Intelligent control method and device for hydraulic support and fully-mechanized coal mining face control platform

Abstract

The application provides a hydraulic support intelligent control method and device and a fully-mechanized coal mining face control platform.The method comprises the following steps: acquiring first point cloud data in real time, wherein the first point cloud data is point cloud data of a coal mining scene environment collected based on a view angle of a coal mining machine; acquiring second point cloud data in real time, wherein the second point cloud data is point cloud data of the coal mining scene environment collected based on a view angle of a hydraulic support; constructing a three-dimensional scene of the coal mining scene environment based on the first point cloud data and the second point cloud data; determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information affecting safe operation of the coal mining machine; determining a control strategy of the hydraulic support based on the key information of the coal mining scene, and controlling operation of the hydraulic support based on the control strategy. The application realizes intelligent control of the hydraulic support, can better match an operation state of the coal mining machine, and provides better support for the coal mining machine.

Description

Technical Field

[0001] This invention relates to the field of fully mechanized mining face technology, and in particular to an intelligent control method, device and control platform for hydraulic supports and fully mechanized mining faces. Background Technology

[0002] During the coal mining process, hydraulic supports are key support equipment, and their operating status directly affects coal mining efficiency and operational safety.

[0003] According to relevant technologies, the monitoring and control of the operating status of hydraulic supports heavily relies on human experience and judgment. Specifically, operators need to adjust the support height, support force, and timing of support movement in real time based on on-site parameters such as the location of the coal mining machine and the roof pressure, combined with their personal experience. This experience-driven operation mode is subject to the subjectivity of human experience, which can easily lead to judgment errors and make it difficult to guarantee the stability of the support effect. Moreover, it is costly and inefficient, making it difficult to meet the development needs of intelligent and unmanned operations in modern coal mines. Summary of the Invention

[0004] This invention provides a method, device, and control platform for intelligent control of hydraulic supports and fully mechanized mining faces, which realizes intelligent control of hydraulic supports, can better match the operating status of coal mining machines, and provide better support for coal mining machines.

[0005] This invention provides an intelligent control method for a hydraulic support. The method includes: acquiring first point cloud data in real time, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of a coal mining machine; acquiring second point cloud data in real time, wherein the second point cloud data is point cloud data of the coal mining scene environment collected from the perspective of a hydraulic support; constructing a three-dimensional scene of the coal mining scene environment based on the first point cloud data and the second point cloud data; determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information affecting the safe operation of the coal mining machine; determining a control strategy for the hydraulic support based on the key information of the coal mining scene, and controlling the operation of the hydraulic support based on the control strategy.

[0006] According to the intelligent control method for hydraulic supports provided by the present invention, the step of constructing a three-dimensional scene of a coal mining scenario based on the first point cloud data and the second point cloud data specifically includes: fusing the first point cloud data and the second point cloud data to obtain fused point cloud data; constructing global coordinates of the coal mining scenario based on the fused point cloud data; and constructing a three-dimensional scene of the coal mining scenario based on the global coordinates.

[0007] According to the intelligent control method for hydraulic supports provided by the present invention, before constructing a three-dimensional scene of the coal mining environment based on the global coordinates, the method further includes: performing redundancy removal processing on the global coordinates to obtain a first preprocessed global coordinate; performing gap filling processing on the first preprocessed global coordinate to obtain a second preprocessed global coordinate; the construction of the three-dimensional scene of the coal mining environment based on the global coordinates specifically includes: constructing the three-dimensional scene of the coal mining environment based on the second preprocessed global coordinate.

[0008] According to a hydraulic support intelligent control method provided by the present invention, before determining the control strategy of the hydraulic support based on the key information of the coal mining scenario, the method further includes: calling a pre-trained control strategy generation model, wherein the control strategy generation model is used to obtain a control strategy of the hydraulic support that matches the key information of the coal mining scenario based on the key information of the coal mining scenario; the determination of the control strategy of the hydraulic support based on the key information of the coal mining scenario specifically includes: inputting the key information of the coal mining scenario into the control strategy generation model to obtain the control strategy of the hydraulic support output by the control strategy generation model.

