Train bottom position positioning method and device, computer equipment and storage medium

Abstract

The application relates to a train underframe position positioning method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: determining underframe elevation data based on the distance between a detection robot and a train underframe, wherein the underframe elevation data is used to describe the distance between a ranging sensor of the detection robot and the train underframe; determining current position information of the detection robot according to position information of a parking area where the train is located; determining initial position information of each initial component in the underframe position of the train according to the underframe elevation data and the current position information; determining target position information from a plurality of initial position information according to distance distribution information of a target component; and positioning the target component in the train underframe according to the target position information. The method can improve positioning accuracy.

Description

Technical Field

[0001] This application relates to the field of rail transit train detection technology, and in particular to a method, device, computer equipment, storage medium and computer program product for locating the position of a train undercarriage. Background Technology

[0002] In daily life, high-speed rail, trains, and construction transport vehicles are important means of transportation. In order to ensure the safe operation of trams, it is necessary to regularly inspect the undercarriage of the trains for faults. Before the fault inspection, the undercarriage of the train to be inspected needs to be located because the position of the train at the station and the articulation state between the carriages are different each time.

[0003] In traditional technology, image recognition is generally used to identify images of the train's undercarriage, and the train's undercarriage is located based on the image recognition data and the vehicle's mileage data.

[0004] However, locating the train undercarriage using images of the train undercarriage and train mileage information may result in low positioning accuracy due to distortion of the undercarriage images and inaccuracy of the train mileage information. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for positioning the undercarriage of a train, which can improve positioning accuracy, in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for locating the position of a train undercarriage. The method includes:

[0007] Based on the distance between the detection robot and the undercarriage of the train, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the undercarriage of the train;

[0008] Based on the location information of the train's stopping area, the current location information of the detection robot is determined;

[0009] Based on the vehicle undercarriage elevation data and the current position information, the initial position information of each initial component is determined in the vehicle undercarriage position of the train;

[0010] Based on the distance distribution information of the target component, the target position information is determined from multiple initial position information.

[0011] Based on the target location information, the target component is located under the train.

[0012] In one embodiment, determining the initial position information of each initial component based on the undercarriage elevation data and the current position information includes:

[0013] Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information.

[0014] In one embodiment, determining the initial position information of each initial component of the train based on the plurality of target elevation data and the plurality of first position information includes:

[0015] A target coordinate system is constructed with the position direction of the parking area where the train is located as the X direction, the elevation direction of the train undercarriage as the Y direction, and the initial position of the detection robot as the origin. The target elevation data and the first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate value of the initial component in the target coordinate system. Based on the contour coordinate value, the center coordinate value of the center position of the initial component in the target coordinate system is determined. The coordinate value of the center coordinate value in the X direction is used as the initial position information.

[0016] In one embodiment, determining the target location information from multiple initial location information based on the distance distribution information of the target component includes:

[0017] Based on the multiple initial position information, the actual relative distance of each initial component is determined; the initial position information that conforms to the distance distribution information among the actual relative distances is taken as the target position information.

[0018] In one embodiment, the method further includes:

[0019] Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

[0020] In one embodiment, the detection robot includes:

[0021] A laser triangulation sensor is used to collect elevation data of the undercarriage of a parked train; a ruler reader is used to read the current position information of the inspection robot; a PCI acquisition card is used to read the elevation data of the undercarriage of the train collected by the laser triangulation sensor and the current position information read by the ruler reader; wherein, the data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

[0022] Secondly, this application also provides a position positioning device for the undercarriage of a train. The device includes:

[0023] The undercarriage elevation data determination module is used to determine the undercarriage elevation data based on the distance between the detection robot and the undercarriage of the train. The undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the undercarriage of the train.

[0024] The current location information determination module is used to determine the current location information of the detection robot based on the location information of the train's stopping area;

[0025] The initial position information determination module is used to determine the initial position information of each initial component in the position under the train based on the undercarriage elevation data and the current position information.

