Design method and processing device for track fine-tuning scheme based on fastener point cloud model

Abstract

The present invention discloses a design method and processing device for a track fine-tuning scheme based on a fastener point cloud model. The method includes: obtaining three-dimensional point cloud data of a track, where the three-dimensional point cloud data of the track includes sleeper area data and non-sleeper area data; segmenting the sleeper area data and the non-sleeper area data, and identifying three-dimensional data of fasteners and three-dimensional data of rails based on the sleeper area data; calling a point cloud post-processing algorithm to segment each pre-identified component of the fasteners according to the three-dimensional data of the fasteners; obtaining three-dimensional point cloud data of the pre-identified components; calculating the three-dimensional point cloud data of the pre-identified components to obtain pre-identified data, and comparing the pre-identified data with a standard three-dimensional data model pre-stored in a database to identify the model of the parts; designing a scheme for adjusting or replacing the target components according to the fine-tuning dimensions of the track.

Description

Technical Field

[0001] The present invention belongs to the technical field of track fine adjustment, and more specifically, relates to a design method and processing device for a track fine adjustment scheme based on a fastener point cloud model. Background Art

[0002] Currently, with the continuous expansion of China's high-speed rail network and the progress of technology, the requirements for railway track maintenance inspection are also continuously improving to ensure the safe operation of high-speed rail lines. In railway track maintenance inspection, aspects such as the fastening force of fasteners need to be strictly examined. In addition to inspecting the quality of the fasteners themselves, the correct installation state of the fasteners is also regarded as a crucial link. The correct installation of fasteners includes aspects such as correct position, correct fastening force, and correct connection method. Incorrect installation may cause the fasteners to loosen, fall off, or be insecurely connected, thus posing safety hazards to the railway line and even affecting the stability and safety of train operation. Therefore, the detection of the installation state of fasteners in railway track maintenance inspection usually includes various methods such as on-site inspection, measurement, and testing to ensure that the installation of fasteners meets relevant standards and requirements.

[0003] In addition, with the development of technology, some advanced detection methods such as non-destructive testing technology have also been widely used in the quality detection of fasteners to ensure that the fasteners can maintain stable connection during the operation of high-speed trains without safety hazards such as fracture or loosening. Therefore, railway track maintenance inspection continuously adopts new technologies and new methods to adapt to the continuous improvement and development of high-speed rail operation. Non-destructive testing technology is mainly divided into image detection and laser detection technology. Image detection technology uses cameras and image processing algorithms to perform surface detection on fasteners, and can quickly and accurately detect surface defects, cracks, or other abnormal conditions. Laser detection technology scans the surface of fasteners through laser beams and uses the reflected signals to detect surface defects and shape deviations, with the advantages of high precision and high efficiency.

[0004] However, the above two detection methods cannot detect and identify each component of the fastener and the dimensions of each component in more depth, and thus cannot provide a reference for the precise adjustment of the track. Summary of the Invention

[0005] In view of the above-mentioned defects or improvement requirements of the prior art, in a first aspect, the present invention provides a design method for a track fine adjustment scheme based on a fastener point cloud model. The design method for the track fine adjustment scheme based on the fastener point cloud model includes:

[0006] Obtain the three-dimensional point cloud data of the track, and the three-dimensional point cloud data of the track includes sleeper area data and non-sleeper area data

[0007] Segment the sleeper area data and the non-sleeper area data, and identify the 3D data of the fasteners and the 3D data of the rail according to the sleeper area data;

[0008] According to the 3D data of the fasteners, call the point cloud post-processing algorithm to segment each pre-identified component of the fasteners;

[0009] Obtain the 3D point cloud data of the pre-identified components;

[0010] Calculate the pre-identified data from the 3D point cloud data of the pre-identified components, and compare the pre-identified data with the standard 3D data model pre-stored in the database to identify the part model;

[0011] Adjust or replace the identified target components according to the fine-tuning dimensions of the set track.

