Mine personnel safety management method and system based on live-action three-dimensional and UWB

Abstract

The invention is suitable for the technical field of mine management, and provides a mine personnel safety management method and system based on live-action three-dimensional and UWB, and the method comprises the following steps: constructing a three-dimensional model of a mine based on laser radar, unmanned aerial vehicle aerial photography and ground three-dimensional scanning technologies; the real-time position of a mine worker is determined through the UWB positioning technology, and the mine worker wears a UWB positioning tag; analyzing the three-dimensional model, the personnel behavior data and the equipment operation data based on a deep learning algorithm, and determining slope stability information, equipment fault information and abnormal behavior information; the geological exploration data, the mining plan data, the equipment operation data and the personnel position data are integrated, comprehensive analysis is carried out, and a risk early warning and optimized mining scheme is obtained; and constructing a visual interface based on the three-dimensional model, and displaying various monitoring data and analysis results. The method focuses on personnel safety threats caused by slope stability and equipment faults, and ensures personnel safety through accurate identification and early warning of high-risk factors.

Description

Technical Field

[0001] The present invention relates to the technical field of mine management, and specifically relates to a mine personnel safety management method and system based on real scene three-dimensional and UWB. Background Technique

[0002] With the rapid development of the mining economy, the scale of surface mine exploitation has been continuously expanding. However, this has been accompanied by frequent occurrence of various personnel safety accidents, especially those caused by slope collapses and equipment failures. Traditional means of mine personnel safety management mainly rely on manual inspections and simple sensor monitoring, and there are the following problems: 1. Limitations of traditional mine personnel safety management means: Existing monitoring means cannot reflect the dynamic changes during the mine exploitation process in real time. For example, traditional geological monitoring methods rely on manual inspections and regular measurements, and it is difficult to detect changes in slope stability and abnormal equipment operation in a timely manner. Traditional personnel positioning technologies (such as GPS, RFID) have insufficient accuracy in complex environments and are difficult to meet the requirements of high-precision safety monitoring. For example, in the complex terrain and occlusion conditions in the mining area, GPS signals are easily lost, and the RFID positioning accuracy is relatively low, making it impossible to accurately locate the positions of personnel. Geological, exploitation, equipment, personnel and other data are scattered and lack a unified management platform. For example, geological exploration data, exploitation plan data, equipment operation data and personnel position data are stored in different systems respectively, making it difficult to achieve data integration and sharing. There is a lack of intelligent analysis and early warning capabilities for potential risks. For example, traditional monitoring means cannot conduct intelligent analysis on multi-source data and are difficult to discover slope collapse risks and equipment failure hidden dangers in advance. 2. Risks of slope collapses: Slope collapses are one of the most serious safety hazards in mine exploitation and may cause significant casualties and property losses. Traditional monitoring means (such as manual inspections, single sensors) are difficult to comprehensively and real-time evaluate slope stability. For example: Complex geological conditions: Mine slopes are often affected by multiple geological factors (such as rock layer structure, groundwater distribution), and traditional monitoring means are difficult to comprehensively capture changes in these factors. Dynamic changes are difficult to predict: Slope stability changes dynamically with the progress of exploitation and weather conditions, and traditional monitoring means are difficult to predict collapse risks in real time. 3. Safety threats caused by equipment failures: Equipment failures (such as mechanical failures, electrical failures) may trigger safety accidents such as fires and explosions, directly threatening the lives of personnel. Traditional equipment monitoring means cannot achieve comprehensive and real-time monitoring of the equipment operation status and are difficult to discover potential failures in advance. 4. Challenges in personnel behavior management: Personnel entering dangerous areas by mistake or operating in violation of regulations are important reasons for safety accidents. Traditional management means (such as manual inspections, simple warning signs) are difficult to effectively monitor personnel behavior, especially in large-scale mine scenarios. For example: Limited monitoring scope: Traditional management means are difficult to achieve real-time monitoring of the behavior of all personnel in large-scale mine scenarios. Delayed early warning response: When personnel enter dangerous areas by mistake, traditional management means are difficult to issue early warnings and take emergency measures in a timely manner.

[0003] In summary, the existing technologies have obvious deficiencies in real-time monitoring, high-precision positioning, intelligent analysis, and data fusion, and it is difficult to meet the requirements of modern mine safety management. These technical limitations have led to frequent mine safety accidents. Therefore, it is necessary to provide a mine personnel safety management method and system based on real-scene three-dimensional and UWB to solve the above problems. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technologies, the purpose of the present invention is to provide a mine personnel safety management method and system based on real-scene three-dimensional and UWB to solve the problems in the above background technology.

