Coal mine roof collapse real-time monitoring method and system based on laser radar

Abstract

The invention discloses a coal mine roof collapse real-time monitoring method and system based on a laser radar, and belongs to the technical field of coal mine safety monitoring. According to the method, an explosion-proof laser radar is deployed on a hydraulic support of a coal mining working face of a coal mine, and a top plate is periodically scanned to obtain point cloud data; after preprocessing, calculating the volume in parallel by adopting a convex hull method and an inclined bounding box method, and optimizing the weight in combination with a stratigraphic dip angle and geological conditions to realize volume fusion accurate calculation; and comparing the final volume with a preset safety threshold value, triggering multi-stage alarm and generating a data + video evidence chain when continuous N frames exceed the threshold value, and synchronously uploading the data + video evidence chain to a coal mine intelligent management and control platform to realize periodic continuous monitoring. According to the method, the roof collapse risk is upgraded from qualitative judgment to quantitative early warning, the method has the advantages of being high in real-time performance, outstanding in anti-interference capacity, high in system integration degree and the like, the defects that an existing monitoring method is high in subjectivity and single in information dimension, and quantitative early warning cannot be achieved are effectively overcome, and the method meets the development requirement of an intelligent mine.

Description

Technical Field

[0001] This invention relates to the field of coal mine safety monitoring technology, specifically to a method and system for real-time monitoring of coal mine roof collapse based on lidar, which is particularly suitable for three-dimensional monitoring and collapse early warning of the suspended roof area in coal mining faces in smart mines, realizing integrated intelligent control of monitoring, early warning and management. Background Technology

[0002] During underground coal mining operations, if the coal seam that has not collapsed at the top of the working face (i.e., the overhanging roof) accumulates over a long period of time, it can easily trigger major safety accidents such as roof collapse when its volume or covered area exceeds the safety threshold, seriously threatening the lives of workers and the mine's production order. Therefore, real-time and accurate monitoring of the overhanging roof area, and risk warning based on the monitoring results, is a crucial link in ensuring safe coal mine production.

[0003] Currently, monitoring of coal mine roof collapse mainly relies on manual observation, pressure sensor monitoring, or ordinary video surveillance, but these existing technologies have significant drawbacks: 1. Manual observation is limited by labor costs and working hours, making it impossible to achieve 24-hour uninterrupted monitoring. Furthermore, the judgment results are highly subjective and difficult to quantify. Often, by the time danger is discovered, the best time to deal with it has already been missed, resulting in a serious lag. 2. Pressure sensors can only sense pressure changes in the supporting structure and cannot directly obtain the spatial morphology of the roof rock layer and the actual volume / area information of the overhang. The information dimension is limited and it is difficult to fully reflect the risk status. 3. Ordinary video surveillance is easily affected by the complex underground environment. Dim lighting and high dust concentration will seriously interfere with the monitoring effect and cannot provide accurate three-dimensional geometric data, making it impossible to achieve early warning based on quantitative indicators; 4. Existing technologies generally lack the ability to accurately calculate the volume / area of ​​suspended ceilings, and cannot achieve automatic alarms based on set quantitative thresholds, resulting in insufficient scientific rigor and reliability of early warnings.

[0004] LiDAR technology has been successfully applied in fields such as autonomous driving and topographic mapping, and its advantages in 3D spatial scanning and volume measurement have been verified. However, a search revealed no complete solution for applying LiDAR technology to roof collapse monitoring in underground coal mines and deeply integrating it with intelligent coal mine management platforms to achieve real-time early warning. Existing LiDAR technologies are not adapted to the special environment of underground coal mines (such as high dust, strong vibration, and electromagnetic interference), and lack algorithmic processing logic and system interaction mechanisms that are closely integrated with roof collapse monitoring scenarios, thus failing to meet the actual needs of safe coal mine production.

