A method for controlling closed-loop grouting operations between interlayer gaps in high-speed railway ballastless track

By using a robotic system for multimodal sensor data fusion and adaptive control, the entire process of repairing gaps in ballastless tracks of high-speed railways has been automated. This solves the problem of disconnect between inspection and construction in existing technologies and improves the consistency and reliability of repair quality.

CN123109015APending Publication Date: 2026-11-17RAILWAY CONSTR RES INST OF CHINA ACAD OF RAILWAY SCI CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611624024.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-20
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

In existing methods for repairing joints in ballastless tracks of high-speed railways, the detection, construction, and evaluation processes are disconnected, and the grouting process parameters lack adaptive control. This results in the repair quality being highly dependent on manual experience and making it difficult to guarantee consistency and repeatability.

Method used

A robotic system is used to fuse multimodal sensor data, extract the geometric parameters of the joint, generate hole layout coordinates and grouting process parameters, and realize the full-process automated control of drilling, hole cleaning, laying of grouting pipes, grouting and quality evaluation. Combined with adaptive control law, the grouting pressure is adjusted to ensure grout fullness and repair quality.

Benefits of technology

It achieves fully automated closed-loop control from disease identification to repair acceptance, improving the consistency and reliability of joint repair quality, and ensuring precise control of grouting volume and objective evaluation of repair quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123109015A_ABST
    Figure CN123109015A_ABST
Patent Text Reader

Abstract

This invention discloses a closed-loop grouting operation control method for interlayer gaps in high-speed railway ballastless track, relating to the field of maintenance and repair of high-speed railway ballastless track. The method includes: a robot self-inspecting and navigating to the work starting point; extracting gap geometric parameters based on multimodal sensor data to generate hole layout coordinates and grouting process parameters; performing drilling and hole cleaning operations to obtain grouting channels; laying grouting pipes in each grouting channel and sealing the gap edge to establish a grouting channel network; performing hole-by-hole grouting through the grouting channel network and adjusting the grouting pressure to complete all grouting operations; cutting off the exposed portion of each grouting pipe to be flush with the track slab surface; and evaluating the repair quality based on the detection data of the repair area to generate quality evaluation data. This method achieves closed-loop control throughout the entire process from defect identification to repair acceptance, improving the consistency and reliability of gap repair quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of maintenance and repair of ballastless tracks for high-speed railways, and more specifically to a method for controlling closed-loop grouting operations between interlayer gaps in ballastless tracks for high-speed railways. Background Technology

[0002] Ballastless track for high-speed railways has become the main structural form of high-speed railway lines due to its advantages such as high stability and smoothness. However, under the long-term coupling effect of temperature load, train dynamic load and foundation deformation, the interface between the track slab and the lower support layer (such as CA mortar filling layer or base plate) is prone to delamination and separation. The appearance of separation not only weakens the overall structure, but also provides a channel for corrosive media such as rainwater and chloride ions. In severe cases, it may cause the track slab to warp or even break, directly threatening the safety of train operation.

[0003] Currently, the main method for treating joints in ballastless tracks is grouting. Existing methods typically rely on manual inspection or independent testing equipment for joint detection and location, while the design of the grouting layout is largely based on the operator's field experience. Grouting operations often require separate equipment or devices. This separation of detection, design, and construction results in a long information transmission chain from defect discovery to repair completion, lacking unified data benchmarks and effective coordination mechanisms between different processes, easily leading to information gaps and process interruptions. Furthermore, existing methods often use fixed values ​​or rely on manual adjustment for grouting pressure control, making it difficult to adaptively adjust based on the actual geometry of the joint and the real-time status during grouting. After repair, quality evaluation also primarily relies on manual visual inspection, lacking objective assessment methods.

[0004] Furthermore, existing methods often focus on improving specific processes (such as grouting materials, grouting devices, or single testing methods), but fail to address the issues of data integration and process coordination throughout the entire process from defect identification to repair acceptance. For example, the extraction of joint geometry parameters and the generation of hole layout schemes lack a linkage based on the same data source; the setting of grouting process parameters cannot be dynamically adjusted according to joint level and real-time status data; and the quality evaluation after repair lacks a benchmark for comparison with the test data before repair. These deficiencies lead to a high dependence on manual experience in repair quality and make it difficult to ensure the consistency and repeatability of repair effects in different work areas.

