Open pit coal mine data fusion method and device, electronic equipment and storage medium

Abstract

The invention provides an opencast coal mine data fusion method and device, electronic equipment and a storage medium, relates to the technical field of data processing, and realizes automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data by constructing a unified data interaction platform and configuring a standardized interface protocol. Meanwhile, a three-dimensional real-scene model is generated based on automatic processing of field data collected by an unmanned aerial vehicle and a laser radar, loading and rendering are carried out in the platform, incremental updating is carried out on the three-dimensional real-scene model of a mining area by adopting a dynamic updating mechanism in combination with mine production real-time data, and volume change calculation is carried out based on the updated model; in addition, a cross-professional data association model is established by using an intelligent collaborative decision engine, and linkage analysis is performed according to the three-dimensional live-action model updated in real time and the safety monitoring data to generate risk behavior early warning information and output a mining plan dynamic optimization scheme, so that the problem of low data circulation efficiency in the prior art can be solved.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a data fusion method and apparatus, electronic equipment and storage medium for open-pit coal mines. Background Technology

[0002] In intelligent production in open-pit coal mines, technologies such as UAV surveying, lidar, and 5G communication have built a multi-source data acquisition and transmission system to support the entire process of geological exploration and mining design. With the acceleration of unmanned and intelligent mining, there is an urgent need for a comprehensive interactive system that integrates geology, surveying, mining, and safety to meet the needs of real-time monitoring and dynamic decision-making. However, current systems mostly adopt an independent construction model for specialized systems, lacking a unified data interaction platform. This not only leads to low data flow efficiency (cycle exceeding 72 hours) and a resource allocation error rate as high as 15%, but also causes significant deviations between mining plans and actual surface changes due to the fragmentation of data from geological modeling, surveying, and safety monitoring systems. Separation of personnel / vehicle positioning and slope monitoring data results in risk warning response times exceeding 10 minutes. At the same time, traditional two-dimensional drawings are difficult to intuitively present three-dimensional spatial relationships, large-scale point cloud data relies on manual processing, and the 10G data loading speed cannot meet real-time requirements, further limiting the efficiency of design verification. These problems ultimately result in significant deficiencies in the timeliness of data fusion, spatial correlation analysis capabilities, and visualization accuracy of existing technologies, restricting the improvement of mine production efficiency and the upgrading of safety management. Summary of the Invention

[0003] This disclosure provides a data fusion method and apparatus, electronic equipment, and storage medium for open-pit coal mines. Its main objective is to at least partially address one of the technical problems in related technologies.

[0004] According to a first aspect of this disclosure, a data fusion method for open-pit coal mines is provided, comprising: Build a unified data interaction platform and configure standardized interface protocols to enable automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data; Based on the field data collected by UAVs and LiDAR, a three-dimensional reality model is generated through automated processing, and the three-dimensional reality model is loaded and rendered in the unified data interaction platform. By combining real-time mine production data, a dynamic update mechanism is used to incrementally update the three-dimensional real-scene model of the mining area, and volume change is calculated based on the updated three-dimensional real-scene model. By utilizing an intelligent collaborative decision-making engine, a cross-disciplinary data association model is established. Based on the real-time updated 3D reality model and safety monitoring data, a linkage analysis is performed to generate risk behavior early warning information and output dynamic optimization schemes for mining plans.

[0005] Optionally, the construction of a unified data interaction platform and the configuration of standardized interface protocols to achieve automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data include: The data format conversion module converts multi-source heterogeneous data into a unified geographic information data format. The coordinate system module transforms spatial data from different sources into a unified coordinate system, enabling spatial alignment of multi-source data.

[0006] Optionally, the on-site data collected by UAVs and LiDAR is automatically processed to generate a 3D reality model, and the 3D reality model is loaded and rendered in the unified data interaction platform, including: The original point cloud data is denoised by combining statistical filtering and radius filtering to improve data quality; By employing 3D data slicing technology, large-scale real-world data is divided into several data blocks, enabling fast loading and multi-device browsing under ordinary hardware environments.

[0007] Optionally, the step of incrementally updating the 3D reality model of the mining area using a dynamic update mechanism, incorporating real-time mine production data, and calculating volume changes based on the updated 3D reality model includes: By comparing data from two periods, the spatial changes in the mining area are identified, and the model update range is determined based on the displacement. The triangular network difference algorithm is used to calculate the volume change of the digital elevation model of the mining area.

[0008] Optionally, the step of utilizing an intelligent collaborative decision-making engine to establish a cross-disciplinary data association model, performing linked analysis based on the real-time updated 3D model and safety monitoring data, generating risk behavior early warning information, and outputting a dynamic optimization scheme for the mining plan includes: Based on the spatial relationship between electronic fences and location data, a risk assessment model is constructed, which triggers an early warning when the location point is detected to deviate from the safe area. A multi-objective optimization algorithm is used to iteratively generate the design parameters of the mining bench under the constraints of satisfying the accuracy of coal and rock quantity and the optimization of transportation path.