[0005] Therefore, there is an urgent need for a technical solution that can overcome the shortcomings of existing technologies, achieve precise quantitative monitoring and real-time early warning of the overhanging roof area, and seamlessly integrate with the coal mine intelligent management and control system, so as to improve the intelligence level of coal mine roof monitoring and ensure safe production in the mine. Summary of the Invention

[0006] This invention aims to address the problems of existing coal mine roof collapse monitoring methods, such as strong subjectivity, limited information dimensions, inability to provide quantitative early warning, and weak anti-interference capabilities. It provides a real-time monitoring method and system for coal mine roof collapse based on lidar, with specific objectives including: 1. Achieve non-contact, high-precision, all-weather 3D scanning of the suspended roof area, and complete accurate quantitative calculation of the suspended roof volume; 2. Based on quantitative volume indicators, safety thresholds are set to achieve automatic and real-time early warning of roof collapse risks, guiding workers to evacuate in a timely manner and take preventive measures; 3. Construct an integrated system that is deeply integrated with the coal mine intelligent management and control platform to realize functions such as automatic uploading of monitoring data, hierarchical management of alarms, retention of evidence chains, and trend analysis, thereby improving the level of intelligence and precision in coal mine safety production.

[0007] According to a first aspect of the present invention, the present invention provides a method for real-time monitoring of roof collapse in coal mines based on lidar, the method comprising the following steps: S1: LiDAR Deployment: Explosion-proof LiDAR is installed on the hydraulic support of the coal mining face. The scanning angle of the LiDAR is adjusted according to the monitoring area to ensure complete coverage of the roof area to be monitored, so as to achieve a blind-spot-free scan of the suspended roof area.

[0008] S2: Point cloud data acquisition: Control the lidar to periodically scan the roof at preset time intervals (which can be dynamically adjusted according to the risk level) to collect the original point cloud data of the roof and the collapsed body in real time, providing a data basis for subsequent volume calculation.

[0009] S3: Point Cloud Data Preprocessing: Performs a series of processing steps on the collected raw point cloud data to improve data quality, specifically including: 1. Noise filtration: Removes random noise points caused by factors such as underground dust and equipment vibration; 2. Multi-site cloud registration: If multiple lidars are used for collaborative monitoring, the point cloud data of different sites need to be unified under the same coordinate system, such as the world coordinate system or the camera coordinate system. 3. Coordinate System 1: Convert the original polar coordinate point cloud data of the lidar into a 3D point cloud in the world coordinate system or camera coordinate system suitable for volume calculation; 4. Abnormal point removal: The variable-angle-based feedback density algorithm is adopted to delete the abnormal reflection feedback points caused by inconsistent scanning frequencies and low object reflectivity. The specific steps are as follows: S31: Calculate the local density D(i) of point i. The calculation formula is: D(i) = N(i) / [π×R²], where N(i) represents the number of neighboring points within a radius R centered on point i, and R is the search radius; S32: Calculate the weighted density WD(i) of point i. The calculation formula is: WD(i) = D(i)×I(i) / I_avg, where I(i) is the reflection intensity of point i, and I_avg is the average reflection intensity of all points; S33: Calculate the adaptive threshold T(θ). The calculation formula is: T(θ) = T0×[1 + k×|sin(θ)|], where T0 is the reference threshold, θ is the scanning angle, and k is the angle correction coefficient with a value range of 0.1 - 0.3; S34: If WD(i) < T(θ), then determine that point i is an abnormal reflection feedback point and delete it.

[0010] S4: Parallel calculation of multiple algorithms: 1. Calculation by convex hull method: The convex hull method is a commonly used geometric modeling method for calculating the volume of 3D point clouds. Its core principle is to find the smallest convex polyhedron (i.e., convex hull) that can completely enclose all the point cloud data of the collapsed body. By calculating the internal space volume of this convex polyhedron, the maximum outer envelope volume V_convex of the collapsed body is obtained. The advantage of this method is its strong inclusiveness for discrete point clouds, which can quickly adapt to the irregular spatial morphology of the collapsed body. Even if there are local missing points in the point cloud (such as partial data missing caused by underground dust occlusion), it can still completely cover the target area through convex hull construction, avoiding volume miscalculation caused by data gaps. Therefore, it is suitable for directly characterizing the overall spatial occupancy scale of the collapsed body and serving as a basic reference for volume calculation.

