Train compartment position identification method, device and equipment and gantry crane

Abstract

Embodiments of the present application provide a train carriage position identification method, device and equipment and a portal crane, and relate to the technical field of railway carriage loading. The method comprises: acquiring point cloud data and first positioning information collected by scanning a working train in an extension direction; determining a working train carriage position according to the point cloud data and the first positioning information; based on the working train carriage position, controlling the portal crane to perform a box lifting operation on a working train carriage corresponding to the working train carriage position, and acquiring second positioning information of the working train carriage in real time during the box lifting operation; and updating the working train carriage position according to the second positioning information to obtain an updated working train carriage position. The method is used to correct point cloud data errors and improve the accuracy of the position information of the train carriage.

Description

Train carriage location identification methods, devices, equipment and gantry cranes Technical Field

[0001] This application relates to the field of railway carriage loading technology, and in particular to a method, device, equipment and gantry crane for identifying the position of a train carriage. Background Technology

[0002] With the development of information technology and automation technology, railway carriage loading and unloading is gradually moving towards automation and intelligence. When carrying out automatic loading and unloading operations on trains in railway yards, it is necessary to know the accurate location information of the train carriages in order to control loading and unloading equipment such as carriage cranes and gantry cranes to reach the accurate working position for automatic loading and unloading operations.

[0003] Currently, the laser point cloud data of the train is usually collected by setting up a laser scanner on a dynamic acquisition vehicle, thereby constructing a laser point cloud map of the train. The constructed laser point cloud map of the train is then compared with the laser point cloud map pre-stored in the computing system to correct the constructed laser point cloud map of the train and obtain the location information of the train carriages.

[0004] However, during the dynamic data acquisition process, the movement of the acquisition vehicle may affect the accuracy of the laser scanner, leading to errors in the point cloud data and thus affecting the accuracy of the final train carriage location information. Summary of the Invention

[0005] This application provides a method, device, equipment, and gantry crane for identifying the position of train carriages, in order to correct point cloud data errors and improve the accuracy of train carriage position information.

[0006] In a first aspect, embodiments of this application provide a method for identifying the location of a train carriage, including:

[0007] Acquire point cloud data and initial positioning information collected by scanning the working train in the extended direction;

[0008] The location of the working train carriage is determined based on point cloud data and initial positioning information;

[0009] Based on the position of the working train car, the gantry crane is controlled to perform lifting operations on the working train car corresponding to the working train car position, and the second positioning information of the working train car is obtained in real time during the lifting operation.

[0010] Based on the second positioning information, the position of the working train carriage is updated to obtain the updated position of the working train carriage.

[0011] In one possible implementation, determining the position of the working train carriage based on point cloud data and first positioning information includes:

[0012] Based on the first positioning information, coordinate transformation is performed on the point cloud data to obtain the point cloud data in the railway yard coordinate system;

[0013] The point cloud data in the railway yard coordinate system is filtered according to the preset car height threshold and train width threshold to obtain the point cloud data of the working train car.

[0014] The location of the working train carriages is determined based on the point cloud data of the working train carriages.

[0015] In one possible implementation, determining the location of the working train car based on the point cloud data of the working train car includes:

[0016] Clustering is performed on the point cloud data of the working train carriages to obtain the train carriage point cloud dataset;

[0017] Determine the extreme value data in the point cloud dataset of train carriages; the extreme value data represents the boundary range of the train carriages.

[0018] The location of the working train carriages is determined based on the extreme value data.

[0019] In one possible implementation, determining the location of the working train car based on extreme value data includes:

[0020] The extreme value data are sorted according to their magnitude to obtain an extreme value sequence;

[0021] Pairwise comparisons are performed on adjacent extreme value data within the extreme value sequence to determine the extreme value differences;

[0022] When the extreme value difference meets the preset extreme value difference threshold, the train car point cloud dataset is determined to be the point cloud dataset of the same train car, and the updated train car point cloud dataset is obtained.

[0023] The location of the working train car is determined based on the updated train car point cloud dataset.

[0024] In one possible implementation, after determining the location of the working train car based on the updated train car point cloud dataset, the method further includes:

[0025] Based on the location of the working train carriage, determine the point cloud data of the working train carriage and the point cloud data of the upper plane of the working train carriage;

[0026] Based on the point cloud data of the upper plane of the working train carriage, the points in the point cloud data that are higher than the upper plane of the working train carriage in the width direction are filtered to obtain the point cloud dataset of the protruding parts.

[0027] Based on the point cloud dataset of the protruding parts, the target location of the working train carriage is determined.

[0028] In one possible implementation, determining the target location of the work train carriage based on the point cloud dataset of the protruding parts includes:

[0029] Clustering is performed on the point cloud dataset of protruding parts to obtain the target protruding part point cloud dataset, which represents the independent protruding parts on the working train carriage.

[0030] Based on the point cloud dataset of the prominent parts of the target, the target location of the working train carriage is determined.

[0031] In one possible implementation, the position of the work train car is updated based on the second positioning information to obtain the updated position of the work train car, including:

[0032] Based on the second positioning information, determine the center position of the working train carriage;

[0033] Based on the center position, the position of the working train car is updated to obtain the updated position of the working train car.

[0034] Secondly, embodiments of this application provide a train carriage position identification device, comprising:

[0035] The acquisition module is used to acquire point cloud data and first positioning information collected by scanning the working train in the extension direction;

[0036] The determination module is used to determine the position of the working train carriage based on point cloud data and the first positioning information;

[0037] The control module is used to control the gantry crane to perform lifting operations on the corresponding working train car based on the position of the working train car, and to obtain the second positioning information of the working train car in real time during the lifting operation.

[0038] The adjustment module is used to update the position of the working train carriage based on the second positioning information, so as to obtain the updated position of the working train carriage.

[0039] In one possible implementation, the determining module is specifically used for:

[0040] Based on the first positioning information, coordinate transformation is performed on the point cloud data to obtain the point cloud data in the railway yard coordinate system;

[0041] The point cloud data in the railway yard coordinate system is filtered according to the preset car height threshold and train width threshold to obtain the point cloud data of the working train car.