[0009] Optional, also includes: The 3D real-scene model is optimized for multi-terminal display, and multi-level detail technology is used to dynamically adjust the model rendering accuracy according to the terminal performance. By combining a web graphics library rendering engine, it enables the synchronous loading and concurrent access of large-scale data across multiple terminals.

[0010] According to a second aspect of this disclosure, an open-pit coal mine data fusion device is provided, comprising: The building unit is used to build a unified data interaction platform and configure standardized interface protocols to achieve automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data. The data acquisition unit is used to generate a 3D reality model based on the field data collected by UAVs and LiDAR through automated processing, and to load and render the 3D reality model in the unified data interaction platform. The update unit is used to incrementally update the three-dimensional real-scene model of the mining area by combining real-time mine production data and adopting a dynamic update mechanism, and to calculate the volume change based on the updated three-dimensional real-scene model. The analysis unit is used to establish a cross-disciplinary data association model using an intelligent collaborative decision engine. It performs linked analysis based on real-time updated 3D reality models and safety monitoring data to generate risk behavior early warning information and output dynamic optimization schemes for mining plans.

[0011] Optionally, building blocks are also used for: The data format conversion module converts multi-source heterogeneous data into a unified geographic information data format. The coordinate system module transforms spatial data from different sources into a unified coordinate system, enabling spatial alignment of multi-source data.

[0012] Optionally, the acquisition unit is also used for: The original point cloud data is denoised by combining statistical filtering and radius filtering to improve data quality; By employing 3D data slicing technology, large-scale real-world data is divided into several data blocks, enabling fast loading and multi-device browsing under ordinary hardware environments.

[0013] Optionally, the update unit is also used for: By comparing data from two periods, the spatial changes in the mining area are identified, and the model update range is determined based on the displacement. The triangular network difference algorithm is used to calculate the volume change of the digital elevation model of the mining area.

[0014] Optionally, the analysis unit is also used for: Based on the spatial relationship between electronic fences and location data, a risk assessment model is constructed, which triggers an early warning when the location point is detected to deviate from the safe area. A multi-objective optimization algorithm is used to iteratively generate the design parameters of the mining bench under the constraints of satisfying the accuracy of coal and rock quantity and the optimization of transportation path.

[0015] Optional, also includes: The adjustment unit is used to optimize the multi-terminal display of the 3D real-scene model, and uses multi-level detail technology to dynamically adjust the model rendering accuracy according to the terminal performance; combined with the web graphics library rendering engine, it realizes the synchronous loading and concurrent access of large-scale data on multiple terminals.

[0016] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0017] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0018] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0019] The data fusion method, apparatus, electronic equipment, and storage medium for open-pit coal mines disclosed herein achieve automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data by constructing a unified data interaction platform and configuring standardized interface protocols. Simultaneously, it automatically processes on-site data collected by UAVs and lidar to generate a 3D reality model, which is then loaded and rendered on the platform. Furthermore, it uses a dynamic update mechanism to incrementally update the 3D reality model of the mining area based on real-time mine production data and calculates volume changes based on the updated model. In addition, it utilizes an intelligent collaborative decision engine to establish a cross-disciplinary data association model, performing linked analysis based on the real-time updated 3D reality model and safety monitoring data to generate risk behavior early warning information and output dynamic optimization schemes for mining plans. Therefore, it can solve the problems in existing technologies caused by the independent construction mode of professional systems and the lack of a unified data interaction platform, resulting in low data flow efficiency, high resource allocation error rate, significant deviation between mining plans and actual surface changes, delayed risk warning response, low efficiency in large-scale data processing, and poor visualization effects.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A flowchart illustrating a data fusion method for open-pit coal mines provided in this embodiment of the disclosure; Figure 2 This is a schematic diagram of the structure of an open-pit coal mine data fusion device provided in an embodiment of the present disclosure; Figure 3 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0022] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] The following description, with reference to the accompanying drawings, outlines an embodiment of an open-pit coal mine data fusion method, apparatus, electronic device, and storage medium.

[0024] Figure 1 This is a flowchart illustrating a data fusion method for open-pit coal mines provided in an embodiment of this disclosure.

[0025] like Figure 1 As shown, the method includes the following steps: Step 101: Build a unified data interaction platform and configure standardized interface protocols to enable automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data.