[0011] 2. Calculation by bounding box method: The inclined bounding box method adopted in this invention is an optimized upgrade of the traditional axis-aligned bounding box method. Its core principle is to first extract the true formation attitude (i.e., roof dip angle α and floor dip angle β) from the roof / floor point cloud data, and then construct the smallest bounding box consistent with the formation inclination direction based on this inclination angle, rather than constructing a rectangular box along the coordinate axes. The volume V_box is obtained by calculating the volume of the inclined bounding box. This method can accurately match the natural inclination morphology of the coal mine roof / floor, effectively eliminating the volume calculation deviation (systematic error) caused by the inconsistency between the traditional axis-aligned bounding box and the formation attitude. It is especially suitable for characterizing the volume of the overhanging roof area significantly affected by the formation dip angle, making the calculation result more consistent with the actual underground geological structure.

[0012] S5: Precise calculation of volume fusion: To improve the accuracy and fit of volume calculations, weight parameters are optimized based on stratigraphic dip angle and geological conditions (rock quality, fault density, etc.). A weighted fusion calculation of V_convex and V_box is then performed to obtain the final volume V_final of the collapse body. Specifically, the V_convex method of the convex hull method focuses on reflecting the actual spatial location of the collapse body, while the V_box method of the inclined bounding box method focuses on matching the stratigraphic attitude to eliminate systematic errors; the two are highly complementary. The weight calculation employs a specifically designed formula that fully considers geological factors such as roof stability, floor stability, rock quality indicators, and fault density. The weight ratio of the two algorithms can be dynamically adjusted according to different geological conditions to ensure that the calculation results highly match the actual geological structure, balancing the completeness and accuracy of the volume calculation.

[0013] Among them, the weights W_c of the convex hull method and W_b of the bounding box method are satisfied with the constraint W_c+W_b=1. The final volume of the collapsed body V_final=W_c×V_convex+W_b×V_box is calculated by the weighted formula. The formula for calculating W_c is: W_c = W_base_c + ΔW_roof + ΔW_floor - ΔW_geo; ΔW_roof=k_r×|sin(α)|×S_r, where α is the roof inclination angle, S_r is the roof stability (range [0,1], 1 indicates the highest stability), and k_r is the roof influence coefficient (range [0.1,0.2]). ΔW_floor=k_f×|sin(β)|×S_f, where β is the floor tilt angle, S_f is the floor stability (range [0,1], 1 indicates the highest stability), and k_f is the floor influence coefficient (range [0.1,0.2]). ΔW_geo=k_g×(1-RQD / 100)×(1+D_f), where RQD is the rock quality index (range [0,100]), D_f is the fault density coefficient (range [0,1]), and k_g is the geological influence coefficient (range [0.2,0.3]).

[0014] S6: Threshold judgment and multi-level alarm, specifically including: Threshold comparison: The final volume V_final is compared with the preset safety threshold (determined in real time based on factors such as tunnel size, support capacity, and geological conditions); Alarm determination: If V_final exceeds the safety threshold for N consecutive frames, it is determined to be a valid alarm, the system status is set to 1 and the alarm start time is recorded; if V_final is below the safety threshold for M consecutive frames, it is determined to be an alarm cleared, the status is set to -1 and the end time is recorded. Multi-level alarm: After a valid alarm is triggered, a three-level alarm mechanism is activated simultaneously, including on-site audible and visual alarms, monitoring center alerts, and mobile terminal push notifications, which respectively realize on-site personnel evacuation warnings, emergency visualization at the dispatch center, and precise notifications to management personnel; Evidence chain generation: When an alarm is triggered, the system automatically captures or records on-site video at the moment of the alarm (such as RTSP stream screenshots or short videos), and associates it with alarm information (volume data, alarm time, monitoring location, etc.) to form a complete evidence chain of "data + video".

