Automatic coal inventory system based on artificial intelligence and depth data

Abstract

The invention discloses an automatic coal stocktaking system based on artificial intelligence and depth data, which comprises no less than three groups of coal stocktaking devices uniformly arranged at the top of each circular coal yard, each coal stocktaking device comprises a laser scanner, a rotary holder, a protective cover and a bracket, and further comprises a data acquisition module, a volume estimation unit and a wireless communication module, the volume estimation module is configured to perform volume estimation based on the three-dimensional model. The invention belongs to the technical field of artificial intelligence, and effectively solves the long-standing problems of low automation degree, high labor intensity, slow data acquisition, long data processing time and poor accuracy of a traditional coal stocktaking method in a coal yard.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence, and specifically refers to an automatic coal yard inventory system based on artificial intelligence and deep data. Background Art

[0002] Coal yard inventory is to take inventory of the coal storage in a thermal power plant, which is divided into manual inventory and laser coal yard inventory. With the continuous rise of the current thermal coal price, the coal management in thermal power plants is an important part of production management. The monthly benefits of thermal power plants are closely related to the power generation and coal consumption, which has a direct impact on the economic operation of the power plant. Since the fuel cost of thermal power plants accounts for the vast majority of the entire production cost, the measurement of the coal storage in the coal yard directly affects the economic indicators of the power plant. Therefore, quickly and accurately measuring the volume and quality of the coal piles in the coal yard is a routine task for each power plant to conduct cost accounting, economic benefit evaluation and scientific management. The inventory of the coal storage in the coal yard also ensures the rationality of the coal yard reserve. With the expansion of thermal power plant units and the increase of coal prices, coal yard inventory has increasingly become an indispensable link for power generation enterprises. The method of coal yard inventory has evolved from the original manual tape measure coal yard inventory to high-tech laser automatic coal yard inventory. The main principle of manual inventory is as follows: First, the piled coal is shaped by a bucket wheel stacker-reclaimer, usually into a relatively regular trapezoid or rectangle. Then, it is manually measured with a tape measure, and its volume is obtained through calculation, and the weight is obtained according to the density. The main principle of the laser automatic coal yard inventory instrument is as follows: A high-precision laser scanner is used to collect the surface of the stockyard. Through computer processing of the stockpile contour data, a 3D graph of the stockyard is reconstructed, and information such as the volume of the stockpile is calculated. Combining the set density, the weight of the stockpile is obtained.

[0003] An automatic coal yard inventory system is an automated system applied to coal mines, power plants, and steel mills, used to automate the process of coal collection, transportation, and loading. Using modern technologies and equipment, it replaces traditional manual operations and improves production efficiency and safety. However, the automatic coal yard inventory system has poor adaptability to changes in coal piles. Therefore, there is a coal pile detection operation in the actual automatic coal yard inventory system. Since the coal pile and the surrounding environment are basically black scenes affected by long-term stacking, it is difficult to distinguish the changes in different coal piles from ordinary images. Therefore, generally, lidar equipment is used to obtain the point cloud data of the coal pile, and the situation of the coal pile is judged by analyzing the point cloud data.

[0004] In the coal unloading ditch, the phenomenon of coal blending is widespread, and the means of manually recording coal quality are too traditional and extensive. Moreover, coal blending also exists in the transfer station during the coal unloading process, making it difficult to provide accurate identification results. Summary of the Invention

[0005] The technical problem to be solved by the present invention is the problems existing in the traditional coal yard coal inventory method for a long time, such as low automation level, high labor intensity, slow data acquisition, long data processing time, and poor accuracy.

[0006] The technical solution adopted by the present invention is as follows: The automatic coal inventory system based on artificial intelligence and depth data proposed by the present invention includes a coal inventory device. There are no less than three groups of the coal inventory devices, which are evenly arranged on the top of each circular coal yard. The coal inventory device includes a laser scanner, a rotary cloud platform, a protective cover, and a bracket, and further includes a data acquisition module, a volume estimation unit, and a wireless communication module. The volume estimation module is configured to perform volume estimation based on the three-dimensional model.

[0007] Further, the data acquisition module constructs a three-dimensional coordinate system, projects auxiliary points onto the three-dimensional coordinate system, and the scan data obtained by the laser scanners distributed within the coal yard range can be fused to generate a unified three-dimensional model of the coal yard.

[0008] Further, a fine triangulation algorithm is adopted to reconstruct the triangular mesh of all three-dimensional point data on the cross-sections, obtain the three-dimensional coordinates of the coal yard surface in real time and dynamically, and realize the function of importing the three-dimensional point cloud data into the platform 3D modeling system through the wireless communication module, so as to realize the real-time update of the material yard data on the three-dimensional platform.