[0009] According to the intelligent control method for hydraulic supports provided by the present invention, the control strategy generation model is trained in the following manner: acquiring multiple sets of key information of historical coal mining scenarios, and historical control strategies of hydraulic supports corresponding to each set of key information of historical coal mining scenarios; constructing a training dataset based on multiple sets of key information of historical coal mining scenarios and corresponding historical control strategies of hydraulic supports; and training the control strategy generation model based on the training dataset to obtain a trained control strategy generation model.

[0010] According to the intelligent control method for hydraulic supports provided by the present invention, the key information of the coal mining scene includes at least one or more of the following: the running trajectory information of the coal mining machine, the speed information of the coal mining machine, the attitude information of the coal mining machine, the position information of the hydraulic support, the height information of the hydraulic support, and the geological information of the coal mining scene environment.

[0011] According to the intelligent control method for hydraulic supports provided by the present invention, the first point cloud data is obtained by means of a laser scanning device deployed on the coal mining machine.

[0012] According to the intelligent control method for hydraulic supports provided by the present invention, the second point cloud data is obtained by means of a laser scanning device deployed on the hydraulic support.

[0013] The present invention also provides an intelligent control device for a hydraulic support, the device comprising: a first acquisition module for acquiring first point cloud data in real time, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of a coal mining machine; a second acquisition module for acquiring second point cloud data in real time, wherein the second point cloud data is point cloud data of the coal mining scene environment collected from the perspective of a hydraulic support; a construction module for constructing a three-dimensional scene of the coal mining scene environment based on the first point cloud data and the second point cloud data; a determination module for determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information affecting the safe operation of the coal mining machine; and a generation module for determining a control strategy for the hydraulic support based on the key information of the coal mining scene, and controlling the operation of the hydraulic support based on the control strategy.

[0014] The present invention also provides a fully mechanized mining face control platform, the fully mechanized mining face control platform comprising: a coal mining machine equipped with a laser scanning device; a hydraulic support equipped with a laser scanning device; and a processor, wherein the processor is used to execute the intelligent control method for the hydraulic support as described in any one of the present invention. The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent control method for hydraulic supports as described above.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent control method for hydraulic supports as described above.

[0016] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the intelligent control method for hydraulic supports as described above.

[0017] This invention provides an intelligent control method, device, and fully mechanized mining face control platform for hydraulic supports. The method includes: real-time acquisition of first point cloud data, wherein the first point cloud data is point cloud data of the mining scene environment collected from the perspective of the coal mining machine; real-time acquisition of second point cloud data, wherein the second point cloud data is point cloud data of the mining scene environment collected from the perspective of the hydraulic support; constructing a three-dimensional scene of the mining scene environment based on the first and second point cloud data; determining key information of the mining scene based on the three-dimensional scene, wherein the key information of the mining scene is scene information affecting the safe operation of the coal mining machine; determining a control strategy for the hydraulic support based on the key information of the mining scene, and controlling the operation of the hydraulic support based on the control strategy. This achieves intelligent control of the hydraulic support, enabling better matching of the operating status of the coal mining machine and providing better support for the coal mining machine. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the intelligent control method for hydraulic supports provided by the present invention.

[0020] Figure 2 This is a flowchart illustrating the process of constructing a three-dimensional scene of a coal mining environment based on the first point cloud data and the second point cloud data provided by the present invention.

[0021] Figure 3 This is a schematic diagram of the process of constructing a three-dimensional scene of the coal mining scenario environment based on the global coordinates provided by the present invention.

[0022] Figure 4 This is a structural schematic diagram of the intelligent control device for hydraulic supports provided by the present invention.

[0023] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0025] The intelligent control method for hydraulic supports provided by this invention achieves all-round three-dimensional spatial perception of the working face by deploying a distributed lidar network (corresponding to a laser scanning device) on the coal mining machine and the hydraulic supports; it integrates multi-source heterogeneous point cloud data into a unified three-dimensional scene by using data processing and fusion technology; and it generates precise collaborative control commands based on intelligent decision-making algorithms to drive the hydraulic supports and the coal mining machine to achieve efficient collaborative operation.

[0026] Figure 1 This is a flowchart illustrating the intelligent control method for hydraulic supports provided by the present invention.