[0015] S7: System integration and closed-loop monitoring, specifically including: Data Upload: Simultaneously upload monitoring data (raw point cloud data, preprocessed data, final volume data), alarm information, and evidence chain to the coal mine intelligent management and control platform; Data storage: All monitoring data is stored in a database for subsequent risk trend analysis and prediction; Periodic monitoring: The system automatically executes a new round of monitoring according to preset strategies (for example, the LiDAR scanning frequency and safety threshold can be adjusted according to the risk level), forming a continuous and closed-loop monitoring and management system.

[0016] According to a second aspect of the present invention, the present invention also provides a real-time monitoring system for coal mine roof collapse based on lidar, the system comprising the following functional modules: LiDAR deployment module: Used to install lidar on the hydraulic support of the coal mining face and adjust the scanning angle to cover the roof area to be monitored; Data acquisition module: used to control the lidar to periodically scan the top plate at preset time intervals and collect the original point cloud data of the top plate and the collapsed body; Data preprocessing module: used to perform noise filtering, multi-site cloud registration, coordinate system unification, and outlier removal operations on the raw point cloud data; Multi-algorithm computation module: This module performs parallel computation using multiple algorithms on the preprocessed point cloud data. It includes a convex hull computation unit and a bounding box computation unit, which execute the two volume calculation logics described in step S4, respectively, outputting V_convex and V_box. The convex hull computation unit has built-in convex hull construction sub-units and volume calculation sub-units, responsible for quickly generating the minimum convex polyhedron of the collapse point cloud and calculating its volume. The bounding box computation unit has built-in dip angle extraction sub-units and inclined bounding box construction sub-units, first accurately extracting the stratum dip angle, then constructing an inclined bounding box matching the stratum attitude and completing the volume calculation. Parallel computation of these two sub-units improves the overall volume calculation efficiency.

[0017] Volume Fusion Module: This module determines the weights of each calculation result and calculates the final volume of the collapsed body through weighted fusion. Specifically, it includes a weight calculation unit and a weighted fusion unit. First, it calculates the weights W_c and W_b using specific formulas, and then performs weighted fusion to obtain the final volume V_final. Threshold judgment and alarm module: This module compares the final volume of the collapsed body V_final with a preset safety threshold and outputs alarm information based on the comparison result. Specifically, this module includes a threshold comparison unit, an alarm judgment unit, a multi-level alarm unit, and an evidence chain generation unit, and executes the threshold judgment, alarm triggering, and evidence chain generation logic described in step S6. System integration module: used to upload monitoring data, alarm information and evidence chain to the coal mine intelligent management and control platform to realize data storage, trend analysis and periodic closed-loop monitoring.

[0018] According to a third aspect of the present invention, a terminal device is provided, comprising: Processor; and A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0019] According to a fourth aspect of the present invention, a non-transitory machine-readable storage medium is provided, on which executable code is stored, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0020] Compared with the prior art, the present invention has the following significant advantages: Achieving precise quantitative early warning: Upgrading traditional qualitative risk assessment to volume-based quantitative early warning, through multi-algorithm fusion and geological factor weighted optimization, the volume calculation accuracy is high, and the early warning results are scientific and reliable, effectively improving the accuracy of roof collapse risk identification; Strong real-time and continuous performance: The automated monitoring process enables 24 / 7 unattended real-time monitoring. The entire process of data collection, processing, and early warning is conducted without human intervention, completely overcoming the lag and intermittency of manual monitoring. Outstanding anti-interference capability: LiDAR technology is minimally affected by dim lighting and high dust concentration in underground mines, making it more adaptable to complex underground environments compared to visual monitoring solutions; at the same time, targeted preprocessing algorithms and multi-algorithm fusion strategies further enhance the robustness of volume calculation and avoid the limitations of a single algorithm. High system integration: The system adopts a design that seamlessly integrates with the intelligent management and control platform of coal mines, realizing integrated management of monitoring data, early warning information, and evidence chain. It supports risk trend analysis and dynamic monitoring strategy adjustment, which is in line with the development trend of smart mines and provides intelligent support for the entire process of safe coal mine production.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0022] The above and other objects, features and advantages of the present invention will become more apparent from the more detailed description of exemplary embodiments of the invention in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the invention.

