Coal stack three-dimensional dynamic monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a coal stack three-dimensional dynamic monitoring method and device, electronic equipment and a storage medium, and relates to the technical field of coal yard monitoring. The method comprises the following steps: acquiring coal stack contour data; based on the coal stack contour data, calling a three-dimensional vector modeling engine to generate a coal stack three-dimensional model; the coal stack three-dimensional model is updated according to the preset frequency based on a preset animation engine, and a coal stack monitoring report is generated according to the coal type of the updated coal stack three-dimensional model and the stock of the coal type. Meanwhile, the coal stack three-dimensional model is dynamically updated according to the set frequency through a preset animation engine, coal stack form evolution and coal type stock change can be tracked in real time, a coal stack monitoring report is generated based on the updated three-dimensional model, the coal stack spatial form and coal type information are deeply fused, and the coal stack monitoring accuracy is improved. And a comprehensive and accurate decision basis is provided for coal enterprises.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of coal yard monitoring, and in particular to a coal pile three-dimensional dynamic monitoring method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the coal industry, accurately grasping the form, volume, and coal type and stock of coal piles is crucial for coal storage management, transportation scheduling, and sales plan formulation.

[0003] Currently, related technologies determine the form of coal piles through manual measurement and recording, that is, a worker uses a measuring tool (such as a tape measure, a laser range finder, etc.) to measure the size of a coal pile and records relevant data, and then estimates the volume and coal type stock of the coal pile according to experience.

[0004] As can be seen, manual measurement and recording require a large amount of manpower and time, and especially in the case of a large number of coal piles or complex shapes, the measurement work becomes more difficult and time-consuming. SUMMARY

[0005] The present disclosure provides a coal pile three-dimensional dynamic monitoring method and device, electronic equipment and storage medium. Its main purpose is to solve the problem of manual measurement and recording in related technologies. The present disclosure automatically acquires coal pile contour data and generates a three-dimensional model, achieving a substantial improvement in monitoring efficiency and a significant enhancement in precision, can reflect the dynamic changes of coal piles in real time, and effectively integrates the three-dimensional form of coal piles and the coal type stock information, providing comprehensive and accurate data support for coal enterprise management decisions.

[0006] According to a first aspect of the present disclosure, a coal pile three-dimensional dynamic monitoring method is provided, comprising:

[0007] acquiring coal pile contour data;

[0008] generating a coal pile three-dimensional model based on the coal pile contour data by calling a three-dimensional vector modeling engine;

[0009] updating the coal pile three-dimensional model according to a preset frequency based on a preset animation engine, to generate a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the coal type stock.

[0010] In some embodiments, acquiring coal pile contour data includes: collecting coal pile surface discrete point data through a cantilever coal level detection device; recursively optimizing noise and dynamic deviation in the coal pile surface discrete point data to obtain optimized coal pile surface discrete point data; dividing the optimized coal pile surface discrete point data into mutually exclusive triangles, and generating coal pile contour data according to the empty circle criterion.

[0011] In some embodiments, based on the coal pile contour data, calling a three-dimensional vector modeling engine to generate a coal pile three-dimensional model comprises: importing the coal pile contour data into the three-dimensional vector modeling engine, generating a closed coal pile surface through a surface reconstruction algorithm; optimizing the coal pile surface through a mesh simplification algorithm, and outputting an optimized coal pile three-dimensional model.

[0012] In some embodiments, based on the preset animation engine updating the coal pile three-dimensional model at a preset frequency, the method comprises: generating different precision model versions corresponding to the coal pile three-dimensional model by using a mesh simplification algorithm; determining the distance of each region of the coal pile from the camera, and based on a preset distance threshold, determining the precision model version corresponding to each region; and generating an optimized coal pile three-dimensional model by using the precision model version corresponding to each region.

[0013] In some embodiments, generating a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the stock of the coal type comprises: performing feature extraction on the updated coal pile three-dimensional model, performing coal type classification in combination with a machine learning model, to obtain the coal type category corresponding to the updated coal pile three-dimensional model; determining the stock of each coal type category based on the volume of the coal pile corresponding to the coal pile three-dimensional model and the density corresponding to each coal type category; and generating a coal pile monitoring report by using the coal type category and the stock of each coal type category.