[0026] The target location information determination module is used to determine the target location information from multiple initial location information based on the distance distribution information of the target component;

[0027] The target component positioning module is used to locate the target component under the train based on the target location information.

[0028] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0029] Based on the distance between the detection robot and the train undercarriage, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the train undercarriage; based on the location information of the train's stopping area, the current position information of the detection robot is determined; based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location; based on the distance distribution information of the target component, the target position information is determined from multiple initial position information; based on the target position information, the target component is located on the train undercarriage.

[0030] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0031] Based on the distance between the detection robot and the train undercarriage, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the train undercarriage; based on the location information of the train's stopping area, the current position information of the detection robot is determined; based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location; based on the distance distribution information of the target component, the target position information is determined from multiple initial position information; based on the target position information, the target component is located on the train undercarriage.

[0032] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0033] Based on the distance between the detection robot and the train undercarriage, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the train undercarriage; based on the location information of the train's stopping area, the current position information of the detection robot is determined; based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location; based on the distance distribution information of the target component, the target position information is determined from multiple initial position information; based on the target position information, the target component is located on the train undercarriage.

[0034] The aforementioned train undercarriage positioning method, device, computer equipment, storage medium, and computer program product determine the undercarriage elevation data based on the distance between the detection robot and the train undercarriage. This undercarriage elevation data describes the distance between the detection robot's ranging sensor and the train undercarriage. The current position information of the detection robot is determined based on the location information of the train's stopping area. During data acquisition, the current position information of the detection robot is determined simultaneously with the acquisition of the train undercarriage elevation data. Since the location information of the train's stopping area varies, determining the current position information of the detection robot based on the location information of the train's stopping area is more accurate, thus improving the accuracy of train undercarriage positioning. Based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location. This is achieved through the train undercarriage... The initial position information is determined by using elevation data between the robot and the detection robot, as well as the robot's current position information when collecting elevation data. This method requires less computation and improves positioning efficiency. Based on the distance distribution information of the target component, the target position information is determined from multiple initial position information sources. Based on the target position information, the target component is located under the train. Since the positional offset between each component and the target component is known, the positioning of the train undercarriage can be completed based on the position of the target component, improving positioning efficiency. After obtaining the initial position information of the initial component, this application further verifies the initial position information based on the distance distribution information of the target component, thus obtaining the target position information of the target component. This improves the accuracy of the target position information, thereby improving the accuracy of positioning the target component under the train, and ultimately improving the overall accuracy of train undercarriage positioning. Attached Figure Description

[0035] Figure 1 This is a diagram illustrating the application environment of a train undercarriage positioning method in one embodiment.

[0036] Figure 2 This is a flowchart illustrating a method for locating the position of the train undercarriage in one embodiment;

[0037] Figure 3 This is a two-dimensional curve of the axle under the train in one embodiment;

[0038] Figure 4 This is a structural block diagram of a train undercarriage positioning device in one embodiment;

[0039] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0041] The train undercarriage positioning method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 and inspection robot 106 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Terminal 102 determines the undercarriage elevation data based on the distance between inspection robot 106 and the undercarriage of the train, where the undercarriage elevation data describes the distance between the ranging sensor of the inspection robot and the undercarriage of the train. Terminal 102 determines the current position information of the inspection robot based on the location information of the train's stopping area. Terminal 102 determines the initial position information of each initial component within the undercarriage of the train based on the undercarriage elevation data and the current position information. Terminal 102 determines the target position information from multiple initial position information based on the distance distribution information of the target component. Terminal 102 locates the target component under the train based on the target position information. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and IoT devices. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0042] In one embodiment, such as Figure 2 As shown, a method for locating the position of a train undercarriage is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0043] Step 202: Based on the distance between the detection robot and the train undercarriage, determine the undercarriage elevation data, whereby the undercarriage elevation data is used to describe the distance between the detection robot's ranging sensor and the train undercarriage.

[0044] Step 204: Determine the current location of the detection robot based on the location information of the train's stopping area.