[0027] The following will combine Figure 1 The process of the intelligent control method for hydraulic supports provided by the present invention will be described.

[0028] In an exemplary embodiment of the present invention, combined with Figure 1 As can be seen, the intelligent control method for hydraulic supports may include steps 110 to 150, and each step will be described below.

[0029] In step 110, the first point cloud data is acquired in real time, wherein the first point cloud data is the point cloud data of the coal mining scene environment collected from the perspective of the coal mining machine.

[0030] In one embodiment, the coal mining machine moves continuously during the mining process. Point cloud acquisition equipment deployed on the coal mining machine, such as lidar (hereinafter referred to as a laser scanning device), scans the surrounding environment at high frequency to generate first point cloud data. This first point cloud data includes the three-dimensional coordinate information of objects in front of the coal wall, roof, floor, hydraulic supports, conveyors, etc. The precise position and motion state of the coal mining machine can be calculated using multi-view geometry principles.

[0031] In step 120, the second point cloud data is acquired in real time, wherein the second point cloud data is the environmental point cloud data of the coal mining scene collected from the perspective of the hydraulic support.

[0032] In one embodiment, a point cloud acquisition device deployed on the hydraulic support also scans its surrounding environment at high frequency to generate second point cloud data. This second point cloud data focuses on the scene near the hydraulic support, such as the gaps between supports, the condition of the roof, and the position of the coal mining machine.

[0033] In step 130, a three-dimensional scene of the coal mining scenario environment is constructed based on the first point cloud data and the second point cloud data.

[0034] In one embodiment, the first and second point cloud data can be preprocessed, including denoising, such as using statistical filtering to remove outliers; coordinate unification, such as converting the data to global coordinates; and registration, such as using iterative nearest-point algorithms or other point cloud registration methods to align the multi-view point clouds. Then, point cloud fusion techniques, such as voxel meshing or surface reconstruction algorithms, are used to construct a complete, real-time 3D model of the coal mining scene. This model is represented in point cloud or mesh form, and the 3D scene of the coal mining environment can cover the geometry of the coal mining machine, hydraulic supports, and the entire working face.

[0035] In step 140, based on the three-dimensional scene, key information of the coal mining scene is determined, wherein the key information of the coal mining scene is the scene information that affects the safe operation of the coal mining machine.

[0036] In one embodiment, in a three-dimensional scene, key information affecting the safe operation of the coal mining machine can be identified through feature extraction algorithms, such as deep learning-based object detection or traditional geometric analysis.

[0037] In another exemplary embodiment of the present invention, the key information of the coal mining scene may include at least one or more of the following: the operating trajectory information of the coal mining machine, the speed information of the coal mining machine, the attitude information of the coal mining machine, the position information of the hydraulic support, the height information of the hydraulic support, and the geological information of the coal mining scene environment.

[0038] In step 150, based on key information of the coal mining scenario, a control strategy for the hydraulic support is determined, and the operation of the hydraulic support is controlled based on the control strategy.

[0039] In another embodiment, a control strategy for the hydraulic support can be determined based on key information from the coal mining scenario, and the operation of the hydraulic support can be controlled based on this strategy. The control strategy can be sent to the hydraulic support control system in the form of commands, which drives the solenoid valves or hydraulic motors of the hydraulic support to perform corresponding actions. The control process is cyclical in real time to ensure continuous adaptation to environmental changes. Control commands can be transmitted to the hydraulic support control system via an industrial network, converted into valve group control signals to drive the hydraulic support to perform lowering, moving, and raising actions. In this embodiment, through multi-view point cloud data fusion, the 3D scene is more comprehensive and reliable, capable of adapting to complex and changing coal mining environments, such as geological changes or equipment layout adjustments, thereby ensuring that the operation of the hydraulic support can better match the operating status of the coal mining machine and provide better support for the coal mining machine.