[0042] The location of the working train carriages is determined based on the point cloud data of the working train carriages.

[0043] In one possible implementation, the location of the work train car is determined based on the point cloud data of the work train car. The determining module is specifically used for:

[0044] Clustering is performed on the point cloud data of the working train carriages to obtain the train carriage point cloud dataset;

[0045] Determine the extreme value data in the point cloud dataset of train carriages; the extreme value data represents the boundary range of the train carriages.

[0046] The location of the working train carriages is determined based on the extreme value data.

[0047] In one possible implementation, the location of the working train car is determined based on extreme value data, and the determining module is specifically used for:

[0048] The extreme value data are sorted according to their magnitude to obtain an extreme value sequence;

[0049] Pairwise comparisons are performed on adjacent extreme value data within the extreme value sequence to determine the extreme value differences;

[0050] When the extreme value difference meets the preset extreme value difference threshold, the train car point cloud dataset is determined to be the point cloud dataset of the same train car, and the updated train car point cloud dataset is obtained.

[0051] The location of the working train car is determined based on the updated train car point cloud dataset.

[0052] In one possible implementation, after determining the location of the working train car based on the updated train car point cloud dataset, the determining module is further configured to:

[0053] Based on the location of the working train carriage, determine the point cloud data of the working train carriage and the point cloud data of the upper plane of the working train carriage;

[0054] Based on the point cloud data of the upper plane of the working train carriage, the points in the point cloud data that are higher than the upper plane of the working train carriage in the width direction are filtered to obtain the point cloud dataset of the protruding parts.

[0055] Based on the point cloud dataset of the protruding parts, the target location of the working train carriage is determined.

[0056] In one possible implementation, the target location of the work train carriage is determined based on the point cloud dataset of the protruding part, and the module is specifically used for:

[0057] Clustering is performed on the point cloud dataset of protruding parts to obtain the target protruding part point cloud dataset, which represents the independent protruding parts on the working train carriage.

[0058] Based on the point cloud dataset of the prominent parts of the target, the target location of the working train carriage is determined.

[0059] In one possible implementation, the adjustment module is specifically used for:

[0060] Based on the second positioning information, determine the center position of the working train carriage;

[0061] Based on the center position, the position of the working train car is updated to obtain the updated position of the working train car.

[0062] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0063] The memory stores instructions that the computer executes;

[0064] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0065] Fourthly, embodiments of this application provide a gantry crane, including: a gantry crane body, a positioning device and radar mounted on the gantry crane trolley, and electronic equipment mounted on the gantry crane body;

[0066] The gantry crane body is used for lifting operations on the corresponding working train carriages.

[0067] Positioning device, used to collect positioning information;

[0068] Radar is used to scan the working train in the extended direction;

[0069] An electronic device for performing the first aspect and / or various possible implementations of the first aspect as described above.

[0070] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0071] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0072] The train carriage position identification method, device, equipment, and gantry crane provided in this application embodiment scan the working train in the extension direction to obtain point cloud data and first positioning information of the working train. The point cloud data and the first positioning information are combined to initially determine the position of the working train carriage, so that the gantry crane can perform lifting operations on the working train carriage corresponding to the working train carriage position. The second positioning information of the train carriage is obtained, and the initially determined position of the working train carriage is updated and adjusted to obtain the adjusted position of the working train carriage. By fusing multi-source information, the positioning information can be used to compensate for the error of point cloud data caused by the movement of the gantry crane, so as to more accurately determine the position of the train carriage and reduce the error caused by a single data source. At the same time, by correcting the position of the working train carriage twice, the deviation of the train carriage position that may occur during dynamic acquisition can be compensated. Attached Figure Description

[0073] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0074] Figure 1 is a schematic diagram of the railway storage yard provided in this application;

[0075] Figure 2 is a flowchart illustrating the train carriage location identification method provided in this application.

[0076] Figure 3 is a flowchart illustrating the train carriage location identification method provided in this application (II).

[0077] Figure 4 is a flowchart illustrating the train carriage location identification method provided in this application.

[0078] Figure 5 is a flowchart illustrating another method for identifying the position of a train carriage provided in this application.

[0079] Figure 6 is a flowchart illustrating another method for identifying the position of a train carriage provided in this application.

[0080] Figure 7 is a structural schematic diagram of the train carriage position identification device provided in this application;

[0081] Figure 8 is a structural schematic diagram of the gantry crane provided in this application;

[0082] Figure 9 is a schematic diagram of the structure of the electronic device provided in this application.

[0083] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0084] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0085] First, let me explain the terms used in this application:

[0086] A gantry crane, also known as a portal crane, is a large lifting device used for loading, unloading, handling, and stacking heavy goods. It is usually installed on rails and can move along the rails. Its structure is similar to a door frame, usually consisting of two columns and a crossbeam. A trolley is mounted on the crossbeam and can move along the crossbeam.

[0087] Railway storage yard: refers to a dedicated area used for storing and managing goods related to railway transportation. It has multiple tracks to support the loading, unloading, storage and transshipment of railway goods.

[0088] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0089] In existing technologies, laser scanners are typically placed on dynamic objects, such as data acquisition vehicles, to continuously collect data during operation. The laser scanner determines distance by emitting a laser beam and measuring its reflection time. By converting this distance data into three-dimensional coordinates, a laser point cloud map of the train is constructed. The constructed laser point cloud map of the train is then compared with a pre-stored laser point cloud map in the computing system to correct the constructed laser point cloud map of the train and obtain the position information of the train carriages.

[0090] However, during the data acquisition process, the acquisition vehicle may experience shaking while traveling on the track, affecting the stability of the laser beam and introducing motion errors. As a result, the acquired point cloud data may be distorted or offset, leading to inaccurate laser point cloud maps. Furthermore, the acquired data includes not only the point cloud of the train but also the point cloud of the surrounding environment. Therefore, although the constructed laser point cloud map of the train can be corrected by comparing it with the pre-stored laser point cloud map in the computing system to obtain the position information of the train carriages, the point cloud map itself is inaccurate because it includes point clouds of non-train carriages. Consequently, the obtained position information of the train carriages may also deviate from the actual position information.

