Method and device for real-time detection of deformation of an empty rail track beam

Abstract

Embodiments of the present application provide a kind of air rail track beam shape change real-time detection method, device, storage medium and electronic equipment, the method comprises: obtaining the laser point cloud data generated by laser radar scanning track beam at target position, as original laser point cloud data;Based on the original laser point cloud data, the internal structure parameters of the track beam at the target position are calculated and extracted;Based on the internal structure parameters, the deformation of the track beam at the target position is detected by pre-constructed sample parameters, and detection log is recorded.The technical scheme of the embodiment of the present application can realize the precise real-time detection of the deformation of the air rail track beam, and realize the remote operation and maintenance of the air rail track beam.

Description

Technical Field

[0001] This application relates to the field of track inspection technology, and more specifically, to a method, device, storage medium, and electronic equipment for real-time detection of deformation of an empty track beam. Background Technology

[0002] With the commencement of elevated rail operations in my country, such as the demonstration line of the collection and distribution system at Qingdao Port, the daily operation and maintenance of the elevated rail system has become increasingly important. Under the long-term load of vehicles, the elevated rail beams may experience settlement, deformation, and groove gap deformation. Failure to address these deformations promptly can pose safety hazards to vehicle operation. However, the high pressure, wide grooves, and relatively dark environment within the elevated rail system present significant safety risks and heavy workloads for maintenance personnel. Therefore, achieving intelligent and accurate detection of elevated rail beam deformation and enabling remote operation and maintenance of the elevated rail beams are urgent technical challenges that need to be addressed. Summary of the Invention

[0003] The embodiments of this application provide a method, device, storage medium, and electronic device for real-time detection of deformation of an air track beam, thereby enabling intelligent and accurate detection of deformation of the air track beam and remote operation and maintenance of the air track beam.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to a first aspect of the present application, a method for real-time detection of deformation of an air track beam is provided. The method includes: acquiring laser point cloud data generated by a lidar scanning the track beam at a target location, as raw laser point cloud data; calculating and extracting internal structural parameters of the track beam at the target location based on the raw laser point cloud data; and detecting the deformation of the track beam at the target location based on the internal structural parameters and by using pre-constructed sample parameters.

[0006] In some embodiments of this application, based on the aforementioned scheme, the original laser point cloud data consists of laser data from several laser points. The step of calculating and extracting the internal structural parameters of the track beam at the target location based on the original laser point cloud data includes: replacing noisy laser data in the original laser point cloud data to obtain reference laser point cloud data; smoothing the reference laser point cloud data to obtain target laser point cloud data; and calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data.

[0007] In some embodiments of this application, based on the foregoing scheme, the laser data includes the distance between the laser point and the lidar, and the replacement of noisy laser data in the original laser point cloud data includes: for each target laser point, obtaining the distance corresponding to the target laser point as the target distance, wherein the target laser point is any one of the plurality of laser points; if the target distance is greater than a first preset distance or less than a second preset distance, then the laser data corresponding to the target laser point is defined as the noisy laser data, and the noisy laser data is replaced by the laser data corresponding to the laser point adjacent to the target laser point, wherein the first preset distance is greater than the second preset distance.

[0008] In some embodiments of this application, based on the foregoing scheme, the smoothing process of the reference laser point cloud data includes: sliding segmenting the reference laser point cloud data according to a preset window to obtain multiple sets of sub-reference laser point cloud data; calculating smoothed filtered laser data based on each laser data in each set of target sub-reference laser point cloud data, wherein the smoothed filtered laser data is used to suppress fluctuations in each laser data in the target sub-reference laser point cloud data, and the target sub-reference laser point cloud data is any one of the multiple sets of sub-reference laser point cloud data; and replacing each laser data in each set of target sub-reference laser point cloud data with the smoothed filtered laser data for each set of target sub-reference laser point cloud data.

[0009] In some embodiments of this application, based on the foregoing scheme, the step of calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data includes: determining laser breakpoints among the plurality of laser points based on the target laser point cloud data; dividing the plurality of laser points into multiple laser point sets through the laser breakpoints, and generating laser feature lines based on the laser points in each laser point set to obtain a set of laser feature lines, wherein the set of laser feature lines is used to characterize the cross-sectional profile of the track beam in the radial direction at the target location; and determining the internal structural parameters of the track beam at the target location based on the set of laser feature lines.