[0026] In the embodiments of this disclosure, to address the problem of fragmented storage of multi-disciplinary data in independent systems and the difficulty in efficient interoperability in existing open-pit coal mine production, this technical solution first constructs a unified data interaction platform. This platform serves as the core carrier for data aggregation and interaction, and through the configuration of standardized interface protocols, it enables the automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data. The standardized interface protocols are used to standardize the transmission formats and interaction logic of different types of data, ensuring that data from different acquisition devices or professional systems can be accessed to the platform according to a unified standard. Data identification, verification, and integration can be completed without manual intervention, thereby breaking down "information silos" and achieving centralized management of multi-source data. As one implementation method, field measurement data collected by UAVs, geological information acquired by geological exploration equipment, mining parameters generated by mining equipment operation, and safety monitoring data transmitted back by slope monitoring sensors can be automatically accessed and integrated through the platform's standardized interfaces to form a unified mine data resource pool.

[0027] By combining a unified data interaction platform with standardized interface protocols, the problems of fragmented multi-disciplinary data and low access efficiency in existing technologies are effectively solved. It realizes the automatic integration of geological, surveying, mining, and safety data, laying a unified data foundation for data processing, analysis, and application in subsequent mine production, and significantly improving the overall utilization and circulation efficiency of mine data.

[0028] Step 102: Based on the on-site data collected by the UAV and LiDAR, a three-dimensional reality model is generated through automated processing, and the three-dimensional reality model is loaded and rendered in the unified data interaction platform.

[0029] In the embodiments of this disclosure, to address the problems of lack of unified data source support, low model generation efficiency, and difficulty in coordinating with data interaction platforms in existing open-pit coal mine 3D scene depiction, this technical solution uses real-scene data collected on-site at the open-pit coal mine as a foundation. A 3D real-scene model is generated through a pre-defined automated processing flow, and then loaded and rendered in a unified data interaction platform. The on-site data may include various sensor-collected data reflecting the terrain, landforms, and facility distribution of the open-pit coal mine. The automated processing flow covers core aspects such as data noise reduction, coordinate calibration, feature extraction, and model construction to ensure that the generated 3D real-scene model accurately reflects the actual situation at the coal mine. The loading and rendering of the 3D real-scene model on the unified data interaction platform aims to establish a connection between the model and other data on the platform, providing a contextual basis for subsequent data visualization and analysis. As one implementation method, UAVs can be used to collect coal mine surface image data, and LiDAR can be used to collect 3D point cloud data of the mining area. After automatically processing these two types of data to generate a 3D real-scene model of the mining area, the model is loaded and rendered in real-time on the unified data interaction platform, achieving an intuitive presentation of the mining area scene.

[0030] By automatically processing on-site data to generate 3D reality models and collaborating with a unified data interaction platform, the problem of 3D model generation relying on manual labor and being disconnected from the data platform in existing technologies is effectively solved. This not only improves the generation efficiency and accuracy of 3D reality models, but also realizes the correlation and integration of model and platform data, providing scenario-based support for the visualization management and decision analysis of subsequent mine production.

[0031] Step 103: Combine real-time mine production data and use a dynamic update mechanism to incrementally update the three-dimensional real-scene model of the mining area, and calculate the volume change based on the updated three-dimensional real-scene model.

[0032] In the embodiments of this disclosure, to address the problems of existing open-pit coal mine 3D reality models being difficult to update synchronously with production dynamics and the calculation of coal volume in mining areas lagging behind actual operation progress, this technical solution, based on the generated 3D reality model, combines real-time mine production data and employs a dynamic update mechanism to incrementally update the 3D reality model of the mining area, and completes the volume change calculation based on the updated 3D reality model. The real-time mine production data can encompass various real-time feedback data reflecting the dynamics of mining operations. The dynamic update mechanism is used to trigger the model update process based on real-time data and limit the update scope. Incremental updates can adjust only the model data of the mining area, avoiding resource consumption and efficiency losses caused by full updates. The volume change calculation is based on the updated model that accurately matches the actual situation on site, ensuring that the calculation results are consistent with the actual mining situation. As one implementation method, real-time production data such as the real-time operating location of mining equipment and the amount of material transported can be connected to the system. When the data shows that mining operations have been completed in a certain area, the dynamic update mechanism automatically triggers an incremental update of the model for that mining area, and then calculates the coal and rock volume change in that area based on the updated model.

[0033] By using real-time production data to drive incremental model updates and volume calculations based on the updated model, the problems of asynchronous 3D models and on-site production, as well as lagging volume calculations, in existing technologies are effectively solved. This ensures that the 3D reality model always matches the actual mining progress, and that the volume data is accurate and reliable, providing real-time data support for mine resource management and mining plan optimization.

[0034] Step 104: Utilize the intelligent collaborative decision-making engine to establish a cross-disciplinary data association model. Based on the real-time updated 3D real-scene model and safety monitoring data, conduct joint analysis to generate risk behavior early warning information and output dynamic optimization schemes for the mining plan.