[0091] In addressing the aforementioned technical problems, the inventors' technical concept is as follows: Simply using a laser scanner to collect distance data and construct a laser point cloud map of the train suffers from data errors due to data stitching from a single data source. However, by using a high-precision positioning device to follow the movement of the moving object and synchronously collect positioning information, and then fusing this positioning information with the point cloud data collected by the laser scanner, the initial position of the train carriages can be determined through analysis and processing. This corrects errors in the point cloud data and improves the overall accuracy of the data. Furthermore, to prevent interference from non-train carriage data in the point cloud data, after initially determining the train carriage position, a gantry crane can be controlled to reach that position for operation. During the operation, the positioning information of the train carriages is monitored and acquired in real time, allowing for secondary correction of the carriage positions, thereby further improving positioning accuracy and obtaining a more precise train carriage location.

[0092] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0093] Figure 1 is a schematic diagram of the railway storage yard provided in this application. As shown in Figure 1, it includes: a gantry crane body, a gantry crane trolley, a train, a positioning device, radar, and an automation system. Among them:

[0094] Automation systems can refer to electronic devices, such as programmable logic controllers (PLCs), which use computers to operate equipment or perform tasks. Radar can be a 3D LiDAR scanner, and the positioning device can be a Global Positioning System (GPS). In some embodiments, the positioning device can also be a radio frequency identification (RFID) system, an inertial navigation system (INS), etc.

[0095] Specifically, the automation system can be installed in the operator's cab on the gantry crane itself, or in other locations, to control the gantry crane to perform gantry crane operations.

[0096] Both the 3D LiDAR scanner and GPS can be installed on the gantry crane trolley. As the gantry crane moves in the railway yard, it can acquire relevant information about the train and its carriages in real time. In some embodiments, the 3D LiDAR scanner can also be installed on the main beam of the gantry crane above the train tracks.

[0097] In this embodiment, a positioning device and radar are installed on the gantry crane trolley. As the gantry crane moves in the railway yard, the radar acquires point cloud data, and the positioning device acquires the positioning information of the train and its carriages. This information is then sent to the automation system. The automation system processes this data and information to determine the position of the working train carriage and sends instructions to the gantry crane based on the position of the working train carriage. This controls the gantry crane to perform the lifting operation. During the lifting operation, the positioning device acquires the positioning information of the working train carriage and corrects the position of the working train carriage to obtain an accurate position.

[0098] Figure 2 is a flowchart illustrating the train carriage position identification method provided in this application. As shown in Figure 2, the method may include:

[0099] S201. Acquire point cloud data and first positioning information collected by scanning the work train in the extended direction.

[0100] Among them, "operational train" can refer to a train that is carrying out loading, unloading or other container hoisting operations in a railway yard.

[0101] The direction of extension can refer to the longitudinal direction of the train, that is, the direction along which the train carriages are arranged.

[0102] Point cloud data refers to a dataset composed of numerous points acquired during the scanning of a train. Each point has its coordinates in three-dimensional space, representing the surface shape of the train. Point cloud data can be obtained by measuring the train with a laser scanner to acquire its three-dimensional surface data. In this embodiment, a 3D LiDAR scanner can be used to collect point cloud data.

[0103] The first positioning information refers to the spatial location data of the train obtained through a positioning device, which typically includes three-dimensional coordinate information. In this embodiment, the first positioning information can be obtained in real time via GPS.

[0104] In this embodiment, the system uses a 3D LiDAR scanner to move along the length of the train while scanning it to capture surface information of the entire train. Simultaneously, a positioning device provides first positioning information, which can be used to describe the train's specific position and orientation during the scan.

[0105] It should be noted that in the process of acquiring the point cloud data and first positioning information of the working train, it is also necessary to synchronize the point cloud data and the first positioning information in time and space to ensure that the two can be effectively combined.

[0106] S202. Determine the position of the working train carriage based on point cloud data and first positioning information.

[0107] In this embodiment, data fusion technology can be used to integrate point cloud data obtained from radar with the first positioning information provided by the positioning device. By combining the two data sources and analyzing the fused data through an algorithm, the outline and features of the train carriages can be identified. Based on the analysis results, the position of the train carriages in the railway yard can be calculated. As the gantry crane moves in the railway yard, the position and range of the train carriages in the railway yard can be mapped one by one. Finally, the position map of the train carriages in the railway yard can be obtained, thereby determining the position of the working train carriages.

[0108] As an example, determining the location of a working train car may involve coordinate transformation. This involves calculating a rotation matrix or translation vector on the point cloud data acquired by the radar, based on the positioning information and the radar's deviation relative to the gantry crane, thereby transforming the radar's coordinate system to the railway yard's coordinate system. Then, the point cloud data undergoes filtering or noise reduction processing to remove outliers and noise, resulting in the boundary range of the working train car. This determines the position and extent of the working train car within the railway yard's coordinate system. The boundary range of the working train car includes its length, width, and height.

[0109] Specifically, point cloud data can be filtered or denoised by separating the working train carriages based on the width variation at the carriage connections. Then, filtering, planar extraction, and clustering methods can be used to obtain the boundary range of the working train carriages. The carriage connections are made using welded components, such as connectors, resulting in width variations in the scanned point cloud data. This width variation allows for the separation of interfering objects.

[0110] It should be noted that since the point cloud data and the first positioning information are both acquired dynamically in real time, the obtained position of the working train car is its approximate position in the coordinate system of the railway yard, which may have some error with the actual position. However, for the gantry crane operation, this position can meet the basic operating requirements of the gantry crane and can control the gantry crane to move to the position of the working train car to carry out the gantry crane operation.

[0111] Understandably, combining multi-source data can reduce errors from a single data source and improve the accuracy of location determination. Furthermore, through data fusion and analysis, interference information from non-train carriages that may exist in point cloud data can be effectively filtered out, improving the purity of the data and thus more reliably identifying the location of the train carriages. At the same time, the identification of the working train carriages provides basic data for subsequent caisson operations and position correction, ensuring the smooth progress of subsequent operations.