[0014] In some embodiments, based on the preset animation engine updating the coal pile three-dimensional model at a preset frequency, the method comprises: displaying the updated coal pile three-dimensional model on an operation screen.

[0015] In some embodiments, displaying the updated coal pile three-dimensional model on the operation screen, the method comprises: determining a screen click position in response to an operator interaction instruction; emitting a ray from the screen click position and performing collision detection with the coal pile three-dimensional model to obtain intersection coordinates and a coal pile region identifier; determining the coal type category and the stock of the coal type category corresponding to the coal pile region identifier from a database, and displaying the coal type category and the stock of the coal type category on the operation screen.

[0016] According to a second aspect of the present disclosure, a coal pile three-dimensional dynamic monitoring device is provided, comprising:

[0017] An acquisition unit is configured to acquire coal pile contour data.

[0018] A calling unit is configured to call a three-dimensional vector modeling engine to generate a coal pile three-dimensional model based on the coal pile contour data.

[0019] An updating unit is configured to update the coal pile three-dimensional model based on a preset animation engine at a preset frequency, and generate a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the stock of the coal type.

[0020] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0021] at least one processor; and

[0022] a memory connected in communication with the at least one processor; wherein

[0023] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0024] According to a fourth aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to perform the method of the first aspect.

[0025] The coal pile three-dimensional dynamic monitoring method, device, electronic device and storage medium provided by the present disclosure mainly include the following technical solutions: obtaining coal pile contour data; based on the coal pile contour data, calling a three-dimensional vector modeling engine to generate a coal pile three-dimensional model; and based on a preset animation engine, updating the coal pile three-dimensional model at a preset frequency to generate a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the inventory of the coal type. The present disclosure uses an automatic means to obtain coal pile contour data, and constructs a precise three-dimensional model with the help of a three-dimensional vector modeling engine, thereby avoiding the low efficiency and error problems caused by manual measurement in related technologies, significantly improving the monitoring efficiency and data accuracy. At the same time, the coal pile three-dimensional model is dynamically updated at a set frequency by the preset animation engine, which can track the evolution of the coal pile shape and the change of the coal inventory in real time, ensuring that the enterprise can master the latest data at any time. Based on the updated three-dimensional model, a coal pile monitoring report is generated, realizing the deep fusion of coal pile spatial form and coal type information, and providing comprehensive and accurate decision-making basis for coal enterprises.

[0026] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0027] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0028] Figure 1 A flowchart of a coal pile three-dimensional dynamic monitoring method provided by an embodiment of the present disclosure is shown in the figure;

[0029] Figure 2 A flowchart of another coal pile three-dimensional dynamic monitoring method provided by an embodiment of the present disclosure is shown in the figure;

[0030] Figure 3A structural schematic diagram of a coal pile three-dimensional dynamic monitoring device provided by an embodiment of the present disclosure is provided.

[0031] Figure 4 A schematic block diagram of an example electronic device provided by an embodiment of the present disclosure is provided. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, which should be considered in a descriptive sense only. Thus, it will be apparent to one of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0033] A coal pile three-dimensional dynamic monitoring method, device, electronic device and storage medium are described below with reference to the accompanying drawings.

[0034] Figure 1 A flowchart of a coal pile three-dimensional dynamic monitoring method provided by an embodiment of the present disclosure is provided.

[0035] As Figure 1 shown, the method comprises the following steps:

[0036] Step 101: Obtain coal pile contour data.

[0037] In an embodiment of the present disclosure, the present disclosure can collect coal pile surface discrete point data by means of a cantilever coal level detection device, implement recursive optimization processing on noise and dynamic deviation in the data, obtain optimized discrete point data, and then segment the data into mutually exclusive triangles and generate data that can accurately reflect the coal pile contour according to the empty circle criterion, thereby providing a basis for subsequent three-dimensional modeling.

[0038] Step 102: Based on the coal pile contour data, call a three-dimensional vector modeling engine to generate a coal pile three-dimensional model.

[0039] In an embodiment of the present disclosure, the present disclosure can import coal pile contour data into a three-dimensional vector modeling engine, use a surface reconstruction algorithm to generate a closed coal pile surface, and then use a mesh simplification algorithm to optimize the surface and remove redundant data, thereby outputting a more efficient and easier-to-process optimized coal pile three-dimensional model on the basis of ensuring model accuracy.