[0005] The present invention is implemented as follows. The mine personnel safety management method based on real-scene three-dimensional and UWB includes the following steps:

[0006] Construct a three-dimensional model of the mine based on lidar, drone aerial photography, and ground three-dimensional scanning technologies;

[0007] Determine the real-time positions of mine personnel through UWB positioning technology. Mine personnel wear UWB positioning tags to determine personnel behavior data;

[0008] Retrieve equipment operation data, and analyze the three-dimensional model, personnel behavior data, and equipment operation data based on deep learning algorithms to determine slope stability information, equipment failure information, and abnormal behavior information;

[0009] Integrate geological exploration data, mining plan data, equipment operation data, and personnel position data, and comprehensively analyze the data using big data analysis algorithms to obtain risk warnings and optimized mining plans;

[0010] Construct a visualization interface based on the three-dimensional model, and display various monitoring data and analysis results on the visualization interface.

[0011] As a further solution of the present invention: The step of constructing a three-dimensional model of the mine based on lidar, drone aerial photography, and ground three-dimensional scanning technologies specifically includes:

[0012] Obtain point cloud data of the mine terrain based on lidar, obtain image data of the mining area through drone aerial photography, and collect detailed information through ground three-dimensional scanning technology;

[0013] Perform preprocessing on the obtained multi-source data, including denoising, registration, and fusion. The multi-source data includes point cloud data, image data, and detailed information;

[0014] Generate a three-dimensional model of the mine based on three-dimensional reconstruction algorithms, regularly obtain the latest data, and update the three-dimensional model to reflect the real-time changes in mine mining.

[0015] As a further solution of the present invention: the steps of analyzing the 3D model, personnel behavior data, and equipment operation data based on a deep learning algorithm to determine slope stability information, equipment failure information, and abnormal behavior information specifically include:

[0016] Analyze the geological features in the 3D model based on a convolutional neural network, where the geological features include geological structure and stress distribution, to obtain slope stability information;

[0017] Analyze the equipment operation data based on a recurrent neural network, where the equipment operation data includes vibration, temperature, and current parameters, to obtain equipment failure information;

[0018] Analyze the personnel behavior data based on an object detection algorithm, where the personnel behavior data includes position trajectory and behavior pattern, to obtain abnormal behavior information.

[0019] As a further solution of the present invention: when constructing the 3D model of the mine, generate the 3D model based on the Poisson surface reconstruction algorithm, and fuse texture mapping and digital elevation model; identify the change area through a difference detection algorithm and update the model to reflect the real-time state of the mine.

[0020] As a further solution of the present invention: the steps of integrating geological exploration data, mining plan data, equipment operation data, and personnel location data, and comprehensively analyzing the data using a big data analysis algorithm to obtain risk warnings and optimized mining plans specifically include:

[0021] Standardize and access geological exploration data, mining plan data, equipment operation data, and personnel location data, and store them in a PostgreSQL spatio-temporal database;

[0022] Extract key features based on PCA dimensionality reduction, and segment time series data based on a sliding window algorithm;

[0023] Identify risk hotspots through K-means clustering, and call a pre-trained CNN / LSTM model to calculate the failure probability;

[0024] Generate an optimized mining plan based on fuzzy logic to fuse multi-source risk indicators.

[0025] As a further solution of the present invention: when constructing a visualization interface based on the 3D model, real-time render the personnel positions through point cluster markers, generate a heat map of equipment status based on kernel density estimation, and set up a geographical fence to highlight dangerous areas.

[0026] Another object of the present invention is to provide a mine personnel safety management system based on real-scene 3D and UWB, and the system includes:

[0027] A 3D model construction module, which is used to construct a 3D model of the mine based on lidar, drone aerial photography, and ground 3D scanning technologies;

[0028] The UWB personnel positioning module is used to determine the real-time positions of mine personnel through UWB positioning technology. Mine personnel wear UWB positioning tags to determine personnel behavior data;

[0029] The deep learning analysis module is used to retrieve equipment operation data and analyze the 3D model, personnel behavior data, and equipment operation data based on deep learning algorithms to determine slope stability information, equipment failure information, and abnormal behavior information;

[0030] The data fusion analysis module is used to integrate geological exploration data, mining plan data, equipment operation data, and personnel position data, and comprehensively analyze the data using big data analysis algorithms to obtain risk warnings and optimized mining plans;

[0031] The visualization management module is used to construct a visualization interface based on the 3D model and display various monitoring data and analysis results on the visualization interface.