[0023] Figure 1 This is a schematic diagram of the three-dimensional spatial relationship between the tunnel support and the roof collapse process in an embodiment of the present invention; Figure 2 This is a flowchart of the algorithm for the real-time monitoring method of coal mine roof collapse based on lidar according to the present invention; Figure 3 This is a schematic diagram of the structure of a computing device according to an exemplary embodiment of the present invention. Detailed Implementation

[0024] Preferred embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms "first," "second," "third," etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this invention, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0027] The technical solutions of the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] (I) Parameter settings for the implementation example This embodiment uses a fully mechanized mining face in a coal mine as an application scenario. Figure 1 This is a three-dimensional spatial relationship diagram (top view, side view, front view) of the tunnel support and roof collapse process in an embodiment of the present invention, showing the positional relationship of the tunnel structure, support zone, self-collapse zone, collapse zone after the removal of the support, and roof collapse morphology.

[0029] Based on the above scenario, the specific parameters in this embodiment are as follows: 1. Hardware deployment: A 16-line explosion-proof lidar is selected and installed at the hinge of the No. 5 end bracket of the working face. The scanning angle is adjusted to 30 degrees horizontally upward to achieve backward scanning coverage of the area to be monitored on the top plate. 2. System parameter configuration: Set the parameters in the configuration file ([config.py](config.py)) of the coal mine intelligent management and control platform: 1) Alarm volume threshold: volume_threshold = 15.0 m³ (determined based on the roadway size, support capacity, and geological conditions of the working face). 2) The effective alarm determination duration is judge_frame=N=5; 3) The alarm cancellation determination lasts for 3 frames (M=3). 4) LiDAR scanning interval = 10 seconds (can be adjusted according to risk level); 5) Evidence chain video recording duration = 5 seconds; 6) Parameters related to weight calculation: W_base_c=0.6, k_r=0.15, k_f=0.15, k_g=0.25.

[0030] (II) System Operation Process The system executes the following algorithm flow, such as Figure 2 As shown: 1. After the lidar is started, it periodically scans the top plate at intervals of 10 seconds to collect raw point cloud data in real time and transmits the data to the business model via JSON stream; 2. After receiving each frame of point cloud data, the business model performs preprocessing operations sequentially: 1) Noise filtering: Removes random noise points caused by dust; 2) Coordinate System 1: Convert polar coordinate point cloud to world coordinate system 3D point cloud; 3) Outlier removal: Outliers are removed using a feedback density algorithm based on variable angles to ensure data authenticity; 3. Perform two algorithms in parallel on the preprocessed point cloud data: 1) The convex hull method calculates V_convex = 16.2 m³; 2) Using the bounding box method, the top slab inclination angle α = 15° and the floor inclination angle β = 8° were extracted, and V_box = 14.8 m³ was calculated. 4. Volume fusion calculation: 1) Based on the geological data of this working face: S_r=0.8 (roof stability), S_f=0.9 (floor stability), RQD=85 (rock quality index), D_f=0.1 (fault density coefficient); 2) Calculate the impact factors: ΔW_roof=0.15×|sin(15°)|×0.8≈0.031; ΔW_floor=0.15×|sin(8°)|×0.9≈0.019; ΔW_geo=0.25×(1-85 / 100)×(1+0.1)=0.041; 3) Calculate the weights W_c = 0.6 + 0.031 + 0.019 - 0.041 = 0.609, W_b = 1 - 0.609 = 0.391; 4) The final volume V_final = 0.609 × 16.2 + 0.391 × 14.8 ≈ 15.6 m³; 5. Threshold judgment and alarm: 1) If V_final is greater than 15.0m³ for 5 consecutive frames, the system determines it as a valid alarm, sets the state code to 1, and records the alarm start time; 2) Triggering a Level 3 Alarm: The on-site audible and visual alarm is activated, alerting workers to evacuate; the dispatch center's large screen prominently displays the hazard and volume data of the working face; alarm information (including monitoring location, volume data, and alarm time) is pushed to the mobile devices of management personnel. 3) Start the evidence chain generation thread, record 5 seconds of on-site video, and associate it with the alarm data; 6. Data Upload and Management: 1) The business model uploads alarm JSON information, volume data, and video evidence to the coal mine intelligent management and control platform using the self.send() method; 2) The platform displays the alarm information in the alarm center list, and administrators can view the evidence video via the link; 3) All monitoring data is stored in a database for subsequent trend analysis; 4) The system continues to monitor at 10-second intervals. When V_final is below 15.0m³ for 3 consecutive frames, the alarm is cleared, the status is set to -1, the end time is recorded, and the alarm is terminated.