[0040] Step 103: Based on a preset animation engine, update the coal pile three-dimensional model at a preset frequency, to generate a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the inventory of the coal type.

[0041] In the embodiments of the present disclosure, the present disclosure can update the coal pile three-dimensional model according to the preset animation engine at a preset frequency (such as every hour, every day, etc.) to reflect the dynamic changes of the coal pile.

[0042] In the updating process, after updating the coal pile three-dimensional model according to the preset animation engine at a preset frequency, a mesh simplification algorithm can be further used to generate different precision model versions corresponding to the coal pile three-dimensional model; the distances between each region of the coal pile and the camera are determined, and based on a preset distance threshold, the precision model version corresponding to each region is determined; and the optimized coal pile three-dimensional model is generated by using the precision model version corresponding to each region, so as to adapt to the display requirements in different scenes.

[0043] Specifically, the present disclosure can generate different precision model versions corresponding to the coal pile three-dimensional model by using the mesh simplification algorithm, and these versions can be selected and used according to actual needs. The distances between each region of the coal pile and the camera are determined, and based on a preset distance threshold, the distance between each region and the camera is determined. For the region close to the camera, a high-precision model version is selected to ensure the display effect; for the region far away from the camera, a low-precision model version is selected to reduce the data amount. According to the determination result, the precision model version corresponding to each region is determined. The coal pile three-dimensional model is integrated and optimized by using the precision model version corresponding to each region, and the final optimized coal pile three-dimensional model is generated, which can improve the rendering efficiency under the premise of ensuring the display effect.

[0044] Meanwhile, the present disclosure can also extract features from the updated coal pile three-dimensional model, classify the coal types by combining a machine learning model, and obtain the coal type categories corresponding to the updated coal pile three-dimensional model; based on the volume of the coal pile corresponding to the coal pile three-dimensional model and the density corresponding to each coal type category, the inventory of each coal type category is determined; and by using the coal type categories and the inventory of each coal type category, a coal pile monitoring report containing the coal type categories and the inventory information is generated.

[0045] Specifically, the present disclosure extracts features from the updated coal pile three-dimensional model, and extracts feature information such as the shape, color, and texture of the coal pile. By combining a machine learning model (such as a support vector machine, a neural network, etc.), the feature information is analyzed and processed, and the coal in the coal pile is classified to obtain the coal type categories corresponding to the updated coal pile three-dimensional model. Based on the volume of the coal pile corresponding to the coal pile three-dimensional model and the density corresponding to each coal type category, the inventory of each coal type category is determined by the calculation method of volume multiplied by density. By using the coal type categories and the inventory of each coal type category, a coal pile monitoring report is generated, which contains the type and quantity information of various coals in the coal pile, and provides an important basis for the management and decision-making of coal enterprises.

[0046] Furthermore, the present disclosure can also display the updated three-dimensional model of the coal pile on the operation screen after updating the three-dimensional model of the coal pile according to the preset frequency based on the preset animation engine, so that the operator can intuitively view it and the operator can intuitively observe the real-time status of the coal pile. At the same time, in response to the operator's interactive instructions, when the operator clicks a certain position on the operation screen, the screen click position is determined, and collision detection is performed with the three-dimensional model of the coal pile through rays to obtain the intersection coordinates and the coal pile area identification to which it belongs (that is, rays are emitted from the screen click position, collision detection is performed with the three-dimensional model of the coal pile, and the intersection coordinates and the coal pile area identification to which it belongs are obtained), and the coal type category and inventory information of the corresponding area are queried and displayed from the database (that is, the coal type category and coal type category inventory corresponding to the coal pile area identification are determined from the database, so that the coal type category and coal type category inventory are displayed on the operation screen), realizing human-computer interaction and facilitating the operator to obtain detailed information.

