Railway bolt connection state determination method, device, equipment, medium and product

Abstract

The embodiments of the present disclosure disclose a railway bolt connection state determination method, device, equipment, medium and product, comprising: determining a point cloud data set corresponding to a railway bolt assembly based on point cloud data corresponding to a railway connection area; the railway connection area includes the railway bolt assembly; clustering each point cloud data in the point cloud data set according to first distance information between any two point cloud data in the point cloud data set to obtain a clustering cluster set; in the case that the number of clustering clusters in the clustering cluster set meets a preset number judgment condition, determining a target feature distance according to minimum distance information between any two clustering clusters; the target feature distance is the maximum distance in each minimum distance information; determining the connection state of the railway bolt assembly based on the target feature distance and a preset distance judgment condition. The technical scheme reduces the artificial operation and maintenance cost, realizes accurate determination of the railway bolt loosening state, and is suitable for intelligent inspection in a variable environment.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent railway operation and maintenance technology, and in particular to a method, apparatus, equipment, medium and product for determining the state of railway bolt connections. Background Technology

[0002] In high-speed railways and heavy-haul transportation systems, the reliability of bolted connections is directly related to train operation safety. Loosening of bolts can lead to decreased connection stiffness, increased vibration, and even serious accidents such as component detachment. Currently, mainstream inspection methods still rely on manual inspection, such as the tapping and listening method or the torque re-tightening method, which suffer from problems such as high subjectivity, low efficiency, and difficulty in quantifying the degree of loosening.

[0003] In recent years, 3D point cloud technology has been widely used in industrial inspection scenarios due to its advantages such as high precision, non-contact operation, and the ability to reconstruct geometry. Research shows that when a bolt loosens, a gap will form between it and the washer, or between the washer and the base (such as a rail or bracket). Microscopic gaps on the order of 3 mm. However, existing point cloud-based global matching or deformation analysis methods struggle to accurately capture such localized micro-gaps, and typically rely on large amounts of labeled data or complex training processes, resulting in high deployment costs and poor adaptability. Summary of the Invention

[0004] This disclosure provides a method, apparatus, equipment, medium, and product for determining the state of railway bolt connections, enabling accurate determination of the loosening state of railway bolts.

[0005] Firstly, a method for determining the state of railway bolted connections is provided, including: Based on the point cloud data corresponding to the railway connection area, a point cloud dataset corresponding to the railway bolt assembly is determined; the railway connection area includes the railway bolt assembly. Based on the first distance information between any two point cloud data in the point cloud dataset, each point cloud data in the point cloud dataset is clustered to obtain a set of clusters; If the number of clusters in the cluster set meets a preset quantity judgment condition, the target feature distance is determined based on the minimum distance information between any two clusters; the target feature distance is the maximum distance among all the minimum distance information. Based on the target feature distance and the preset distance judgment condition, the connection status of the railway bolt assembly is determined.

[0006] Secondly, a device for determining the state of railway bolted connections is provided, comprising: The point cloud dataset determination module is used to determine the point cloud dataset corresponding to the railway bolt assembly based on the point cloud data corresponding to the railway connection area; the railway connection area includes the railway bolt assembly. The cluster set determination module is used to cluster each point cloud data in the point cloud dataset according to the first distance information between any two point cloud data in the point cloud dataset, so as to obtain a cluster set. The target feature distance determination module is used to determine the target feature distance based on the minimum distance information between any two clusters when the number of clusters in the cluster set meets a preset quantity judgment condition; the target feature distance is the maximum distance among all the minimum distance information. The connection status determination module is used to determine the connection status of the railway bolt assembly based on the target feature distance and preset distance judgment conditions.

[0007] Thirdly, an electronic device is provided, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method for determining the state of railway bolt connections as described in the first aspect above.

[0008] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method for determining the state of railway bolt connections as described in the first aspect above.

[0009] Fifthly, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the method for determining the state of railway bolt connections as described in the first aspect above.