[0040] This invention provides an intelligent control method for hydraulic supports, comprising: real-time acquisition of first point cloud data, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of a coal mining machine; real-time acquisition of second point cloud data, wherein the second point cloud data is point cloud data of the coal mining scene environment collected from the perspective of a hydraulic support; constructing a three-dimensional scene of the coal mining scene environment based on the first and second point cloud data; determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information affecting the safe operation of the coal mining machine; determining a control strategy for the hydraulic support based on the key information of the coal mining scene, and controlling the operation of the hydraulic support based on the control strategy. This achieves intelligent control of the hydraulic support, enabling better matching of the operating state of the coal mining machine and providing better support for the coal mining machine.

[0041] Figure 2 This is a flowchart illustrating the process of constructing a three-dimensional scene of a coal mining environment based on the first point cloud data and the second point cloud data provided by the present invention.

[0042] The following will combine Figure 2 The process of constructing a three-dimensional scene of a coal mining scenario based on the first point cloud data and the second point cloud data provided by the present invention will be described.

[0043] In an exemplary embodiment of the present invention, combined with Figure 2 As can be seen, constructing a three-dimensional scene of the coal mining scenario environment based on the first point cloud data and the second point cloud data may include steps 210 to 230, and each step will be described below.

[0044] In step 210, the first point cloud data and the second point cloud data are fused to obtain fused point cloud data.

[0045] In one embodiment, since the two point cloud data come from sensors at different locations, they reside in their own independent local coordinates. In this embodiment, coordinate transformation unifies them into a common temporary coordinate system. During application, coarse registration is performed using initial pose data provided by the onboard positioning and orientation system of the acquisition device, such as an IMU or encoder. Based on the coarse registration, a precise point cloud registration algorithm, such as the iterative nearest-point algorithm, is used to accurately calculate the rotation and translation matrices between the two point cloud sets. Through iterative optimization, the average distance between corresponding points in the overlapping area of ​​the two point clouds is minimized, thereby achieving high-precision alignment. Furthermore, the precisely registered first and second point cloud data are merged into a unified, dense fused point cloud data. In another example, for the overlapping area in the fused point cloud data, point cloud densification processing can be performed to obtain more refined surface geometry information.

[0046] In step 220, global coordinates of the coal mining scenario environment are constructed based on the fused point cloud data.

[0047] In step 230, a three-dimensional scene of the coal mining environment is constructed based on global coordinates.

[0048] In one embodiment, all 3D points in the obtained fused point cloud data can be transformed to a predefined coordinate system through coordinate transformation. At this point, all scene elements have absolute coordinates in a unified coordinate system, thus obtaining the global coordinates of the coal mining scene environment. It can be understood that the global coordinates include the coordinates of scene elements within the coal mining scene environment.

[0049] Furthermore, based on the constructed global coordinates, a 3D scene of the coal mining environment is determined. It can be understood that the 3D scene is a digital 3D model in global coordinates that includes all key equipment and environmental topography of the coal mining face; this model is dynamically updated as the point cloud data is updated in real time.

[0050] In this embodiment, by fusing point cloud data from the perspectives of the coal mining machine and the hydraulic support, including the first point cloud data and the second point cloud data, the problem of insufficient field of view of a single sensor caused by equipment obstruction, distance limitation and other reasons is effectively made up for. This generates a more complete and comprehensive environmental model than any single data source, that is, a three-dimensional scene of the coal mining environment, which provides a more reliable data foundation for safety decision making.

[0051] Figure 3 This is a schematic diagram of the process of constructing a three-dimensional scene of the coal mining scenario environment based on the global coordinates provided by the present invention.

[0052] The following will combine Figure 3 The process of constructing a three-dimensional scene of the coal mining environment based on the global coordinates provided by the present invention will be described.

[0053] In an exemplary embodiment of the present invention, combined with Figure 3 As can be seen, constructing a three-dimensional scene of the coal mining environment based on the global coordinates may include steps 310 to 330, and each step will be described below.

[0054] In step 310, redundancy removal is performed on the global coordinates to obtain the first preprocessed global coordinates.

[0055] In one embodiment, a statistical outlier removal algorithm can be used. This algorithm analyzes the distance distribution between each point and its neighbors, identifying and filtering out points whose distances are much greater than the average, i.e., outliers, which are usually noise. This results in a first preprocessed global coordinate system with more uniform point cloud density, a smaller data volume, and a cleaner dataset. It can be understood that the first preprocessed global coordinate system can be considered a fused point cloud dataset with more uniform point cloud density, a smaller data volume, and a cleaner dataset.