[0010] In some embodiments of this application, based on the foregoing scheme, determining the laser breakpoint among the plurality of laser points based on the target laser point cloud data includes: selecting any two adjacent laser points from the plurality of laser points; obtaining the distance between the two adjacent laser points based on the target laser point cloud data; and determining the two adjacent laser points as the laser breakpoint if the difference between the distances between the two adjacent laser points is greater than a preset parameterized adaptive threshold.

[0011] In some embodiments of this application, based on the foregoing scheme, the step of fitting and generating laser feature lines based on laser points in each laser point set includes: for each target laser point set, selecting multiple laser points from the target laser point set as seed laser points, wherein the target laser point set is any one of the multiple laser point sets; performing linear fitting on the seed laser points in the target laser point set to generate the laser feature line corresponding to the target laser point set.

[0012] According to a second aspect of the embodiments of this application, a device for detecting the deformation of an air track beam is provided. The device includes: an acquisition unit for acquiring laser point cloud data generated by a lidar scanning the track beam at a target position, as raw laser point cloud data; a data processing unit for calculating and extracting internal structural parameters of the track beam at the target position based on the raw laser point cloud data; and a detection recording unit for detecting the deformation of the track beam at the target position based on the internal structural parameters and using pre-constructed sample parameters, and recording a detection log.

[0013] According to a third aspect of the embodiments of this application, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores at least one piece of program code, the at least one piece of program code being loaded and executed by a processor to perform the operations performed by the method described in any of the first aspects above.

[0014] According to a fourth aspect of the present application, an electronic device is provided, including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, the at least one piece of program code being loaded and executed by the one or more processors to perform the operation as described in any of the first aspects above.

[0015] The technical solution proposed in this application acquires laser point cloud data generated by LiDAR scanning the track beam at the target location, using it as the raw laser point cloud data. Then, it calculates and extracts the internal structural parameters of the track beam at the target location using the raw laser point cloud data. Finally, it detects the deformation of the track beam at the target location using the internal structural parameters and pre-constructed sample parameters. In this application, LiDAR scans the track beam at different locations to obtain deformation results of the track beam with location and time labels, forming a detection log record for the track beam. This allows relevant users to understand whether the track beam has deformed at different locations and the degree of deformation through remote operation and maintenance, thereby enabling timely and targeted elimination of safety hazards caused by track beam deformation, improving the safety and reliability of the track, and realizing remote operation and maintenance of the track beam.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 A flowchart of a real-time deformation detection method for an air track beam according to an embodiment of this application is shown;

[0019] Figure 2 A schematic diagram of a scene showing a lidar scanning the track beam at a target location according to an embodiment of this application is shown;

[0020] Figure 3 The internal structural parameters of the track beam at the target location are calculated and extracted based on the original laser point cloud data according to one embodiment of this application;

[0021] Figure 4 A detailed flowchart illustrating the calculation and extraction of internal structural parameters of the track beam at the target location based on the target laser point cloud data according to an embodiment of this application is shown.

[0022] Figure 5 A schematic diagram of feature line extraction according to an embodiment of this application is shown;

[0023] Figure 6 A block diagram of a real-time detection device for air track deformation according to an embodiment of this application is shown;

[0024] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0025] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0026] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0027] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0029] It should be noted that "multiple" in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0032] The following detailed description of some embodiments of this application will be provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0033] See Figure 1 The flowchart illustrates a real-time deformation detection method for an air track beam according to an embodiment of this application, which specifically includes steps 110 to 130.

[0034] Step 110: Obtain the laser point cloud data generated by the lidar scanning the track beam at the target position, as the original laser point cloud data.

[0035] In some implementations, the lidar can be a single-line lidar, mounted on an inspection platform such as an inspection vehicle. The movement of the inspection platform allows for scanning of the track beam at different locations within the empty track. The laser point cloud data consists of laser data from several laser points. It can be understood that the lidar contains several laser beams, each with a corresponding sequence number. Each laser beam scanning the track beam generates a corresponding laser point. When the lidar scans the empty track beam at a specific time and location, it generates laser point cloud data corresponding to that specific time and location.

[0036] In some implementations, a positioning module can be installed in the inspection vehicle to monitor the current position of the inspection vehicle in real time to determine the target position; the inspection vehicle can also be connected to a remote monitoring center via a wireless communication module so that the remote monitoring center can receive and process the laser point cloud data obtained by the lidar scan in real time, so as to monitor the deformation of the air track beam at different positions in real time, thereby realizing remote operation and maintenance of the air track beam deformation.