[0032] As a further solution of the present invention: The 3D model construction module includes:

[0033] The multi-source data acquisition unit is used to obtain point cloud data of the mine terrain based on lidar, obtain image data of the mining area through UAV aerial photography, and collect detailed information through ground 3D scanning technology;

[0034] The data preprocessing unit is used to preprocess the acquired multi-source data, including denoising, registration, and fusion. The multi-source data includes point cloud data, image data, and detailed information;

[0035] The 3D model construction unit is used to generate a 3D model of the mine based on 3D reconstruction algorithms, regularly obtain the latest data, and update the 3D model to reflect the real-time changes in mine mining.

[0036] As a further solution of the present invention: The deep learning analysis module includes:

[0037] The slope stability unit is used to analyze the geological features in the 3D model based on a convolutional neural network. The geological features include geological structure and stress distribution to obtain slope stability information;

[0038] The equipment failure determination unit is used to analyze equipment operation data based on a recurrent neural network. The equipment operation data includes vibration, temperature, and current parameters to obtain equipment failure information;

[0039] The abnormal behavior recognition unit is used to analyze personnel behavior data based on object detection algorithms. The personnel behavior data includes position trajectories and behavior patterns to obtain abnormal behavior information.

[0040] As a further solution of the present invention: The data fusion and analysis module includes:

[0041] A data access and storage unit, which is used to standardize the access of geological exploration data, mining plan data, equipment operation data and personnel location data, and store them in the PostgreSQL spatio-temporal database;

[0042] A key feature extraction unit, which is used to extract key features based on PCA dimensionality reduction and segment time series data based on the sliding window algorithm;

[0043] A failure probability calculation unit, which is used to identify risk hot spots through K-means clustering and call a pre-trained CNN / LSTM model to calculate the failure probability;

[0044] A mining optimization plan unit, which is used to generate a mining optimization plan based on fuzzy logic fusion of multi-source risk indicators.

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

[0046] By combining the real-scene three-dimensional technology, UWB positioning technology and deep learning algorithm, the present invention not only improves the safety of mine mining, but also optimizes the resource utilization rate and management efficiency. In particular, the present invention focuses on the slope stability and the personnel safety threats caused by equipment failures, and maximally guarantees the personnel safety by accurately identifying and warning these high-risk factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of a mine personnel safety management method based on real-scene three-dimensional and UWB.

[0048] Figure 2 It is a flowchart of constructing a three-dimensional model in a mine personnel safety management method based on real-scene three-dimensional and UWB.

[0049] Figure 3 It is a flowchart of determining abnormal information in a mine personnel safety management method based on real-scene three-dimensional and UWB.

[0050] Figure 4 It is a flowchart of comprehensive data analysis in a mine personnel safety management method based on real-scene three-dimensional and UWB.

[0051] Figure 5 It is a structural schematic diagram of a mine personnel safety management system based on real-scene three-dimensional and UWB. DETAILED DESCRIPTION OF THE INVENTION

[0052] To make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The following describes in detail the specific implementation of the present invention in conjunction with specific embodiments.

[0054] As Figure 1 shown, an embodiment of the present invention provides a mine personnel safety management method based on real scene three-dimensional and UWB, and the method includes the following steps:

[0055] S100, construct a three-dimensional model of the mine based on lidar, UAV aerial photography and ground three-dimensional scanning technology;

[0056] S200, determine the real-time position of mine personnel through UWB positioning technology, and the mine personnel wear UWB positioning tags to determine personnel behavior data;

[0057] S300, retrieve equipment operation data, and analyze the three-dimensional model, personnel behavior data and equipment operation data based on deep learning algorithms to determine slope stability information, equipment failure information and abnormal behavior information;

[0058] S400, integrate geological exploration data, mining plan data, equipment operation data and personnel position data, and comprehensively analyze the data using big data analysis algorithms to obtain risk warnings and optimized mining plans;

[0059] S500, construct a visualization interface based on the three-dimensional model, and display various monitoring data and analysis results on the visualization interface.

