Railway whole-row cargo rapid measurement and over-limit grade intelligent determination method

Abstract

The invention discloses a rapid measurement and over-limit grade intelligent judgment method for railway whole-row cargoes. The method comprises the following steps: step 1, cargo three-dimensional point cloud data acquisition: an operator holds a mobile measurement device integrated with a laser radar scanner, an inertial measurement unit (IMU) and a global positioning system (GNSS) module and walks along a whole train loaded with cargoes, continuous three-dimensional laser scanning is carried out on goods and vehicles, and high-density three-dimensional point cloud data are obtained. According to the invention, a handheld device is adopted for rapid walking scanning, manual climbing measurement is replaced, the operation efficiency is improved by several times, the safety risk of high-altitude operation is thoroughly eliminated, the complete point cloud contour of goods is obtained through three-dimensional laser scanning, the one-sidedness and error of manual single-point measurement are avoided, and the measurement result is more comprehensive and higher in precision.

Description

Technical Field

[0001] This invention relates to the field of LVDS port display screen self-adaptation system technology, and more specifically to a method for rapid measurement and intelligent determination of over-limit level of freight in a railway train. Background Technology

[0002] Oversized cargo transportation is a crucial component of railway freight transport, and its safety is paramount. Currently, the detection of oversized cargo after loading primarily relies on traditional manual measurement methods. Workers use tools such as tape measures and laser rangefinders, climbing onto the roof of the wagon or using elevated platforms to measure critical parts of the cargo.

[0003] This method has the following significant drawbacks:

[0004] 1. Inefficient and unsafe: Manual measurement is time-consuming and labor-intensive, and there are safety risks associated with personnel working at heights.

[0005] 2. Incomplete data and limited accuracy: Only discrete and limited feature point dimensions can be obtained, and complete contour information of the goods cannot be obtained. It is easy to miss judgment due to insufficient measurement points.

[0006] 3. High subjectivity and low degree of automation: The determination of the over-limit level relies heavily on human experience. The process of comparing the measurement data with the limit map in the "Rules for the Transportation of Over-limit and Overweight Goods by Railway" is cumbersome and prone to errors.

[0007] 4. Data silos and difficulty in integration: Measurement results are mostly paper records or simple spreadsheets, which are difficult to integrate seamlessly with freight production operations and management platforms, and cannot provide structured data support for subsequent transportation organization, telegram applications and other processes.

[0008] Therefore, a new technical solution is needed to address this issue. Summary of the Invention

[0009] The purpose of this invention is to provide a method for rapid measurement and intelligent determination of over-limit levels of freight in railway trains, which solves the problems mentioned in the background art.

[0010] To achieve the above objectives, the present invention provides the following technical solution: a method for rapid measurement and intelligent determination of over-limit level of freight trains, comprising the following steps:

[0011] Step 1: Cargo 3D point cloud data acquisition: The operator uses a handheld mobile measurement device that integrates a lidar scanner, inertial measurement unit (IMU) and global positioning system (GNSS) module to walk along the entire train loaded with cargo and perform continuous 3D laser scanning of the cargo and vehicles to obtain high-density 3D point cloud data.

[0012] Step 2: Intelligent processing of point cloud data and establishment of track surface coordinate system: Upload the raw point cloud data collected in Step 1 to the processing terminal. The terminal performs point cloud segmentation, extraction of track surface and centerline, establishment of track surface coordinate system, point cloud projection and cross-sectional slice generation.

[0013] Step 3: Automatic determination and level identification of exceeding limits: Pre-store or call the limit contour polygon template, and compare the limit template with each projection slice generated in step 2 to identify the location and level of exceeding limits.

[0014] Step 4: Data Connectivity and Application: The judgment results from Step 3 will be automatically generated into a structured data report and uploaded to the freight production operation and management platform through the data interface.