[0005] Therefore, how to design a closed-loop grouting operation control method for interlayer gaps in high-speed railway ballastless track, realize the closed-loop automatic operation of the entire process from defect identification to repair acceptance, and improve the consistency of repair quality is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] In view of this, the present invention provides a closed-loop grouting operation control method for interlayer gaps in high-speed railway ballastless track, which aims to solve the problems of disconnection between detection, construction and evaluation links and lack of adaptive adjustment of grouting process parameters in existing gap repair methods, thereby realizing automatic closed-loop control of the entire process from defect identification to repair acceptance, and improving the consistency and reliability of gap repair quality.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] A method for controlling closed-loop grouting operations between interlayer gaps in high-speed railway ballastless track includes the following steps: S1. Perform a self-check of the robot system and navigate to the starting point of the target work area; S2. Control the robot system to move along the work section and acquire multimodal sensing data. Based on the multimodal sensing data, extract the joint geometry parameters and generate the hole layout coordinates and grouting process parameters for each grouting hole. S3. Control the robot system to perform drilling and hole cleaning operations according to the hole layout coordinates to obtain grouting channels; S4. Based on the hole coordinates, control the robot system to lay grouting pipes in each grouting channel and seal the edge of the joint, establishing a grouting channel network that connects each grouting pipe with the joint cavity. S5. According to the grouting process parameters, grouting is performed hole by hole through the grouting channel network, and the grouting pressure is adjusted based on the status data until the fullness judgment condition is met, then switch to the next grouting hole to complete all grouting operations. S6. Control the robot system to cut off the exposed part of each grouting pipe until it is flush with the surface of the track slab; S7. Assess the repair quality by combining the detection data of the repaired area and generate quality evaluation data.

[0009] Preferably, in step S2, extracting the gap geometry parameters based on the multimodal sensing data includes: Using the positional pose information as a spatial reference, the extended Kalman filter algorithm is used to perform spatiotemporal synchronous fusion of multimodal sensing data, and output the three-dimensional contour point set of the gap region; the multimodal sensing data includes three-dimensional lidar point cloud, visible light image and infrared thermal image; Based on a plane segmentation and region growing algorithm, the track slab reference plane is fitted from the set of 3D contour points. The projection contour of the gap on the reference plane is extracted, and the geometric parameters of the gap are calculated. The geometric parameters of the gap include the average width. Maximum width Maximum depth Length L and azimuth angle θ.

[0010] Preferably, in step S2, generating the hole layout coordinates and grouting process parameters for each grouting hole includes: Based on maximum width Determine the gap level and output the gap level indicator G; The hole arrangement is determined according to the gap level identifier G. Based on the gap length L and the hole arrangement, the minimum safe distance between each hole and the fastener is used as a constraint to generate the hole coordinates of each grouting hole, so that the grouting holes are arranged along the gap direction. The diameter of each grouting hole is determined according to the joint level identifier G, and the maximum joint depth is determined according to the joint level identifier G. Determine the depth of each grouting hole; determine the grouting pressure range based on the joint level identifier G, as a grouting process parameter.

[0011] Preferably, S3 includes: The drilling operation motion path is planned based on the hole layout coordinates, and the drilling path planning result is obtained; According to the drilling path planning results, the machine moves sequentially to each hole location and performs drilling according to the hole diameter and depth corresponding to each grouting hole. During drilling, the drill rod feed resistance is monitored in real time. When the feed resistance exceeds the safety threshold, the feed is stopped and the hole position is skipped. After each hole is drilled, debris inside the hole is blown out with a preset air pressure and the hole wall is cleaned with a preset rotation speed to obtain the grouting channel.

[0012] Preferably, the obtained drilling path planning result includes: For each target hole coordinate, the corresponding target pose of the robotic arm end effector is solved using an inverse kinematics numerical iterative algorithm. ; Based on the current joint angle of the robotic arm As the initial configuration, with the target pose. To terminate the constraint, an initial joint trajectory from the initial configuration to the target configuration is generated in the joint space using fifth-order polynomial interpolation. Collision detection is performed in the preset configuration space. If the initial joint trajectory interferes with the fastener obstacle model, an artificial potential field is introduced to apply a repulsive force to the trajectory segment where the interference occurs for obstacle avoidance correction. Local trajectory replanning is performed with the optimization objectives of smooth joint velocity and minimum energy consumption to generate the collision-free optimal joint trajectory q(t). The drilling path planning result is formed by splicing the joint trajectories of each segment.

[0013] Preferably, in step S5, adjusting the grouting pressure based on the status data includes: Based on the current grouting pressure p(t) and cumulative grouting volume V(t) during the grouting process; The current grouting pressure p(t) and the preset grouting pressure benchmark value are used as the reference values. The deviation e(t) between them, and the rate of change of grouting pressure (t) is used as the state input, and the optimal grouting pressure setpoint for the next time step is calculated using an adaptive control law. (t+1), and the actual grouting pressure is made to track the optimal grouting pressure setting value through the PID control algorithm.