[0056] In step 320, the first preprocessed global coordinates are filled with missing data to obtain the second preprocessed global coordinates.

[0057] In one embodiment, gaps in the first preprocessed global coordinates can be filled using interpolation based on neighboring point diffusion. By analyzing the normal vectors and curvatures of the hole edge points, new coordinate points are inferred and generated to fill the missing areas, thus obtaining the second preprocessed global coordinates. It can be understood that the second preprocessed global coordinates can be considered a fused point cloud dataset with a more continuous surface and more complete geometric information.

[0058] In step 330, a three-dimensional scene of the coal mining environment is constructed based on the second preprocessed global coordinates.

[0059] In another embodiment, optimized high-quality point cloud data, i.e., the global coordinates after the second preprocessing, can be used to construct the final 3D scene for decision-making. During application, this optimized point cloud data can be used to construct a more accurate and complete 3D scene of the coal mining environment for subsequent analysis through direct rendering or surface reconstruction algorithms, such as Poisson reconstruction.

[0060] In yet another exemplary embodiment of the present invention, continuing with the previously described embodiments as an example, before determining the control strategy of the hydraulic support based on key information of the coal mining scenario (corresponding to step 150), the intelligent control method for the hydraulic support may further include the following steps: The pre-trained control strategy generation model is invoked, whereby the control strategy generation model is used to obtain the control strategy of the hydraulic support that matches the key information of the coal mining scenario based on the key information of the coal mining scenario. Among them, the control strategy for the hydraulic support, determined based on key information from the coal mining scenario (corresponding to step 150), can be implemented in the following way: Key information from the coal mining scenario is input into the control strategy generation model to obtain the control strategy for the hydraulic support output by the control strategy generation model.

[0061] In one embodiment, key information extracted in real-time from the coal mining scenario can be used as input and transmitted to the invoked control strategy generation model. Internally, the model performs instantaneous calculations and inferences on the input information based on its learned knowledge. Further, the model directly outputs one or more specific, executable control strategies for hydraulic supports. This output may be a specific action command or a probability distribution of a comprehensive action sequence. In application, the comprehensive action sequence with the highest probability can be selected as the final control strategy for the hydraulic support. This embodiment, by using a pre-trained model, enables the system to learn complex patterns and causal relationships from data, handling unforeseen scenarios and generating more intelligent and flexible control strategies.

[0062] In yet another exemplary embodiment of the present invention, the control strategy generation model can be trained in the following manner, continuing with the previously described embodiments: Acquire key information from multiple sets of historical coal mining scenarios, as well as historical control strategies for hydraulic supports corresponding to the key information from each set of historical coal mining scenarios; A training dataset is constructed based on key information from multiple historical coal mining scenarios and corresponding historical control strategies for multiple hydraulic supports. The control policy generation model is trained based on the training dataset to obtain the trained control policy generation model.

[0063] In one embodiment, a large amount of historical data can be collected from existing automated or manually controlled coal mining faces with complete data records. Each set of data includes key information of historical coal mining scenarios and corresponding historical control strategies for hydraulic supports. The key information of historical coal mining scenarios can be key parameters extracted from historical point cloud data, such as, but not limited to: real-time distance between the coal mining machine and the supports, roof subsidence sequence, coal wall flatness, current support posture (e.g., inclination angle), and historical support strength data. The corresponding historical control strategies for hydraulic supports can be control commands that were actually executed and verified to be safe and effective under the aforementioned specific historical scenarios.

[0064] Furthermore, the collected raw data can be organized into a standardized dataset that can be directly used by the model. For example, the collected historical data can be verified and cleaned to remove records with obvious errors or missing information, thereby obtaining a training dataset. The control policy generation model can then be trained based on the training dataset to obtain a trained control policy generation model.

[0065] In this embodiment, the model's learning process is based on facts and data, and is trained on a large amount of real historical data. This gives the control strategy output by the model a solid foundation in reality, thereby ensuring the reliability of the model itself and the scientific nature of the decision-making.