[0012] In the first aspect, obtaining the 3D point cloud data of the track, and segmenting the sleeper area data and the non-sleeper area data includes:

[0013] Obtain the height data of each pre-identified fastener of the track;

[0014] Set a standard height threshold;

[0015] Compare the height of all pre-identified fasteners with the standard height threshold. If it is greater than the standard height threshold, it is determined as the sleeper area; if it is less than the standard height threshold, it is determined as the non-sleeper area;

[0016] In the first aspect, calculating the 3D point cloud data of the pre-identified components includes calculating the pre-identified data of the pre-identified components according to the following formula:

[0017] T R = h2 - h3 + T Iron -T Rail -T Rubber (Formula 1)

[0018] Where, T R represents the thickness of the under-rail shim; h2 represents the height of the edge of the rail base; h3 represents the height of the upper surface of the retaining shoulder of the base plate; T Iron represents the height difference between the upper surface of the retaining shoulder of the base plate and the upper surface of the center of the base plate; T Rail represents the thickness of the rail base; T Rubber represents the thickness of the buffer pad.

[0019] In the first aspect, calculating the 3D point cloud data of the pre-identified components includes calculating the pre-identified data of the pre-identified components according to the following formula:

[0020] T P = h3 - h5 - T Pillar -T Buffer (Formula 2)

[0021] Among them, T P represents the thickness of the heightening pad under the tie plate; h3 represents the height of the upper surface of the tie plate limit shoulder; h5 represents the height of the track slab; T Pillar represents the height difference between the upper surface of the tie plate limit shoulder and the bottom surface of the tie plate; T Buffer represents the thickness of the insulating buffer pad.

[0022] In the first aspect, calculating the three-dimensional point cloud data of the pre-identification component includes calculating the pre-identification data of the pre-identification component according to the following formula:

[0023] W p = w mid -w rail (Formula 3)

[0024] Among them, W p is the horizontal position of the rail, w mid is the horizontal distance of the center of the anchor bolt in the direction perpendicular to the rail in the fastener coordinate system, w rail is the position of the bottom edge of the rail in the direction perpendicular to the rail in the fastener coordinate system.

[0025] In the first aspect, according to the set fine-tuning dimensions of the track, adjusting the identified target component includes:

[0026] Comparing the preset standard horizontal parameter of the rail with the identified horizontal offset parameter of the rail to determine whether there is a preset difference;

[0027] If there is, adjust the horizontal offset of the rail to the standard horizontal parameter.

[0028] In the first aspect, before comparing the pre-identification data with the pre-stored standard three-dimensional data model, the method further includes:

[0029] Pre-storing the standard data of all target components into the database, and the database is the storage end of a mobile terminal, a PC or the cloud.

[0030] In the first aspect, the method further includes:

[0031] Comparing the pre-identification data with the pre-stored standard three-dimensional data model. If the pre-identification data and the standard three-dimensional data model do not match, feedback the corresponding signal and mark the pre-identification data as unknown data.

[0032] In a first aspect, the method includes, after receiving the feedback signal:

[0033] Performing secondary identification on the marked unknown data;

[0034] If the unknown data does not match the standard 3D data model in the database, re-detect the standard 3D data model in the database.

[0035] In a second aspect, the present invention provides a processing device, including:

[0036] A processor and a memory, where a computer program is stored in the memory, and when the processor calls the computer program in the memory, it executes the method described in any one of the above.

[0037] Generally speaking, compared with the prior art through the above technical solutions conceived by the present invention, the following beneficial effects can be achieved:

[0038] 1. The design method of the track fine-tuning scheme based on the fastener point cloud model of the present invention first obtains the 3D point cloud data of the track, and then based on the 3D point cloud data, calls the point cloud post-processing algorithm to segment each pre-identified component of the fastener, and then further calculates the 3D point cloud data of the segmented pre-identified components, thereby accurately identifying the target component.