[0014] Preferably, in step S5, the saturation determination condition is: the cumulative grouting volume V(t) reaches the estimated grouting volume. The preset ratio; The estimated grouting volume Represented as:

[0015] Where α is the shape compensation coefficient. The average width of the seam. This represents the maximum depth of the gap. This is the seam length. This is the loss coefficient of the grouting material.

[0016] Preferably, S7 includes: Combining the full-coverage image data of the repair area, the continuity of the sealing adhesive and the surface flatness deviation are extracted through image segmentation. When the proportion of missing sealing adhesive is less than the first preset threshold and the surface flatness deviation is less than the second preset threshold, the sealing quality is determined to be qualified. Based on the ultrasonic scanning data of the repair area, the proportion of the interface debonding area is calculated by analyzing the ratio of the reflected wave amplitude to the reference wave amplitude. When the proportion of the interface debonding area is less than the third preset threshold, the interface bonding state is judged to be qualified. When both the edge sealing quality and the interface bonding state are qualified, the comprehensive evaluation result is qualified; otherwise, it is unqualified, and the unqualified location and index deviation value are marked to generate quality evaluation data.

[0017] As can be seen from the above technical solution, compared with the prior art, the technical solution of the present invention has the following beneficial effects: 1. This method extracts the geometric parameters of the joint based on multimodal sensor data fusion and generates the hole layout coordinates and grouting process parameters. According to the hole layout coordinates, it sequentially executes the fully automated process of drilling, hole cleaning, pipe laying, edge sealing, grouting and pipe cutting. It realizes the effective connection from joint detection and scheme generation to repair operation execution, avoids the process interruption caused by the separation of detection and repair links, and ensures the continuity and consistency of the entire repair process.

[0018] 2. The grouting pressure is adjusted in real time based on the grouting status data, and the fullness is judged by the preset ratio of the cumulative grouting volume reaching the estimated value. This achieves precise control of the grouting volume and quantitative judgment of the grouting fullness, avoiding insufficient or excessive grouting. At the same time, the sealing quality and interface bonding status are evaluated by combining visual image segmentation and ultrasonic reflection wave analysis, which realizes the comprehensive evaluation of repair quality and precise location of unqualified positions, ensuring the reliability of the evaluation results. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 A flowchart of a closed-loop grouting operation control method for interlayer joints in high-speed railway ballastless track provided in this embodiment of the invention; Figure 2 This is a schematic diagram of the process of obtaining grouting channels provided in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] like Figure 1 As shown in the figure, this embodiment provides a closed-loop grouting operation control method for interlayer joints in high-speed railway ballastless track, including the following steps: S1. Perform a self-check of the robot system and navigate to the starting point of the target work area; S2. Control the robot system to move along the work section and acquire multimodal sensing data. Based on the multimodal sensing data, extract the joint geometry parameters and generate the hole layout coordinates and grouting process parameters for each grouting hole. S3. Control the robot system to perform drilling and hole cleaning operations according to the hole layout coordinates to obtain grouting channels; S4. Based on the hole coordinates, control the robot system to lay grouting pipes in each grouting channel and seal the edge of the joint, establishing a grouting channel network that connects each grouting pipe with the joint cavity. S5. According to the grouting process parameters, grouting is performed hole by hole through the grouting channel network, and the grouting pressure is adjusted based on the status data until the fullness judgment condition is met, then switch to the next grouting hole to complete all grouting operations. S6. Control the robot system to cut off the exposed part of each grouting pipe until it is flush with the surface of the track slab; S7. Assess the repair quality by combining the detection data of the repaired area and generate quality evaluation data.

[0023] This method integrates joint detection, scheme generation, borehole cleaning, grouting pipe laying and sealing, adaptive grouting, pipe cutting and leveling, and quality evaluation into a unified automated operation scheme. The steps are based on the coordinates of the holes, grouting process parameters, grouting duct status, and detection data for transmission and execution, realizing full-process data connection and automatic process connection from defect identification to repair acceptance. At the same time, during the grouting process, the grouting pressure is dynamically adjusted based on the status data and the grouting termination is controlled by the fullness judgment condition, which effectively ensures the density of grout filling under different joint conditions and improves the stability and controllability of repair quality.

[0024] The following provides a further explanation of each step and related features in the above method; In this embodiment, S1 involves performing a self-check on the robot system and navigating to the starting point of the target work area; including: After powering on, it performs hardware self-test and sensor calibration verification. Once normal is confirmed, it obtains work section information including mileage range via wireless communication. Based on the work area information, and constrained by the absolute position given by the positioning system and the mileage range, a global path planning algorithm is used to generate the optimal global path from the current position to the target work area. During the journey, a local path planning algorithm is used to integrate real-time obstacle detection data for obstacle avoidance. After reaching the starting point of the target work section, the vehicle is precisely positioned and parked to obtain the parking position information, which is then used as the starting point of the operation.