[0066] In yet another exemplary embodiment of the present invention, the first point cloud data can be obtained in the following manner, using the previously described embodiments as an example: The first point cloud data was collected using a laser scanning device deployed on the coal mining machine.

[0067] In one embodiment, laser scanning devices can be deployed at multiple points on the end of the coal mining machine to collect first point cloud data, thereby enabling three-dimensional scanning and calculating the precise position and motion state of the coal mining machine through multi-view geometric principles.

[0068] In yet another exemplary embodiment of the present invention, the second point cloud data can be obtained in the following manner, continuing with the previously described embodiments: The second point cloud data was acquired using a laser scanning device deployed on a hydraulic support.

[0069] In one embodiment, laser scanning devices can be deployed at intervals at the end of the hydraulic support to collect second point cloud data. During application, environmental point cloud data can be continuously collected to identify key equipment targets and calculate spatial position relationships.

[0070] As described above, the intelligent control method for hydraulic supports provided by this invention collects point cloud data of the working face in real time through multiple scanning devices on the hydraulic supports and the coal mining machine during longwall mining operations. This identifies various equipment targets and extracts their spatial relationships. The collected point cloud data is then fused and processed to establish a global three-dimensional scene based on the coal mining machine. Redundant data is removed and missing information is filled through optimization algorithms, forming a complete digital working face model. As the coal mining machine advances, key information such as its position, speed, and hydraulic support status can be extracted from the three-dimensional scene. Artificial intelligence technology is used to analyze the current working conditions, predict future operating trends, and automatically generate the optimal follow-up control strategy for the hydraulic supports based on geological conditions and equipment operating parameters. Control commands are transmitted to the electro-hydraulic control system via a network, driving the hydraulic supports to perform lowering, moving, and raising actions according to the calculated timing and position, maintaining precise coordination with the coal mining machine. Throughout the process, the safety assurance system continuously monitors equipment operating parameters and adjusts the control strategy or triggers a safety shutdown when an abnormality is detected. This intelligent collaborative control based on 3D scanning enables the coal mining machine and hydraulic support to automatically adjust operating parameters according to actual working conditions, achieving truly intelligent mining.

[0071] The intelligent control device for hydraulic supports provided by the present invention is described below. The intelligent control device for hydraulic supports described below can be referred to in correspondence with the intelligent control method for hydraulic supports described above.

[0072] Figure 4This is a structural schematic diagram of the intelligent control device for hydraulic supports provided by the present invention.

[0073] The following will combine Figure 4 The structure of the intelligent control device for hydraulic supports provided by the present invention will be described.

[0074] In an exemplary embodiment of the present invention, combined with Figure 4 As can be seen, the intelligent control device for hydraulic supports may include a first acquisition module 410, a second acquisition module 420, a construction module 430, a determination module 440, and a generation module 450. Each module will be described in detail below.

[0075] The first acquisition module 410 can be configured to acquire first point cloud data in real time, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the coal mining machine. The second acquisition module 420 can be configured to acquire second point cloud data in real time, wherein the second point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the hydraulic support. The construction module 430 can be configured to construct a three-dimensional scene of the coal mining scenario environment based on the first point cloud data and the second point cloud data; The determination module 440 can be configured to determine key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information that affects the safe operation of the coal mining machine; The generation module 450 can be configured to determine the control strategy of the hydraulic support based on the key information of the coal mining scenario, and control the operation of the hydraulic support based on the control strategy.

[0076] In an exemplary embodiment of the present invention, the construction module 430 can construct a three-dimensional scene of the coal mining environment based on the first point cloud data and the second point cloud data in the following manner: The first point cloud data and the second point cloud data are fused to obtain fused point cloud data. Based on the fused point cloud data, the global coordinates of the coal mining scene environment are constructed; Based on the global coordinates, a three-dimensional scene of the coal mining environment is constructed.

[0077] In an exemplary embodiment of the present invention, the construction module 430 may further be configured to: Redundancy removal is performed on the global coordinates to obtain the first preprocessed global coordinates; The first preprocessed global coordinates are filled with gaps to obtain the second preprocessed global coordinates. The construction module 430 can construct a three-dimensional scene of the coal mining environment based on the global coordinates in the following manner: Based on the second preprocessed global coordinates, a three-dimensional scene of the coal mining environment is constructed.