[0112] S203. Based on the position of the working train car, control the gantry crane to perform lifting operations on the working train car at the corresponding working train car position, and obtain the second positioning information of the working train car in real time during the lifting operation.

[0113] Among them, container handling refers to the process of loading and unloading containers or other goods using equipment such as gantry cranes or yard cranes.

[0114] The second positioning information refers to the position data of the working train carriages obtained during the caisson lifting operation after the lifting device has completed grabbing and lowering the caisson.

[0115] In this embodiment, based on the position of the working train car determined in S202, the gantry crane is controlled to move to that position so as to accurately align with the working train car for container lifting operations. During the container lifting operation, the spreader moves to the designated position of the working train car to perform container loading and unloading operations. At the same time, the positioning device continuously monitors the position of the working train car and obtains second positioning information. This information can be used to update the position information of the working train car for a second time.

[0116] It should be noted that railway wagons in railway yards come in various types, including open wagons, frames, and flatbeds. Flatbeds include both open and non-openwork types. Furthermore, different working positions exist within a single wagon depending on the size and quantity of containers. Therefore, by acquiring the second positioning information of the working wagon during container lifting operations in real time, the position for placing or grabbing containers (i.e., the working position) can be determined, allowing for updates to the wagon's position.

[0117] S204. Based on the second positioning information, update the position of the working train car to obtain the updated position of the working train car.

[0118] In this embodiment, the position of the work train carriage is corrected a second time based on the acquired second positioning information to determine the precise boundary range of the work train carriage, thereby obtaining the adjusted position of the work train carriage. As a result, the operating parameters of the gantry crane can be adjusted according to the adjusted position of the work train carriage, reducing operation delays caused by position errors, ensuring the accuracy and safety of subsequent hoisting operations on the work train carriage, and improving overall operation efficiency.

[0119] As an example, by analyzing the second positioning information and comparing it with the position data of the working train carriage determined by dynamic acquisition, position deviations or changes are identified. Based on the comparison results, the deviation between the data collected during the initial movement of the gantry crane and the static data obtained during the operation of the gantry crane is detected. Based on the detected deviation, the required adjustment amount is calculated and applied to the position data of the working train carriage to correct its position and attitude in three-dimensional space, thus obtaining the adjusted position of the working train carriage.

[0120] Understandably, the gantry crane remains stationary during the hoisting operation, thus obtaining more accurate second positioning information. By updating the position of the working train car in the coordinate system of the railway yard based on the second positioning information, a more accurate position of the working train car is obtained.

[0121] In one possible implementation, S204 can be specifically implemented through the following steps:

[0122] Based on the second positioning information, the center position of the working train car is determined, and the position of the working train car is updated according to the center position to obtain the updated position of the working train car.

[0123] The center position refers to the center position of the working train car during the current caisson operation, i.e., the geometric center point.

[0124] In this embodiment, the working position is calculated based on the location of the working train car and the specific work task (e.g., the working train car, and the position within the working train car is the front car, middle car, and rear car). The gantry crane is then controlled to move to the corresponding position to complete the lifting operation. The second positioning information of the working train car is acquired in real time during the lifting operation. The center position of the current working train car is calculated by combining the second positioning information and the work task, and the position map of the train car in the railway yard is updated to obtain the adjusted position of the working train car. This provides more accurate position information for subsequent operations on the working train car, thereby improving work efficiency.

[0125] The train carriage position identification method provided in this application embodiment dynamically scans the working train to obtain point cloud data and first positioning information of the working train. The point cloud data and the first positioning information are combined to initially determine the position of the working train carriage, so that the gantry crane can perform lifting operations on the working train carriage. At this time, the second positioning information of the train carriage is obtained, and the initially determined position of the working train carriage is updated and adjusted to obtain the adjusted position of the working train carriage. By combining the point cloud data and positioning information and correcting the position of the working train carriage a second time, the deviation of the train carriage position that may occur during the dynamic acquisition process can be compensated for, and a more accurate position of the train carriage can be obtained.

[0126] Figure 3 is a flowchart illustrating the train carriage position identification method provided in this application. As shown in Figure 3, this embodiment, based on the embodiment in Figure 2, provides a detailed description of S202, which specifically includes the following steps:

[0127] S301. Based on the first positioning information, perform coordinate transformation on the point cloud data to obtain the point cloud data in the railway yard coordinate system.

[0128] Among them, the railway yard coordinate system can refer to the global coordinate system used to describe the position and orientation of all objects in the railway yard, and it is a fixed reference coordinate system.

[0129] In this embodiment, the point cloud data is data acquired by radar and is data in the radar coordinate system. Since the radar has a certain deviation relative to the gantry crane, it is necessary to correct the radar coordinate system data based on the acquired first positioning information, perform a linear transformation on the coordinates of each point, and map it to the global coordinate system of the railway yard to make it consistent with the railway yard coordinate system.

[0130] Understandably, unifying all data into a global coordinate system facilitates subsequent analysis and processing, makes it easier to integrate different data sources, and reduces errors caused by inconsistencies in coordinate systems. The point cloud data in the transformed railway yard coordinate system can accurately reflect the position and orientation of train carriages in the railway yard coordinate system.

[0131] S302. Based on the preset car height threshold and train width threshold, the point cloud data in the railway yard coordinate system is filtered to obtain the point cloud data of the working train car.

[0132] The carriage height threshold refers to a preset height range based on the dimensions of the operating train, used to filter point cloud data that matches the height of the train carriages, helping to exclude points that are higher or lower than the specified height and do not belong to the carriages. Similarly, the train width threshold refers to a preset width range based on the dimensions of the operating train, used to filter point cloud data that matches the width of the train carriages, helping to exclude points that are higher or lower than the specified width and do not belong to the carriages.

[0133] In this embodiment, the point cloud data in the railway yard coordinate system is traversed, and the coordinates of each point are checked, including whether the height coordinate of each point is within the car height threshold range and whether the width coordinate of each point is within the train width threshold range. Points that meet the height and width threshold conditions are retained to form a new point cloud dataset, representing the point cloud data of the working train car.