[0031] (III) Implementation Results In this embodiment, the system achieves 24-hour uninterrupted monitoring of the suspended roof area of ​​the fully mechanized mining face, with volume calculation error controlled within 5% and alarm response time less than 1 second, effectively avoiding the lag and misjudgment risk of manual monitoring; the lidar maintains stable operation in high dust environments, and its anti-interference capability is significantly better than traditional video surveillance; the seamless integration with the coal mine intelligent management and control platform enables rapid response and closed-loop management of emergencies, providing reliable technical support for safe mine production.

[0032] Figure 3 This is a schematic diagram of the structure of a computing device according to an exemplary embodiment of the present invention.

[0033] See Figure 3 The computing device 300 includes a memory 310 and a processor 320.

[0034] The processor 320 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0035] Memory 310 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 320 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 310 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 310 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0036] The memory 310 stores executable code, which, when processed by the processor 320, can cause the processor 320 to execute part or all of the methods described above.

[0037] Furthermore, the method according to the present invention can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the above-described method of the present invention.

[0038] Alternatively, the present invention can also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) thereon, which, when executed by a processor of an electronic device (or computing device, server, etc.), causes the processor to perform part or all of the steps of the method described above according to the present invention.

[0039] The present invention has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have their own emphasis; for parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to the present invention. Furthermore, it is understood that the steps in the method of the embodiments of the present invention can be adjusted, combined, and deleted according to actual needs, and the modules in the device of the embodiments of the present invention can be combined, divided, and deleted according to actual needs.

[0040] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both.

[0041] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0042] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for real-time monitoring of roof collapse in coal mines based on lidar, characterized in that, It includes the following steps: S1: Deploy a lidar on the hydraulic support of the coal mining face in the coal mine, and adjust the scanning angle of the lidar so that it covers the roof area to be monitored; S2: Periodically scan the roof by the lidar at a preset time interval to collect the original point cloud data of the roof and the collapsed body; S3: Preprocess the original point cloud data, and the preprocessing includes noise filtering, multi-station point cloud registration, coordinate system unification, and outlier removal; S4: Perform parallel computing of multiple algorithms on the preprocessed point cloud data S5: Determine the weights of each calculation result, and calculate the final volume of the collapsed body through weighted calculation: S6: Compare the final volume of the collapsed body with a preset safety threshold, output an alarm message according to the comparison result, and when the alarm is triggered, synchronously intercept or record the video evidence at the alarm moment, and generate a complete evidence chain in association with the alarm message.

2. The method according to claim 1, characterized in that, The outlier removal in step S3 adopts a feedback density algorithm based on a variable angle, which specifically includes: S31: Calculate the local density D(i) of point i, and the calculation formula is: D(i) = N(i) / [π×R²], where N(i) represents the number of neighboring points within a radius R centered on point i, and R is the search radius; S32: Calculate the weighted density WD(i) of point i, and the calculation formula is: WD(i) = D(i)×I(i) / I_avg, where I(i) is the reflection intensity of point i, and I_avg is the average reflection intensity of all points; S33: Calculate the adaptive threshold T(θ), and the calculation formula is: T(θ) = T0×[1 + k×|sin(θ)|], where T0 is the reference threshold, θ is the scanning angle, and k is the angle correction coefficient, and the value range is 0.1 - 0.3; S34: If WD(i) < T(θ), then determine that point i is a reflection feedback outlier and delete it.