[0039] 2. The design method of the track fine-tuning scheme based on the fastener point cloud model of the present invention can confirm the model and size of the target component after identifying the target component, thereby providing data support for the precise adjustment of the track. Description of the Drawings

[0040] Figure 1 It is a flowchart of the design method of the track fine-tuning scheme based on the fastener point cloud model in the embodiment of the present invention;

[0041] Figure 2 It is a broken line graph of the insulation block accuracy analysis in the second embodiment of the present invention Figure 1 ;

[0042] Figure 3 It is a broken line graph of the insulation block accuracy analysis in the second embodiment of the present invention Figure 2 ;

[0043] Figure 4 It is a broken line graph of the insulation block accuracy analysis in the second embodiment of the present invention Figure 3 ;

[0044] Figure 5 It is a broken line graph of the insulation block accuracy analysis in the second embodiment of the present invention Figure 4 ;

[0045] Figure 6Precision analysis broken line of the insulating block in the second embodiment of the present invention Figure 5 ;

[0046] Figure 7 Precision analysis broken line of the thickness of the under-rail pad in the second embodiment of the present invention Figure 1 ;

[0047] Figure 8 Precision analysis broken line of the thickness of the under-rail pad in the second embodiment of the present invention Figure 2 ;

[0048] Figure 9 Precision analysis broken line of the thickness of the under-rail pad in the second embodiment of the present invention Figure 3 . Detailed implementation manners

[0049] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0050] Before the design method of the track fine-tuning scheme based on the fastener point cloud model of the present invention is described in detail, the fastener structure involved in the method of this embodiment will be disclosed to facilitate the understanding of the technology of this embodiment by those skilled in the art. First, the high-speed railway tracks in our country can be divided into two types: ballastless tracks and ballasted tracks. Among them, ballastless tracks mainly use WJ-7 type, WJ-8 type, and W300-1 type fasteners, and ballasted tracks mainly use elastic clip V type fasteners.

[0051] For the WJ-7 type fastener, it is composed of a T-shaped bolt, a nut, a flat washer, an elastic clip, an insulating block, a tie plate, an under-rail pad, an insulating buffer pad, a heavy spring washer, a flat spacer, an anchor bolt, and a pre-embedded sleeve. In addition, for the need of rail height adjustment, an under-rail height adjustment pad and an under-tie plate height adjustment pad are also included.

[0052] The WJ-7 type fastener system is mainly used for the CRTS I type slab ballastless track structure. The left and right adjustment amounts of a single rail are -6 to +6 mm, and it is a continuous stepless adjustment.

[0053] The specific adjustment method of the WJ-7 type fastener is as follows: The adjustment of the rail height position is completed by replacing the rail height adjustment pads under the rail, the height adjustment pads under the tie plate, and the insulating buffer pads. The vertical adjustment amount for a single rail is -4 to +26 mm. The rail height adjustment pads under the rail are divided into three specifications of 1, 2, and 5 mm according to the thickness. The total thickness of the rail height adjustment pads placed under the rail shall not be greater than 10 mm, and the number of the rail height adjustment pads under the rail shall not exceed two (excluding the 0.5 mm adjustment pads). To improve the vertical adjustment accuracy, a 0.5 mm adjustment shim is allowed to be used. The height adjustment pads under the tie plate have only one specification of 8 mm. The total number of the height adjustment pads under the tie plate inserted shall not exceed two, and the total thickness shall not exceed 16 mm. The insulating buffer pads are divided into two specifications of 2 mm and 6 mm, and 6 mm is used for normal installation. The configuration of the height adjustment fittings is shown in Table 1.

[0054] Table 1 Configuration Table of Height Adjustment Fittings for WJ-7 Type Fastener System

[0055]

[0056] For the WJ-7 type fastener, it is composed of screw spikes, flat washers, elastic bars, insulating gauge blocks, gauge brackets, pads under the rail, tie plates, elastic pads under the tie plate, and embedded sleeves. In addition, for the need of adjusting the rail height position, it also includes fine adjustment pads under the rail and height adjustment pads under the tie plate.