[0037] In some implementations, before the inspection vehicle begins detecting the deformation of the empty track beam, a self-test module can be used to check the connectivity between the lidar, positioning module, and wireless communication module to ensure the effectiveness of the inspection vehicle's deformation detection work.

[0038] In some implementations, the target location information can be determined by determining the position of the inspection vehicle in the Frenet coordinate system of the air track or in the global coordinate system relative to a reference point. Specifically, the inspection vehicle can obtain its location information through onboard sensors, such as odometers (Odom) or radio frequency identification (RFID) beacons; it can also obtain its location information in the global coordinate system through the Global Positioning System (GPS) or the Beidou Navigation System (BDS), and then perform coordinate transformation to obtain the relative position information of the inspection vehicle's coordinate system on the air track; the inspection vehicle can also directly obtain its position information in the global coordinate system of a reference point through an inertial measurement unit (IMU). The specific method for determining the target location is not limited herein.

[0039] In some implementations, the laser point cloud data includes, but is not limited to, the time information of the lidar scanning the track beam at the target location, the intensity information of each laser point, the angle information of the lidar when acquiring the laser point cloud data, the distance information of each laser point from the lidar, etc.

[0040] In this embodiment, by recording the target location information and the time information of the lidar scanning the track beam at the target location, it is beneficial to form a log record of the deformation detection of the empty track beam, which facilitates the formation of traceable detection records and enables timely processing of detected abnormal data.

[0041] See also Figure 1 Step 120: Calculate and extract the internal structural parameters of the track beam at the target location based on the original laser point cloud data.

[0042] To enable those skilled in the art to better understand this embodiment, the following will introduce... Figure 2 Please provide an explanation.

[0043] See Figure 2 The diagram illustrates a scenario where a lidar, according to an embodiment of this application, scans the track beam at a target location. Figure 2 The scenario shown depicts a lidar unit mounted on an inspection platform scanning a track beam at a target location. (The sentence is incomplete and requires further context.) Figure 2 It can be seen that the cross-sectional profile of the track beam scanned at the target location in the radial direction includes the left side, right side, top, and bottom surfaces of the track beam, as well as the groove.

[0044] It should be noted that the internal structural parameters in this embodiment include, but are not limited to, the width information of the groove located on the bottom surface of the track beam, the length information of the top surface of the track beam, the length information of the left side surface of the track beam, the length information of the right side surface of the track beam, the length information of the bottom surface of the track beam, the parallelism between the left and right sides of the track beam, the parallelism between the bottom and top surfaces of the track beam, the perpendicularity between the left and top surfaces of the track beam, the perpendicularity between the right and top surfaces of the track beam, the perpendicularity between the left and bottom surfaces of the track beam, and so on.

[0045] In some embodiments, the specific implementation of calculating and extracting the internal structural parameters of the track beam at the target location based on the original laser point cloud data can be as follows: Figure 3 Perform the steps shown.

[0046] See Figure 3 This paper illustrates the calculation and extraction of internal structural parameters of the track beam at the target location based on the original laser point cloud data according to an embodiment of this application, specifically including steps 121 to 123.

[0047] Step 121: Replace the noisy laser data in the original laser point cloud data to obtain reference laser point cloud data.

[0048] It is understandable that when the lidar scans the track beam at the target location, some noisy laser data will appear if some laser points are out of range or some laser beams in the lidar are damaged. If these noisy laser data are not processed, it will affect the accuracy of the internal structural feature parameters extracted later.

[0049] In some implementations, the replacement of noisy laser data can be achieved by following steps 1211 to 1212 to obtain reference laser point cloud data.

[0050] Step 1211: For each target laser point, obtain the distance corresponding to the target laser point as the target distance. The target laser point is any one of the several laser points.

[0051] Step 1212: If the target distance is greater than a first preset distance or less than a second preset distance, then the laser data corresponding to the target laser point is defined as the noise laser data, and the noise laser data is replaced by the laser data corresponding to the laser point adjacent to the target laser point, wherein the first preset distance is greater than the second preset distance.