[0134] S303. Determine the location of the working train carriages based on the point cloud data of the working train carriages.

[0135] In this embodiment, the filtered point cloud data is analyzed to identify the geometric features of the train carriages, such as length, width, height and shape, and key features, such as the edges, corners and center points of the carriages, are extracted from the point cloud data. These features can be used to calculate the position and orientation of the carriages. Thus, the position of the train carriages in three-dimensional space is calculated using the extracted features.

[0136] In one possible implementation, S303 can be specifically implemented through the following steps:

[0137] First, the point cloud data of the working train carriages is clustered to obtain a train carriage point cloud dataset. Then, the extreme values ​​in the train carriage point cloud dataset are determined, and the extreme values ​​represent the boundary range of the train carriages. Finally, the location of the working train carriages is determined based on the extreme values.

[0138] Clustering refers to dividing point cloud data into multiple groups (or clusters), where points in each group have similar characteristics. In this embodiment, clustering is used to identify and separate point cloud data of train carriages.

[0139] In point cloud datasets, extreme values ​​refer to points with the maximum or minimum coordinate values. These points are typically located on the boundaries of train carriages and represent the spatial extent of the train carriages, including the range of length, width, and height.

[0140] As an example, cluster analysis of the point cloud data of the working train carriages is performed using methods such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and K-means. This divides the point cloud data into different clusters to identify point cloud datasets belonging to the train carriages and eliminate points irrelevant to noise and other interference. Then, in the train carriage point cloud dataset, extreme values ​​for each coordinate axis (e.g., X, Y, Z axes) are calculated, including finding the maximum and minimum coordinate values. Based on these extreme values, the center position and boundary range of the working train carriages are calculated to fully describe their position in three-dimensional space.

[0141] In some embodiments, ground interference can be removed by using a pass-through rate method based on information such as the height and width of the train carriages to obtain point cloud data of the working train carriages.

[0142] Understandably, clustering can effectively separate the point cloud data of train carriages, eliminate noise, and improve recognition accuracy. At the same time, accurately defining the boundary range and center position of the carriages using extreme value data ensures the accuracy of calculating the position of the working train carriages.

[0143] Furthermore, based on the extreme value data, the specific implementation of determining the location of the working train carriages can be achieved through the following steps:

[0144] First, the extreme value data are sorted according to their magnitude to obtain an extreme value sequence. Then, adjacent extreme value data within the extreme value sequence are compared pairwise to determine the extreme value difference. Thus, when the extreme value difference meets a preset extreme value difference threshold, the train car point cloud dataset is determined to be a point cloud dataset of the same train car, resulting in an updated train car point cloud dataset. Finally, the location of the working train car is determined based on the updated train car point cloud dataset.

[0145] The extreme value sequence is an ordered list obtained by sorting the extreme value data, which reflects the size relationship of the boundary points of the train carriages.

[0146] In an extreme value sequence, the difference between adjacent extreme values ​​can be used to determine whether they belong to the same train carriage.

[0147] The extreme value difference threshold is a preset value based on the size of the train carriage. It is used to determine whether the extreme value difference is small enough to determine whether adjacent extreme values ​​belong to the same carriage.

[0148] The train carriage location identification method provided in this application identifies the train carriages by filtering point cloud data in the railway yard coordinate system based on information such as the height and width of the train carriages. This results in the point cloud data of the working train carriages, which are then processed to separate the carriages and determine their locations. By utilizing precise point cloud data and feature extraction technology, the location of the train carriages can be accurately determined, thus improving positioning accuracy.

[0149] Figure 4 is a flowchart illustrating the train carriage location identification method provided in this application. As shown in Figure 4, this embodiment describes the train carriage location identification method based on the embodiment in Figure 3. After determining the location of the working train carriage according to the updated train carriage point cloud dataset, the method may further include:

[0150] S401. Based on the location of the working train carriage, determine the point cloud data of the working train carriage and the point cloud data of the upper plane of the working train carriage.

[0151] Among them, the point cloud data of the plane on the working train carriage refers to the point cloud data of the plane on the train carriage used to carry the container.

[0152] In this embodiment, based on the determined location of the working train car, the point cloud dataset of the entire working train car is located. From this dataset, the point cloud data of the entire car, including all surfaces and structures, is extracted. Then, by analyzing the point cloud data, the upper plane of the car is identified. Typically, the upper plane is the point cloud data located at the highest position. During the identification of the upper plane, geometric analysis methods, such as plane fitting or height thresholding, can be used to accurately extract the point cloud data of the upper plane.

[0153] S402. Based on the point cloud data of the upper plane of the working train carriage, the points in the point cloud data that are higher than the upper plane of the working train carriage in the width direction are filtered to obtain the point cloud dataset of the protruding parts.

[0154] The width direction of a train carriage refers to the lateral direction of the train carriage, that is, the direction perpendicular to the direction of travel of the carriage.

[0155] The point cloud dataset for protruding parts refers to the point cloud data that exists above the upper plane of the carriage in the width direction. These points represent the hollows, protrusions or other structures on the carriage.

[0156] In this embodiment, a reference plane is determined using point cloud data of the upper surface of the work train carriage. This plane represents the normal upper surface of the carriage. Then, the point cloud data in the width direction is analyzed to identify points higher than the reference plane. All point cloud data higher than the reference plane are filtered out to form a new point cloud dataset, namely the protruding part point cloud dataset.

[0157] S403. Based on the point cloud dataset of the protruding parts, determine the target location of the working train carriage.

[0158] In this embodiment, the point cloud dataset of the protruding parts is analyzed in detail, and the positional relationship between the point cloud dataset of the protruding parts and the outer boundary of the carriage is combined to remove the areas of foot pedals, handrails or other welded parts included in the range of the working train carriage, thereby obtaining a more accurate range.

[0159] Understandably, by filtering the points in the point cloud data that are higher than the top plane of the working train car in the width direction, the protrusions on the car can be identified, the structure of the car can be determined, and the range of the car can be further filtered.