[0009] Further, when the volume estimation unit performs volume estimation, it performs surface mesh reconstruction based on the mesh reconstruction algorithm for the three-dimensional model, calculates the projected area of each mesh on the XY plane, and further obtains the elevation information of the three-dimensional model in the Y-axis direction of the three-dimensional coordinate system. Based on the discrete integral algorithm, an estimated value of the coal pile volume is obtained.

[0010] Further, the scan data is first accessed through the network to the data server of the stacker-reclaimer unattended system for processing. The data can be compared and merged with the real-time three-dimensional model of the background of the unmanned aerial vehicle (UAV) monitoring system and automatically delete the invalid points to obtain the three-dimensional model data of the coal yard.

[0011] Further, the scan inventory work is manually controlled, or the automatic scan inventory is set at time intervals.

[0012] Further, when the scan unit enters the next scan cycle, the data of the changed part of the coal yard is compared and updated, and the time stamp of the three-dimensional model is marked for the updated data.

[0013] Further, a three-dimensional point cloud database of the coal pile is built to store and access the three-dimensional modeling of the coal pile and the real-time three-dimensional state information of the coal pile. The point cloud data can be transferred in and out, and the data can be viewed through software. The point cloud data should support the use and viewing by third-party software.

[0014] Furthermore, the display modes of the three-dimensional model include point cloud model, wireframe model, solid model, terrain model, mesh model, and simulation model.

[0015] Furthermore, the reference plane and coordinate axes can be displayed, and operations such as zooming in, zooming out, panning, and rotating of the three-dimensional model are supported.

[0016] Compared with the prior art, the beneficial effects achieved by the present invention with the above structure are as follows:

[0017] 1. Process visualization and information integration: By setting up an operation station related to the digital coal yard in the coal conveying centralized control room, the equipment automation and working process become more visualized and information-integrated, reducing the management complexity and also contributing to fault diagnosis and equipment maintenance;

[0018] 2. Improvement of the personnel operation environment: Automated operations reduce the labor intensity and risks during operations.

[0019] 3. Enhancement of the enterprise economic benefits: By improving the automation level of the system, this project helps to enhance the economic benefits and production safety of the enterprise. This promotes the comprehensive improvement of quality and efficiency of the enterprise, and enhances its competitiveness and sustainability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow schematic diagram of the automatic coal inventory system based on artificial intelligence and deep data according to an embodiment of the present invention;

[0021] Figure 2 It is a structural schematic diagram of the coal inventory device according to an embodiment of the present invention;

[0022] Figure 3 It is a schematic diagram of the display mode categories of the three-dimensional model according to an embodiment of the present invention.

[0023] The drawings are used to provide a further understanding of the invention and constitute a part of the specification. They are used to explain the invention together with the embodiments of the invention and do not constitute a limitation to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0025] As shown in the figure, the automatic coal yard inventory system based on artificial intelligence and deep data proposed by the present invention includes a coal yard inventory device. There are no less than three groups of the coal yard inventory devices, which are evenly arranged on the top of each circular coal yard. The coal yard inventory device includes a laser scanner, a rotating cloud platform, a protective cover and a bracket, and also includes a data acquisition module, a volume estimation unit and a wireless communication module. The volume estimation module is configured to estimate the volume based on the three-dimensional model.

[0026] The data acquisition module constructs a three-dimensional coordinate system and projects auxiliary points onto the three-dimensional coordinate system. The scan data obtained by the laser scanners distributed within the coal yard range can be fused to generate a unified three-dimensional model of the coal yard. Using a fine triangulation algorithm, the three-dimensional point data on all cross-sections is reconstructed into a triangular mesh to dynamically obtain the three-dimensional coordinates of the coal yard surface in real time. The three-dimensional point cloud data is imported into the platform 3D modeling system function through the wireless communication module to realize the real-time update of the material yard data on the three-dimensional platform.

[0027] When the volume estimation unit performs volume estimation, it performs surface mesh reconstruction based on the mesh reconstruction algorithm for the three-dimensional model, calculates the projected area of each mesh on the XY plane, and then obtains the elevation information of the three-dimensional model in the Y-axis direction of the three-dimensional coordinate system. Based on the discrete integral algorithm, an estimated value of the coal pile volume is obtained.

[0028] The scan data is first connected to the data server of the unattended system of the stacker-reclaimer through the network for processing. The data can be compared and merged with the real-time three-dimensional model of the background of the unmanned aerial vehicle (UAV) system and the waste points can be automatically deleted to obtain the three-dimensional model data of the coal yard.

[0029] The manual control of the scanning and inventory work can also be set with a time interval for automatic scanning and inventory. Through timing control, the automatic cyclic scanning work is realized with a unit time as the cycle, reducing the trouble of manual operation.

[0030] When the scanning unit enters the next scanning cycle, the data of the changed part of the coal yard is compared and updated. After the update, the time tag of the three-dimensional model is marked for the data. After establishing the time tag, it is convenient to query and accurately locate the information at different times, facilitating the extraction and archiving of information.