[0035] In the embodiments of this disclosure, to address the problems of insufficient effective correlation of cross-disciplinary data and difficulty in combining risk warning and mining plan optimization with real-world dynamics in existing open-pit coal mines, this technical solution utilizes an intelligent collaborative decision engine to construct a cross-disciplinary data correlation model. This model establishes a logical relationship between a real-time updated 3D real-world model and safety monitoring data, and then conducts linkage analysis based on the two, ultimately generating risk behavior warning information and outputting a dynamic optimization scheme for the mining plan. The intelligent collaborative decision engine, as the core processing unit, undertakes the functions of data correlation logic construction, linkage analysis calculation, and decision scheme generation. The cross-disciplinary data correlation model can flexibly correlate the spatial state information reflected in the 3D real-world model with the risk state information reflected in the safety monitoring data according to the mine's production needs, ensuring that the analysis process takes into account both real-world dynamics and safety hazards. The linkage analysis integrates the core information of the two types of data to identify potential risks and assess the adaptability of existing mining plans. As one implementation method, the spatial location of the mining area in the real-time three-dimensional reality model can be associated with the slope displacement data in the safety monitoring data through the association model. The linkage analysis can be used to determine whether there is a risk of slope instability and generate an early warning. At the same time, the bench advancement parameters in the mining plan can be optimized according to the actual progress of the mining area.

[0036] By combining an intelligent collaborative decision-making engine with a cross-disciplinary data association model, the problems of data isolation, delayed risk warning, and rigid mining plans in existing technologies are effectively solved. This enables linkage decision-making between real-world dynamics and safety data, which not only improves the timeliness and accuracy of risk warnings but also allows mining plans to dynamically adapt to the actual situation on site, providing intelligent decision support for the safe management and efficient operation of mine production.

[0037] The open-pit coal mine data fusion method disclosed herein achieves automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data by constructing a unified data interaction platform and configuring standardized interface protocols. Simultaneously, it automatically processes on-site data collected by UAVs and lidar to generate a 3D reality model, which is then loaded and rendered on the platform. Furthermore, it uses a dynamic update mechanism to incrementally update the 3D reality model of the mining area based on real-time mine production data and calculates volume changes based on the updated model. In addition, it utilizes an intelligent collaborative decision engine to establish a cross-disciplinary data association model, performing linked analysis based on the real-time updated 3D reality model and safety monitoring data to generate risk behavior early warning information and output dynamic optimization schemes for mining plans. Therefore, it can solve the problems in existing technologies caused by the independent construction mode of professional systems and the lack of a unified data interaction platform, resulting in low data flow efficiency, high resource allocation error rate, significant deviation between mining plans and actual surface changes, delayed risk warning response, low efficiency in large-scale data processing, and poor visualization effects.

[0038] As a specific implementation of this disclosure, based on the basic scheme, the construction of a unified data interaction platform is further defined, and a standardized interface protocol is configured to realize the automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data, including: converting multi-source heterogeneous data into a unified geographic information data format through a data format conversion module; and converting spatial data from different sources to a unified coordinate system through a coordinate system module to achieve spatial alignment of multi-source data.

[0039] Specifically, in the process of building a unified data interaction platform and configuring standardized interface protocols to achieve automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data, the data format conversion module first performs format detection on the accessed multi-source heterogeneous data. For example, it identifies common CAD formats for geological information, LAS point cloud formats for measurement data, CSV table formats for storing mining parameters, and MQTT protocol stream data formats used for safety monitoring data. Then, it calls the pre-stored format mapping rules within the module to uniformly convert various types of data into industry-standard geographic information data formats (such as SHP vector format or GeoJSON format). For unstructured data... According to the data, the system will automatically supplement field attribute identifiers to ensure data integrity. The coordinate system module pre-sets the target coordinate system applicable to open-pit coal mines (such as the Xi'an 80 coordinate system or the CGCS2000 national geodetic coordinate system). Through the built-in seven-parameter coordinate transformation algorithm, it reads the original coordinate system parameters of spatial data from different sources (such as the WGS84 coordinate system of UAV data and the local coordinate system of the mining area of ​​lidar data), calculates the translation, rotation and scaling parameters required for coordinate transformation, and then accurately transforms the original spatial data to the target unified coordinate system, realizing a one-to-one correspondence between the spatial locations of multi-source data such as stratigraphic boundaries in geological information and slope points in measurement data.

[0040] The data format conversion module eliminates format barriers between multiple data sources, avoiding data access failures due to format incompatibility. At the same time, the coordinate system module solves the problem of spatial data misalignment, ensuring that the integrated data can be correlated in spatial dimensions. This provides accurate and compatible data prerequisites for subsequent data analysis and applications based on the unified data interaction platform.