[0047] In summary, the three-dimensional dynamic monitoring method for coal stacks provided by the embodiment of the present disclosure obtains coal stack contour data; based on the coal stack contour data, calls a three-dimensional vector modeling engine to generate a three-dimensional model of the coal stack; based on a preset animation engine, updates the three-dimensional model of the coal stack at a preset frequency, so as to generate a coal stack monitoring report based on the coal type and the inventory of the coal type in the updated three-dimensional model of the coal stack. The coal stack contour data is obtained by automated means, and an accurate three-dimensional model is constructed with the help of a three-dimensional vector modeling engine, thereby avoiding the inefficiency and error problems caused by manual measurement in related technologies, significantly improving monitoring efficiency and data accuracy, and at the same time, dynamically updating the three-dimensional model of the coal stack at a set frequency through a preset animation engine can track the evolution of the coal stack morphology and changes in the inventory of coal types in real time, ensuring that the enterprise has the latest data at any time, and generating a coal stack monitoring report based on the updated three-dimensional model, which deeply integrates the spatial morphology of the coal stack with the coal type information, and provides a comprehensive and accurate decision-making basis for coal enterprises.

[0048] Figure 2 A schematic flow chart of another method for three-dimensional dynamic monitoring of coal stacks provided in an embodiment of the present disclosure. Figure 2 based on Figure 1 In the embodiment shown, step 101 and step 102 are further defined. Figure 2 In the embodiment shown, step 101 includes step 201, step 202 and step 203, and step 102 includes step 204 and step 205. Figure 2 As shown, the method includes the following steps.

[0049] Step 201: Collect discrete point data on the surface of the coal pile through a cantilever coal level detection device.

[0050] In the embodiments of the present disclosure, the present disclosure can use a cantilever coal level detection device to comprehensively scan the surface of the coal pile and obtain a large amount of discrete point data of the surface of the coal pile, which contains the position information of the surface of the coal pile and is the basis for generating the coal pile contour data.

[0051] Specifically, the cantilever coal level detection device is installed in a suitable position in advance (the suitable position can be adjusted according to actual conditions and manual experience, which is not limited in the embodiments of the present disclosure), so that it can cover the surface of the coal pile. The cantilever coal level detection device uses sensor technologies such as laser and ultrasonic wave to scan the surface of the coal pile according to certain sampling frequency and spatial distribution rules, obtains the position coordinates (such as three-dimensional coordinates x, y, z) of each sampling point, and forms a discrete point data set of the surface of the coal pile, that is, the discrete point data of the surface of the coal pile in the present disclosure. For example, the laser sensor emits a laser beam to irradiate the surface of the coal pile, and the position information of the sampling point is calculated by measuring the reflection time and angle of the laser beam.

[0052] In step 202, the noise and dynamic deviation in the discrete point data of the surface of the coal pile are recursively optimized to obtain the optimized discrete point data of the surface of the coal pile.

[0053] In the embodiments of the present disclosure, since the discrete point data of the surface of the coal pile collected may contain noise (such as abnormal data points caused by equipment errors and environmental interference) and dynamic deviation (such as slight fluctuations on the surface of the coal pile), the present disclosure can use filtering algorithms and recursive algorithms to recursively optimize and process these data, remove the noise and correct the dynamic deviation, and obtain more accurate and reliable optimized discrete point data of the surface of the coal pile.

[0054] Specifically, the present disclosure can use filtering algorithms such as Gaussian filtering and median filtering to reduce the noise of the discrete point data of the surface of the coal pile. Taking Gaussian filtering as an example, the present disclosure can use a Gaussian function to perform weighted average on the discrete point data, the weight is determined according to the distance between the point and the center point, and the weight is larger when the distance is closer, so as to smooth the data and reduce the influence of noise.

[0055] Meanwhile, the present disclosure uses recursive algorithms such as Kalman filtering. Kalman filtering is based on system state model and measurement model to predict and update the above-mentioned noise-reduced discrete point data. In each recursive step, the optimal state estimation value is calculated according to the current measurement value and the prediction value of the last step, and the state covariance matrix is updated to reflect the uncertainty of the estimation. Through continuous iteration, the dynamic deviation is gradually reduced, and the optimized discrete point data is obtained.

[0056] In step 203, the optimized discrete point data of the surface of the coal pile is divided into mutually exclusive triangles, and the coal pile contour data is generated according to the empty circle criterion.

[0057] In embodiments of the present disclosure, the optimized discrete point data of the coal pile surface is divided into mutually exclusive triangles, i.e., there is no overlapping part between the triangles, and the triangles can completely cover the coal pile surface. Then, the triangles are further processed according to the empty circle criterion (in the triangulation, no other points are contained in the circumscribed circle of each triangle), and finally the coal pile contour data capable of accurately describing the contour of the coal pile is generated.