[0010] This disclosure provides a method, apparatus, device, medium, and product for determining the connection status of railway bolts. The method includes: determining a point cloud dataset corresponding to a railway bolt assembly based on point cloud data corresponding to a railway connection area; the railway connection area includes the railway bolt assembly; clustering each point cloud data in the point cloud dataset according to a first distance information between any two point cloud data in the point cloud dataset to obtain a cluster set; when the number of clusters in the cluster set meets a preset quantity judgment condition, determining a target feature distance based on the minimum distance information between any two clusters; the target feature distance is the maximum distance among the minimum distance information; and determining the connection status of the railway bolt assembly based on the target feature distance and the preset distance judgment condition. This technical solution obtains point cloud data of the railway bolt assembly and separates the point clouds corresponding to bolts, washers, and bases, and uses the distance information between points to perform cluster analysis to obtain clusters for each component. When the number of clusters meets the expectation, the minimum distance between any two clusters is calculated and the maximum value is extracted as the target feature distance. Finally, the connection status of the bolt assembly is determined based on the comparison result of this distance and a preset threshold. The above technical solution reduces the cost of manual operation and maintenance, enables accurate determination of the loosening status of railway bolts, has strong robustness and engineering practicality, and is suitable for intelligent inspection in changing on-site environments.

[0011] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this disclosure, nor is it intended to limit the scope of the embodiments of this disclosure. Other features of the embodiments of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a method for determining the state of railway bolt connections provided in Embodiment 1 of this disclosure; Figure 2 This is a schematic diagram illustrating the execution process of another method for determining the state of railway bolt connections provided in Embodiment 1 of this disclosure; Figure 3 This is a schematic diagram of the structure of a device for determining the state of railway bolt connections provided in Embodiment 2 of this disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of this disclosure. Detailed Implementation

[0014] To enable those skilled in the art to better understand the solutions of the embodiments of this disclosure, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the protection scope of the embodiments of this disclosure.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This is a flowchart of a method for determining the state of railway bolt connections according to Embodiment 1 of this disclosure. This embodiment is applicable to situations where the state of railway bolt connections needs to be determined. This method can be executed by a device for determining the state of railway bolt connections. This device can be implemented in hardware and / or software and can be configured in an electronic device, including but not limited to computers, PCs, electronic devices, and servers, which are devices with data processing capabilities. Figure 1 As shown, the method includes: S110. Based on the point cloud data corresponding to the railway connection area, determine the point cloud dataset corresponding to the railway bolt assembly; the railway connection area includes the railway bolt assembly.

[0017] In this embodiment, point cloud data corresponding to the railway connection area can be extracted to determine the point cloud dataset corresponding to the railway bolt assembly. The railway connection area refers to a key part of the railway track system that requires mechanical connection, fixation, or assembly using fasteners such as bolt assemblies. For example, the railway connection area can be the track fastener or bogie connection area. The railway bolt assembly is a combination of key mechanical components in the railway track structure used for connection, fastening, and positioning, typically consisting of bolts, washers, and bases (or nuts, washers, anchors, etc.).

[0018] For example, a local region of interest for a railway bolt assembly containing bolts, gaskets, and base can be located by using a preset spatial coordinate range or a two-dimensional-three-dimensional mapping algorithm. Irrelevant background point clouds can then be removed to obtain a point cloud dataset corresponding to the railway bolt assembly.

[0019] The preset spatial coordinate range refers to pre-defining a specific cubic or polyhedral region in the 3D point cloud space. The spatial range of interest is defined by setting minimum and maximum coordinate values ​​in the X, Y, and Z directions. Only point cloud data falling within this coordinate range is retained, while background point cloud data outside the range is discarded. The 2D-3D mapping algorithm refers to a method for locating the region of interest by utilizing the correspondence between a 2D image and a 3D point cloud. Typically, a 2D image of the railway scene is first captured by a camera. Object detection or image segmentation algorithms are then used to identify the pixel positions of bolt components in the image. Finally, based on camera calibration parameters and the imaging model, the pixel coordinates in the 2D image are converted into coordinate positions in 3D space, thereby locating the corresponding local region in the 3D point cloud.