3. The method according to claim 1, characterized in that, Step S4 specifically includes: S41: For the point cloud data of the collapsed body, adopt the convex hull method to construct a point cloud convex hull model, calculate the internal space volume of the convex hull, and obtain the volume V_convex of the collapsed body; S42: For the point cloud data of the roof and the floor, extract the formation dip angle. Among them, the formation dip angle includes the roof dip angle α and the floor dip angle β. Based on the formation dip angle, construct an inclined bounding box and calculate the volume V_box.

4. The method according to claim 3, characterized in that, Step S5 specifically includes: Determine the convex hull method weight W_c and the bounding box method weight W_b based on the formation dip angle and geological conditions, and satisfy the constraint condition W_c + W_b = 1. Calculate the final volume V_final of the collapsed body through the weighted formula V_final = W_c×V_convex + W_b×V_box; Among them, the calculation formula of W_c is: W_c = W_base_c + ΔW_roof + ΔW_floor - ΔW_geo; ΔW_roof = k_r×|sin(α)|×S_r, α is the roof dip angle, S_r is the roof stability, and k_r is the roof influence coefficient; ΔW_floor = k_f×|sin(β)|×S_f, β is the floor dip angle, S_f is the floor stability, and k_f is the floor influence coefficient; ΔW_geo=k_g×(1-RQD / 100)×(1+D_f), where RQD is the rock quality index, D_f is the fault density coefficient, and k_g is the geological influence coefficient.

5. The method according to claim 1, characterized in that, Step S6 specifically includes: If the final volume of the collapsed body exceeds the safety threshold for N consecutive frames, it is determined to be a valid alarm, a first alarm status flag is generated and the start time is recorded, and multi-level alarms are triggered. If the final volume V_final of the collapsed body is lower than the safety threshold for M consecutive frames, the alarm is determined to be lifted, a second alarm status flag is generated, and the end time is recorded.

6. The method according to claim 5, characterized in that, The multi-level alarm system includes on-site audible and visual alarms, monitoring center alerts, and mobile push notifications.

7. The method according to any one of claims 1-7, characterized in that, Also includes: S7: Upload monitoring data, alarm information, and evidence chain to the coal mine intelligent management and control platform, store the monitoring data for trend analysis, and periodically execute a new round of monitoring according to a preset strategy to form closed-loop management.

8. A real-time monitoring system for roof collapse in coal mines based on lidar, characterized in that, include: LiDAR deployment module: Used to install lidar on the hydraulic support of the coal mining face and adjust the scanning angle to cover the roof area to be monitored; Data acquisition module: used to control the lidar to periodically scan the top plate at preset time intervals and collect the original point cloud data of the top plate and the collapsed body; Data preprocessing module: used to perform noise filtering, multi-site cloud registration, coordinate system unification, and outlier removal operations on the raw point cloud data; Multi-algorithm computation module: Used for parallel computation of multiple algorithms on preprocessed point cloud data. Volume fusion module: Determines the weights of each calculation result and calculates the final volume of the collapsed body through weighted summation. Threshold judgment and alarm module: It is used to compare the final volume of the collapsed body with a preset safety threshold, output alarm information according to the comparison result, and simultaneously capture or record video evidence at the time of the alarm when the alarm is triggered, and generate a complete evidence chain by associating it with the alarm information.

9. A terminal device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-7.

10. A non-transitory machine-readable storage medium having executable code stored thereon, characterized in that, When the executable code is executed by the processor of the electronic device, the processor performs the method as described in any one of claims 1-7.

Images