[0052] It is understood that if the target distance is greater than a first preset distance, the laser data corresponding to the target laser point can be considered as laser data exceeding the range; if the target distance is less than a second preset distance, the laser data corresponding to the target laser point can be considered as damaged and invalid laser data. In both cases, the laser data corresponding to the target laser point is abnormal noise laser data. The first preset distance can be the maximum range of the lidar, and the second preset distance can be the minimum detection range of the lidar.

[0053] It should be noted that since each laser point has a corresponding laser beam and laser beam number, the laser points adjacent to the target laser point are the laser points corresponding to the laser beam numbers adjacent to the laser beam number of the target laser point.

[0054] In this embodiment, replacing noisy laser data with neighboring data can increase the accuracy of extracting internal structural parameters of the track beam.

[0055] See also Figure 3 Step 122: Smooth the reference laser point cloud data to obtain the target laser point cloud data.

[0056] In some embodiments, the specific implementation of smoothing the reference laser point cloud data to obtain the target laser point cloud data can be performed according to the following steps 1221 to 1223.

[0057] Step 1221: Perform sliding segmentation on the reference laser point cloud data according to the preset window to obtain multiple sets of sub-reference laser point cloud data.

[0058] It should be noted that the size of the preset window can be determined based on the number of adjacent laser points. For example, five adjacent laser points can be used as one preset window, and then the reference laser point cloud data can be slidably segmented with a sliding step of one laser point to obtain multiple sets of sub-reference laser point cloud data. It can be understood that the number of sets of sub-reference laser point cloud data is consistent with the number of laser points.

[0059] Step 1222: Based on each laser data in each set of target sub-reference laser point cloud data, calculate smoothed filtered laser data. The smoothed filtered laser data is used to suppress the fluctuation influence of each laser data in the target sub-reference laser point cloud data. The target sub-reference laser point cloud data is any one of the multiple sets of sub-reference laser point cloud data.

[0060] It is understandable that the raw laser point cloud data obtained will have slight fluctuations in the laser data of each laser point due to the characteristics of the lidar system, which will produce systematic errors. Therefore, it is necessary to smooth the reference laser point cloud data to obtain smoothed and filtered laser data, thereby eliminating systematic errors and improving the accuracy of extracting internal structural parameters in the later stage.

[0061] In one implementation, the smoothed laser data is calculated using a weighted median filtering algorithm. For example, a preset window is defined as five adjacent laser points.

[0062] r[i]=a1*r[i-2]+a2*r[i-1]+a3*r[i]+a4*r[i+1]+a5*r[i+2]

[0063] Where r[i] represents the distance of the laser point located in the middle position in the target sub-reference laser point cloud data; a1, a2, a3, a4 and a5 are weight coefficients, and a1+a2+a3+a4+a5=1, and a3>a4>a5, and a3>a2>a1.

[0064] In another implementation, the smoothed filtered laser data can be calculated using an algebraic averaging algorithm. For example, if a preset window is defined as five adjacent laser points, then:

[0065] r[i]=(r[i-2]+r[i-1]+r[i]+r[i+1]+r[i+2]) / 5

[0066] Where r[i] represents the distance of the laser point located in the middle position in the target sub-reference laser point cloud data.

[0067] It is understood that using the weighted median filtering algorithm in the first embodiment to calculate the smoothed laser data can achieve a better smoothing effect. Of course, in this embodiment, the corresponding smoothing method for the reference laser point cloud data can be designed according to different application scenarios, and this application does not limit it here.

[0068] Step 1223: For each set of target sub-reference laser point cloud data, replace each laser data in the target sub-reference laser point cloud data with the smoothed filtered laser data.

[0069] It should be noted that a smoothed laser data can be obtained in each set of target sub-reference laser point cloud data. This smoothed laser data can replace the laser data of several laser points in this application. For example, if a smoothed laser data corresponding to the third-order laser beam is obtained in the first preset window, this smoothed laser data can be used to replace the original laser data corresponding to the third-order laser beam.

[0070] See also Figure 3 Step 123: Calculate and extract the internal structural parameters of the track beam at the target location based on the target laser point cloud data.

[0071] In some embodiments, the specific implementation of calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data can be as follows: Figure 4 Implemented in the manner described.

[0072] See Figure 4 This document illustrates a detailed flowchart of a method for calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data, according to an embodiment of this application. Specifically, it includes steps 1231 to 1233.

[0073] Step 1231: Based on the target laser point cloud data, determine the laser breakpoint among the plurality of laser points.