[0041] As a specific implementation of this disclosure, based on the basic solution, the on-site data collected by UAVs and LiDAR is further defined to generate a three-dimensional reality model through automated processing, and the three-dimensional reality model is loaded and rendered in the unified data interaction platform. This includes: performing noise reduction processing on the original point cloud data, using a combination of statistical filtering and radius filtering to improve data quality; and using three-dimensional data slicing technology to divide the large-scale reality data into several data blocks to achieve fast loading and multi-terminal browsing under ordinary hardware environments.

[0042] Specifically, during the process of automatically processing on-site data collected by UAVs and LiDAR to generate 3D reality models, and loading and rendering them in a unified data interaction platform, a noise reduction process is initiated for the original point cloud data (including surface point clouds acquired by UAV aerial photography and fine point clouds of the mining area scanned by LiDAR). First, a statistical filtering algorithm is used to search for neighboring points of each point cloud data (e.g., setting the neighbor search radius to 0.3m and the number of neighboring points to 15), calculating the average distance and standard deviation from the neighboring points to the point, and identifying and removing points with a distance greater than "average distance + 2 times the standard deviation" as outlier noise points. Then, a radius filtering algorithm is used with the same neighbor search radius to filter out sparse points with fewer than 8 neighboring points (these points are mostly isolated points caused by environmental interference) and delete them. By combining two filtering steps, environmental noise and equipment error points in the point cloud data are removed, significantly improving the data purity. During the loading and rendering stage of the 3D reality model, 3D data slicing technology is used to divide large-scale reality data (such as point cloud and texture data of more than 10G) into several regular data blocks at intervals of 50m in the X and Y directions, according to the actual spatial range of the mining area. Each data block is accompanied by a spatial coordinate index. When loading the model in the unified data interaction platform, the system only calls the data blocks within the coverage of the current browsing view, without loading all the data. This enables the model to be loaded in seconds on ordinary office computers (such as hardware configuration with i5 CPU and 8G memory) and to be browsed smoothly on multiple terminals (such as mining tablets and monitoring center servers).

[0043] By combining statistical filtering and radius filtering for noise reduction, noise interference in the original point cloud data is effectively removed, ensuring the modeling accuracy of the 3D reality model. At the same time, by using 3D data slicing technology, the problem of slow loading of large-scale reality data in ordinary hardware environments is solved, reducing the hardware deployment cost of the system, ensuring that multiple terminals can efficiently access the 3D model, and improving the convenience of the model in practical applications.

[0044] As a specific implementation of this disclosure, based on the basic scheme, the following is further defined: combining real-time mine production data, using a dynamic update mechanism to incrementally update the three-dimensional real-scene model of the mining area, and calculating volume changes based on the updated three-dimensional real-scene model, including: identifying the spatial changes of the mining area by comparing data from two periods, and determining the model update range based on the displacement; and using a triangulation difference algorithm to calculate volume changes in the digital elevation model of the mining area.

[0045] Specifically, when incrementally updating the 3D reality model of the mining area using a dynamic update mechanism by combining real-time mining production data (such as real-time operating coordinates of mining equipment, shovel and haulage records, and feedback data from the mining area boundary) and calculating volume changes, a two-phase data comparison operation is first performed: the baseline 3D model data of the mining area constructed before the update is selected as the first-phase data, and the latest data of the mining area collected in real time by UAVs and LiDAR is selected as the second-phase data. Through automatic spatial coordinate matching technology, the two-phase data are aligned in a unified coordinate system. Then, the 3D displacement of the corresponding spatial points (including horizontal displacement of the X and Y axes and elevation displacement of the Z axis) is calculated point by point, and a displacement threshold (such as 5cm) is preset. Areas with displacement exceeding this threshold are identified as mining areas that need to be updated, thus clarifying the specific spatial range of the incremental model update and avoiding invalid updates to unchanged areas. In the volume change calculation stage, the triangular mesh differential algorithm is adopted: First, an irregular triangular mesh (TIN) is constructed based on the point cloud data of the mining area in the two phases of data to form the corresponding digital elevation models (DEMs) for the two phases; then, by matching the topological relationships of the triangular mesh, the triangular facets at the corresponding positions in the two phases of models are found, and the difference in elevation direction and the corresponding projected area of ​​each matched triangular facet are calculated. Then, the volume change value corresponding to a single triangular facet is calculated by using the volume calculation formula (such as the accumulation of prism volumes based on the triangular facets). Finally, the volume change values ​​of all corresponding triangular facets are accumulated to obtain the total volume change result of the mining area. The error in the calculation process is controlled within 3%, which meets the accuracy requirements of actual mine production measurement.

[0046] By comparing data from two phases, the mining area is accurately identified and the update range is limited, which effectively reduces the amount of data processing required for model updates and significantly improves the efficiency of incremental updates. At the same time, the triangular network difference algorithm ensures high accuracy in volume calculation by accurately capturing elevation changes, providing accurate data for mine volume statistics, resource management and mining plan adjustments, and avoiding large errors caused by traditional estimation methods.