[0057] The specific adjustment method of the WJ-8 type fastener is as follows: The lateral adjustment of the WJ-8 type fastener is achieved by replacing the gauge brackets and insulating gauge blocks. The adjustment amount for a single rail is -7 to +7 mm. The gauge brackets are divided into five specifications of No. 2, 4, 7, 10, and 12, and No. 7 is used for standard configuration; the insulating gauge blocks are divided into five specifications of No. 7, 8, 9, 10, and 11, and No. 9 is used for standard configuration. To improve the lateral adjustment accuracy, a 0.5-step progression can be adopted, that is, in special cases, five specifications of 7.5, 8.5, 9.5, 10.5, and 11.5 can be used. The configuration of the gauge adjustment fittings is shown in Table 2.

[0058] Table 2 Configuration Table of Gauge Adjustment Fittings for WJ-8 Type Fastener System

[0059]

[0060] The vertical adjustment of the WJ-8 type fastener is completed by replacing the pads under the rail, the fine adjustment pads under the rail, and the height adjustment pads under the tie plate. The vertical adjustment amount for a single rail is -4 to +26 mm.

[0061] The under-rail pads are available in five specifications of 2, 3, 4, 5 and 6 mm, and 6 mm is used during normal installation; the under-rail fine-tuning pads are divided into three specifications according to thickness, namely 1, 2 and 5 mm. To improve the vertical adjustment accuracy, an adjustment shim of 0.5 mm is allowed to be used; the height-adjusting pads under the base plates are divided into two specifications according to thickness, namely 10 and 20 mm, and are used in pairs. The adjustment of the rail height position is completed by replacing the under-rail pads, under-rail fine-tuning pads and height-adjusting pads under the base plates. Each type of under-rail pad is divided into two types: constant resistance and small resistance. The adjustment range of the rail height position is -4 mm to +26 mm, and the specific configuration is shown in Table 3.

[0062] Table 3 Configuration Table of Height Adjustment Fittings for WJ-8 Fastener System

[0063] Adjustment of rail elevation Thickness of the pad under the rail Total thickness of the fine-tuning pad under the rail Elevation pad under the tie plate -4 2 0 0 -3 3 0 0 -2 4 0 0 -1 5 0 0 0 6 0 0 +1～+6 6 1～6 0 +7 3 0 10 +8 4 0 10 +9 5 0 10 +10 6 0 10 +11～+16 6 1～6 10 +17 3 0 20 +18 4 0 20 +19 5 0 20 +20 6 0 20 +21～+26 6 1～6 20

[0064] For the W300-1 type fastener, it is composed of elastic rail clips, insulating gaskets, gauge blocks, tie bolts, insulating sleeves, rail pads, base plates and elastic pads. In addition, for the need of rail height adjustment, height-adjusting pads are also included.

[0065] The W300-1 type fastener system is mainly used for CRTS II type slab and double-block ballastless track structures. The lateral adjustment is completed by replacing different gauge blocks. The lateral adjustment amount of a single rail is -8 to +8 mm. The standard gauge blocks are divided into two types: Wfp15a type blocks (applicable to 300-1a type fasteners) and Wfp15u type blocks (applicable to 300-1u type fasteners). To meet the need of rail left and right position adjustment, there are 16 specifications from Wfp15a±1 (Wfp15u±1) to Wfp15a±8 (Wfp15u±8), with each level being 1 mm. The configuration of gauge adjustment fittings is shown in Table 4.

[0066] Table 4 Configuration Table of Gauge Adjustment Fittings for W300-1 Type Fastener System

[0067]

[0068]

[0069]

[0070] The vertical adjustment of the W300-1 type fastener is achieved by replacing the rail pads, base plates and elastic pads. The vertical adjustment range for a single rail is -4 to +26 mm. The standard thickness of the rail pad (Zw692-6) is 6 mm. To meet the requirements of elevation adjustment, rail pads with thicknesses of 2, 3, 4, 5, 7, and 8 mm are provided. To improve the precision of vertical fine adjustment, a 0.5-mm rail pad is allowed to be used. The elastic elevation pads are available in two specifications: 6 and 10 mm. The elevation adjustment range of the 300-1 type fastener for the rail is -4 mm to +26 mm. The specific configurations are shown in Table 5.