[0060] In the embodiments of the present invention, a high-precision 3D model of a mine is constructed by using lidar (LiDAR), UAV aerial photography, and terrestrial 3D scanning technology, and dynamic update of the 3D model is supported. High-precision real-time positioning of personnel is achieved through ultra-wideband (UWB) technology, supporting centimeter-level positioning accuracy and adapting to large-scale mine scenarios. Specifically, multiple UWB positioning base stations are arranged in the mining area. Here, Decawave DWM1000 base stations are arranged. The signal consistency is ensured through the time synchronization protocol to form a positioning network covering the whole area. Data interaction is achieved through wireless communication between the base stations. The TDOA (Time Difference of Arrival) algorithm is used to calculate the position of personnel, and the least squares method is used to optimize the coordinate solution. The UWB positioning tag adopts a low-power design and supports long-term operation. The system calculates the 3D coordinates of personnel through the intersection of signals from multiple base stations, and uses filtering algorithms (such as Kalman filtering) to improve the positioning accuracy and stability. Real-time personnel positioning is achieved with an accuracy of up to centimeter level, and the behavior of personnel entering dangerous areas can be monitored and early warnings can be issued; moreover, in case of emergencies (such as collapses, fires), the trapped personnel can be quickly located. When constructing a visualization interface based on the 3D model, the position of personnel is rendered in real time through point clusters, a heat map of equipment status is generated based on kernel density estimation (KDE), and a geographical fence is set to highlight dangerous areas. The visualization interface will display information such as the current status of mine exploitation, personnel positions, and equipment status in real time, provide risk early warnings and emergency response plans, quickly locate trapped personnel and generate rescue paths (combined with the 3D model) in case of collapses or fires, and support remote monitoring and decision-making by management personnel.

[0061] As Figure 2 shown, as a preferred embodiment of the present invention, the steps of constructing a 3D model of a mine based on lidar, UAV aerial photography, and terrestrial 3D scanning technology specifically include:

[0062] S101, obtaining high-density point cloud data of the mine terrain based on lidar, obtaining high-resolution image data of the mining area through UAV aerial photography, and collecting detailed information through terrestrial 3D scanning technology;

[0063] S102, preprocessing the obtained multi-source data, including denoising, registration, and fusion. The multi-source data includes point cloud data, image data, and detailed information;

[0064] S103, generating a 3D model of the mine based on 3D reconstruction algorithms, regularly obtaining the latest data, and updating the 3D model to reflect the real-time changes in mine exploitation.

[0065] In the embodiments of the present invention, multi-source data is obtained through LiDAR (Velodyne VLP-32), UAV aerial photography (DJI Mavic 2Pro), and terrestrial three-dimensional scanning (Leica ScanStation P40). Then, the multi-source data needs to be preprocessed. Here, the statistical outlier removal (SOR) algorithm is used to clean the point cloud noise, and OpenCV is used for image distortion correction and radiation equalization. When constructing the three-dimensional model of the mine, a three-dimensional model is generated based on the Poisson surface reconstruction algorithm, and texture mapping and digital elevation model are fused; the change area is identified through the difference detection algorithm, and the model is updated to reflect the real-time state of the mine. The real-time updated three-dimensional mine model supports the monitoring of the mining progress and the visualization of geological risks.

[0066] As Figure 3 shown, as a preferred embodiment of the present invention, the steps of analyzing the three-dimensional model, personnel behavior data, and equipment operation data based on the deep learning algorithm to determine the slope stability information, equipment failure information, and abnormal behavior information specifically include:

[0067] S301, analyzing the geological features in the three-dimensional model based on the convolutional neural network (CNN), where the geological features include geological structure and stress distribution, to obtain the slope stability information;

[0068] S302, analyzing the equipment operation data based on the recurrent neural network (RNN), where the equipment operation data includes vibration, temperature, and current parameters, to obtain the equipment failure information;

[0069] S303, analyzing the personnel behavior data based on the object detection algorithm (such as YOLO), where the personnel behavior data includes position trajectory and behavior pattern, to obtain the abnormal behavior information.