[0015] In a preferred embodiment of the present invention, the method for intelligent processing of point cloud data and establishment of orbital coordinate system in step 2 includes the following steps:

[0016] S1: Point cloud segmentation: The target point cloud, including trains and cargo, is segmented using a point cloud segmentation algorithm;

[0017] S2: Track surface and centerline extraction: The point cloud segmentation algorithm is used to automatically identify and extract the point cloud of the rail surface, and then fit the plane equation and centerline of the two rails.

[0018] S3: Establish the track surface coordinate system: with the track centerline as the X-axis, the direction perpendicular to the horizontal plane as the Z-axis, and the direction within the horizontal plane perpendicular to the X-axis as the Y-axis, establish the track surface coordinate system;

[0019] S4: Point cloud projection and cross-sectional slice generation: The point cloud data of the entire cargo is converted to the orbital coordinate system, and a series of projection planes perpendicular to the X-axis are generated at fixed intervals along the X-axis direction. The cargo point cloud is projected onto these projection planes to form a projection slice point set.

[0020] In a preferred embodiment of the present invention, the point cloud segmentation algorithm in step S1 includes the RANSAC algorithm or the region growing method.

[0021] In a preferred embodiment of the present invention, the fixed interval in step S4 is 0.1 meters or 0.5 meters.

[0022] In a preferred embodiment of the present invention, step 3, automatic over-limit determination and level identification, includes:

[0023] S1: Clearance template overlay: Pre-store or call up the polygonal templates of different levels of clearance outlines defined in the "Rules for the Transportation of Oversized and Overweight Goods by Railway". The different levels include Level 1, Level 2 and Super Oversized.

[0024] S2: Determination of Over-Limit Location and Level: Identify points or regions in the projected slice that exceed the outline of the limit template, record the mileage location, direction of exceedance, and amount of exceedance of the cross section, and comprehensively determine the overall over-limit level by traversing all cross sections.

[0025] In a preferred embodiment of the present invention, the data connectivity and application in step 4 includes: generating a structured data report from the judgment result and uploading it to the freight production operation and control platform through an API interface, which is used to automatically or assistedly generate station application telegrams, provide data support for transportation organization, and realize data traceability and refined management of the entire process of oversized cargo transportation.

[0026] In a preferred embodiment of the present invention, the mobile measurement device supports the SLAM algorithm, enabling accurate mobile scanning in environments without GPS signals.

[0027] In a preferred embodiment of the present invention, the processing terminal is a mobile terminal or a cloud server.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] 1. The use of handheld devices for rapid walking and scanning replaces manual climbing and measurement, increasing work efficiency several times over and completely eliminating the safety risks of working at heights.

[0030] 2. The complete point cloud outline of the cargo is obtained by 3D laser scanning, which avoids the one-sidedness and error of manual single-point measurement, and the measurement results are more comprehensive and more accurate.

[0031] 3. It has achieved full automation of the process from point cloud processing and coordinate establishment to over-limit judgment, which greatly reduces manual intervention, avoids subjective errors, and makes the judgment results objective and reliable.

[0032] 4. It achieves seamless integration between on-site measurement data and upper-level management information systems, automatically generates structured reports and uploads them to the freight platform, thus opening up data flow. It is a key tool for promoting the "digitalization" and "intelligentization" transformation of railway freight, and provides timely and accurate data support for subsequent telegram applications and transportation organization. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating the overall workflow of the present invention.

[0034] Figure 2 This is a schematic diagram of the data acquisition process of the present invention;

[0035] Figure 3 This is a schematic diagram of the orbital plane coordinate system of the present invention;

[0036] Figure 4 This is a schematic diagram illustrating the over-limit determination process of this invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Please see Figure 1-4 This invention provides a technical solution: a method for rapid measurement and intelligent determination of over-limit level of freight in a railway train.

[0039] Regarding the aforementioned problems: Currently, the detection of oversized cargo after loading mainly relies on traditional manual measurement methods. This involves workers using tools such as measuring tapes and laser rangefinders, climbing onto the roof of the vehicle or using a high platform to measure key parts of the cargo.