[0071] Table 5 Configuration Table of Elevation Adjustment Fittings for W300-1 Type Fastener System

[0072]

[0073] The elastic clip V type fastener consists of screw spikes, flat washers, elastic clips, gauge blocks, rail pads and embedded sleeves, etc. In addition, for elevation adjustment needs, elevation pads are also included.

[0074] There are two types of V-type elastic clips, namely: W2 type elastic clips (with a diameter of 14 mm) used in general sections and X3 type elastic clips (with a diameter of 13 mm) that may be used on bridges. There are two types of rail pads, namely: rubber pads and composite pads that may be used on bridges. When it is necessary to reduce the track resistance on bridges, X3 type elastic clips and composite pads are used. The gauge blocks are available in seven specifications from No. 2 to No. 8. When the standard gauge is used, No. 4 and No. 6 are adopted. The elevation pads are available in four specifications according to thickness: 1 mm, 2 mm, 5 mm and 8 mm, and are placed between the rail pad and the rail bearing surface. At the fishplate, when it is difficult to install W2 type elastic clips and X3 type elastic clips on the small-number gauge blocks, elastic clip I type fasteners and A type elastic clips should be installed.

[0075] Example 1:

[0076] As Figure 1 shown, Example 1 of the present invention proposes a design method for the track fine adjustment scheme based on the fastener point cloud model. The design method for the track fine adjustment scheme based on the fastener point cloud model includes: obtaining the three-dimensional point cloud data of the track, where the three-dimensional point cloud data of the track includes sleeper area data and non-sleeper area data; segmenting the sleeper area data and the non-sleeper area data, and identifying the three-dimensional data of the fasteners and the three-dimensional data of the rails based on the sleeper area data; according to the three-dimensional data of the fasteners, calling a point cloud post-processing algorithm to segment each pre-identified component of the fasteners; obtaining the three-dimensional point cloud data of the pre-identified components; calculating the three-dimensional point cloud data of the pre-identified components to obtain pre-identified data, and comparing the pre-identified data with the standard three-dimensional data model pre-stored in the database to identify the part model; designing a scheme for adjusting or replacing the target components according to the fine adjustment dimensions of the track.

[0077] Specifically, for a design method of an orbit fine-tuning scheme based on a fastener point cloud model of the present invention, first obtain the three-dimensional point cloud data of the orbit, and then, based on the three-dimensional point cloud data, call a point cloud post-processing algorithm to segment each pre-identified component of the fastener. Further, calculate the three-dimensional point cloud data of the segmented pre-identified components, and then accurately identify the target components. After the target components are identified, the model and size of the target components can be confirmed, thereby providing data support for the precise adjustment of the orbit.

[0078] Further, obtaining the three-dimensional point cloud data of the orbit and segmenting the sleeper area data and the non-sleeper area data includes: obtaining the height data of each pre-identified fastener of the orbit; setting a standard height threshold; then comparing the heights of all pre-identified fasteners with the standard height threshold. If it is greater than the standard height threshold, it is determined as the sleeper area, and if it is less than the standard height threshold, it is determined as the non-sleeper area.

[0079] Among them, for the step of comparing the pre-identified data with the standard three-dimensional data model pre-stored in the database, it should be noted that the three-dimensional data model recognition method is the ICP least squares method to identify the best-matching fastener type and classify the three-dimensional data of the pre-identified fasteners. Specifically, set the fastener standard three-dimensional model as P and the point cloud data as Q, and each component in P has been pre-classified. Therefore, in the obtained point cloud Q, the component type of the point p in the standard three-dimensional model P corresponding to each point q is the component type of point q. By the method of nearest point search, the point p in the standard model P corresponding to the point q in the sampling point Q can be found, the component type of the point q can be obtained, and then through the clustering segmentation of the types, the three-dimensional point clouds of each component can be identified. The main components are the under-rail shim, gauge block, gauge stopper, elastic clip, bolt, rail (part of the rail in the fastener area), etc.