[0058] Specifically, the present disclosure can use a triangulation algorithm, such as Delaunay triangulation, to divide the optimized discrete point data into mutually exclusive triangles by constructing a triangulation mesh satisfying the empty circle criterion. The empty circle criterion requires that no other discrete points are contained in the circumscribed circle of each triangle, which can ensure the quality and stability of the triangulation mesh.

[0059] Then, the boundary extraction is performed on the triangulation mesh, and the contour boundary of the coal pile is determined according to the connection relationship and position information of the triangles. For example, by traversing the triangulation mesh, the triangles located on the boundary are found, and the edges of these triangles are connected to form the coal pile contour data of the coal pile.

[0060] In step 204, the coal pile contour data is imported into a three-dimensional vector modeling engine, and a closed coal pile surface is generated by a surface reconstruction algorithm.

[0061] In embodiments of the present disclosure, the present disclosure can import the obtained coal pile contour data into a three-dimensional vector modeling engine, and process the contour data using a surface reconstruction algorithm to generate a closed coal pile surface, which can intuitively show the shape and structure of the coal pile.

[0062] Specifically, the present disclosure can import the coal pile contour data into a three-dimensional vector modeling engine, such as Blender or 3ds Max, in a specific file format (such as OBJ, STL, etc.). Then, a surface reconstruction algorithm is used, such as calling the Poisson surface reconstruction algorithm by writing a script (such as a Python script for Blender), to treat the coal pile contour data as an indicator function, solve the Poisson equation to obtain an implicit surface, and then convert the implicit surface to an explicit triangular mesh surface, thereby generating a closed coal pile surface. That is, the coal pile contour data is regarded as an indicator function, which takes the value of 1 inside the coal pile and 0 outside. In actual processing, an approximate indicator function is constructed according to the discrete point set, and the normal vector of each point is estimated by a neighborhood search algorithm (such as K-neighbor algorithm). Then, a vector field is constructed by combining the distance information from the point to the contour, and the direction of the vector field points to the inside of the coal pile, and the size is related to the distance and the direction of the normal vector. Then, the Poisson equation is solved (F is an indicator function, V is a vector field), the space is discretized into a voxel grid using the finite difference method, the equation is discretized into a linear equation Ax = b (A is the coefficient matrix, x is the discrete value of the indicator function, and b is the constant vector) and solved to obtain the discrete value of the indicator function; finally, the Marching Cubes algorithm is used to extract the isosurface (usually F = 0.5) from the discrete value of the indicator function, each voxel is divided into different topological structures, the connection mode of the isosurface is determined according to the value of the indicator function at the vertex of the voxel, and a smooth and closed coal pile surface is obtained after processing by the Laplace smoothing algorithm.

[0063] In step 205, the coal pile surface is optimized by a mesh simplification algorithm, and an optimized coal pile three-dimensional model is output.

[0064] In the embodiments of the present disclosure, since the generated coal pile surface may contain a large number of triangular meshes, the model data is too large, which is not conducive to subsequent processing and display. Therefore, the present disclosure can use a mesh simplification algorithm (such as an edge collapse algorithm) to optimize the coal pile surface, reduce the number of triangular meshes under the premise of ensuring the accuracy of the model, output an optimized coal pile three-dimensional model, and improve the processing efficiency and display effect of the model.

[0065] Specifically, the present disclosure can use a mesh simplification algorithm, such as a vertex clustering algorithm, an edge collapse algorithm, etc. Taking the edge collapse algorithm as an example, the present disclosure can reduce the number of triangles by collapsing the edges in the mesh. When collapsing the edges, the position of the vertex after collapsing is calculated according to the length, angle and geometric characteristics of the surrounding triangles of the edge, and the connection relationship of the vertex and the triangle related to the collapsed edge is updated. After multiple edge collapse operations, the coal pile surface mesh is gradually simplified, and an optimized coal pile three-dimensional model is obtained and output as a common three-dimensional model file format, such as FBX, OBJ, etc.

[0066] In step 206, the coal pile three-dimensional model is updated at a preset frequency based on a preset animation engine to generate a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the inventory of the coal type.