[0040] The solution is as follows: A method for rapid measurement and intelligent determination of oversized / overweight levels of freight trains, comprising the following steps:

[0041] Step 1: Cargo 3D point cloud data acquisition: The operator uses a handheld mobile measurement device that integrates a lidar scanner, inertial measurement unit (IMU) and global positioning system (GNSS) module to walk along the entire train loaded with cargo and perform continuous 3D laser scanning of the cargo and vehicles to obtain high-density 3D point cloud data.

[0042] Step 2: Intelligent processing of point cloud data and establishment of track surface coordinate system: Upload the raw point cloud data collected in Step 1 to the processing terminal. The terminal performs point cloud segmentation, extraction of track surface and centerline, establishment of track surface coordinate system, point cloud projection and cross-sectional slice generation.

[0043] Step 3: Automatic determination and level identification of exceeding limits: Pre-store or call the limit contour polygon template, and compare the limit template with each projection slice generated in step 2 to identify the location and level of exceeding limits.

[0044] Step 4: Data Connectivity and Application: The judgment results from Step 3 will be automatically generated into a structured data report and uploaded to the freight production operation and management platform through the data interface.

[0045] The further improved method for intelligent processing of point cloud data and establishment of the orbital coordinate system in step 2 includes the following steps:

[0046] S1: Point cloud segmentation: The target point cloud, including trains and cargo, is segmented using a point cloud segmentation algorithm;

[0047] S2: Track surface and centerline extraction: The point cloud segmentation algorithm is used to automatically identify and extract the point cloud of the rail surface, and then fit the plane equation and centerline of the two rails.

[0048] S3: Establish the track surface coordinate system: with the track centerline as the X-axis, the direction perpendicular to the horizontal plane as the Z-axis, and the direction within the horizontal plane perpendicular to the X-axis as the Y-axis, establish the track surface coordinate system;

[0049] S4: Point cloud projection and cross-sectional slice generation: The point cloud data of the entire cargo is converted to the orbital coordinate system, and a series of projection planes perpendicular to the X-axis are generated at fixed intervals along the X-axis direction. The cargo point cloud is projected onto these projection planes to form a projection slice point set.

[0050] Further improvements include using the RANSAC algorithm or region growing method in step S1 for point cloud segmentation. Using RANSAC or region growing methods for point cloud segmentation can more accurately separate the point clouds of trains and goods from complex raw point cloud data, improving the accuracy and efficiency of subsequent processing. The RANSAC algorithm has good robustness to noise and outliers, while the region growing method can segment based on the local features of the point cloud. Combining the two can address point cloud segmentation needs in different scenarios.

[0051] In a further improvement, the fixed interval in step S4 is 0.1 meters or 0.5 meters: the projection plane is generated along the X-axis at fixed intervals of 0.1 meters or 0.5 meters, and the data density can be adjusted according to actual needs. Smaller intervals (such as 0.1 meters) can provide more detailed cargo contour information, suitable for scenarios with high accuracy requirements; larger intervals (such as 0.5 meters) can reduce the amount of data processing and improve processing speed, suitable for scenarios with high efficiency requirements.

[0052] In a further improvement, step 3, the automatic determination and level identification of exceeding limits, includes:

[0053] S1: Clearance template overlay: Pre-store or call up the polygonal templates of different levels of clearance outlines defined in the "Rules for the Transportation of Oversized and Overweight Goods by Railway". The different levels include Level 1, Level 2 and Super Oversized.

[0054] S2: Determination of Over-Limit Location and Level: Identify points or regions in the projected slice that exceed the outline of the limit template, record the mileage location, direction of exceedance, and amount of exceedance of the cross section, and comprehensively determine the overall over-limit level by traversing all cross sections.

[0055] By pre-storing or recalling polygonal templates of different clearance profiles and comparing them with the generated projection slices, the location and level of exceeding limits can be automatically identified. This method avoids the subjectivity and error of manual comparison, improving the accuracy and reliability of exceeding limit determination. Simultaneously, recording the mileage location of the cross-section, the direction of the exceedance, and the amount of exceedance provides detailed data support for subsequent transportation organization.