[0074] In some implementations, the laser breakpoint can be determined by following steps 12311 to 12313.

[0075] Step 12311: Select any two adjacent laser points from the plurality of laser points.

[0076] Step 12312: Based on the target laser point cloud data, obtain the distance between any two adjacent laser points.

[0077] Step 12313: If the difference in distance between any two laser points is greater than a preset parameterized adaptive threshold, then the two laser points are determined as the laser breakpoint.

[0078] In some implementations, an adaptive threshold method based on adjacent points can be used to determine the laser breakpoint. Specifically, the laser breakpoint can be adaptively obtained based on the lidar measurement error, angular resolution, and distance between the laser points. That is, the preset parameterized adaptive threshold can be set to "λ + k * r[i] * δ", where λ is the lidar ranging system error; k is an adjustment factor; r[i] is the distance between the i-th laser point and any two adjacent laser points; and δ is the lidar angular resolution. It should be noted that the preset parameterized adaptive threshold is not a fixed parameter, but rather changes with the distance between the i-th laser point and the adjacent laser point.

[0079] To enable those skilled in the art to better understand this embodiment, the following will be combined with... Figure 5 The laser breakpoint is described below.

[0080] See Figure 5The diagram illustrates a schematic representation of feature line extraction according to an embodiment of this application.

[0081] From Figure 5 As can be seen, during the scanning of the track beam at the target location by the lidar, it may encounter obstacles such as wires and baffles in the empty track, resulting in a large distribution distance between the laser points. For example... Figure 5 As shown in the laser breakpoint diagram, it can be understood that there may be multiple other laser points between two adjacent laser breakpoints, or there may be no other laser points (i.e., relatively independent laser breakpoints).

[0082] In this embodiment, by extracting the laser breakpoint, the extraction speed of subsequent laser feature lines can be accelerated, thereby improving the speed of extracting the internal structural parameters of the track beam.

[0083] See also Figure 4 Step 1232: Divide the plurality of laser points into multiple sets of laser points through the laser breakpoints, and generate laser feature lines based on the laser points in each set of laser points to obtain a set of laser feature lines. The set of laser feature lines is used to characterize the cross-sectional profile of the track beam in the radial direction of the track beam at the target position.

[0084] It is understandable that if there are multiple other laser points between two adjacent laser breakpoints, then these two adjacent laser breakpoints and the other laser points between them can be considered as a set of laser points.

[0085] In some implementations, the specific embodiment of fitting and generating laser feature lines can be performed according to steps 12321 to 12322 below.

[0086] Step 12321: For each set of target laser points, select multiple laser points from the set of target laser points as seed laser points, where the set of target laser points is any one of the multiple sets of laser points.

[0087] In some implementations, a subset of laser points from the target laser point set may be selected as seed laser points. This application does not limit the number of seed laser points selected or whether the selected seed laser points are consecutive.

[0088] Step 12322: Perform linear fitting on the seed laser points in the target laser point set to generate the laser feature line corresponding to the target laser point set.

[0089] In some implementations, a seed region expansion calculation method can be used to determine the laser feature line. That is, a portion of continuous laser points in the target laser point set can be selected as seed laser points. Then, the selected seed laser points are fitted to an initial straight line using the least squares method to obtain the straightness coefficient of the initial straight line. Next, laser points that conform to the growth rules of the initial straight line are searched at both ends of the initial straight line segment as added laser points. If the added laser points are found, they are added to the initial straight line, and the initial straight line and the added laser points are fitted to an updated straight line again using the least squares method to obtain the straightness data of the updated straight line. The initial straight line is grown by continuously searching for added laser points in this way to obtain the laser feature line corresponding to the target laser point set.

[0090] The above-mentioned principle for selecting laser points that conform to the initial linear growth rule as the criteria for adding laser points can be based on... To determine, where a, b, c are the linear coefficients of the initial straight line fitted using the least squares method, and X... i and Y i The coordinates represent the laser point to be added; the threshold is used to determine whether the laser point to be added can be defined as the laser point to be added.

[0091] It should be noted that the above selection is related to the performance parameters of the onboard sensors on the inspection vehicle.

[0092] It is understandable that the linear coefficients mentioned above change continuously with the addition of laser points. Each time a determination is made as to whether a laser point can be added, the updated linear coefficients should be used. Finally, by fitting the laser feature line of the target laser point set, the corresponding linear coefficients will also be obtained. Specifically, for each laser point set, a corresponding laser feature line can be generated, thus obtaining a set of laser feature lines.