[0020] S120. Based on the first distance information between any two point cloud data in the point cloud dataset, cluster each point cloud data in the point cloud dataset to obtain a set of clusters.

[0021] It is known that after obtaining the point cloud dataset corresponding to the railway bolt assembly, the first distance information between any two point cloud data points in the dataset can be calculated. This first distance information can be the spatial distance between any two point cloud data points. For example, the first distance information can be the Euclidean distance, which is the straight-line distance between two points in Euclidean space. It is the most commonly used spatial distance metric, reflecting the actual geometric interval between two points in three-dimensional space; a smaller value indicates that the two points are closer.

[0022] As described above, after obtaining the first distance information between any two point cloud data, each first distance information can be compared with a preset threshold. Point cloud data that are close to each other in position and whose distance is less than the preset threshold can be divided into a cluster. In this way, the point cloud dataset can be divided into several clusters to form a cluster set.

[0023] For example, for a point cloud dataset, the Euclidean distance clustering algorithm is used for connected component segmentation. The core clustering parameters are set as follows: the threshold for the Euclidean distance between adjacent point cloud data in the X, Y, and Z coordinate directions is 1 mm. When the difference is 1mm, they are considered to be the same connected component and grouped into one cluster. By traversing all point clouds in this way, multiple independent point cloud clusters are automatically generated. It should be explained that when the bolt is not loose, the bolt, washer, and base will have gaps due to their tight fit. Clusters of 1mm; when bolts loosen, gaps appear between components, creating spacing. Independent clusters of 1 mm. During the clustering process, isolated noise points (single or a small number of points that do not meet the connectivity condition) are automatically filtered to ensure the validity of the clustering results.

[0024] S130. When the number of clusters in the cluster set meets the preset quantity judgment condition, the target feature distance is determined based on the minimum distance information between any two clusters; the target feature distance is the maximum distance among all the minimum distance information.

[0025] It is known that after obtaining the cluster set, the number of clusters in the cluster set can be determined. It can be determined whether the number of clusters meets a preset quantity judgment condition. This preset quantity judgment condition can be a condition for judging the number of clusters; for example, the preset quantity judgment condition can be that the number of clusters is not 1.

[0026] Following the above description, if the number of clusters meets the preset quantity judgment condition, the minimum distance information between point cloud data of any two clusters can be calculated, and the maximum value among the minimum distance information is determined as the target feature distance. The target feature distance is used to represent the most significant separation degree or assembly gap between railway bolt assemblies. The minimum distance information can be the minimum Euclidean distance between point cloud data of any two clusters. For example, the two closest point cloud data in two clusters can be selected, and their X, Y, and Z Euclidean distances can be calculated as the target feature distance between the two clusters. The target feature distance can be a reference value for the actual gap between the bolt, washer, and base in the railway bolt assembly.

[0027] S140. Based on the target feature distance and preset distance judgment conditions, determine the connection status of the railway bolt assembly.

[0028] It is known that after the target feature distance is determined, it can be compared with a preset distance judgment condition to determine the connection status of the railway bolt assembly. The preset distance judgment condition can be a pre-set condition used to judge the target feature distance, such as the target feature distance being less than or equal to a preset threshold. For example, the preset distance judgment condition could be that the target feature distance is less than or equal to 1 mm.