[0047] As a specific implementation of this disclosure, based on the basic scheme, it further defines the use of an intelligent collaborative decision-making engine to establish a cross-professional data association model, and to perform linkage analysis based on the real-time updated three-dimensional model and safety monitoring data to generate risk behavior early warning information and output a dynamic optimization scheme for the mining plan. This includes: constructing a risk judgment model based on the spatial relationship between electronic fences and positioning data, and triggering an early warning when the positioning point is detected to deviate from the safe area; and using a multi-objective optimization algorithm to iteratively generate mining bench design parameters under the constraints of coal and rock quantity accuracy and transportation path optimization.

[0048] Specifically, when using the intelligent collaborative decision engine to establish a cross-professional data association model, and combining real-time updated 3D models with safety monitoring data for linkage analysis to generate risk warnings and optimize mining plans, the risk assessment model is first constructed: In the 3D model of the unified data interaction platform, based on the mine safety regulations (such as dangerous slope areas, prohibited equipment areas, and restricted personnel operation areas), a closed polygonal electronic fence is delineated using a set of spatial coordinate points, and the 3D coordinate parameters of the fence boundary are stored; the positioning data in the safety monitoring data comes from the Beidou positioning terminal carried by personnel and the vehicle-mounted positioning module. The terminal transmits the 3D coordinates of the positioning point to the intelligent collaborative decision engine in real time (updated once every 30 seconds). The engine uses a spatial distance calculation algorithm to compare the shortest distance between the positioning point coordinates and the electronic fence boundary in real time, and presets a safety distance threshold (such as 5 meters for personnel and 8 meters for vehicles). When the distance between the positioning point and the fence boundary is less than the corresponding threshold, it is determined to be a deviation from the safe area, and a risk warning is immediately triggered. The warning information includes the violation object (personnel / vehicle number), real-time location coordinates, and violation type (approaching a slope / restricted area), and is simultaneously pushed to the monitoring center display terminal and the mobile terminal of the violation object. In the stage of generating a dynamic optimization scheme for the mining plan, a multi-objective optimization algorithm (such as the non-dominated sorting genetic algorithm NSGA-II) is adopted: the accuracy of coal and rock quantity (calculation error ≤2%) and the optimization of transportation path (path length shortened by ≥10% compared to the current path) are set as constraints, and the mining bench height, slope angle, and advance step distance are used as optimization variables. The engine calls the coal and rock distribution data of the mining area and the road network data of the mining area in the real-time 3D model, initializes the algorithm population (population size 100), and iterates through selection, crossover, and mutation operations (50 iterations) to select the Pareto optimal solution that satisfies the dual constraints. The optimal mining bench design parameters (such as bench height 12m, slope angle 65°, and advance step distance 20m) are extracted from it to form a dynamic optimization scheme.

[0049] By comparing electronic fences with location data in real time, risky behaviors can be accurately and quickly identified, effectively shortening the early warning response time and reducing the probability of safety accidents in the mining area. The mining bench parameters generated by the multi-objective optimization algorithm under dual constraints not only ensure the accuracy of coal and rock quantity measurement but also reduce transportation costs, thereby improving the economy and rationality of mining operations.

[0050] As a specific implementation of this disclosure, based on the basic solution, the embodiments of this disclosure further include: optimizing the multi-terminal display of the three-dimensional real-scene model, using multi-level detail technology to dynamically adjust the model rendering accuracy according to the terminal performance; and combining a web graphics library rendering engine to achieve synchronous loading and concurrent access of large-scale data on multiple terminals.

[0051] Specifically, when optimizing the multi-terminal display of the 3D reality model and achieving synchronous loading and concurrent access across multiple terminals, the configuration is first carried out for multi-level detail technology: A 4-level detail (LOD) model is pre-built for the 3D reality model according to the terminal performance level. LOD0 corresponds to the highest precision (texture resolution 2048×2048 pixels, retaining 90% of the original triangle faces), LOD1 reduces the texture resolution to 1024×1024 pixels and retains 70% of the triangle faces, LOD2 has a texture resolution of 512×512 pixels and retains 50% of the triangle faces, and LOD3 has a texture resolution of 256... ×256 pixels, retaining 30% of the triangular facets; when the terminal connects to the unified data interaction platform, the system automatically detects the terminal's hardware performance (e.g., the monitoring center server is detected as having an 8-core CPU, 16GB of RAM, and 4GB of video memory; the mining tablet is detected as having a 4-core CPU, 4GB of RAM, and 1GB of video memory; and the administrator's mobile phone is detected as having a 2-core CPU, 2GB of RAM, and 512MB of video memory), and matches the corresponding LOD level—the server loads LOD0 to meet the high-precision display requirements, the tablet loads LOD2 to balance accuracy and smoothness, and the mobile phone loads LOD3 to ensure the rapid presentation of the basic scene, dynamically adjusting the model rendering accuracy. For multi-terminal synchronous loading and concurrent access, the WebGL web graphics library rendering engine is used to divide the 3D real-scene model data into 50m×50m spatial blocks, with each block having a unique spatial coordinate index. When a terminal initiates an access request, the engine calculates the required data blocks based on the terminal's current viewing angle, requests and loads the blocks within the field of view via HTTP protocol, and simultaneously enables a local caching mechanism to store the loaded blocks (cache validity period of 24 hours). For concurrent access scenarios, the engine has a built-in request queue management module that limits the number of block requests initiated by a single terminal to no more than 3 at the same time. The concurrent requests received by the server are sorted according to the "first-come, first-served" principle to ensure that when 50 terminals access the server at the same time, the loading progress difference between the terminals does not exceed 2 seconds, thus achieving synchronous loading and stable concurrent access of large-scale data.