[0070] In the embodiments of the present invention, the slope stability information includes the probability value of slope stability, and the equipment failure information includes the probability value of equipment failure and the failure type. In this way, the risk of slope collapse can be predicted, and preventive measures can be taken in advance; equipment failures can be predicted to reduce personnel safety accidents caused by equipment failures; and abnormal personnel behaviors can be identified to prevent personnel safety accidents. Specifically, after inputting geological data, features are extracted through CNN (convolution kernel 3×3), and the stability probability value (0-1) is output. When analyzing sensor data such as vibration and temperature, the LSTM network captures the temporal dependence and classifies the failure types (normal / minor / serious). Abnormal behaviors in the video stream (such as not wearing a safety helmet) are identified through YOLOv5 object detection, and dangerous actions are classified by Softmax. Finally, various results will be weighted and fused (such as slope risk weight 0.5, equipment risk 0.3, abnormal behavior 0.2) to generate a comprehensive risk score.

[0071] As Figure 4As shown in the figure, as a preferred embodiment of the present invention, the steps of integrating geological exploration data, mining plan data, equipment operation data, and personnel location data, and comprehensively analyzing the data using big data analysis algorithms to obtain risk warnings and optimized mining plans specifically include:

[0072] S401, standardize the access of geological exploration data, mining plan data, equipment operation data, and personnel location data, and store them in the PostgreSQL spatio-temporal database;

[0073] S402, extract key features based on PCA dimensionality reduction, and segment time series data based on the sliding window algorithm;

[0074] S403, identify risk hotspots through K-means clustering, and call the pre-trained CNN / LSTM model to calculate the failure probability;

[0075] S404, generate an optimized mining plan based on fuzzy logic fusion of multi-source risk indicators (such as a slope displacement > 0.5m triggering a high risk).

[0076] As Figure 5 shown, the embodiment of the present invention also provides a mine personnel safety management system based on real scene three-dimensional and UWB, and the system includes:

[0077] A three-dimensional model construction module 100, which is used to construct a three-dimensional model of the mine based on lidar, UAV aerial photography, and ground three-dimensional scanning technologies;

[0078] A UWB personnel positioning module 200, which is used to determine the real-time position of mine personnel through UWB positioning technology. Mine personnel wear UWB positioning tags to determine personnel behavior data;

[0079] A deep learning analysis module 300, which is used to retrieve equipment operation data, and analyze the three-dimensional model, personnel behavior data, and equipment operation data based on deep learning algorithms to determine slope stability information, equipment failure information, and abnormal behavior information;

[0080] A data fusion analysis module 400, which is used to integrate geological exploration data, mining plan data, equipment operation data, and personnel location data, and comprehensively analyze the data using big data analysis algorithms to obtain risk warnings and optimized mining plans;

[0081] A visualization management module 500, which is used to construct a visualization interface based on the three-dimensional model, and display various monitoring data and analysis results on the visualization interface.

[0082] As a preferred embodiment of the present invention, the three-dimensional model construction module 100 includes:

[0083] The multi-source data acquisition unit is used to obtain the point cloud data of the mine terrain based on lidar, obtain the image data of the mining area through UAV aerial photography, and collect detailed information through ground 3D scanning technology;

[0084] The data preprocessing unit is used to preprocess the obtained multi-source data, including denoising, registration and fusion. The multi-source data includes point cloud data, image data and detailed information;

[0085] The 3D model construction unit is used to generate the 3D model of the mine based on the 3D reconstruction algorithm, regularly obtain the latest data, and update the 3D model to reflect the real-time changes of the mine exploitation.

[0086] As a preferred embodiment of the present invention, the deep learning analysis module 300 includes:

[0087] The slope stability unit is used to analyze the geological features in the 3D model based on the convolutional neural network. The geological features include geological structure and stress distribution, and obtain the slope stability information;

[0088] The equipment fault determination unit is used to analyze the equipment operation data based on the recurrent neural network. The equipment operation data includes vibration, temperature and current parameters, and obtain the equipment fault information;

[0089] The abnormal behavior recognition unit is used to analyze the personnel behavior data based on the object detection algorithm. The personnel behavior data includes position trajectory and behavior pattern, and obtain the abnormal behavior information.

[0090] As a preferred embodiment of the present invention, the data fusion analysis module 400 includes:

[0091] The data access and storage unit is used to standardize the access of geological exploration data, mining plan data, equipment operation data and personnel location data, and store them in the PostgreSQL spatio-temporal database;

[0092] The key feature extraction unit is used to extract key features based on PCA dimensionality reduction and segment time series data based on the sliding window algorithm;

[0093] The fault probability calculation unit is used to identify the risk hot spot area through K-means clustering and call the pre-trained CNN / LSTM model to calculate the fault probability;

[0094] The mining optimization scheme unit is used to generate the mining optimization scheme based on the fuzzy logic fusion of multi-source risk indicators.