[0056] Further improvements include, in step 4, data connectivity and application: generating a structured data report from the judgment results and uploading it to the freight production operation and control platform via an API interface. This report is used to automatically or assistedly generate station application telegrams, provide data support for transportation organization, and achieve data traceability and refined management throughout the entire process of oversized cargo transportation. The automatic generation of a structured data report from the judgment results and its uploading to the freight production operation and control platform via an API interface achieves seamless integration between on-site measurement data and the upper-level management information system. This not only improves data processing efficiency but also provides timely and accurate data support for subsequent telegram applications and transportation organization, promoting the "digitalization" and "intelligentization" transformation of railway freight.

[0057] Furthermore, the mobile measurement device supports the SLAM algorithm, enabling precise mobile scanning even in environments without GPS signals. This expands the applicability of the measurement method, enhancing its flexibility and reliability and ensuring the acquisition of high-quality 3D point cloud data in various environments.

[0058] Furthermore, the processing terminal can be a mobile terminal or a cloud server. Setting the processing terminal to a mobile terminal or a cloud server allows for the selection of a suitable processing method based on actual needs. Mobile terminals facilitate on-site operation and real-time processing, while cloud servers offer more powerful computing capabilities and storage space, making them suitable for processing large-scale data. This flexibility improves the applicability and efficiency of the measurement method.

[0059] Working principle: It uses a high-precision handheld LiDAR scanner (such as GeoSLAM ZEB Horizon or similar devices), which has a built-in IMU and vision sensor and supports SLAM (Simultaneous Localization and Mapping) algorithm, enabling accurate mobile scanning in environments without GPS signals.

[0060] The operator starts the equipment and walks along one side of the train at a normal pace, beginning at either the front or rear of the vehicle, ensuring the equipment effectively scans the sides and top of the cargo. A full scan around the train can be performed to obtain more comprehensive data. After scanning, the equipment imports the raw point cloud data into a processing terminal, such as a high-performance laptop or cloud server, via Wi-Fi or USB.

[0061] The terminal software automatically runs the algorithm. First, it uses a deep learning point cloud segmentation algorithm or a traditional algorithm (such as RANSAC) to segment target point clouds such as tracks, vehicles, and cargo from the original point cloud. Next, it uses the RANSAC algorithm to quickly fit two rail planes and calculate the track centerline. Then, it establishes a rail plane coordinate system: with the track centerline as the X-axis (train travel direction), the vertical plane upwards as the Z-axis, and the direction perpendicular to the X-axis in the horizontal plane as the Y-axis (train width direction). The global point cloud is transformed to this coordinate system. Along the X-axis, a series of cross-sectional projection planes perpendicular to the X-axis are generated at fixed intervals of 0.5 meters. The cargo point cloud is projected onto these planes to form a series of "projection slices" reflecting the cross-sectional contours of the cargo. Finally, the projection of the point cloud of each "projection slice" on the YZ plane is compared with the pre-stored Level 1, Level 2, and Super Overweight / Oversized Cargo Clearance Templates in the "Railway Overweight and Oversized Cargo Transportation Rules". For example, if a cross-sectional profile exceeds the "Level 2 Over-limit" limit template but not the "Super Over-limit" template in the positive Y-axis direction (right side), the system automatically records the cross-sectional position (X coordinate), classifies it as Level 2 Over-limit, and calculates the excess distance. The system iterates through all cross-sections and takes the most severe cross-sectional level as the overall over-limit level for that batch of goods.

[0062] The software automatically generates structured reports in JSON or XML format containing key information such as the level, location, and quantity of over-limit items. These reports are transmitted to the freight production operation and control platform via a security data interface (such as an API) on the railway intranet. Upon receiving the data, the platform automatically fills in the corresponding fields in the telegram application form; staff only need to verify and confirm before submission, significantly improving work efficiency. Simultaneously, all data is archived for traceability and refined management of the transportation process.