[0093] For example, such as Figure 5 As shown, Figure 5 These are laser feature lines obtained after processing the laser point cloud data generated by the lidar scanning of a certain section of the track beam in the air track. Figure 5 As can be seen, there is one laser feature line on the top surface of the track beam, one laser feature line on the left side of the track beam, one laser feature line on the right side of the track beam, and two laser feature lines on the bottom surface of the track beam. These laser feature lines can be considered as a set of laser feature lines.

[0094] In this embodiment, by extracting laser feature lines, the internal structure of the track beam can be more accurately represented based on the geometric features of the intersection between the lines, so as to more accurately detect the deformation of the track beam.

[0095] See also Figure 4Step 1233: Determine the internal structural parameters of the track beam at the target position based on the set of laser feature lines.

[0096] In some implementations, the obtained set of laser feature lines can be further filtered according to length, that is, only some laser feature lines that meet certain length requirements are left to determine the internal structural parameters of the track beam at the target position, so that some interfering laser feature lines can be eliminated and the extraction rate of internal structural parameters can be improved.

[0097] It should be noted that the laser feature lines in the laser feature line set include, but are not limited to, line segment length data, line segment endpoint data, line segment straightness coefficient data, line segment position data, etc.

[0098] It is understandable that the internal structural parameters of the track beam can be determined by determining information such as the angle and distance between different laser feature lines.

[0099] For example, it can be done through To determine the perpendicularity of the left side and top surface of the track beam; where The verticality of the left and top surfaces of the track beam is indicated; a1, b1, and c1 represent the straightness coefficients of the laser feature lines on the left side of the track beam, and satisfy a1*X+b1Y+c1=0; a2, b2, and c2 represent the straightness coefficients of the laser feature lines on the top surface of the track beam, and satisfy a2*X+b2Y+c2=0.

[0100] See also Figure 1 Step 130: Based on the internal structural parameters, detect the deformation of the track beam at the target position using pre-constructed sample parameters.

[0101] It should be noted that the pre-built sample parameters can be a comprehensive database of air track structure parameters based on the air track mileage, or simplified track structure parameters in a segmented design.

[0102] For example, if the perpendicularity of the sample parameters constructed between the left side and top surface of the track beam at the target location is 90°, then it can be based on the above... The value is compared with 90° to detect the deformation of the empty track beam.

[0103] The method for detecting deformation of air track beams provided in this application has low environmental requirements, can automatically perform detection tasks, and has high robustness. By designing preprocessing steps to replace noisy laser data and smooth filtered laser data, the accuracy of laser feature line extraction can be improved, making the deformation detection method more accurate. In addition, by designing the confirmation of laser breakpoints, the computational complexity is reduced, and real-time requirements can be met.

[0104] In some embodiments of this application, the technical solutions provided involve acquiring laser point cloud data generated by a lidar scanning a track beam at a target location, which is then used as the raw laser point cloud data. The internal structural parameters of the track beam at the target location are then calculated and extracted using the raw laser point cloud data. Finally, the deformation of the track beam at the target location is detected using the internal structural parameters and pre-built sample parameters. In this application, the deformation results of the track beam with location and time labels are obtained by scanning the empty track beam at different locations using lidar. This generates a detection log record for the empty track beam, allowing relevant users to remotely monitor whether the track beam has deformed at different locations and the degree of deformation, thereby enabling timely and targeted elimination of safety hazards caused by deformation of the track beam, improving the safety and reliability of the empty track, and achieving remote maintenance of the track beam.

[0105] The following describes an embodiment of the apparatus described in this application, which can be used to execute the real-time deformation detection method for the empty track beam in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the real-time deformation detection method for the empty track beam described above in this application.

[0106] Figure 6 A block diagram of a real-time detection device for air track deformation according to an embodiment of this application is shown.

[0107] Reference Figure 6 As shown, an air track beam deformation detection device 600 according to an embodiment of this application includes: an acquisition unit 601, a data processing unit 602, and a detection recording unit 603.

[0108] The acquisition unit 601 is used to acquire laser point cloud data generated by the lidar scanning the track beam at the target position, as the original laser point cloud data; the data processing unit 602 is used to calculate and extract the internal structural parameters of the track beam at the target position based on the original laser point cloud data; and the detection and recording unit 603 is used to detect the deformation of the track beam at the target position based on the internal structural parameters and through pre-constructed sample parameters, and record the detection log.