[0052] Through multi-layered detail technology, terminals with different hardware performance can adapt to the rendering requirements of 3D real-world models. This avoids resource waste on high-configuration terminals and solves the problems of loading lag or failure to load on low-configuration terminals. Combined with the WebGL engine's fragmentation processing, caching, and queue management mechanism, it effectively eliminates latency differences in synchronous loading across multiple terminals and server congestion issues caused by concurrent access. This ensures the stability of collaborative model viewing by multiple roles in the mining area (monitoring center, on-site operators, and managers) and improves the system's adaptability to actual application scenarios.

[0053] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0054] Corresponding to the above-described open-pit coal mine data fusion method, this disclosure also proposes an open-pit coal mine data fusion device. Since the device embodiments of this disclosure correspond to the above-described method embodiments, details not disclosed in the device embodiments can be referred to the above-described method embodiments, and will not be repeated here.

[0055] Figure 2 This is a schematic diagram of the structure of an open-pit coal mine data fusion device provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, it includes: Building unit 21 is used to build a unified data interaction platform and configure standardized interface protocols to achieve automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data; The acquisition unit 22 is used to generate a three-dimensional real scene model based on the field data collected by UAV and LiDAR through automated processing, and to load and render the three-dimensional real scene model in the unified data interaction platform. Update unit 23 is used to incrementally update the three-dimensional real scene model of the mining area by combining real-time mine production data and adopting a dynamic update mechanism, and to calculate the volume change based on the updated three-dimensional real scene model. Analysis unit 24 is used to establish a cross-professional data association model using an intelligent collaborative decision engine, and to perform linkage analysis based on the real-time updated 3D real scene model and safety monitoring data to generate risk behavior early warning information and output dynamic optimization schemes for mining plans.

[0056] The open-pit coal mine data fusion device disclosed herein achieves automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data by constructing a unified data interaction platform and configuring standardized interface protocols. Simultaneously, it automatically processes on-site data collected by UAVs and lidar to generate a 3D reality model, which is then loaded and rendered on the platform. Furthermore, it uses a dynamic update mechanism to incrementally update the 3D reality model of the mining area based on real-time mine production data and calculates volume changes based on the updated model. In addition, it utilizes an intelligent collaborative decision engine to establish a cross-disciplinary data association model, performing linked analysis based on the real-time updated 3D reality model and safety monitoring data to generate risk behavior early warning information and output dynamic optimization schemes for mining plans. Therefore, it can solve the problems in existing technologies caused by the independent construction mode of professional systems and the lack of a unified data interaction platform, resulting in low data flow efficiency, high resource allocation error rate, significant deviation between mining plans and actual surface changes, delayed risk warning response, low efficiency in large-scale data processing, and poor visualization effects.

[0057] Furthermore, in one possible implementation of this embodiment, the construction unit 21 is also used for: The data format conversion module converts multi-source heterogeneous data into a unified geographic information data format. The coordinate system module transforms spatial data from different sources into a unified coordinate system, enabling spatial alignment of multi-source data.

[0058] Furthermore, in one possible implementation of this embodiment, the acquisition unit 22 is also used for: The original point cloud data is denoised by combining statistical filtering and radius filtering to improve data quality; By employing 3D data slicing technology, large-scale real-world data is divided into several data blocks, enabling fast loading and multi-device browsing under ordinary hardware environments.

[0059] Furthermore, in one possible implementation of this embodiment, the updating unit 23 is also used for: By comparing data from two periods, the spatial changes in the mining area are identified, and the model update range is determined based on the displacement. The triangular network difference algorithm is used to calculate the volume change of the digital elevation model of the mining area.

[0060] Furthermore, in one possible implementation of this embodiment, the analysis unit 24 is also used for: Based on the spatial relationship between electronic fences and location data, a risk assessment model is constructed, which triggers an early warning when the location point is detected to deviate from the safe area. A multi-objective optimization algorithm is used to iteratively generate the design parameters of the mining bench under the constraints of satisfying the accuracy of coal and rock quantity and the optimization of transportation path.