[0078] In an exemplary embodiment of the present invention, the generation module 450 may further be configured to: The pre-trained control strategy generation model is invoked, wherein the control strategy generation model is used to obtain a control strategy for the hydraulic support that matches the key information of the coal mining scenario based on the key information of the coal mining scenario. The generation module 450 can determine the control strategy of the hydraulic support based on the key information of the coal mining scenario in the following ways: The key information of the coal mining scenario is input into the control strategy generation model to obtain the control strategy of the hydraulic support output by the control strategy generation model.

[0079] In an exemplary embodiment of the present invention, the generation module 450 may train the control strategy generation model in the following manner: Acquire key information from multiple sets of historical coal mining scenarios, as well as historical control strategies for hydraulic supports corresponding to the key information from each set of historical coal mining scenarios; A training dataset is constructed based on key information from multiple historical coal mining scenarios and corresponding historical control strategies for multiple hydraulic supports. The control policy generation model is trained based on the training dataset to obtain a trained control policy generation model.

[0080] In an exemplary embodiment of the present invention, the key information of the coal mining scene includes at least one or more of the following: the operating trajectory information of the coal mining machine, the speed information of the coal mining machine, the attitude information of the coal mining machine, the position information of the hydraulic support, the height information of the hydraulic support, and the geological information of the coal mining scene environment.

[0081] In an exemplary embodiment of the present invention, the first acquisition module 410 may obtain the first point cloud data in the following manner: The first point cloud data was acquired using a laser scanning device deployed on the coal mining machine.

[0082] In an exemplary embodiment of the present invention, the second acquisition module 420 may obtain the second point cloud data in the following manner: The second point cloud data is acquired using a laser scanning device deployed on the hydraulic support.

[0083] Based on the same inventive concept, the present invention also provides a fully mechanized mining face control platform, which will be described below with reference to the following embodiments.

[0084] In an exemplary embodiment of the present invention, the fully mechanized mining face control platform may include a coal mining machine, a hydraulic support, and a processor. The coal mining machine is equipped with a laser scanning device; the hydraulic support is equipped with a laser scanning device; and the processor is used to execute the intelligent control method for the hydraulic support as described in any one of the embodiments. Through the fully mechanized mining face control platform of this embodiment, intelligent control of the hydraulic support can be achieved, better matching the operating status of the coal mining machine and providing better support for the coal mining machine.

[0085] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute a hydraulic support intelligent control method, which includes: acquiring first point cloud data in real time, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the coal mining machine; acquiring second point cloud data in real time, wherein the second point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the hydraulic support; constructing a three-dimensional scene of the coal mining scene environment based on the first point cloud data and the second point cloud data; determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information affecting the safe operation of the coal mining machine; determining the control strategy of the hydraulic support based on the key information of the coal mining scene, and controlling the operation of the hydraulic support based on the control strategy.

[0086] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent control method for hydraulic supports provided by the above methods. The method includes: acquiring first point cloud data in real time, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the coal mining machine; acquiring second point cloud data in real time, wherein the second point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the hydraulic support; constructing a three-dimensional scene of the coal mining scene environment based on the first point cloud data and the second point cloud data; determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information that affects the safe operation of the coal mining machine; determining a control strategy for the hydraulic support based on the key information of the coal mining scene, and controlling the operation of the hydraulic support based on the control strategy.

[0088] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the intelligent control method for hydraulic supports provided by the methods described above. This method includes: acquiring first point cloud data in real time, wherein the first point cloud data is point cloud data of a coal mining scene environment collected from the perspective of a coal mining machine; acquiring second point cloud data in real time, wherein the second point cloud data is point cloud data of a coal mining scene environment collected from the perspective of a hydraulic support; constructing a three-dimensional scene of the coal mining scene environment based on the first point cloud data and the second point cloud data; determining key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information affecting the safe operation of the coal mining machine; determining a control strategy for the hydraulic support based on the key information of the coal mining scene, and controlling the operation of the hydraulic support based on the control strategy.