[0045] The terminal and the inspection robot communicate via a network. The terminal can control the robot's movement and data collection by outputting control commands. The inspection robot is equipped with a distance sensor and a ruler reader. The distance sensor is used to collect the distance between the robot and the undercarriage of the parked train. The robot collects data at a certain frequency as it moves. As the robot moves to different positions under the parked train, the distance between the distance sensor and the undercarriage changes, meaning the undercarriage elevation data will differ at different collection positions. The location information of the train's parking area can be determined by a fixed ruler, which can be a one-dimensional positioning barcode or a QR code. The fixed ruler can be set on one side of the inspection robot's movement trajectory, i.e., the side of the parked train track and parallel to it. The ruler reader is used to read the fixed ruler information set in the parked train's parking area to determine the current position information of the inspection robot during its movement. The current location information refers to the fixed scale information corresponding to the data acquisition position of the inspection robot. The current location information corresponds to the vehicle undercarriage elevation data. Each vehicle undercarriage elevation data corresponds to a current location information. The current location information is used to locate the data acquisition position of the inspection robot.

[0046] Furthermore, since the stopping area of ​​the train is equipped with a fixed scale, it is not necessary to continuously collect the undercarriage elevation of the entire train during data collection. Because the stopping position of the train is fixed, the positional relationship of the undercarriage elevation data collected multiple times can be determined according to the corresponding fixed scale information, rather than relying entirely on the time relationship.

[0047] As an example, steps 202 and 204 include: the terminal controls the detection robot to move under the parked train; during the movement, the detection robot's ranging sensor collects the distance between the detection robot and the parked train's undercarriage at a certain frequency; based on the distance between the detection robot's ranging sensor and the train's undercarriage, the undercarriage elevation data is determined; and while the ranging sensor collects data, the detection robot's ruler reader reads the information of a fixed ruler set in the parked area of ​​the parked train as the detection robot's current position information, with each undercarriage elevation data corresponding to one current position information.

[0048] Step 206: Based on the undercarriage elevation data and current position information, determine the initial position information of each initial component in the undercarriage position of the train.

[0049] The initial position information can be obtained by filtering the vehicle undercarriage elevation data and current position information based on the external contour of the target component. The position corresponding to the initial position information is the location of the initial component. Since the initial position information is obtained by filtering based on the external contour of the target component, the initial component includes the target component and other components with similar contours to the target component. The target component refers to a vehicle undercarriage component with fixed characteristics, which can be an axle, bearing, wheel tread, or wheel hub. The initial position information of the initial component can be the current position information corresponding to the center position of the initial component, or it can include the vehicle undercarriage elevation data corresponding to the center position of the target component and the current position information.

[0050] Furthermore, such as Figure 3 As shown, a two-dimensional curve can also be drawn based on the vehicle under-floor elevation data and the current position information. For example, the vehicle under-floor elevation data and the current position information can be used as coordinate values ​​in the X and Y directions, respectively, and a two-dimensional curve can be obtained by fitting.

[0051] As an example, step 206 includes: filtering the undercarriage elevation data according to the feature information of the target component to obtain multiple target elevation data; determining multiple corresponding first position information from the current position information based on the multiple target elevation data, and determining the middle first position information of the multiple first position information as the initial position information of the stopped train.

[0052] As an example, the initial position information of the target orientation includes five fixed scale markings, specifically {1, 2, 3, 4, 5}, then the initial position information of the middle is 3.

[0053] Step 208: Determine the target position information from multiple initial position information based on the distance distribution information of the target component.

[0054] It is important to note that while the initial position information is determined based on the characteristic information of the target component, other components may possess the same characteristic information as the target component. This could result in the initial position information including the position information of other components, meaning it may include not only the target component but also other train undercarriage components. This embodiment verifies the accuracy of multiple initial position information sets based on the distance distribution information of the target component. This ensures that the selected target position information is indeed the position information of the target component, thereby guaranteeing the accuracy of the target component's positioning.