[0061] Furthermore, in one possible implementation of this embodiment, such as Figure 2 As shown, it also includes: The adjustment unit 25 is used to optimize the multi-terminal display of the three-dimensional real scene model, and adopts multi-level detail technology to dynamically adjust the model rendering accuracy according to the terminal performance; combined with the web graphics library rendering engine, it realizes the synchronous loading and concurrent access of large-scale data under multiple terminals.

[0062] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0063] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0064] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0065] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 302 or a computer program loaded from storage unit 308 into RAM (Random Access Memory) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.

[0066] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0067] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as the open-pit coal mine data fusion method. For example, in some embodiments, the open-pit coal mine data fusion method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, computing unit 301 may be configured to perform the aforementioned open-pit coal mine data fusion method by any other suitable means (e.g., by means of firmware).

[0068] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0069] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0070] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0071] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0072] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0073] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0074] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0075] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0076] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0077] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0078] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data fusion method for open-pit coal mines, characterized in that, include: Build a unified data interaction platform and configure standardized interface protocols to enable automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data; Based on the field data collected by UAVs and LiDAR, a three-dimensional reality model is generated through automated processing, and the three-dimensional reality model is loaded and rendered in the unified data interaction platform. By combining real-time mine production data, a dynamic update mechanism is used to incrementally update the three-dimensional real-scene model of the mining area, and volume change is calculated based on the updated three-dimensional real-scene model. By utilizing an intelligent collaborative decision-making engine, a cross-disciplinary data association model is established. Based on the real-time updated 3D reality model and safety monitoring data, a linkage analysis is performed to generate risk behavior early warning information and output dynamic optimization schemes for mining plans.

2. The method according to claim 1, characterized in that, The construction of a unified data interaction platform, configuring standardized interface protocols to achieve automatic access and integration of geological information, measurement data, mining parameters, and safety monitoring data, includes: The data format conversion module converts multi-source heterogeneous data into a unified geographic information data format. The coordinate system module transforms spatial data from different sources into a unified coordinate system, enabling spatial alignment of multi-source data.

3. The method according to claim 1, characterized in that, The on-site data collected by UAVs and LiDAR is automatically processed to generate a 3D reality model, which is then loaded and rendered in the unified data interaction platform, including: The original point cloud data is denoised by combining statistical filtering and radius filtering to improve data quality; By employing 3D data slicing technology, large-scale real-world data is divided into several data blocks, enabling fast loading and multi-device browsing under ordinary hardware environments.

4. The method according to claim 1, characterized in that, The method involves combining real-time mine production data and employing a dynamic update mechanism to incrementally update the 3D reality model of the mining area, and calculating volume changes based on the updated 3D reality model, including: By comparing data from two periods, the spatial changes in the mining area are identified, and the model update range is determined based on the displacement. The triangular network difference algorithm is used to calculate the volume change of the digital elevation model of the mining area.

5. The method according to claim 1, characterized in that, The process utilizes an intelligent collaborative decision-making engine to establish a cross-disciplinary data association model. Based on real-time updated 3D models and safety monitoring data, it performs linked analysis to generate risk behavior early warning information and outputs dynamic optimization schemes for mining plans, including: Based on the spatial relationship between electronic fences and location data, a risk assessment model is constructed, which triggers an early warning when the location point is detected to deviate from the safe area. A multi-objective optimization algorithm is used to iteratively generate the design parameters of the mining bench under the constraints of satisfying the accuracy of coal and rock quantity and the optimization of transportation path.

6. The method according to claim 1, characterized in that, Also includes: The 3D real-scene model is optimized for multi-terminal display, and multi-level detail technology is used to dynamically adjust the model rendering accuracy according to the terminal performance. By combining a web graphics library rendering engine, it enables the synchronous loading and concurrent access of large-scale data across multiple terminals.

7. A data fusion device for open-pit coal mines, characterized in that, include: The building unit is used to build a unified data interaction platform and configure standardized interface protocols to achieve automatic access and integration of geological information, measurement data, mining parameters and safety monitoring data. The data acquisition unit is used to generate a 3D reality model based on the field data collected by UAVs and LiDAR through automated processing, and to load and render the 3D reality model in the unified data interaction platform. The update unit is used to incrementally update the three-dimensional real-scene model of the mining area by combining real-time mine production data and adopting a dynamic update mechanism, and to calculate the volume change based on the updated three-dimensional real-scene model. The analysis unit is used to establish a cross-disciplinary data association model using an intelligent collaborative decision engine. It performs linked analysis based on real-time updated 3D reality models and safety monitoring data to generate risk behavior early warning information and output dynamic optimization schemes for mining plans.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images