[0095] By combining real - scene 3D technology, UWB positioning technology, and deep - learning algorithms, the present invention proposes a brand - new ground mine personnel safety management system. This system not only improves the safety of mine exploitation but also optimizes resource utilization and management efficiency. In particular, the present invention focuses on the personnel safety threats caused by slope collapses and equipment failures, and maximally ensures personnel safety by accurately identifying and warning these high - risk factors. With the continuous progress of technology, this system will play a greater role in the mining industry and other fields, providing strong support for safe production and sustainable development.

[0096] The present invention has the following remarkable advantages: 1. High - precision personnel positioning: Centimeter - level positioning accuracy: High - precision personnel positioning is achieved through UWB technology, meeting the requirements in complex mine environments. Support for large - scale scenarios: The system supports simultaneous positioning of multiple people and adapts to large - scale mine scenarios. 2. Intelligent analysis capabilities: Application of deep - learning algorithms: Multi - source data is intelligently analyzed using convolutional neural networks (CNNs), recurrent neural networks (RNNs), and object - detection algorithms (such as YOLO). Slope stability prediction: By analyzing geological features in 3D models, slope stability is accurately predicted. Equipment fault diagnosis: By analyzing equipment operation data, potential faults are detected in advance. Personnel behavior analysis: By analyzing personnel behavior patterns, abnormal operations are identified. 3. Data fusion and visual management: Integration of multi - source data: The system integrates multi - source data such as geology, exploitation, equipment, and personnel to achieve efficient data management and sharing. Intuitive visual interface: Through a 3D visual interface, information such as the current status of mine exploitation, personnel positions, and equipment status is intuitively displayed, facilitating managers to quickly grasp the mine dynamics. 4. Scalability and adaptability: Flexible system design: The system design has good scalability and can adapt to mine scenarios of different scales and types. Adaptation to complex environments: The system can still maintain high - precision positioning and stable operation under complex terrain and occlusion conditions. 5. Reducing the losses caused by safety accidents: Reducing personnel casualties: Through real - time monitoring and warning, personnel casualty accidents are effectively prevented. Reducing economic losses: By detecting and handling potential risks in advance, economic losses caused by safety accidents are reduced.

[0097] The above only details the preferred embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0098] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0099] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0100] After considering the specification and the disclosure of the embodiments, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. A mine personnel safety management method based on real-scene 3D and UWB, characterized in that: The method comprises the following steps: Build a 3D model of the mine based on LiDAR, drone aerial photography and ground 3D scanning technology; The real-time location of mine personnel is determined through UWB positioning technology. Mine personnel wear UWB positioning tags to determine personnel behavior data; Retrieve equipment operation data, analyze the three-dimensional model, personnel behavior data and equipment operation data based on deep learning algorithms, and determine slope stability information, equipment failure information and abnormal behavior information; Integrate geological exploration data, mining plan data, equipment operation data and personnel location data, and use big data analysis algorithms to conduct comprehensive analysis of the data to obtain risk warnings and optimize mining plans; A visualization interface is built based on the three-dimensional model to display various monitoring data and analysis results on the visualization interface.

2. The mine personnel safety management method based on real scene 3D and UWB according to claim 1 is characterized in that: The steps of constructing a three-dimensional model of a mine based on laser radar, drone aerial photography and ground three-dimensional scanning technology specifically include: Obtain point cloud data of mine terrain based on LiDAR, obtain image data of the mine area through drone aerial photography, and collect detailed information through ground 3D scanning technology; Preprocessing the acquired multi-source data, including denoising, registration and fusion, wherein the multi-source data includes point cloud data, image data and detail information; Generate a 3D model of the mine based on the 3D reconstruction algorithm, obtain the latest data regularly, and update the 3D model to reflect the real-time changes in mining.

3. The mine personnel safety management method based on real scene 3D and UWB according to claim 1 is characterized in that: The steps of analyzing the three-dimensional model, personnel behavior data and equipment operation data based on the deep learning algorithm to determine the slope stability information, equipment failure information and abnormal behavior information include: Analyze geological features in the three-dimensional model based on a convolutional neural network, wherein the geological features include geological structure and stress distribution, and obtain slope stability information; Analyze equipment operation data based on recurrent neural network, including vibration, temperature and current parameters, to obtain equipment fault information; Based on the target detection algorithm, personnel behavior data is analyzed, which includes location trajectory and behavior pattern, to obtain abnormal behavior information.