[0055] The distance distribution information of the target components can include the spacing between target components or the distance distribution between adjacent target components. This distance distribution information can be obtained from the train's factory parameters. Specifically, taking axles as an example, the distance distribution information of the target components can be the spacing between axles or the positional distribution between axles.

[0056] As an example, step 208 includes: determining the actual distance distribution information of each initial component based on multiple initial position information; and determining the target position information from multiple initial position information based on the actual distance distribution information and the distance distribution information of the target component obtained from the factory parameters.

[0057] Step 210: Locate the target component under the train car based on the target location information.

[0058] Among them, the target position information obtained from multiple initial position information is the position information of the target component, and the target component can be located under the train based on the position information of the target component.

[0059] The aforementioned method for locating the train undercarriage determines the undercarriage elevation data based on the distance between the detection robot and the train undercarriage. This elevation data describes the distance between the detection robot's ranging sensor and the train undercarriage. The current position of the detection robot is determined based on the location information of the train's stopping area. During data acquisition, the current position of the detection robot is determined simultaneously with the acquisition of the train undercarriage elevation data. Since the location information of the train's stopping area varies, determining the current position of the detection robot based on the train's stopping area information is more accurate, thus improving the accuracy of train undercarriage positioning. Based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage area. The method also considers the distance between the train undercarriage and the detection robot. The initial position information is determined using elevation data and the corresponding current position information during elevation data acquisition. This method involves minimal computation and improves positioning efficiency. Based on the distance distribution information of the target component, the target position information is determined from multiple initial position information sources. Using the target position information, the target component is located under the train. Since the positional offset between each component and the target component is known, the positioning of the train undercarriage can be completed based on the position of the target component, further improving positioning efficiency. After obtaining the initial position information of the initial component, this application further verifies the initial position information based on the distance distribution information of the target component, thereby obtaining the target position information of the target component. This improves the accuracy of the target position information, thus improving the accuracy of positioning the target component under the train, and consequently, improving the overall accuracy of train undercarriage positioning.

[0060] In one embodiment, the initial position information of each initial component is determined in the undercarriage position of the train based on the undercarriage elevation data and the current position information, including:

[0061] Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-body elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information.

[0062] The stopped train may include a variety of target components, each with a different external contour. Specifically, the data distribution of each target component in the elevation data is different, meaning that the distribution pattern of each target component is different. The preset distribution pattern refers to the elevation data distribution pattern of a target component. There may be multiple target components. The train's undercarriage elevation data includes multiple target elevation data that conform to the preset distribution pattern. In a specific embodiment, the target component may be one or more components with fixed characteristics, such as axles, bearings, wheel treads, or wheel hubs, which are not limited here.

[0063] As an example, the target component is an axle with a diameter of 180mm. The axle's external contour is an arc. The axle's distribution pattern is that the current position information spans between 180mm and 200mm. The undercarriage elevation data has the characteristic of gradually decreasing and then gradually increasing. At the same time, the undercarriage elevation data satisfies the characteristic that the difference between the maximum and minimum values ​​is within the axle radius. Each axle data represents a target elevation data.

[0064] In this embodiment, multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information. The initial position information obtained in this way includes the position information of the target component, which helps to select the position of subsequent target components.

[0065] In one embodiment, determining the initial position information of each initial component of the train based on multiple target elevation data and multiple first position information includes:

[0066] A target coordinate system is constructed with the X-direction representing the location of the train's stopping area, the Y-direction representing the elevation of the train's undercarriage, and the initial position of the detection robot as the origin. The target elevation data and the first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate values ​​of the initial component in the target coordinate system. Based on the contour coordinate values, the center coordinate values ​​of the initial component's center position in the target coordinate system are determined. The center coordinate values ​​in the X-direction are used as the initial position information.

[0067] As an example, the fixed scale information corresponding to the initial position of the detection robot is 5, the target elevation data is {10, 9, 8.5, 9, 10}, and the corresponding first position information is {9, 10, 11, 12, 13}. Then the coordinates in the target coordinate system are {(4, 10), (5, 9), (6, 8.5), (7, 9), (8, 10)}.