[0160] In one possible implementation, S403 can be specifically implemented through the following steps:

[0161] First, the point cloud dataset of protruding parts is clustered to obtain the target protruding part point cloud dataset, which represents the independent protruding parts on the working train carriage. Then, based on the target protruding part point cloud dataset, the target position of the working train carriage is determined.

[0162] Independent protruding parts refer to different structures or objects that are separated from each other on the carriage, such as welded parts, which can affect the position of the working train carriage.

[0163] The train carriage location identification method provided in this application identifies protruding parts by filtering the points in the point cloud data that are higher than the upper plane of the working train carriage in the width direction of the train carriage. This allows for further correction of the boundary range of the working train carriage, thereby obtaining a more accurate boundary range and target location of the working train carriage.

[0164] Figure 5 is a flowchart illustrating another train carriage position identification method provided in this application. As shown in Figure 5, the method may include:

[0165] S501. Obtain the GPS module location information in real time and correct it to the center position of the gantry crane trolley, and record it as the gantry crane's location information.

[0166] Among them, the initial position information of the gantry crane in the railway yard is GPS0(x, y, yaw), and the real-time GPS positioning information of the gantry crane is GPS0(x, y, yaw). i (x, y, yaw). Among them, GPS i x represents the distance in the direction of the gantry crane trolley; GPS i y represents the distance in the direction of the gantry crane trolley; GPS i yaw represents the yaw angle of the gantry crane.

[0167] S502. Based on the radar's position relative to the center of the gantry crane trolley and the gantry crane's starting position in the railway yard, convert the radar coordinate system to the railway yard coordinate system.

[0168] In this embodiment, the radar point cloud is A{(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)}. Based on the GPS location information GPS0(x, y, yaw) at the starting position of the storage yard; and the real-time GPS positioning information GPS of the gantry crane... i The coordinate transformation of point cloud A using (x, y, yaw) and the radar position information relative to the gantry crane is performed to obtain point cloud B {(x1, y1, z1), (x2, y2, z2)...(xn, yn, zn)} relative to the railway yard.

[0169] S503. Determine whether the train car width value or the sudden change value of the car's direction meets the set value requirements.

[0170] In this embodiment, a pass-through rate method can be used to remove ground interference based on information such as train car height and train width, obtaining the train point cloud C{(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)}, and then determining whether W > Ws or X > Xs. Here, W represents the car width value; Ws represents the set car width value; X represents the abrupt change value in the car's main carriage direction; and Xs represents the set car's main carriage direction value.

[0171] S504 If yes, then separate the train cars and record the position range of the train cars directly below the gantry crane; otherwise, repeat S502.

[0172] In this embodiment, the point cloud C is processed by planar extraction, clustering, etc., to separate the carriages and obtain multiple carriage point sets D0{(x1, y1, z1), (x2, y2, z2)...(xn, yn, zn)},...,D n {(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)}.

[0173] Calculate the point set D0, ..., D nThe extreme values are obtained to get the array E0 of corresponding extreme values (D0(min, max), …, D n (min, max)).

[0174] The array E0 is sorted to get the array E1 (D0(min, max), …, D n (min, max)).

[0175] Where, min represents the boundary of the car body close to the starting position of the yard; max represents the boundary of the car body far from the starting position of the yard.

[0176] S505. Determine whether the position range of the current train car body coincides with the position range of the train car body recorded at the previous moment.

[0177] S506. If not, add the position range of the train car body to the whole train car body diagram; otherwise, execute S504 again.

[0178] In this embodiment, the data in the array E1 is judged and combined for the same car body. If abs(D i+1 .min - D i .max) < Vs or D i .max is within D i+1 (min, max), it is considered to be the same car body, and the array E2 (D0(min, max), …, D n (min, max)) is obtained.

[0179] Then, filter the data F0(min, max, cx, cy) in the initial array E2 where D i .min ≤ GPS i .x and D i .max ≥ GPS i .x, which is the range of the current car body. Where, Vs represents a preset value; cx represents the center of the car body in the direction of the large vehicle; cy represents the center of the car body in the direction of the small vehicle.

[0180] Otherwise, it is considered not to be the same car body, and the position range of the train car body needs to be added to the whole train car body diagram.

[0181] Optionally, the current point set H{(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)} of the current carriage below the gantry crane and the point set I{(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)} of the current carriage upper plane can be extracted based on the data F0. Then, based on the point sets H and I, the point set M{(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)} of the protruding parts above the upper surface of the central region in the width direction of the carriage can be extracted. By clustering, the protruding parts in the point set M can be extracted to obtain multiple protruding part point sets N0{(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)},…,N n {(x1, y1, z1), (x2, y2, z2)…(xn, yn, zn)}, then calculate the point set N. i The range is determined by combining its positional relationship with the outer boundary of the carriage and removing the areas of footrests, handrails or other welded parts included in the carriage boundary range F0(min, max, cx, cy), thereby obtaining a more accurate range F1(min, max, cx, cy).

[0182] S507. Determine whether the gantry crane has completed the collection of the location range of all carriages on the train.

[0183] S508 If yes, then the initial map of the train carriages in the railway yard is obtained; otherwise, S501 is executed again.

[0184] The train carriage location identification method provided in this application collects initial three-dimensional data of the train carriages and their surrounding environment, unifies the data into the railway yard coordinate system, and then filters out irrelevant point cloud data, retaining only the parts related to the train carriages, thereby improving the purity and accuracy of the data. Furthermore, through carriage separation, boundary extraction, and location mapping, a complete train carriage location map is created, providing location information for the automated system. Through precise positioning and mapping, the efficiency and safety of yard operations are improved.

[0185] Figure 6 is a flowchart illustrating another method for identifying the location of train carriages provided in this application. As shown in Figure 6, based on the embodiment in Figure 5, after obtaining the initial mapping of the train carriages in the railway yard, this method further includes:

[0186] S601. Based on the initial mapping of the train carriages in the railway yard, determine the location of the working train carriages and control the gantry crane to carry out the operation.