[0080] Further, before comparing the pre-identified data after three-dimensional point cloud calculation of the pre-identified components with the standard data of the target components in the pre-set database, the method further includes: pre-storing the standard data of all target components in the database, and the database is the storage end of a mobile terminal, a PC or the cloud.

[0081] Further, the method further includes: comparing the pre-identified data with the pre-stored standard three-dimensional data model. If the pre-identified data does not match the standard three-dimensional data model, feedback the corresponding signal and mark the pre-identified data as unknown data.

[0082] This is because the pre-identified data obtained initially is incorrect, resulting in a situation where it cannot be compared with the standard data in the database. For example, if the pre-identified component recognized is not part of the fastener, when comparing with the standard data, after a mismatch occurs, the mismatch signal is promptly fed back to notify the system or the staff for timely identification to avoid misidentification.

[0083] Further, after receiving the feedback signal, perform secondary identification on the marked unknown data. If the unknown data does not match the standard data in the database, re-check whether there is any missing in the standard three-dimensional data model in the database. If there is a missing, update the unknown data to the standard database. If there is no missing, determine that the unknown data is junk data and eliminate it to avoid affecting the subsequent track fine-tuning plan.

[0084] Further, the calculation of the three-dimensional point cloud data of the pre-identified component includes calculating the pre-identified data of the pre-identified component according to the following formula:

[0085] T R = h2 - h3 + T Iron -T Rail -T Rubber (Formula 1)

[0086] Among them, T R represents the thickness of the sub-rail pad; h2 represents the height of the edge of the rail bottom; h3 represents the height of the upper surface of the limit shoulder of the tie plate; T Iron represents the height difference between the upper surface of the limit shoulder of the tie plate and the upper surface of the center of the tie plate; T Rail represents the thickness of the rail bottom; T Rubber represents the thickness of the buffer pad. Obtain the data of the sub-rail pad according to the above formula. Compare the pre-identified data with the standard data in the database to identify the standard component corresponding to the pre-identified data;

[0087] Further, the calculation of the three-dimensional point cloud data of the pre-identified component includes calculating the pre-identified data of the pre-identified component according to the following formula:

[0088] T P = h3 - h5 - T Pillar -T Buffer (Formula 2)

[0089] Among them, T P represents the thickness of the shim under the tie plate; h3 represents the height of the upper surface of the limit shoulder of the tie plate; h5 represents the height of the track slab; T Pillar represents the height difference between the upper surface of the limit shoulder of the tie plate and the bottom surface of the tie plate; T Buffer represents the thickness of the insulating buffer pad.

[0090] Furthermore, calculating the three-dimensional point cloud data of the pre-recognized component includes calculating the pre-recognized data of the pre-recognized component according to the following formula:

[0091] W p =w mid -w rail (Formula 3)

[0092] Among them, W p is the horizontal position of the rail, w mid is the horizontal distance of the anchor bolt center in the direction perpendicular to the rail in the fastener coordinate system, w rail It is the position of the bottom edge of the rail in the direction perpendicular to the rail in the fastener coordinate system.

[0093] This is because, in order to maintain the standard track gauge of 1435mm and to ensure the smoothness of the rails, the horizontal position of the rails needs to be adjusted regularly or irregularly. The through hole through which the anchor bolt passes through the iron pad is elliptical, which ensures that the fastener system can be horizontally displaced within the elliptical through hole. For example, the horizontal translation range of the WJ-7 type fastener is ±6mm. That is, when the horizontal distance of the center of the anchor bolt in the direction perpendicular to the rail in the fastener coordinate system and the position of the bottom edge of the rail in the direction perpendicular to the rail in the fastener coordinate system are known, the horizontal offset of the rail can be calculated by subtracting the horizontal distances of the two fasteners in a pair of fastener systems.