[0068] As an example, the target component is an axle, and the axle's contour coordinates in the target coordinate system are... Construct the matrix equation:

[0069]

[0070] In this process, the matrix equations are solved using Cramer's method to calculate h, k, and p, with the axle center coordinates being (h, k) and the axle radius being... .

[0071] In this embodiment, a target coordinate system is established, and the center coordinates of the initial component of the stopped train are solved using mathematical methods. The position of the initial component is located based on the center coordinates, which helps to improve the accuracy of the initial component positioning.

[0072] In one embodiment, the target location information is determined from multiple initial location information based on the distance distribution information of the target component, including:

[0073] Based on multiple initial position information, the actual relative distance of each initial component is determined; the initial position information that matches the distance distribution information among the actual relative distances is taken as the target position information.

[0074] The relative distances between the target components are fixed. For example, a train carriage has 3 axles. The relative distance between axle 1 and axle 2 is 2m, and the relative distance between axle 2 and axle 3 is 1.5m.

[0075] Specifically, based on multiple initial position information, the actual relative distance between adjacent initial components is calculated; the actual relative distance is matched with the distance distribution information of the target component obtained from the train parameters; if the matching accuracy is greater than or equal to a preset threshold, the initial position information corresponding to the actual relative distance is used as the target position information.

[0076] As an example, a train carriage has 3 axles. The actual relative distance between axle 1 and axle 2 is 1.98m, and the actual relative distance between axle 2 and axle 3 is 1.5m. The distance distribution information obtained from the train parameters is 2m and 1.5m. The preset threshold is 0.02m. It can be seen that the matching error between axle 1 and axle 2 is 0.02m, and the matching error between axle 2 and axle 3 is 0. The maximum matching error is less than the preset threshold. Therefore, the position information corresponding to the 3 axles is taken as the target position information.

[0077] In this embodiment, the actual relative distance of each initial component is determined based on multiple initial position information; the initial position information that matches the distance distribution information among the actual relative distances is used as the target position information to determine the target position information of the target component, thereby helping to locate the target component under the train.

[0078] In one embodiment, the method for locating the position of the train undercarriage further includes:

[0079] Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

[0080] The relative positions of each component of the train undercarriage to the target component are fixed, and the position offset information is used to characterize the relative positions of each component of the train undercarriage to the target component.

[0081] Specifically, the relative positional distances between each component of the train undercarriage and the target component are obtained; the target position information and the relative positional distances are fused to determine the positioning information corresponding to each component; and the position of each component of the train undercarriage is located based on the positioning information.

[0082] In this embodiment, the target position information of the target component is used as the positioning reference. Based on the relative position distance between each component of the train undercarriage and the target component, the positioning position information of each component of the train undercarriage is determined. Based on the positioning position information, the position of each component of the train undercarriage is located. In this way, only the target position information of the target component needs to be obtained to locate the position of all components of the train undercarriage, which can improve the positioning efficiency.

[0083] In one embodiment, the detection robot includes:

[0084] A laser triangulation sensor is used to collect elevation data of the undercarriage of the parked train; a ruler reader is used to read the current position information of the inspection robot; a PCI acquisition card is used to read the elevation data of the undercarriage of the train collected by the laser triangulation sensor and the current position information read by the ruler reader; the data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

[0085] The PCI acquisition card can be replaced with a PCI Express card, which has a faster acquisition speed than the PCI acquisition card.

[0086] In this embodiment, the data acquisition frequency of both the laser triangulation sensor and the ruler reader can reach 1kHz. The data acquisition frequency of the PCI acquisition card is matched with that of the laser triangulation sensor, which can ensure the real-time data reading and ensure that the vehicle under-ground elevation data corresponds to the current position information.

