. The sorted sub-bounding boxes are then assigned serial numbers so that the sub-bounding box with the smallest evaluation result value is numbered 1. The serial number of each sub-bounding box is used as the risk level, that is, the smaller the risk level value, the higher the risk;

[0081] The operation of marking the structural risk level of each area on the supporting structure model in the visualization module is to mark each sub-bounding box. When marking each sub-bounding box, each sub-bounding box is marked in the form of a text information pop-up window, and the content of the text information pop-up window is the risk level of the sub-bounding box;

[0082] The picking module is interactively connected to the perception module through a wireless network. The perception module is interactively connected to a recording unit through a wireless network. The perception module is interactively connected to the evaluation module and the monitoring module through a wireless network. The monitoring module is interactively connected to the early warning module and the visualization module through a wireless network. The visualization module is interactively connected to a segmentation unit through a wireless network.

[0083] In this embodiment, the picking module uploads the posture information of the internal support structure of the coal mine shaft, constructs the support structure model based on the posture information, picks key points on the support structure module, and the perception module is post-operated to perceive the status information of the internal support structure of the coal mine shaft and the internal environment information of the coal mine shaft. The recording unit synchronously stores the status information and environment information perceived by the perception module. The evaluation module further receives the status information and environment information perceived by the perception module, and evaluates the safety of the internal support structure of the coal mine shaft based on the status information and environment information. The monitoring module is used to receive the safety of the internal support structure of the coal mine shaft evaluated by the evaluation module cloud in real time, set an early warning trigger threshold, and compare the early warning trigger threshold with the safety evaluation result of the internal support structure of the coal mine shaft to determine whether the internal support structure of the coal mine shaft is safe. When the monitoring module determines that the internal support structure of the coal mine shaft is unsafe, the early warning module issues a preset audio early warning prompt. Finally, the visualization module applies the segmentation unit to segment the bounding box of the support structure model and marks the structural risk level of each area on the support structure model.

[0084] Through the operation of the system in the above embodiment, a real-time, highly intelligent, low-dependence on manual management and accurate monitoring early warning system is provided for the coal mine shaft structure, which can effectively protect the performance of the coal mine shaft structure and ensure that coal mine construction can be carried out in a safe environment for a long time.

[0085] In summary, the system in the above embodiment constructs a model of the internal support structure of a coal mine shaft by integrating multi-dimensional data and accurately captures key points. It can simultaneously monitor multiple parameters such as structural posture, vibration, position offset, and corrosive gas and liquid content. Relying on a dynamic calculation model, it assesses structural safety in real time and triggers audio warnings when data is continuously abnormal, creating a time window for potential hazards to be detected. At the same time, the system intelligently determines the number of monitoring points based on model complexity and spatial volume, and quantifies the criticality of points by combining neighborhood connectivity contribution, spatial distribution characteristics, and structural morphology to ensure monitoring coverage of key areas. The visualization module divides the model bounding box into equal volumes, performs a refined safety rating on each sub-area, and annotates the risk level with a text pop-up window, intuitively presenting structural weaknesses and assisting managers in quickly locating high-risk areas. This enables multi-level safety monitoring from the global to the local level, effectively improving the scientific nature, accuracy, and timeliness of coal mine shaft structural safety monitoring.

[0086] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion, characterized in that: include: The picking module is used to upload the posture information of the internal support structure of the coal mine shaft, build the support structure model based on the posture information, and pick key points on the support structure module; A perception module is used to perceive the status information of the internal support structure of the coal mine shaft and the internal environment information of the coal mine shaft; An evaluation module is used to receive the state information and environmental information sensed by the perception module and evaluate the safety of the internal support structure of the coal mine shaft based on the state information and environmental information; The monitoring module is used to receive the safety of the internal support structure of the coal mine shaft in real time from the cloud evaluation module, set the early warning trigger threshold, and compare the early warning trigger threshold with the safety evaluation results of the internal support structure of the coal mine shaft to determine whether the internal support structure of the coal mine shaft is safe; The early warning module is used to issue a preset audio early warning prompt when the monitoring module determines that the internal support structure of the coal mine shaft is unsafe; The visualization module is used to mark the structural risk level of each area on the supporting structure model.

2. A coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 1, characterized in that: The posture information of the internal support structure of the coal mine shaft uploaded by the picking module includes: the structural size of the support structure, the distribution position of the support structure, and after the support structure model is built, all the sub-model connection positions on the support structure model are captured, and the positions of the designed number are picked from all the captured sub-model connection positions and recorded as key points; Among them, in the support structure model construction stage, independent model construction operations are performed on all components that make up the support structure based on the structural dimensions of the support structure in the support structure posture information, that is, the sub-models of the support structure model. Then, based on the distribution position of the support structure in the support structure posture information, each independently constructed model is placed in the corresponding distribution position and combined to obtain the support structure model.

3. The coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 1 is characterized in that: When picking the key points, the number of picked design points follows: the larger the volume of the supporting structure model space, the more the number of design picks, the more complex the supporting structure model structure, the more the number of design picks, and the number of picked key points is not less than three; The complexity of the support structure model is calculated by the following formula: Where: C is the complexity of the supporting structure model; V max 、E max 、F max The maximum number of vertices, edges, and faces in the support structure model; V min 、E min 、F min The minimum number of vertices, edges, and faces required to construct the model in the supporting structure model; L avg is the average connection length of the upper edge of the supporting structure model; L max is the diagonal length of the bounding box of the supporting structure model; V′ is the bounding box volume of the supporting structure model; V is the spatial volume of the supporting structure model; in, Where: v i 、v j are the coordinates of the two vertices of edge i; ||·||2 represents the Euclidean distance.