[0109] In some embodiments of this application, based on the foregoing scheme, the data processing unit 602 further includes: the original laser point cloud data is composed of laser data of a plurality of laser points, and the step of calculating and extracting the internal structural parameters of the track beam at the target position based on the original laser point cloud data includes: replacing the noisy laser data in the original laser point cloud data to obtain reference laser point cloud data; smoothing the reference laser point cloud data to obtain target laser point cloud data; and calculating and extracting the internal structural parameters of the track beam at the target position based on the target laser point cloud data.

[0110] In some embodiments of this application, based on the foregoing scheme, the data processing unit 602 further includes: the laser data includes the distance between the laser point and the lidar; replacing the noisy laser data in the original laser point cloud data includes: for each target laser point, obtaining the distance corresponding to the target laser point as the target distance, wherein the target laser point is any one of the plurality of laser points; if the target distance is greater than a first preset distance or less than a second preset distance, then the laser data corresponding to the target laser point is defined as the noisy laser data, and the noisy laser data is replaced by the laser data corresponding to the laser point adjacent to the target laser point, wherein the first preset distance is greater than the second preset distance.

[0111] In some embodiments of this application, based on the foregoing scheme, the data processing unit 602 further includes: smoothing the reference laser point cloud data, which includes: sliding the reference laser point cloud data according to a preset window to obtain multiple sets of sub-reference laser point cloud data; calculating smoothed filtered laser data based on each laser data in each set of target sub-reference laser point cloud data, wherein the smoothed filtered laser data is used to suppress fluctuations in each laser data in the target sub-reference laser point cloud data, and the target sub-reference laser point cloud data is any one of the multiple sets of sub-reference laser point cloud data; and replacing each laser data in each set of target sub-reference laser point cloud data with the smoothed filtered laser data for each set of target sub-reference laser point cloud data.

[0112] In some embodiments of this application, based on the foregoing scheme, the data processing unit 602 further includes: calculating and extracting the internal structural parameters of the track beam at the target position based on the target laser point cloud data, including: determining laser breakpoints among the plurality of laser points based on the target laser point cloud data; dividing the plurality of laser points into multiple laser point sets through the laser breakpoints, and generating laser feature lines based on the laser points in each laser point set to obtain a set of laser feature lines, wherein the set of laser feature lines is used to characterize the cross-sectional profile of the track beam in the radial direction at the target position; and determining the internal structural parameters of the track beam at the target position based on the set of laser feature lines.

[0113] In some embodiments of this application, based on the foregoing scheme, the data processing unit 602 further includes: selecting any two adjacent laser points from the plurality of laser points; obtaining the distance between the two adjacent laser points based on the target laser point cloud data; and determining the two adjacent laser points as the laser breakpoint if the difference between the distances between the two adjacent laser points is greater than a preset parameterized adaptive threshold.

[0114] In some embodiments of this application, based on the foregoing scheme, the data processing unit 602 further includes: for each set of target laser points, selecting multiple laser points from the set of target laser points as seed laser points, wherein the set of target laser points is any one of the multiple sets of laser points; performing linear fitting on the seed laser points in the set of target laser points to generate a laser feature line corresponding to the set of target laser points.

[0115] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0116] It should be noted that, Figure 7 The computer system 700 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0117] like Figure 7As shown, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 702 or programs loaded from storage portion 708 into Random Access Memory (RAM) 703, such as performing the methods described in the above embodiments. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An Input / Output (I / O) interface 705 is also connected to the bus 704.

[0118] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0119] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs various functions defined in the system of this application.

[0120] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0121] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0122] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0123] In another aspect, this application also provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the real-time deformation detection method for the empty track beam described in the above embodiments.

[0124] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the real-time deformation detection method for the air track beam described in the above embodiments.