[0031] During specific use, during the coal yard inventory process, data is dynamically collected and quickly calculated. The real-time scanning imaging delay is controlled within 2 seconds; during the coal yard inventory process, the three-dimensional contour of the changed coal pile in the coal yard layout map is dynamically updated, and the three-dimensional image refresh frequency should be controlled within 10 seconds; the entire coal yard inventory process is controlled within 5 minutes to achieve accurate and rapid response.

[0032] After selecting the target coal pile, the system automatically calculates information such as the length, width, height, volume, and material properties of the coal pile. The errors between the calculated length, width, and height of the three-dimensional imaging of the coal pile and the actual measurement are all less than 10 centimeters.

[0033] Build a 3D point cloud database for coal piles to store 3D modeling of coal piles and real-time 3D status information of coal piles. The point cloud data can be transferred in and out, and the data can be viewed through software. The point cloud data should support the use and viewing of third-party software.

[0034] The display modes of the 3D model include point cloud model, wireframe model, solid model, terrain model, mesh model, and simulation model. The reference plane and coordinate axes can be displayed, and operations such as zooming in, zooming out, panning, and rotating of the 3D model are supported.

[0035] Adopt a fixed installation method to achieve full coverage, fast response, no measurement dead angle, and real-time dynamic 3D scanning imaging. The system should collect the full-field coal pile data within 5 minutes, quickly establish a 3D model of the yard, and the relative measurement accuracy should meet within 5‰. The above is the usage process of the entire automatic coal inventory system based on artificial intelligence and depth data.

[0036] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0037] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

[0038] The above describes the present invention and its implementation manners. This description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. All in all, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments without creative efforts without departing from the purpose of the present invention, they should all fall within the protection scope of the present invention.

Claims

1. Automatic coal handling system based on artificial intelligence and deep data, characterized by: It includes a coal pan device, which has no less than three groups and is evenly arranged on the top of each circular coal yard. The coal pan device includes a laser scanner, a rotating pan head, a protective cover and a bracket, and also includes a data acquisition module, a volume estimation unit, and a wireless communication module. The volume estimation module is configured to perform volume estimation based on the three-dimensional model.

2. The automatic coal handling system based on artificial intelligence and deep data according to claim 1 is characterized by: The data acquisition module constructs a three-dimensional coordinate system and projects the auxiliary points into the three-dimensional coordinate system. The scanning data acquired by the laser scanners distributed within the coal yard can be fused to generate a unified three-dimensional model of the coal yard.

3. The automatic coal handling system based on artificial intelligence and deep data according to claim 2 is characterized by: A sophisticated meshing algorithm is used to reconstruct the triangulated network of the three-dimensional point data on all sections, and the three-dimensional coordinates of the coal yard surface are obtained in real time and dynamically. The three-dimensional point cloud data is imported into the platform's 3D modeling system through the wireless communication module, realizing real-time update of the material yard data on the three-dimensional platform.

4. The automatic coal handling system based on artificial intelligence and deep data according to claim 3 is characterized by: When performing volume estimation, the volume estimation unit performs surface mesh reconstruction based on a mesh reconstruction algorithm for the three-dimensional model, calculates the projection area of ​​each mesh on the XY plane, and then obtains the elevation information of the three-dimensional model in the Y-axis direction of the three-dimensional coordinate system based on a discrete integration algorithm to obtain an estimated value of the coal pile volume.

5. The automatic coal handling system based on artificial intelligence and deep data according to claim 4 is characterized by: The scanned data is first connected to the data server of the unmanned system of the stacker and reclaimer through the network for processing. The data can be compared and spliced ​​with the real-time three-dimensional model of the background of the drone duty system, and waste points can be automatically deleted to obtain the three-dimensional model data of the coal yard.

6. The automatic coal handling system based on artificial intelligence and deep data according to claim 5 is characterized by: Manually control the scanning and inventory work, or set time intervals for automatic scanning and inventory.

7. The automatic coal handling system based on artificial intelligence and deep data according to claim 6 is characterized by: When the scanning unit enters the next scanning cycle, the data of the changed part of the coal yard is compared and updated, and the updated data is marked with the time tag of the three-dimensional model.

8. The automatic coal handling system based on artificial intelligence and deep data according to claim 7 is characterized by: Build a three-dimensional point cloud database of the coal pile to store and access the three-dimensional modeling of the coal pile and the real-time three-dimensional status information of the coal pile. Point cloud data can be transferred in and out, and data can be viewed through software. Point cloud data should support use and viewing by third-party software.

9. The automatic coal handling system based on artificial intelligence and deep data according to claim 8 is characterized by: The display modes of 3D models include point cloud model, wireframe model, stereo model, terrain model, grid model and simulation model.

10. The automatic coal handling system based on artificial intelligence and deep data according to claim 9 is characterized by: The reference plane and coordinate axis can be displayed, and operations such as zooming in, zooming out, translating, and rotating the 3D model are supported.

Images