4. A coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 3, characterized in that: After the number of key point design picks is determined, the criticality of each captured sub-model connection position is calculated synchronously, and the sub-model connection positions are arranged in descending order based on the criticality of the sub-model connection positions, and a corresponding number of sub-model connection positions are picked up at the front positions of the sub-model connection positions arranged in descending order as key points; K(a)=N a ×α+D a ×β; Where: K(a) is the criticality of the sub-model connection position a; N a 、D a is the neighborhood connection contribution and spatial distribution contribution of the sub-model connection position a; α and β are weight coefficients; Among them, the weight coefficients α and β are both non-zero positive numbers, and the sum of the weight coefficients α and β is 1. After the complexity of the sub-model connection position source sub-model is calculated based on the complexity calculation logic of the supporting structure model, the higher the complexity of the sub-model connection position source sub-model, the larger the value of the weight coefficient β.

5. A coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 4, characterized in that: The N a 、D a The calculation formulas are: Where: EdgeCount(a) is the number of edges connected to the sub-model connection position a; EdgeCount max 、EdgeCount min is the maximum and minimum number of edges connecting all points of the sub-model at the sub-model connection position a; StructuralFactor(a) is the structural factor; Distance(a,Centroid) is the Euclidean distance from the sub-model connection position a to the centroid of its source sub-model; MaxDistance is the maximum distance from all points on the sub-model at the sub-model connection position a to the centroid; SparsityFactor(a) is the sparsity factor; Among them, if the sub-model connection position a is located at a sharp corner or edge of the model, StructuralFactor(a) = 1.5; if it is located in a smooth surface area of ​​the model, StructuralFactor(a) = 1; if the point density in the neighborhood of the sub-model connection position a is less than half of the average point density of the model, SparsityFactor(a) = 1.2; if the point density in the neighborhood is higher than twice the average point density of the model, SparsityFactor(a) = 0.

8.

6. The coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 1 is characterized in that: The number of sensing modules is set based on the number of key points picked up by the picking module, so that each key point is deployed with a group of sensing modules. Each group of sensing modules is integrated with a position sensor, a vibration sensor, and a corrosive gas and liquid content sensor. Each group of sensing modules runs synchronously and continuously based on a preset cycle. The perception module is internally provided with a recording unit, and the recording unit is used to store state information and environmental information perceived by the perception module during operation.

7. The coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 1 is characterized in that: The safety evaluation logic of the internal support structure of the coal mine shaft in the evaluation module is expressed as follows: Where: Q is the safety performance value of the internal support structure of the coal mine shaft; is the similarity quantization value corresponding to the two vibration signals with the smallest similarity in the historical vibration signals perceived by the vibration sensor; x is the total number of position sensors; u y is the total amount of historical position information sensed by the yth position sensor; L(d v ,d v+1 ) is the offset value between the vth sensing position coordinate and the v+1th sensing position coordinate of the yth position sensor; MAX ρ The maximum corrosive gas and liquid content historically sensed by the corrosive gas and liquid content sensor; Among them, the monitoring module continuously receives the safety evaluation results of the internal supporting structure of the coal mine shaft. When the latest three evaluation results decline continuously, the early warning module is triggered to run synchronously.

8. The coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 1 is characterized in that: The visualization module is internally provided with a segmentation unit, which is used to segment the bounding box of the support structure model. The number of segmentations is subject to the following conditions: the higher the monitoring accuracy required by the system end user, the more segmentations are required, and vice versa, the fewer segmentations are required. The segmentation result is: the volumes of the sub-bounding boxes are equal, and the length, width and height are consistent. At the same time, the number of sub-bounding boxes in the length, width and height directions is equal. The incomplete sub-model contained in the sub-bounding box still belongs to the sub-bounding box.

9. The coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 8 is characterized in that: The visualization module uses the evaluation module to perform a security evaluation on the sub-model to which each sub-bounding box belongs, and sorts the sub-bounding boxes from small to large based on the evaluation results. The sorted sub-bounding boxes are then assigned serial numbers so that the sub-bounding box with the smallest evaluation result value is numbered 1. The serial numbers of the sub-bounding boxes are used as risk levels, i.e., the smaller the risk level value, the higher the risk. Among them, the operation of marking the structural risk level of each area on the supporting structure model in the visualization module is the operation of marking each sub-bounding box. When marking each sub-bounding box, each sub-bounding box is marked in the form of a text information pop-up window, and the content of the text information pop-up window is the risk level of the sub-bounding box.

10. The coal mine shaft structure safety monitoring and early warning system based on multi-parameter fusion according to claim 1, characterized in that: The picking module is interactively connected to the perception module via a wireless network, the perception module is interactively connected to a recording unit via a wireless network, the perception module is interactively connected to the evaluation module and the monitoring module via a wireless network, the monitoring module is interactively connected to the early warning module and the visualization module via a wireless network, and the visualization module is interactively connected to a segmentation unit via a wireless network.

Images