[0087] In one embodiment, the data acquisition step involves controlling the detection robot to move under the parked train to collect the distance between the detection robot and the undercarriage of the parked train. Based on the distance between the detection robot's ranging sensor and the undercarriage of the train, the undercarriage elevation data is determined. Furthermore, according to a fixed scale set in the parking area of ​​the parked train, the current position information of the detection robot during the undercarriage elevation data acquisition process is measured. By setting a fixed scale as a reference benchmark, it is not necessary to continuously collect the undercarriage elevation of the entire train during data acquisition, thus improving the flexibility of data acquisition.

[0088] After data acquisition, multiple target elevation data points conforming to a preset distribution pattern are selected from the vehicle undercarriage elevation data. This preset distribution pattern corresponds to the external contour of the target component. Multiple first position information points corresponding to these target elevation data points are determined from the current position information. A target coordinate system is constructed with the train's parking area as the X-direction, the train's undercarriage elevation as the Y-direction, and the initial position of the detection robot as the origin. The target elevation data and first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate values ​​of the initial component. Based on these contour coordinate values, the center coordinates of the initial component's center position in the target coordinate system are determined. The center coordinates in the X-direction are used as the initial position information. Converting the acquired data into coordinates and using mathematical methods to determine the axis position improves positioning efficiency and accuracy.

[0089] Furthermore, based on multiple initial position information, the actual relative distance of each initial component is determined; the initial position information corresponding to the distance distribution information among the actual relative distances is taken as the target position information; based on the preset position offset information between each component and the target component, the position of each component is determined with the target position information. After obtaining the initial position information of the initial components, the initial position information is further verified according to the distance distribution information of the target components. Verifying the target position information of the target components can improve the accuracy of the target position information, thereby improving the accuracy of the positioning of the target components under the train, and thus improving the accuracy of the positioning of the train undercarriage.

[0090] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0091] Based on the same inventive concept, this application also provides a train undercarriage positioning device for implementing the above-described train undercarriage positioning method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more train undercarriage positioning device embodiments provided below can be found in the limitations of the train undercarriage positioning method described above, and will not be repeated here.

[0092] In one embodiment, such as Figure 4 As shown, a train undercarriage positioning device is provided, comprising: an undercarriage elevation data determination module 302, a current position information determination module 304, an initial position information determination module 306, a target position information determination module 308, and a target component positioning module 310, wherein:

[0093] The undercarriage elevation data determination module 302 is used to determine the undercarriage elevation data based on the distance between the detection robot and the undercarriage of the train, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the undercarriage of the train;

[0094] The current location information determination module 304 is used to determine the current location information of the detection robot based on the location information of the train's stopping area;

[0095] The initial position information determination module 306 is used to determine the initial position information of each initial component in the position under the train based on the undercarriage elevation data and the current position information.

[0096] The target location information determination module 308 is used to determine the target location information from multiple initial location information based on the distance distribution information of the target component;

[0097] The target component positioning module 310 is used to locate the target component under the train according to the target position information.

[0098] In one embodiment, the initial location information determination module 306 is further configured to:

[0099] Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information.

[0100] In one embodiment, the initial location information determination module 306 is further configured to:

[0101] A target coordinate system is constructed with the position direction of the parking area where the train is located as the X direction, the elevation direction of the train undercarriage as the Y direction, and the initial position of the detection robot as the origin. The target elevation data and the first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate value of the initial component in the target coordinate system. Based on the contour coordinate value, the center coordinate value of the center position of the initial component in the target coordinate system is determined. The coordinate value of the center coordinate value in the X direction is used as the initial position information.

[0102] In one embodiment, the target location information determination module 308 is further configured to:

[0103] Based on the multiple initial position information, the actual relative distance of each initial component is determined; the initial position information that conforms to the distance distribution information among the actual relative distances is taken as the target position information.