[0029] This embodiment provides a method for determining the connection status of railway bolts, including: determining a point cloud dataset corresponding to a railway bolt assembly based on point cloud data corresponding to a railway connection area; the railway connection area includes the railway bolt assembly; clustering each point cloud data in the point cloud dataset according to a first distance information between any two point cloud data in the point cloud dataset to obtain a cluster set; when the number of clusters in the cluster set meets a preset quantity judgment condition, determining a target feature distance according to the minimum distance information between any two clusters; the target feature distance is the maximum distance among all minimum distance information; and determining the connection status of the railway bolt assembly based on the target feature distance and the preset distance judgment condition. This method reduces manual maintenance costs, achieves accurate determination of the loosening status of railway bolts, has strong robustness and engineering practicality, and is suitable for intelligent inspection in variable on-site environments.

[0030] As an optional implementation of this embodiment, the method for determining the state of railway bolt connections provided in this embodiment further includes: If the number of clusters in the cluster set does not meet the preset quantity judgment condition, the connection status of the railway bolt assembly is determined to be that it has not become loose.

[0031] It is known that the preset quantity judgment condition can be that the number of clusters is not 1. If the number of clusters in the cluster set does not meet the preset quantity judgment condition, it can be considered that the number of clusters in the cluster set is 1. In this case, it can be considered that the bolt, washer, and base are tightly fitted without obvious gaps. Therefore, there is only one cluster obtained by clustering, and it can be determined that the connection status of the railway bolt assembly is not loose. It should be explained that if the bolt, washer, and base are not tightly fitted and there are obvious gaps, the number of clusters obtained by clustering can be 2 or 3. When the number of clusters is 2, it can be considered that two parts of the bolt, washer, and base are tightly fitted. When the number of clusters is 3, it can be considered that the bolt, washer, and base are all tightly fitted.

[0032] For example, if only one cluster is obtained, it indicates that the components of the railway bolt assembly are tightly fitted without gaps, and this is considered normal; if multiple clusters are obtained, and the maximum minimum Euclidean distance between the clusters is... A gap of 1mm indicates a significant gap between components, classifying it as loose; if multiple clusters are obtained, the largest minimum Euclidean distance between all clusters is considered the minimum Euclidean distance. 1mm indicates that there is no obvious gap between the components, which is considered normal and no loosening has occurred; As an optional implementation of this embodiment, before determining the point cloud dataset corresponding to the railway bolt assembly based on the point cloud data corresponding to the railway connection area, the method further includes: The railway connection area is scanned using a 3D image acquisition device to obtain point cloud data corresponding to the railway connection area.

[0033] In this embodiment, a 3D image acquisition device can be used to scan and measure the railway bolt assembly to obtain the 3D spatial coordinate information of the assembly surface, thereby generating point cloud data composed of a large number of discrete 3D points. The 3D image acquisition device can be a 3D camera.

[0034] As an optional implementation of this embodiment, the method for determining the state of railway bolt connections provided in this embodiment further includes: The connection status of the railway bolt assembly is saved to a preset storage location.

[0035] It is known that after obtaining the connection status of the railway bolt assembly, the connection status can be saved to a preset storage location, which can be a pre-defined storage location. It should be explained that the gap area and the status of each component can also be highlighted through a visual interface, clearly outputting the connection status determination result and specific inter-cluster gap values ​​(distance values). All detection data (including gap values, status type, spatial coordinates, timestamps, and point cloud file names) is saved as a JSON log to local or cloud storage to support subsequent detection data traceability and analysis.

[0036] As an optional implementation of this embodiment, determining the target feature distance based on the minimum distance information between any two clusters includes: 1) Traverse any two different clusters in the cluster set to form a cluster pair, wherein the cluster pair includes two different first clusters and second clusters.

[0037] It is known that the clusters in the cluster set can be paired, and any two different clusters can be selected sequentially to form a cluster pair. Each cluster pair can contain two independent first clusters and second clusters. By traversing all possible combinations of the clusters in the cluster set, it is ensured that subsequent calculations can cover the spatial relationship between any two components.

[0038] 2) For any pair of clusters, calculate the second distance information between each point cloud data in the first cluster and each point cloud data in the second cluster.