[0067] In the embodiments of the present disclosure, the present disclosure can select a suitable preset animation engine, such as Unity or UnrealEngine. These engines have powerful three-dimensional graphics rendering and animation processing capabilities. A new project is created in the engine, and the optimized coal pile three-dimensional model file (such as FBX, OBJ format) is imported. Scene parameters are set according to actual needs, for example, lighting conditions (simulate lighting at different time periods, such as sunlight or light effects during the day and night), camera perspective (determine the viewing angle and motion trajectory of the coal pile), etc., to present a more realistic coal pile scene.

[0068] Establish an interface with external data sources (such as sensor systems, databases, etc.) to obtain real-time or regularly updated coal pile-related data, such as changes in coal level height, fine-tuning information for coal pile shape, etc. For example, communicate with the sensor system through the TCP / IP protocol to receive the coal level data sent by the sensor.

[0069] Use a scripting language (such as C# in Unity, Blueprints or C++ in UnrealEngine) in the animation engine to write update logic. According to the preset frequency (such as every 5 minutes, every hour, etc.), trigger the update operation at regular intervals. In the update operation, dynamically adjust the coal pile three-dimensional model according to the obtained external data. For example, if the coal level height data changes, adjust the vertex position or scale of the corresponding part in the model to make the model reflect the actual change in coal pile height.

[0070] To make the model updating process smoother and more natural, the present disclosure can add animation transition effects. For example, when the coal level height changes, use an easing function (such as ease-in-out) to control the change speed of the model height, avoiding abrupt jumps.

[0071] At the same time, the present disclosure can perform feature extraction on the updated coal pile three-dimensional model. Computer vision and image processing techniques can be used to extract features such as color, texture, shape, etc. from the model. For example, by analyzing the color distribution on the surface of the model, different colored coal regions can be distinguished; use texture analysis algorithms (such as gray level co-occurrence matrix) to extract texture features of the coal surface. Use a pre-trained machine learning model (such as support vector machine, convolutional neural network, etc.) to classify the extracted features. The training data can come from historical coal pile samples, each sample containing the three-dimensional model features of the coal pile and the corresponding coal type label. Input the features of the updated model into the classification model to get the coal type of different regions in the coal pile. Calculate the volume of the coal pile based on the updated coal pile three-dimensional model. Three-dimensional geometric algorithms such as polygon mesh volume calculation method can be used to traverse the triangular facets of the model, calculate the volume of each facet, and then accumulate to get the volume of the entire coal pile. Obtain the density values corresponding to different coal types from the database or relevant materials. According to the volume of the coal pile and the density of each coal type, calculate the inventory of each coal type. The calculation formula is: inventory = volume x density.

[0072] After that, the content structure of the monitoring report is determined, including coal pile basic information (such as location, number, etc.), coal type distribution (showing the distribution area and proportion of different coal types in the coal pile in the form of charts or text), inventory statistics of each coal type (listing the inventory value of each coal type), and total volume of the coal pile. The calculated data such as coal type, inventory, and coal pile volume are integrated into the report template. Programming languages such as Python can be used in combination with report generation libraries such as ReportLab to realize automatic filling of data.

[0073] To make the report more intuitive and easy to understand, the present disclosure can further add visual elements. For example, use chart libraries such as Matplotlib and ECharts to generate coal type distribution pie charts, bar charts, etc., to show the proportion and inventory of different coal types. The generated monitoring report is saved in common file formats such as PDF, Word, or Excel. The report can be sent to a designated storage location (such as a local disk, a network server) through a programming interface or sent to relevant personnel by email.

[0074] In summary, the present disclosure accurately imports coal pile contour data into a three-dimensional vector modeling engine and uses a Poisson surface reconstruction algorithm for efficient processing, achieving high-quality conversion from a discrete point set to a closed and smooth coal pile surface. The generated three-dimensional model not only retains the geometric features of the coal pile completely, but also significantly improves the restoration and smoothness of surface details through the conversion of implicit surfaces to explicit triangular meshes, providing accurate and reliable three-dimensional data foundation for subsequent coal pile monitoring, volume calculation, and visualization analysis, while supporting users to flexibly adjust parameters and perform secondary editing according to actual needs, with high practicality and expandability.