[0125] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0126] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0127] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0128] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for real-time detection of deformation of a track beam in an empty rail system, characterized in that, The method includes: Acquire the laser point cloud data generated by the lidar scanning the track beam at the target location, and use it as the raw laser point cloud data; The internal structural parameters of the track beam at the target location are calculated and extracted based on the original laser point cloud data. The original laser point cloud data consists of laser data from several laser points. The calculation and extraction of the internal structural parameters of the track beam at the target location based on the original laser point cloud data includes: replacing noisy laser data in the original laser point cloud data to obtain reference laser point cloud data; smoothing the reference laser point cloud data to obtain target laser point cloud data; and calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data. Specifically, the calculation and extraction of the internal structural parameters of the track beam at the target location based on the target laser point cloud data includes: determining laser breakpoints among the several laser points based on the target laser point cloud data; dividing the several laser points into multiple laser point sets through the laser breakpoints; and fitting and generating laser feature lines based on the laser points in each laser point set to obtain a set of laser feature lines. The set of laser feature lines is used to characterize the cross-sectional profile of the track beam in the radial direction at the target location; and determining the internal structural parameters of the track beam at the target location based on the set of laser feature lines. Based on the internal structural parameters, the deformation of the track beam at the target position is detected by pre-constructed sample parameters, and the detection log is recorded.

2. The method according to claim 1, characterized in that, The laser data includes the distances between the plurality of laser points and the lidar, and the replacement of noisy laser data in the original laser point cloud data includes: For each target laser point, the distance corresponding to the target laser point is obtained as the target distance, wherein the target laser point is any one of the plurality of laser points; If the target distance is greater than a first preset distance or less than a second preset distance, then the laser data corresponding to the target laser point is defined as the noise laser data, and the noise laser data is replaced by the laser data corresponding to the laser point adjacent to the target laser point, wherein the first preset distance is greater than the second preset distance.

3. The method according to claim 1, characterized in that, The smoothing process for the reference laser point cloud data includes: The reference laser point cloud data is slidably segmented according to a preset window to obtain multiple sets of sub-reference laser point cloud data. Based on each laser data in each set of target sub-reference laser point cloud data, smoothed filtered laser data is calculated. The smoothed filtered laser data is used to suppress the fluctuation of each laser data in the target sub-reference laser point cloud data. The target sub-reference laser point cloud data is any one of the multiple sets of sub-reference laser point cloud data. For each set of target sub-reference laser point cloud data, the laser data in the target sub-reference laser point cloud data is replaced by the smoothed filtered laser data.

4. The method according to claim 1, characterized in that, The step of determining the laser breakpoint among the plurality of laser points based on the target laser point cloud data includes: Select any two adjacent laser points from the plurality of laser points; Based on the target laser point cloud data, the distance between any two adjacent laser points is obtained; If the difference in distance between any two adjacent laser points is greater than a preset parameterized adaptive threshold, then the two adjacent laser points are determined as the laser breakpoint.

5. The method according to claim 1, characterized in that, The process of fitting and generating laser feature lines based on laser points in each laser point set includes: For each set of target laser points, multiple laser points are selected from the set of target laser points as seed laser points, where the set of target laser points is any one of the multiple sets of laser points; Linear fitting is performed on the seed laser points in the target laser point set to generate the laser feature line corresponding to the target laser point set.

6. A device for detecting deformation of a track beam in an empty rail system, characterized in that, The device includes: The acquisition unit is used to acquire the laser point cloud data generated by the lidar scanning the track beam at the target position, as the raw laser point cloud data. A data processing unit is used to calculate and extract the internal structural parameters of the track beam at the target location based on the original laser point cloud data. The original laser point cloud data consists of laser data from several laser points. The calculation and extraction of the internal structural parameters of the track beam at the target location based on the original laser point cloud data includes: replacing noisy laser data in the original laser point cloud data to obtain reference laser point cloud data; smoothing the reference laser point cloud data to obtain target laser point cloud data; and calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data. In this process, the step of calculating and extracting the internal structural parameters of the track beam at the target location based on the target laser point cloud data includes: determining laser breakpoints among the plurality of laser points based on the target laser point cloud data; dividing the plurality of laser points into multiple laser point sets through the laser breakpoints, and generating laser feature lines based on the laser points in each laser point set to obtain a set of laser feature lines, wherein the set of laser feature lines is used to characterize the cross-sectional profile of the track beam in the radial direction at the target location; and determining the internal structural parameters of the track beam at the target location based on the set of laser feature lines. The detection and recording unit is used to detect the deformation of the track beam at the target position based on the internal structural parameters and through pre-constructed sample parameters, and to record the detection log.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, The method includes a memory, one or more processors, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors, and the one or more programs contain instructions for performing the method as described in any one of claims 1 to 5.

Images