[0094] It should be noted that track adjustment generally includes two aspects: track height adjustment and horizontal position adjustment. Specifically, in the track fine-tuning plan, it will be required to raise a certain sleeper position by x millimeters. The specific implementation plan is to replace the model combination of the rail height adjustment pads. In actual operation, without auxiliary equipment detection and corresponding detection methods to implement detection, users cannot know the height dimension parameters (data) of the track rails, and cannot make targeted adjustments to the corresponding model of rail pads. The calculation formula of this embodiment can be used to calculate the current rail height adjustment pad size of the rail, and then combined with the size (height) that needs to be adjusted, the rail height adjustment pad model combination is deduced, providing a design basis for the track height fine-tuning plan;

[0095] Similarly, during the track level adjustment process, the embodiments of the present invention can calculate the model of the current gauge baffle and gauge block, and then combine the horizontal amount that needs to be adjusted at that position to deduce the model of the gauge baffle and gauge block required for the track level fine-tuning solution.

[0096] Further, adjusting the identified target component according to the fine-tuning dimension of the set track includes: comparing the identified rail horizontal offset parameter with the preset standard rail horizontal parameter to determine whether there is a preset difference; if so, adjusting the horizontal offset of the rail to the standard horizontal parameter.

[0097] Further, an embodiment of the present invention provides a processing device, including: a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, it executes the method described in any one of the above.

[0098] Embodiment 2:

[0099] The present invention can quickly, accurately, and comprehensively identify the component models of track fasteners. When collecting the three-dimensional point clouds of the left and right WJ-8 type fasteners simultaneously at a speed of 5-10 km / h on a certain high-speed rail line, the size and specification models automatically identified for the fastener components based on the point cloud are compared with the size and specification accuracy of the components investigated manually on-site as follows:

[0100] I. Precision analysis of the insulating block:

[0101] The data recorded manually on-site and the output data of the detection device (IRC) are as follows in the table:

[0102]

[0103]

[0104] Plot the data as a line chart as Figures 2-6 shown. Subtract the output value of the detection device from the size of the insulating block recorded manually on-site to obtain the size error of the insulating block as Figure 6 shown:

[0105] According to the statistics of the above data table, the average error of the insulating block of the left outer fastener is 0.43 mm, and the standard deviation of the error is 0.29 mm; the average error of the insulating block of the left inner fastener is -0.43 mm, and the standard deviation of the error is 0.28 mm; the average error of the insulating block of the right inner fastener is -0.36 mm, and the standard deviation of the error is 0.20 mm; the average error of the insulating block of the right outer fastener is 0.35 mm, and the standard deviation of the error is 0.20 mm.

[0106] II. Precision analysis of the gauge block:

[0107]

[0108]

[0109] As can be seen from the above analysis, only 6 groups of gauge plates out of a total of 240 groups have inconsistent models. The possible reason for the analysis is that the models recorded on site are incorrect, and the accuracy rate of the gauge plates based on this data is 97.5%.

[0110] III. Analysis of the thickness accuracy of the under-rail pads:

[0111] Measure the total thickness of the pads on both the left and right sides every 5 sleepers, and the comparison data results are as follows:

[0112]

[0113] Plot the data as shown in Figures 7-9 shown; subtract the output value of the detection equipment from the pad thickness recorded manually on site to obtain the pad thickness error as shown in Figure 7 shown; the maximum pad thickness error < 1mm; the average error is -0.2mm; the standard deviation of the error is 0.27mm. Using the cumulative distribution function (CDF) of the normal distribution, according to the requirement of the target accuracy of 0.5mm, the proportion of the pad thickness error of -0.5 to 0.5mm is 86.20%.