[0075] Corresponding to the above-mentioned coal pile three-dimensional dynamic monitoring method, the present disclosure also proposes a coal pile three-dimensional dynamic monitoring device. Since the device embodiments of the present disclosure correspond to the above-mentioned method embodiments, for details not disclosed in the device embodiments, reference can be made to the above-mentioned method embodiments, which will not be described in detail in the present disclosure.

[0076] Figure 3 A structural schematic diagram of a coal pile three-dimensional dynamic monitoring device provided by an embodiment of the present disclosure is shown in Figure 3 , which includes:

[0077] The acquisition unit 310 is configured to acquire coal pile contour data.

[0078] The calling unit 320 is configured to call a three-dimensional vector modeling engine to generate a coal pile three-dimensional model based on the coal pile contour data.

[0079] The updating unit 330 is configured to update the coal pile three-dimensional model based on a preset animation engine at a preset frequency, so as to generate a coal pile monitoring report according to the coal type of the updated coal pile three-dimensional model and the stock of the coal type.

[0080] In some embodiments, the acquisition unit 310 is configured to: collect coal pile surface discrete point data by the cantilever coal level detection device; recursively optimize noise and dynamic deviation in the coal pile surface discrete point data to obtain optimized coal pile surface discrete point data; and segment the optimized coal pile surface discrete point data into mutually exclusive triangles, and generate coal pile contour data according to the empty circle criterion.

[0081] In some embodiments, the calling unit 320 is configured to: import the coal pile contour data into a three-dimensional vector modeling engine, and generate a closed coal pile surface by a surface reconstruction algorithm; and optimize the coal pile surface by a mesh simplification algorithm, and output an optimized coal pile three-dimensional model.

[0082] In some embodiments, the updating unit 330 is configured to: after updating the coal pile three-dimensional model based on the preset animation engine at the preset frequency, generate different precision model versions corresponding to the coal pile three-dimensional model by using the mesh simplification algorithm; determine the distance between each region of the coal pile and the camera, and determine the precision model version corresponding to each region based on a preset distance threshold; and generate the optimized coal pile three-dimensional model by using the precision model version corresponding to each region.

[0083] In some embodiments, the updating unit 330 is configured to: extract features from the updated coal pile three-dimensional model, classify the coal type by combining a machine learning model, and obtain the coal type corresponding to the updated coal pile three-dimensional model; determine the stock of each coal type based on the volume of the coal pile corresponding to the coal pile three-dimensional model and the density corresponding to each coal type; and generate a coal pile monitoring report by using the coal type and the stock of each coal type.

[0084] In some embodiments, the updating unit 330 is configured to: after updating the coal pile three-dimensional model based on the preset animation engine at the preset frequency, display the updated coal pile three-dimensional model on an operation screen.

[0085] In some embodiments, the updating unit 330 is configured to: after displaying the updated coal pile three-dimensional model on the operation screen, determine a screen click position according to an interactive instruction of an operator; emit a ray from the screen click position, and perform collision detection with the coal pile three-dimensional model to obtain intersection coordinates and a coal pile region identifier to which the intersection coordinates belong; determine the coal type corresponding to the coal pile region identifier and the stock of the coal type from a database, and display the coal type and the stock of the coal type on the operation screen.

[0086] It should be noted that the foregoing description of the method embodiments applies equally to the apparatus embodiments of the present disclosure, and the principles are the same, and the apparatus embodiments of the present disclosure are not limited herein.

[0087] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0088] Figure 4 A schematic block diagram of an example electronic device 400 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 laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0089] As shown in Figure 4 The device 400 includes a computing unit 401 that can perform various appropriate actions and processes in accordance with a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded into a RAM (Random Access Memory) 403 from a storage unit 408. Various programs and data required for the operation of the device 400 can also be stored in the RAM 403. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0090] Various components in the device 400 are connected to the I / O interface 405, including an input unit 406, such as a keyboard, a mouse, etc., an output unit 407, such as various types of displays, speakers, etc., a storage unit 408, such as a magnetic disk, an optical disk, etc., and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0091] The computing unit 401 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs various methods and processes described above, such as the coal pile three-dimensional dynamic monitoring method. For example, in some embodiments, the coal pile three-dimensional dynamic monitoring method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform the aforementioned coal pile three-dimensional dynamic monitoring method by any other appropriate means, such as by means of firmware.