[0063] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0064] Finally, the following points should be noted: First, in the description of this application, it should be noted that, unless otherwise specified and limited, the terms "installation", "connection", and "linkage" should be interpreted broadly, and can refer to mechanical or electrical connections, or internal connections between two components, or direct connections. "Up", "down", "left", "right", etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may change.

[0065] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for rapid measurement and intelligent determination of over-limit level of freight in a railway train, characterized in that: The method for rapid measurement and intelligent determination of oversized / overweight levels of freight on railway trains includes the following steps: Step 1: Cargo 3D point cloud data acquisition: The operator uses a handheld mobile measurement device that integrates a lidar scanner, inertial measurement unit (IMU) and global positioning system (GNSS) module to walk along the entire train loaded with cargo and perform continuous 3D laser scanning of the cargo and vehicles to obtain high-density 3D point cloud data. Step 2: Intelligent processing of point cloud data and establishment of track surface coordinate system: Upload the raw point cloud data collected in Step 1 to the processing terminal. The terminal performs point cloud segmentation, extraction of track surface and centerline, establishment of track surface coordinate system, point cloud projection and cross-sectional slice generation. Step 3: Automatic determination and level identification of exceeding limits: Pre-store or call the limit contour polygon template, and compare the limit template with each projection slice generated in step 2 to identify the location and level of exceeding limits. Step 4: Data Connectivity and Application: The judgment results from Step 3 will be automatically generated into a structured data report and uploaded to the freight production operation and management platform through the data interface.

2. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 1, characterized in that: The method for intelligent processing of point cloud data and establishment of orbital coordinate system in step 2 includes the following steps: S1: Point cloud segmentation: The target point cloud, including trains and cargo, is segmented using a point cloud segmentation algorithm; S2: Track surface and centerline extraction: The point cloud segmentation algorithm is used to automatically identify and extract the point cloud of the rail surface, and then fit the plane equation and centerline of the two rails. S3: Establish the track surface coordinate system: with the track centerline as the X-axis, the direction perpendicular to the horizontal plane as the Z-axis, and the direction within the horizontal plane perpendicular to the X-axis as the Y-axis, establish the track surface coordinate system; S4: Point cloud projection and cross-sectional slice generation: The point cloud data of the entire cargo is converted to the orbital coordinate system, and a series of projection planes perpendicular to the X-axis are generated at fixed intervals along the X-axis direction. The cargo point cloud is projected onto these projection planes to form a projection slice point set.

3. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 2, characterized in that: The point cloud segmentation algorithm in step S1 includes the RANSAC algorithm or the region growing method.

4. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 2, characterized in that: The fixed interval in step S4 is 0.1 meters or 0.5 meters.

5. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 1, characterized in that: Step 3, the automatic determination and level identification of exceeding limits, includes: S1: Clearance template overlay: Pre-store or call up the polygonal templates of different levels of clearance outlines defined in the "Rules for the Transportation of Oversized and Overweight Goods by Railway". The different levels include Level 1, Level 2 and Super Oversized. S2: Determination of Exceeding Limit Location and Level: Identify points or regions in the projected slice that exceed the outline of the limit template, record the mileage location, direction of the exceedance, and amount of exceedance of the cross section, and comprehensively determine the overall exceeding limit level by traversing all cross sections.

6. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 1, characterized in that: The data connectivity and application in step 4 include: generating a structured data report from the judgment results and uploading it to the freight production operation and control platform via API interface, which is used to automatically or assistedly generate station application telegrams, provide data support for transportation organization, and realize data traceability and refined management of the entire process of oversized cargo transportation.

7. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 1, characterized in that: The mobile measurement device supports the SLAM algorithm, enabling accurate mobile scanning even in environments without GPS signals.

8. The method for rapid measurement and intelligent determination of over-limit level of railway freight trains according to claim 1, characterized in that: The processing terminal is a mobile terminal or a cloud server.

Images