[0089] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0090] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent control of a hydraulic support, characterized in that, The method includes: Real-time acquisition of first point cloud data, wherein the first point cloud data is point cloud data of the coal mining scene environment collected from the perspective of the coal mining machine; Real-time acquisition of second point cloud data, wherein the second point cloud data is environmental point cloud data of the coal mining scene collected from the perspective of the hydraulic support; The first point cloud data and the second point cloud data are fused to obtain fused point cloud data. Based on the fused point cloud data, the global coordinates of the coal mining scene environment are constructed; Redundancy removal is performed on the global coordinates to obtain the first preprocessed global coordinates; The first preprocessed global coordinates are filled with gaps to obtain the second preprocessed global coordinates. Based on the second preprocessed global coordinates, a three-dimensional scene of the coal mining scenario environment is constructed; Based on the three-dimensional scene, key information of the coal mining scene is determined, wherein the key information of the coal mining scene is scene information that affects the safe operation of the coal mining machine; Based on the key information of the coal mining scenario, a control strategy for the hydraulic support is determined, and the operation of the hydraulic support is controlled based on the control strategy.

2. The intelligent control method for hydraulic supports according to claim 1, characterized in that, Before determining the control strategy of the hydraulic support based on the key information of the coal mining scenario, the method further includes: The pre-trained control strategy generation model is invoked, wherein the control strategy generation model is used to obtain a control strategy for the hydraulic support that matches the key information of the coal mining scenario based on the key information of the coal mining scenario. The determination of the control strategy for the hydraulic support based on the key information of the coal mining scenario specifically includes: The key information of the coal mining scenario is input into the control strategy generation model to obtain the control strategy of the hydraulic support output by the control strategy generation model.

3. The intelligent control method for hydraulic supports according to claim 2, characterized in that, The control strategy generation model is trained in the following manner: Acquire key information from multiple sets of historical coal mining scenarios, as well as historical control strategies for hydraulic supports corresponding to the key information from each set of historical coal mining scenarios; A training dataset is constructed based on key information from multiple historical coal mining scenarios and corresponding historical control strategies for multiple hydraulic supports. The control policy generation model is trained based on the training dataset to obtain a trained control policy generation model.

4. The intelligent control method for hydraulic supports according to any one of claims 1 to 3, characterized in that, The key information of the coal mining scene includes at least one or more of the following: the operating trajectory information of the coal mining machine, the speed information of the coal mining machine, the attitude information of the coal mining machine, the position information of the hydraulic support, the height information of the hydraulic support, and the geological information of the coal mining scene environment.

5. The intelligent control method for hydraulic supports according to any one of claims 1 to 3, characterized in that, The first point cloud data was obtained in the following way: The first point cloud data was acquired using a laser scanning device deployed on the coal mining machine.

6. The intelligent control method for hydraulic supports according to any one of claims 1 to 3, characterized in that, The second point cloud data is obtained in the following way: The second point cloud data is acquired using a laser scanning device deployed on the hydraulic support.

7. An intelligent control device for a hydraulic support, characterized in that, The device is used to implement the intelligent control method for hydraulic supports according to any one of claims 1 to 6, and the device comprises: The first acquisition module is used to acquire the first point cloud data in real time, wherein the first point cloud data is the point cloud data of the coal mining scene environment collected from the perspective of the coal mining machine. The second acquisition module is used to acquire the second point cloud data in real time, wherein the second point cloud data is the point cloud data of the coal mining scene environment collected from the perspective of the hydraulic support; A construction module is used to construct a three-dimensional scene of the coal mining scenario environment based on the first point cloud data and the second point cloud data; The determination module is used to determine key information of the coal mining scene based on the three-dimensional scene, wherein the key information of the coal mining scene is scene information that affects the safe operation of the coal mining machine; The generation module is used to determine the control strategy of the hydraulic support based on the key information of the coal mining scenario, and to control the operation of the hydraulic support based on the control strategy.

8. A control platform for a fully mechanized mining face, characterized in that, The longwall mining face control platform includes: Coal mining machine, wherein the coal mining machine is equipped with a laser scanning device; A hydraulic support, wherein the hydraulic support is equipped with a laser scanning device, and A processor, wherein the processor is configured to execute the intelligent control method for hydraulic supports according to any one of claims 1 to 6.

Images