[0187] S602. Obtain the GPS module location information in real time and correct it to the center position of the gantry crane trolley, and record it as the gantry crane's location information.

[0188] S603. Determine whether the difference between the initial position information of the gantry crane and the position of the working train car obtained from the initial mapping of the train car in the railway yard meets the set value requirements.

[0189] S604. If yes, then based on the radar's position relative to the center of the gantry crane trolley and the gantry crane's starting position in the railway yard, convert the radar coordinate system to the railway yard coordinate system; otherwise, re-execute S602.

[0190] S605. Determine whether the train car width value or the sudden change value of the car's direction meets the set value requirements.

[0191] S606 If yes, separate the train cars and record the position range of the train cars directly below the gantry crane; otherwise, execute S604.

[0192] S607. Calculate the position of the working train carriage and make position corrections.

[0193] In this embodiment, the automation system calculates the work position based on the initial train location map and the work task, and sends instructions to the gantry crane control system. The control system then directs the gantry crane to the corresponding position to complete the container grabbing or unloading operation. i And then combined with GPS i The system calculates the center positions cx and cy of the current working carriage and updates the train position map to provide more accurate position information for subsequent operations on the same carriage, thereby improving operational efficiency.

[0194] S608. Determine whether the lock / unlock signal has changed.

[0195] Changes in interlocking signals are typically related to the status or operation of train carriages. Specifically, interlocking information may indicate changes in the system's status, such as the status of the carriage locking device, thereby determining whether the carriage is ready for hoisting operations, such as loading or unloading.

[0196] S609. If yes, update the position of the corresponding working train car in the initial drawing of the entire train car in the railway yard; otherwise, re-execute S606.

[0197] As an example, when the lockout signal changes, the carriage or related equipment transitions from one state (such as locked) to another state (such as unlocked), which means that the hoisting operation for that carriage has been completed. The position of the corresponding working carriage in the initial map of the entire train carriage in the railway yard is updated to ensure that the position map reflects the latest carriage status and position, so as to provide accurate data support for subsequent operations.

[0198] As another example, if the opening and closing signals do not change, S606 is re-executed, that is, the separation of the carriages is reconfirmed or adjusted, and the position range of the train carriages directly below the gantry crane is recorded to ensure the accuracy of the operation.

[0199] The train carriage location identification method provided in this application provides a secondary correction of the initial position through precise positioning. At the same time, by separating the carriages, it can accurately identify the position of train carriages in the railway yard, making up for the shortcomings of the dynamic acquisition process and solving the problem of the uncertain position of the entire train carriages in the railway yard.

[0200] Figure 7 is a structural schematic diagram of the train carriage position identification device provided in this application. As shown in Figure 7, the train carriage position identification device 70 provided in this embodiment includes:

[0201] The acquisition module 701 is used to acquire point cloud data and first positioning information collected by scanning the working train in the extension direction;

[0202] The determination module 702 is used to determine the position of the working train carriage based on point cloud data and the first positioning information;

[0203] The control module 703 is used to control the gantry crane to perform lifting operations on the corresponding working train car based on the position of the working train car, and to obtain the second positioning information of the working train car in real time during the lifting operation.

[0204] The adjustment module 704 is used to update the position of the working train car based on the second positioning information to obtain the updated position of the working train car.

[0205] In one possible implementation, the determining module 702 is specifically used for:

[0206] Based on the first positioning information, coordinate transformation is performed on the point cloud data to obtain the point cloud data in the railway yard coordinate system;

[0207] The point cloud data in the railway yard coordinate system is filtered according to the preset car height threshold and train width threshold to obtain the point cloud data of the working train car.

[0208] The location of the working train carriages is determined based on the point cloud data of the working train carriages.

[0209] In one possible implementation, the location of the work train car is determined based on the point cloud data of the work train car. The determining module 702 is specifically used for:

[0210] Clustering is performed on the point cloud data of the working train carriages to obtain the train carriage point cloud dataset;

[0211] Determine the extreme value data in the point cloud dataset of train carriages; the extreme value data represents the boundary range of the train carriages.

[0212] The location of the working train carriages is determined based on the extreme value data.

[0213] In one possible implementation, the location of the working train car is determined based on extreme value data. The determining module 702 is specifically used for:

[0214] The extreme value data are sorted according to their magnitude to obtain an extreme value sequence;

[0215] Pairwise comparisons are performed on adjacent extreme value data within the extreme value sequence to determine the extreme value differences;

[0216] When the extreme value difference meets the preset extreme value difference threshold, the train car point cloud dataset is determined to be the point cloud dataset of the same train car, and the updated train car point cloud dataset is obtained.

[0217] The location of the working train car is determined based on the updated train car point cloud dataset.

[0218] In one possible implementation, after determining the location of the working train car based on the updated train car point cloud dataset, the determining module 702 is further configured to:

[0219] Based on the location of the working train carriage, determine the point cloud data of the working train carriage and the point cloud data of the upper plane of the working train carriage;

[0220] Based on the point cloud data of the upper plane of the working train carriage, the points in the point cloud data that are higher than the upper plane of the working train carriage in the width direction are filtered to obtain the point cloud dataset of the protruding parts.

[0221] Based on the point cloud dataset of the protruding parts, the target location of the working train carriage is determined.

[0222] In one possible implementation, the target location of the work train carriage is determined based on the point cloud dataset of the protruding part. The determination module 702 is specifically used for:

[0223] Clustering is performed on the point cloud dataset of protruding parts to obtain the target protruding part point cloud dataset, which represents the independent protruding parts on the working train carriage.

[0224] Based on the point cloud dataset of the prominent parts of the target, the target location of the working train carriage is determined.

[0225] In one possible implementation, the adjustment module 704 is specifically used for:

[0226] Based on the second positioning information, determine the center position of the working train carriage;

[0227] Based on the center position, the position of the working train car is updated to obtain the updated position of the working train car.