[0039] It is known that for any cluster pair, the second distance information between each point cloud data in the first cluster and each point cloud data in the second cluster can be calculated. The second distance information can be the spatial distance between any point cloud data in the first cluster and any point cloud data in the second cluster. For example, the second distance information can be the Euclidean distance.

[0040] Specifically, each point cloud data in the first cluster can be arbitrarily selected, and the second distance information (usually Euclidean distance) can be calculated with each point cloud data in the second cluster. The distance set between all point cloud data and point cloud data between the two clusters can be obtained through double traversal.

[0041] 3) Determine the minimum distance information corresponding to each cluster pair based on the second distance information.

[0042] It is known that the minimum value can be extracted from each of the second distance information and used as the minimum distance information corresponding to that cluster pair. The minimum distance information can be used to represent the shortest distance between two components in the railway bolt assembly corresponding to two clusters, that is, the distance between the two components at their closest positions in space, which can reflect the actual assembly gap or contact state between the two components.

[0043] 4) The maximum value among the minimum distance information is determined as the target feature distance.

[0044] It is known that after determining the minimum distance information of all cluster pairs, the maximum value is selected as the final target feature distance. Each cluster can correspond to one component in a railway bolt assembly. It should be noted that each cluster can also correspond to two components in a railway bolt assembly. For example, when there are two clusters, taking the case where two components in the gasket and base are tightly fitted, one cluster can correspond to the bolt component, and the other cluster can correspond to the gasket component and the base component.

[0045] As described above, the target feature distance can be used to represent the distance between the components with the largest spacing in a railway bolt assembly. The target feature distance can correspond to the part of the railway bolt assembly where the loosening is most obvious or the most critical assembly gap, thereby effectively characterizing the connection status of the entire bolt assembly.

[0046] As an optional implementation of this embodiment, determining the connection state of the railway bolt assembly based on the target feature distance and preset distance judgment conditions includes: If the target feature distance does not meet the preset distance judgment condition, the connection status of the railway bolt assembly is determined to be loose; if the target feature distance meets the preset distance judgment condition, the connection status of the railway bolt assembly is determined to be not loose.

[0047] It is known that the determined target feature distance can be compared with the preset distance judgment condition. If the target feature distance does not meet the preset distance judgment condition, the connection status of the railway bolt assembly can be considered as having become loose; if the target feature distance meets the preset distance judgment condition, the connection status of the railway bolt assembly can be considered as not having become loose.

[0048] For example, the preset distance judgment condition can be that the target feature distance is less than or equal to 1 mm, and the number of clusters in the cluster set meets the preset number judgment condition (i.e., there are multiple clusters), if the target feature distance... A gap of 1mm indicates a significant gap between components, suggesting loose bolts; if the target feature distance is... A gap of 1mm indicates that there is no obvious gap between the components, and the bolts are considered to be in normal condition.

[0049] Figure 2 This is a schematic diagram illustrating the execution process of another method for determining the state of railway bolt connections provided in this embodiment, as shown below. Figure 2 As shown, the first step is to acquire point cloud data and locate the region of interest (ROI). Specifically, this includes using a 3D camera to scan and obtain point cloud data of the railway connection area. Then, using a preset spatial coordinate range or a 2D-3D mapping algorithm, the ROI corresponding to the railway bolt assembly is determined from the acquired point cloud data, and the corresponding point cloud dataset is extracted. After obtaining the point cloud dataset, connected component clustering can be performed on the power dataset based on Euclidean distance. The core clustering parameter is set as follows: the Euclidean distance threshold between adjacent points in the X, Y, and Z coordinate directions is 1 mm, which represents the Euclidean distance between two points in the X, Y, and Z coordinate directions. When the distance is 1mm, the points are considered to be in the same connected region and grouped into a single cluster. This method iterates through all point cloud data in the dataset, automatically dividing it into multiple independent and valid point cloud clusters while filtering out isolated noise points to ensure the validity of the clustering results. After obtaining the clusters, the minimum Euclidean distance between any two different clusters can be calculated, and the minimum Euclidean distance corresponding to each cluster is determined as the target feature distance (gap value). After obtaining the target feature distance, it can be further determined whether the target feature distance is less than 1mm. If so, the connection status of the railway bolt assembly is considered normal; otherwise, the connection status is considered loose. After obtaining the connection status of the railway bolt assembly, the detection data during the detection process can be saved as JSON log values ​​locally or in the cloud.