[0104] In one embodiment, the position positioning device under the train is further used for:

[0105] Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

[0106] In one embodiment, the detection robot includes:

[0107] A laser triangulation sensor is used to collect elevation data of the undercarriage of a parked train; a ruler reader is used to read the current position information of the inspection robot; a PCI acquisition card is used to read the elevation data of the undercarriage of the train collected by the laser triangulation sensor and the current position information read by the ruler reader; wherein, the data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

[0108] The various modules in the aforementioned train undercarriage positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0109] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data required for locating the position of the train undercarriage. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for locating the position of the train undercarriage.

[0110] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0111] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0112] Based on the distance between the detection robot and the train undercarriage, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the train undercarriage; based on the location information of the train's stopping area, the current position information of the detection robot is determined; based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location; based on the distance distribution information of the target component, the target position information is determined from multiple initial position information; based on the target position information, the target component is located on the train undercarriage.

[0113] In one embodiment, the processor further performs the following steps when executing the computer program:

[0114] Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information.

[0115] In one embodiment, the processor further performs the following steps when executing the computer program:

[0116] A target coordinate system is constructed with the position direction of the parking area where the train is located as the X direction, the elevation direction of the train undercarriage as the Y direction, and the initial position of the detection robot as the origin. The target elevation data and the first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate value of the initial component in the target coordinate system. Based on the contour coordinate value, the center coordinate value of the center position of the initial component in the target coordinate system is determined. The coordinate value of the center coordinate value in the X direction is used as the initial position information.

[0117] In one embodiment, the processor further performs the following steps when executing the computer program:

[0118] Based on the multiple initial position information, the actual relative distance of each initial component is determined; the initial position information that conforms to the distance distribution information among the actual relative distances is taken as the target position information.

[0119] In one embodiment, the processor further performs the following steps when executing the computer program:

[0120] Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

[0121] In one embodiment, the detection robot includes:

[0122] A laser triangulation sensor is used to collect elevation data of the undercarriage of a parked train; a ruler reader is used to read the current position information of the inspection robot; a PCI acquisition card is used to read the elevation data of the undercarriage of the train collected by the laser triangulation sensor and the current position information read by the ruler reader; wherein, the data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

[0123] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0124] Based on the distance between the detection robot and the train undercarriage, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the train undercarriage; based on the location information of the train's stopping area, the current position information of the detection robot is determined; based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location; based on the distance distribution information of the target component, the target position information is determined from multiple initial position information; based on the target position information, the target component is located on the train undercarriage.

[0125] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0126] Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information.

[0127] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0128] A target coordinate system is constructed with the position direction of the parking area where the train is located as the X direction, the elevation direction of the train undercarriage as the Y direction, and the initial position of the detection robot as the origin. The target elevation data and the first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate value of the initial component in the target coordinate system. Based on the contour coordinate value, the center coordinate value of the center position of the initial component in the target coordinate system is determined. The coordinate value of the center coordinate value in the X direction is used as the initial position information.

[0129] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0130] Based on the multiple initial position information, the actual relative distance of each initial component is determined; the initial position information that conforms to the distance distribution information among the actual relative distances is taken as the target position information.

[0131] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0132] Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

[0133] In one embodiment, the detection robot includes:

[0134] A laser triangulation sensor is used to collect elevation data of the undercarriage of a parked train; a ruler reader is used to read the current position information of the inspection robot; a PCI acquisition card is used to read the elevation data of the undercarriage of the train collected by the laser triangulation sensor and the current position information read by the ruler reader; wherein, the data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

[0135] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0136] Based on the distance between the detection robot and the train undercarriage, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the train undercarriage; based on the location information of the train's stopping area, the current position information of the detection robot is determined; based on the undercarriage elevation data and the current position information, the initial position information of each initial component is determined within the train undercarriage location; based on the distance distribution information of the target component, the target position information is determined from multiple initial position information; based on the target position information, the target component is located on the train undercarriage.

[0137] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0138] Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; multiple first position information corresponding to the multiple target elevation data is determined from the current position information; and the initial position information of each initial component of the train is determined based on the multiple target elevation data and the multiple first position information.