[0092] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a Field Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a System on Chip (SOC), a Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0093] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0094] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage medium can include, without limitation, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory), or flash memory, fiber optics, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0095] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; 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 acoustic, speech, or tactile input.

[0096] The systems and techniques described here can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0097] The computer system can include clients and servers. The clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server is one of communication and distribution, with the server receiving requests from the client and transmitting responses via the communication network. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system. The server can also be a server of a distributed system, or a server combined with a blockchain.

[0098] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors of people (such as learning, reasoning, thinking, planning, etc.), which has both hardware and software technologies. Artificial intelligence hardware technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technology mainly includes computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc. several major directions.

[0099] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which is not limited herein.

[0100] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the disclosure.

Claims

1. A three-dimensional dynamic monitoring method for coal stacks, characterized in that: The method comprises: Obtain coal pile contour data; Based on the coal pile contour data, a three-dimensional vector modeling engine is called to generate a three-dimensional model of the coal pile; The coal stack three-dimensional model is updated at a preset frequency based on a preset animation engine to generate a coal stack monitoring report according to the coal type and the inventory of the coal type in the updated coal stack three-dimensional model.

2. The method according to claim 1, characterized in that The obtaining of coal pile contour data comprises: Collecting discrete point data on the coal pile surface through the cantilever coal level detection device; Recursively optimizing the noise and dynamic deviation in the coal pile surface discrete point data to obtain optimized coal pile surface discrete point data; The optimized discrete point data on the coal pile surface are divided into mutually exclusive triangles, and the coal pile contour data are generated according to the empty circle criterion.

3. The method according to claim 1, characterized in that The generating of the three-dimensional model of the coal stack by calling a three-dimensional vector modeling engine based on the coal stack contour data comprises: Importing the coal pile contour data into the three-dimensional vector modeling engine, and generating a closed coal pile surface through a surface reconstruction algorithm; The coal pile surface is optimized by a mesh simplification algorithm, and an optimized coal pile three-dimensional model is output.

4. The method according to claim 1, wherein After the coal pile three-dimensional model is updated according to a preset frequency based on a preset animation engine, the method includes: Using a mesh simplification algorithm to generate model versions of different accuracies corresponding to the three-dimensional model of the coal pile; Determine the distance between each area of ​​the coal stack and the camera, and based on a preset distance threshold, determine the model version with the corresponding accuracy for each area; The model version with the corresponding accuracy for each area is used to generate an optimized three-dimensional model of the coal pile.

5. The method according to claim 1, wherein Generating a coal pile monitoring report based on the coal type and the inventory of the coal type in the updated three-dimensional model of the coal pile includes: Performing feature extraction on the updated three-dimensional model of the coal stack, and classifying the coal types in combination with a machine learning model to obtain the coal type category corresponding to the updated three-dimensional model of the coal stack; Determining the inventory of each type of coal based on the volume of the coal pile corresponding to the three-dimensional model of the coal pile and the density corresponding to each type of coal; A coal pile monitoring report is generated using the coal type categories and the inventory of each coal type category.

6. The method according to claim 1, characterized in that The method then includes: updating the coal pile three-dimensional model based on a preset animation engine according to a preset frequency; The updated three-dimensional model of the coal stack is displayed on the operation screen.

7. The method according to claim 1, characterized in that The updated coal pile three-dimensional model is displayed on the operation screen, and then the method includes: Respond to operator interaction instructions and determine the screen click location; Emitting a ray from the clicked position on the screen, performing collision detection with the three-dimensional model of the coal pile, and obtaining the intersection coordinates and the identification of the coal pile area to which it belongs; The coal type category and the coal type category inventory corresponding to the coal pile area identification are determined from a database, so as to display the coal type category and the coal type category inventory on the operation screen.

8. A three-dimensional dynamic monitoring device for coal stacks, characterized in that: The device comprises: An acquisition unit, used for acquiring coal pile contour data; A calling unit, configured to call a three-dimensional vector modeling engine to generate a three-dimensional model of the coal stack based on the coal stack contour data; An updating unit is used to update the three-dimensional model of the coal stack according to a preset frequency based on a preset animation engine, so as to generate a coal stack monitoring report according to the coal type and the inventory of the coal type in the updated three-dimensional model of the coal stack.

9. 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images