[0050] The aforementioned technical solution acquires 3D point cloud data using a 3D camera. Based on region-of-interest localization, point cloud connected domain clustering, and inter-cluster distance quantization techniques, it focuses on the microscopic geometric positional relationship between the bolt, washer, and base, achieving automatic detection of millimeter-level bolt loosening. Compared to traditional manual inspection (highly subjective, inefficient, and difficult to quantify) and point cloud registration-based detection methods, this system requires no standard assembly point cloud modeling, no manual annotation, and no pre-training. It boasts high detection accuracy, high sensitivity, and its judgment logic is highly consistent with railway maintenance procedures. Furthermore, this solution can be integrated into track inspection vehicles or handheld detection terminals, offering advantages such as flexible deployment, simplified processes, and strong scalability. It significantly improves the automation level, detection accuracy, and maintenance efficiency of railway bolt loosening detection, providing objective and traceable technical support for intelligent railway operation and maintenance.

[0051] This embodiment also provides an application example of a method for determining the state of railway bolt connections, including: Step 1: Install a 3D camera (2K resolution, depth accuracy) on the track inspection vehicle or the storage shed. (0.5 mm) When the train stops or enters the depot, the target bolt assembly area is scanned to obtain on-site detection point cloud data; by presetting the spatial coordinate range of the bolt assembly, the effective analysis area containing the bolt, gasket and base is directly selected in the original on-site point cloud, and the surrounding irrelevant background point cloud noise is removed, so that the point cloud dataset of the bolt, gasket and base can be determined.

[0052] Step 2: Use the Euclidean distance clustering algorithm (neighborhood radius 0.3mm, minimum cluster size 50) to segment the connected components of the point cloud dataset within the effective analysis area. Set the XYZ Euclidean distance threshold of 1mm for adjacent points, traverse all point clouds, and group points that meet the distance condition into the same cluster. Automatically divide the effective clusters corresponding to bolts, gaskets, and bases, and filter out isolated small clusters (number of clusters). 50), enabling unsupervised component segmentation without relying on Z-axis height distribution layering.

[0053] Step 3: For the clusters obtained in Step 2, calculate the minimum Euclidean distance between any two different clusters (select the two points closest to each other in the two clusters and calculate their XYZ Euclidean distance), and obtain the inter-cluster distances corresponding to the bolt and the washer, and the inter-cluster distances corresponding to the washer and the base. Record the maximum minimum Euclidean distance between the clusters as the core basis for gap determination.

[0054] Step 4: Use the inter-cluster distance obtained in Step 3 as the actual gap between components, where the inter-cluster distance between the bolt and the gasket is d1 (second distance information), and the inter-cluster distance between the gasket and the base is d2 (second distance information); if no cluster corresponding to the gasket is detected, calculate the distance between the clusters corresponding to the bolt and the base as d (second distance information).

[0055] Step 5: Set the loosening threshold to 0.5 mm. Determine the maximum value between d1 and d2. If the maximum value between d1 and d2 is... 0.5 (or d) If d1 and d2 are both less than 0.5 mm (or d is less than 0.5 mm), it is considered "loose bolt"; if d1 and d2 are both less than 0.5 mm (or d is less than 0.5 mm), it is considered "normal".