4. The mine personnel safety management method based on real scene 3D and UWB according to claim 2 is characterized in that: When constructing the 3D model of the mine, a 3D model is generated based on the Poisson surface reconstruction algorithm, integrating texture maps and digital elevation models; the changed areas are identified through the difference detection algorithm, and the model is updated to reflect the real-time status of the mine.

5. The mine personnel safety management method based on real scene 3D and UWB according to claim 1 is characterized in that: The steps of integrating geological exploration data, mining plan data, equipment operation data and personnel location data, and using big data analysis algorithms to comprehensively analyze the data to obtain risk warnings and optimize mining plans specifically include: Standardized access to geological exploration data, mining plan data, equipment operation data, and personnel location data, stored in the PostgreSQL spatiotemporal database; Extract key features based on PCA dimensionality reduction and segment time series data based on sliding window algorithm; Identify risk hotspots through K-means clustering and use pre-trained CNN / LSTM models to calculate failure probability; Based on fuzzy logic, multi-source risk indicators are integrated to generate mining optimization plans.

6. The mine personnel safety management method based on real scene 3D and UWB according to claim 1 is characterized in that: When building a visualization interface based on a three-dimensional model, point cluster markers are used to render personnel locations in real time, a heat map of equipment status is generated based on kernel density estimation, and geographic fences are set to highlight dangerous areas.

7. A mine personnel safety management system based on real-scene 3D and UWB, characterized by: The system comprises: 3D model building module, used to build a 3D model of the mine based on LiDAR, drone aerial photography and ground 3D scanning technology; UWB personnel positioning module, used to determine the real-time location of mine personnel through UWB positioning technology. Mine personnel wear UWB positioning tags to determine personnel behavior data; The deep learning analysis module is used to retrieve equipment operation data and analyze the three-dimensional model, personnel behavior data and equipment operation data based on the deep learning algorithm to determine slope stability information, equipment failure information and abnormal behavior information; Data fusion analysis module, which is used to integrate geological exploration data, mining plan data, equipment operation data and personnel location data, and use big data analysis algorithms to conduct comprehensive analysis of the data to obtain risk warnings and optimize mining plans; The visualization management module is used to build a visualization interface based on the three-dimensional model and display various monitoring data and analysis results on the visualization interface.

8. The mine personnel safety management system based on real scene 3D and UWB according to claim 7 is characterized in that: The three-dimensional model building module includes: The data multi-source acquisition unit is used to obtain point cloud data of the mine terrain based on LiDAR, obtain image data of the mine area through drone aerial photography, and collect detailed information through ground 3D scanning technology; A data preprocessing unit, used for preprocessing the acquired multi-source data, including denoising, registration and fusion, wherein the multi-source data includes point cloud data, image data and detail information; The 3D model building unit is used to generate a 3D model of the mine based on a 3D reconstruction algorithm, regularly obtain the latest data, and update the 3D model to reflect real-time changes in mining.

9. The mine personnel safety management system based on real scene 3D and UWB according to claim 7 is characterized in that: The deep learning analysis module includes: A slope stability unit, used to analyze geological features in the three-dimensional model based on a convolutional neural network, the geological features including geological structure and stress distribution, to obtain slope stability information; An equipment fault determination unit, configured to analyze equipment operation data based on a recurrent neural network, the equipment operation data including vibration, temperature and current parameters, to obtain equipment fault information; The abnormal behavior identification unit is used to analyze personnel behavior data based on the target detection algorithm, the personnel behavior data includes location trajectory and behavior pattern, and obtain abnormal behavior information.

10. The mine personnel safety management system based on real scene 3D and UWB according to claim 7, characterized in that: The data fusion analysis module includes: Data access storage unit, used for standardized access to geological exploration data, mining plan data, equipment operation data and personnel location data, stored in the PostgreSQL spatiotemporal database; Key feature extraction unit, used to extract key features based on PCA dimensionality reduction and segment time series data based on sliding window algorithm; Fault probability calculation unit, used to identify risk hotspots through K-means clustering and call pre-trained CNN / LSTM models to calculate fault probability; The mining optimization plan unit is used to generate mining optimization plans based on fuzzy logic and fusion of multi-source risk indicators.

Images