[0114] Those skilled in the art can easily understand that the above is only a preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A design method for the track fine-tuning scheme based on the fastener point cloud model, characterized in that The design method of the track fine-tuning scheme based on the fastener point cloud model includes: Obtain the three-dimensional point cloud data of the track, and the three-dimensional point cloud data of the track includes sleeper area data and non-sleeper area data; Segment the sleeper area data and the non-sleeper area data, and identify the three-dimensional data of the fasteners and the three-dimensional data of the rails based on the sleeper area data; Based on the three-dimensional data of the fasteners, call the point cloud post-processing algorithm to segment each pre-identified component of the fasteners; Obtain the three-dimensional point cloud data of the pre-identified components; Calculate the three-dimensional point cloud data of the pre-identified components to obtain pre-identified data, and compare the pre-identified data with the standard three-dimensional data model pre-stored in the database to identify the model of the parts; Calculating the three-dimensional point cloud data of the pre-identified components includes calculating the pre-identified data of the pre-identified components according to the following formula: T R = h2 - h3 + T Iron -T Rail -T Rubber (Formula 1) Among them, T R represents the thickness of the track elevation pad; h2 represents the height of the edge of the rail web; h3 represents the height of the upper surface of the retaining shoulder of the tie plate; T Iron represents the height difference between the upper surface of the retaining shoulder of the tie plate and the upper surface of the center of the tie plate; T Rail represents the thickness of the rail web; T Rubber represents the thickness of the buffer pad; Calculating the three-dimensional point cloud data of the pre-identified components includes calculating the pre-identified data of the pre-identified components according to the following formula: T P = h3 - h5 - T Pillar -T Buffer (Formula 2) Among them, T P represents the thickness of the shim plate under the tie plate; h3 represents the height of the upper surface of the tie plate limit shoulder; h5 represents the height of the track slab; T Pillar represents the height difference between the upper surface of the tie plate limit shoulder and the bottom surface of the tie plate; T Buffer represents the thickness of the insulating buffer pad; Calculating the three-dimensional point cloud data of the pre-identified components includes calculating the pre-identified data of the pre-identified components according to the following formula: W p = w mid - w rail (Formula 3) Among them, W p is the horizontal position of the rail, and w mid is the horizontal distance of the center of the anchor bolt in the direction perpendicular to the rail in the fastener coordinate system, and w rail is the position of the bottom edge of the rail in the direction perpendicular to the rail in the fastener coordinate system; Based on the fine-tuning dimensions of the track, design a scheme for adjusting or replacing the pre-identified components.

2. The design method of the track fine adjustment scheme based on the fastener point cloud model according to claim 1, characterized in that, Obtain the three-dimensional point cloud data of the track, and segmenting the sleeper area data and the non-sleeper area data includes: Obtain the height data of each pre-identified fastener of the track; Set a standard height threshold; Compare the heights of all pre-identified fasteners with the standard height threshold. If it is greater than the standard height threshold, it is determined as the sleeper area. If it is less than the standard height threshold, it is determined as the non-sleeper area.

3. The design method of the track fine adjustment scheme based on the fastener point cloud model according to claim 1, characterized in that According to the set fine-tuning dimensions of the track, adjusting the identified pre-identified components includes: Compare with the identified rail horizontal offset parameter according to the preset standard rail horizontal parameter, and judge whether there is a preset difference; If so, adjust the horizontal offset of the rail to the standard horizontal parameter.

4. The design method of the track fine adjustment scheme based on the fastener point cloud model according to claim 1, characterized in that, Before comparing the pre-identified data with the pre-stored standard three-dimensional data model, the method further includes: Pre-store the standard data of all target components into the database, and the database is the storage end of a mobile terminal, a PC or the cloud.

5. The design method of the track fine adjustment scheme based on the fastener point cloud model according to claim 1, characterized in that Compare the pre-identified data with the pre-stored standard three-dimensional data model. If the pre-identified data does not match the standard three-dimensional data model, feedback the corresponding signal and mark the pre-identified data as unknown data.

6. The design method of the track fine-tuning scheme based on the fastener point cloud model according to claim 5, characterized in that, The method includes, after receiving the feedback signal: Perform secondary identification on the marked unknown data; If the unknown data does not match the standard three-dimensional data model in the database, re-detect the standard three-dimensional data model in the database.

7. A processing device, characterized in that, Includes: A processor and a memory, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it executes the method according to any one of claims 1 to 6.

Images