[0139] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0140] A target coordinate system is constructed with the position direction of the parking area where the train is located as the X direction, the elevation direction of the train undercarriage as the Y direction, and the initial position of the detection robot as the origin. The target elevation data and the first position information are converted into coordinate values ​​in the target coordinate system to obtain the contour coordinate value of the initial component in the target coordinate system. Based on the contour coordinate value, the center coordinate value of the center position of the initial component in the target coordinate system is determined. The coordinate value of the center coordinate value in the X direction is used as the initial position information.

[0141] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0142] Based on the multiple initial position information, the actual relative distance of each initial component is determined; the initial position information that conforms to the distance distribution information among the actual relative distances is taken as the target position information.

[0143] In one embodiment, when the computer program is executed by the processor, it further performs the following steps:

[0144] Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

[0145] In one embodiment, the detection robot includes:

[0146] A laser triangulation sensor is used to collect elevation data of the undercarriage of a parked train; a ruler reader is used to read the current position information of the inspection robot; a PCI acquisition card is used to read the elevation data of the undercarriage of the train collected by the laser triangulation sensor and the current position information read by the ruler reader; wherein, the data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

[0147] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for locating the position of a train undercarriage, characterized in that, The method includes: Based on the distance between the detection robot and the undercarriage of the train, the undercarriage elevation data is determined, wherein the undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the undercarriage of the train; Based on the location information of the train's stopping area, the current location information of the detection robot is determined; Multiple target elevation data that conform to a preset distribution pattern are selected from the vehicle under-floor elevation data, wherein the preset distribution pattern corresponds to the outer contour of the target component; Determine multiple first location information corresponding to the multiple target elevation data from the current location information; Based on the multiple target elevation data and the multiple first position information, the initial position information of each initial component of the train is determined, including: constructing a target coordinate system with the position direction of the parking area where the train is located as the X direction, the elevation direction of the train undercarriage as the Y direction, and the initial position of the detection robot as the origin; converting the target elevation data and the first position information into coordinate values ​​in the target coordinate system to obtain the contour coordinate value of the initial component in the target coordinate system; determining the center coordinate value of the center position of the initial component in the target coordinate system based on the contour coordinate value; and using the coordinate value of the center coordinate value in the X direction as the initial position information. Based on the distance distribution information of the target component, the target position information is determined from multiple initial position information. Based on the target location information, the target component is located under the train car, and the position of the train car under the target component is determined based on the position of the target component.

2. The method according to claim 1, characterized in that, The step of determining the target location information from multiple initial location information based on the distance distribution information of the target component includes: Based on the multiple initial position information, determine the actual relative distance between each of the initial components; The initial position information that corresponds to the distance distribution information among the actual relative distances is taken as the target position information.

3. The method according to claim 1, characterized in that, The method further includes: Based on the preset position offset information between each component and the target component, the position of each component is determined together with the target position information.

4. The method according to claim 1, characterized in that, The detection robot includes: Laser triangulation sensor is used to collect elevation data of the undercarriage of parked trains; A ruler reader is used to read the current position information of the inspection robot; The PCI acquisition card is used to read the train undercarriage elevation data acquired by the laser triangulation sensor and the current position information read by the ruler reader; The data reading frequency of the PCI acquisition card is matched with the data acquisition frequency of the laser triangulation sensor.

5. A positioning device for the undercarriage of a train, used to implement the positioning method for the undercarriage of a train as described in claim 1, characterized in that, The device includes: The undercarriage elevation data determination module is used to determine the undercarriage elevation data based on the distance between the detection robot and the undercarriage of the train. The undercarriage elevation data is used to describe the distance between the ranging sensor of the detection robot and the undercarriage of the train. The current location information determination module is used to determine the current location information of the detection robot based on the location information of the train's stopping area; The initial position information determination module is used to determine the initial position information of each initial component in the position under the train based on the undercarriage elevation data and the current position information. The target location information determination module is used to determine the target location information from multiple initial location information based on the distance distribution information of the target component; The target component positioning module is used to locate the target component under the train based on the target location information.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images