[0228] The train carriage position identification device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0229] Figure 8 is a structural schematic diagram of the gantry crane provided in this application. As shown in Figure 8, the gantry crane 80 provided in this embodiment includes: a gantry crane body 801, a positioning device 802 and a radar 803 installed on the gantry crane trolley, and an electronic device 804 installed on the gantry crane body 801;

[0230] The gantry crane body 801 is used for lifting operations on the corresponding working train car.

[0231] Positioning device 802 is used to collect positioning information;

[0232] Radar 803 is used to scan the working train in the extended direction;

[0233] Electronic device 804, used to perform the train carriage position identification method according to the various possible implementations described above.

[0234] The gantry crane provided in this embodiment can execute the method provided in the above-described method embodiments. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0235] Figure 9 is a schematic diagram of the structure of the electronic device provided in this application. As shown in Figure 9, the electronic device 90 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the electronic device 90 further includes a communication component 903. The processor 901, the memory 902, and the communication component 903 are connected via a bus 904.

[0236] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0237] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0238] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0239] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0240] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0241] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0242] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0243] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0244] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0245] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0246] 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0247] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0248] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this 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 of the various embodiments of this 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.

[0249] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0250] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for identifying the position of a train carriage, characterized in that, include: Simultaneously, point cloud data and first positioning information collected by scanning the working train in the extension direction are acquired; during the acquisition of the point cloud data and first positioning information of the working train, the point cloud data and the first positioning information are synchronized in time and space; the position of the working train carriage is determined according to the point cloud data and the first positioning information; based on the position of the working train carriage, the gantry crane is controlled to perform lifting operations on the working train carriage corresponding to the position of the working train carriage, and the second positioning information of the working train carriage is acquired in real time during the lifting operation; the position of the working train carriage is updated according to the second positioning information to obtain the updated position of the working train carriage; the second positioning information refers to the position data of the working train carriage after the lifting device completes the lifting and lowering of the container during the lifting operation. Determining the location of the working train carriage based on the point cloud data and the first positioning information includes: performing coordinate transformation on the point cloud data based on the first positioning information to obtain point cloud data in the railway yard coordinate system; The point cloud data in the railway yard coordinate system is filtered according to preset car height thresholds and train width thresholds to obtain the point cloud data of the working train car; the position of the working train car is determined based on the point cloud data of the working train car, the position of the working train car includes the position and range of the working train car in the railway yard, the range includes the length, width and height of the working train car.

2. The method according to claim 1, characterized in that, The step of determining the location of the working train carriage based on the point cloud data of the working train carriage includes: performing clustering processing on the point cloud data of the working train carriage to obtain a train carriage point cloud dataset; determining the extreme value data in the train carriage point cloud dataset, wherein the extreme value data represents the boundary range of the train carriage; and determining the location of the working train carriage based on the extreme value data.

3. The method according to claim 2, characterized in that, The step of determining the location of the working train carriage based on the extreme value data includes: sorting the extreme value data according to the size relationship of the extreme value data to obtain an extreme value sequence; comparing adjacent extreme value data in the extreme value sequence pairwise to determine the extreme value difference; when the extreme value difference meets a preset extreme value difference threshold, determining that the train carriage point cloud dataset is a point cloud dataset of the same train carriage, and obtaining an updated train carriage point cloud dataset; and determining the location of the working train carriage based on the updated train carriage point cloud dataset.

4. The method according to claim 3, characterized in that, After determining the location of the working train car based on the updated train car point cloud dataset, the method further includes: determining the point cloud data of the working train car and the point cloud data of the upper plane of the working train car based on the location of the working train car; filtering points in the width direction of the train car that are higher than the point cloud data of the upper plane of the working train car based on the point cloud data of the upper plane of the working train car to obtain a protruding part point cloud dataset; and determining the target location of the working train car based on the protruding part point cloud dataset.

5. The method according to claim 4, characterized in that, The step of determining the target location of the work train carriage based on the protruding part point cloud dataset includes: performing clustering processing on the protruding part point cloud dataset to obtain a target protruding part point cloud dataset, wherein the target protruding part point cloud dataset represents an independent protruding part on the work train carriage; and determining the target location of the work train carriage based on the target protruding part point cloud dataset.

6. The method according to any one of claims 1-5, characterized in that, The step of updating the position of the work train carriage according to the second positioning information to obtain the updated position of the work train carriage includes: determining the center position of the work train carriage according to the second positioning information; and updating the position of the work train carriage according to the center position to obtain the updated position of the work train carriage.

7. A train carriage position identification device, characterized in that, include: The acquisition module is used to simultaneously acquire point cloud data and first positioning information collected by scanning the working train in the extension direction; During the process of acquiring point cloud data and first positioning information of the working train, the point cloud data and the first positioning information are synchronized in time and space. The system comprises a determining module for determining the position of the working train carriage based on the point cloud data and the first positioning information; a control module for controlling the gantry crane to perform lifting operations on the working train carriage corresponding to the position of the working train carriage based on the position of the working train carriage, and acquiring the second positioning information of the working train carriage in real time during the lifting operation; and an adjustment module for updating the position of the working train carriage based on the second positioning information to obtain the updated position of the working train carriage. The second positioning information refers to the position data of the working train carriage after the lifting device has completed grabbing and placing the carriage during the lifting operation. Specifically, the determining module is used to: perform coordinate transformation on the point cloud data based on the first positioning information to obtain point cloud data in the railway yard coordinate system; filter the point cloud data in the railway yard coordinate system according to preset carriage height thresholds and train width thresholds to obtain the point cloud data of the working train carriage; and determine the position of the working train carriage based on the point cloud data of the working train carriage, wherein the position of the working train carriage includes the position and range of the working train carriage in the railway yard, and the range includes the length, width, and height of the working train carriage.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A gantry crane, characterized in that, include: The gantry crane body, a positioning device and radar mounted on the gantry crane trolley, and electronic equipment mounted on the gantry crane body; the gantry crane body is used for lifting cargo into a working train car at a corresponding working train car position; the positioning device is used for collecting positioning information; the radar is used for scanning the working train in the extending direction; and the electronic equipment is used for executing the method described in any one of claims 1-6.

Images