[0056] Step 6: Using a 3D renderer, the gap area and abnormal components can be highlighted in red on the display interface, and the corresponding detection results can be output in the status bar of the display interface (e.g., "Detection Result: Bolt loose (gap between washer and base: 0.72 mm)"). The detection results are simultaneously saved as a JSON format log, including timestamp, point cloud file name, gap value, component status, and spatial coordinates, and can be uploaded to the cloud operation and maintenance platform.

[0057] The above technical solution does not require a standard reference point cloud and registration process, nor does it require plane fitting operation. It facilitates algorithm replacement and batch processing and can be deployed on track inspection robots, vehicle-mounted detection terminals, or back-end analysis servers, providing core technical support for intelligent operation and maintenance of railways.

[0058] Example 2 Figure 3 This is a schematic diagram of the structure of a device for determining the state of railway bolt connections provided in Embodiment 2 of this disclosure; as shown... Figure 3 As shown, the device includes: a point cloud dataset determination module 210, a cluster set determination module 220, a target feature distance determination module 230, and a connection state determination module 240.

[0059] The point cloud dataset determination module 210 is used to determine the point cloud dataset corresponding to the railway bolt assembly based on the point cloud data corresponding to the railway connection area; the railway connection area includes the railway bolt assembly. Cluster set determination module 220 is used to cluster each point cloud data in the point cloud dataset according to the first distance information between any two point cloud data in the point cloud dataset, so as to obtain a cluster set; The target feature distance determination module 230 is used to determine the target feature distance based on the minimum distance information between any two clusters when the number of clusters in the cluster set meets a preset quantity judgment condition; the target feature distance is the maximum distance among all the minimum distance information. The connection status determination module 240 is used to determine the connection status of the railway bolt assembly based on the target feature distance and preset distance judgment conditions.

[0060] Embodiment 2 of this disclosure provides a device for determining the status of railway bolt connections, which reduces the cost of manual maintenance, enables accurate determination of the loosening status of railway bolts, has strong robustness and engineering practicality, and is suitable for intelligent inspection in changing on-site environments.

[0061] Furthermore, the target feature distance determination module 230 is also used for: Traverse any two different clusters in the cluster set to form a cluster pair, wherein the cluster pair includes two different first clusters and second clusters; For any pair of clusters, calculate the second distance information between each point cloud data in the first cluster and each point cloud data in the second cluster; The minimum distance information corresponding to the cluster pair is determined based on each of the second distance information; The maximum value among the minimum distance information is determined as the target feature distance.

[0062] Furthermore, the connection status determination module 240 is also used for: If the target feature distance does not meet the preset distance judgment condition, the connection status of the railway bolt assembly is determined to be loose. If the target feature distance meets the preset distance judgment condition, the connection status of the railway bolt assembly is determined to be that it has not become loose.

[0063] Furthermore, the device also includes: The determination module is used to determine that the connection status of the railway bolt assembly is not loose when the number of clusters in the cluster set does not meet the preset quantity judgment condition.

[0064] Furthermore, the device also includes: The point cloud data acquisition module is used to scan the railway connection area using a 3D image acquisition device to obtain point cloud data corresponding to the railway connection area.

[0065] Furthermore, the device also includes: The storage module is used to save the connection status of the railway bolt assembly to a preset storage location.

[0066] The railway bolt connection state determination device provided in this disclosure can execute the railway bolt connection state determination method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0067] Example 3 Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the embodiments of the present disclosure described and / or claimed herein.

[0068] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0069] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0070] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microprocessor, etc. Processor 11 performs the various methods and processes described above, such as the method for determining the state of railway bolt connections.

[0071] In some embodiments, the method for determining the state of railway bolt connections may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the state of railway bolt connections described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the state of railway bolt connections by any other suitable means (e.g., by means of firmware).

[0072] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0073] Computer programs for implementing the methods of embodiments of this disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0074] In the context of embodiments of this disclosure, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0075] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0076] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0077] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0078] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the embodiments of this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of the embodiments of this disclosure can be achieved, and this document does not impose any limitations.

[0079] The specific embodiments described above do not constitute a limitation on the scope of protection of the embodiments disclosed herein. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the embodiments disclosed herein should be included within the scope of protection of the embodiments disclosed herein.

[0080] This disclosure also provides a computer program product, including a computer program and / or instructions, which, when executed by a processor, implements the method for determining the state of railway bolt connections as provided in any embodiment of this application.

[0081] In implementing a computer program product, computer program code for performing the operations of the embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0082] Note that the above are merely preferred embodiments and the technical principles applied in this disclosure. Those skilled in the art will understand that this disclosure is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the protection scope of this disclosure. Therefore, although the embodiments of this disclosure have been described in detail above, this disclosure is not limited to the above embodiments. More other equivalent embodiments may be included without departing from the concept of this disclosure, and the scope of this disclosure is determined by the scope of the appended claims.

Claims

1. A method for determining the state of railway bolted connections, characterized in that, include: Based on the point cloud data corresponding to the railway connection area, a point cloud dataset corresponding to the railway bolt assembly is determined; the railway connection area includes the railway bolt assembly. Based on the first distance information between any two point cloud data in the point cloud dataset, each point cloud data in the point cloud dataset is clustered to obtain a set of clusters; If the number of clusters in the cluster set meets the preset quantity judgment condition, the target feature distance is determined based on the minimum distance information between any two clusters; the target feature distance is the maximum distance among all the minimum distance information. Based on the target feature distance and the preset distance judgment condition, the connection status of the railway bolt assembly is determined.

2. The method according to claim 1, characterized in that, The step of determining the target feature distance based on the minimum distance information between any two clusters includes: Traverse any two different clusters in the cluster set to form a cluster pair, wherein the cluster pair includes two different first clusters and second clusters; For any pair of clusters, calculate the second distance information between each point cloud data in the first cluster and each point cloud data in the second cluster; The minimum distance information corresponding to the cluster pair is determined based on each of the second distance information; The maximum value among the minimum distance information is determined as the target feature distance.

3. The method according to claim 2, characterized in that, The determination of the connection status of the railway bolt assembly based on the target feature distance and preset distance judgment conditions includes: If the target feature distance does not meet the preset distance judgment condition, the connection status of the railway bolt assembly is determined to be loose. If the target feature distance meets the preset distance judgment condition, the connection status of the railway bolt assembly is determined to be that it has not become loose.

4. The method according to claim 1, characterized in that, The method further includes: If the number of clusters in the cluster set does not meet the preset quantity judgment condition, the connection status of the railway bolt assembly is determined to be that it has not become loose.

5. The method according to claim 1, characterized in that, Before determining the point cloud dataset corresponding to the railway bolt assembly based on the point cloud data corresponding to the railway connection area, the method further includes: The railway connection area is scanned using a 3D image acquisition device to obtain point cloud data corresponding to the railway connection area.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: The connection status of the railway bolt assembly is saved to a preset storage location.

7. A device for determining the state of railway bolted connections, characterized in that, include: The point cloud dataset determination module is used to determine the point cloud dataset corresponding to the railway bolt assembly based on the point cloud data corresponding to the railway connection area; the railway connection area includes the railway bolt assembly. The cluster set determination module is used to cluster each point cloud data in the point cloud dataset according to the first distance information between any two point cloud data in the point cloud dataset, so as to obtain a cluster set. The target feature distance determination module is used to determine the target feature distance based on the minimum distance information between any two clusters when the number of clusters in the cluster set meets a preset quantity judgment condition; the target feature distance is the maximum distance among all the minimum distance information. The connection status determination module is used to determine the connection status of the railway bolt assembly based on the target feature distance and preset distance judgment conditions.

8. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method for determining the state of railway bolt connections as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the method for determining the state of railway bolt connections as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for determining the state of railway bolt connections as described in any one of claims 1-6.

Images