[0025] This step ensures the equipment is in normal initial condition through system self-testing and sensor calibration. Based on the work area information, combined with global path planning and local obstacle avoidance strategies, the robot is controlled to autonomously drive to the starting point of the target work area and accurately locate and stop, providing a precise spatial reference and starting pose for subsequent detection and operation.

[0026] In this embodiment S2, the robot system is controlled to move along the work section and acquire multimodal sensing data. Based on the multimodal sensing data, the geometric parameters of the joint are extracted, and the layout coordinates and grouting process parameters of each grouting hole are generated. The extraction of gap geometry parameters based on the multimodal sensing data includes: Using the positional pose information as a spatial reference, the extended Kalman filter algorithm is used to perform spatiotemporal synchronous fusion of multimodal sensing data, and output the three-dimensional contour point set of the gap region; the multimodal sensing data includes three-dimensional lidar point cloud, visible light image and infrared thermal image; Based on a plane segmentation and region growing algorithm, the track slab reference plane is fitted from the set of 3D contour points. The projection contour of the gap on the reference plane is extracted, and the geometric parameters of the gap are calculated. The geometric parameters of the gap include the average width. Maximum width Maximum depth Length L and azimuth angle θ.

[0027] Furthermore, the coordinates of each grouting hole and the grouting process parameters are generated, including: Based on maximum width Determine the gap level and output the gap level indicator G; The hole arrangement is determined according to the gap level identifier G. Based on the gap length L and the hole arrangement, the minimum safe distance between each hole and the fastener is used as a constraint to generate the hole coordinates of each grouting hole, so that the grouting holes are arranged along the gap direction. The diameter of each grouting hole is determined according to the joint level identifier G, and the maximum joint depth is determined according to the joint level identifier G. Determine the depth of each grouting hole; determine the grouting pressure range based on the joint level identifier G, as a grouting process parameter.

[0028] Specifically, the severity level is determined based on the maximum width of the joint, and the joint level identifier G is output. In this embodiment, if the maximum width is ≥3.0 mm, it is judged as Level I; if the maximum width is between 1.5 mm and 3.0 mm, it is judged as Level II; if the maximum width is <1.5 mm, it is judged as Level III. Different levels correspond to different hole layout strategies and grouting process parameters. Furthermore, the arrangement of grout holes is determined based on the joint grade designation G. For Grade I joints, a double-row arrangement is adopted, that is, two rows of grout holes are arranged along the joint direction, with a row spacing of 100 mm and a hole spacing of 250 mm. For Grade II joints, a single-row arrangement is adopted, with a hole spacing of 350 mm. For Grade III joints, a single-row arrangement is also adopted, but the hole spacing can be appropriately increased to 400 mm. Furthermore, based on the hole arrangement pattern and gap length L determined by the gap level identifier G, and combined with the minimum safety distance constraint between each hole position and the fastener (the minimum safety distance constraint is 0.3 m in this embodiment), the hole coordinates of each grouting hole are generated; specifically, taking the azimuth angle of the gap direction as the reference direction, the grouting holes and venting holes are arranged alternately at equal intervals along the gap extension direction according to the above hole spacing, and the starting end of the gap is used as the reference point for the first hole position. The offset of each hole position along the gap direction is calculated in sequence, and the spatial coordinates of each hole position are determined in combination with the normal of the track plate surface, so that the grouting holes are evenly arranged along the gap direction and avoid the fastener position. Furthermore, the diameter of each grouting hole is determined according to the joint level identifier G. In this embodiment, a 10 mm diameter hole is used for Level I, and an 8 mm diameter hole is used for Levels II and III. The depth of each grouting hole is determined according to the maximum joint depth. The grouting pressure range is determined according to the joint level identifier G. In this embodiment, 0.5 MPa is used for Level I, 0.35 MPa for Level II, and 0.25 MPa for Level III, as grouting process parameters. In this step, the stationary pose information is used as a spatial reference. The extended Kalman filter algorithm is used to perform spatiotemporal fusion of multi-source sensor data to output a three-dimensional contour point set of the gap region. Then, the geometric parameters of the gap are extracted based on the plane segmentation and region growth algorithm. The gap level identifier drives the differentiated configuration of parameters such as hole layout, hole spacing, hole diameter, hole depth and grouting pressure to realize the generation of adaptive hole layout schemes for gaps of different severity levels.

[0029] like Figure 2 As shown, in this embodiment, S3 involves controlling the robot system to perform drilling and hole cleaning operations based on the hole layout coordinates to obtain grouting channels; including: The drilling operation motion path is planned based on the hole layout coordinates, and the drilling path planning result is obtained; According to the drilling path planning results, the machine moves sequentially to each hole location and performs drilling according to the hole diameter and depth corresponding to each grouting hole. During drilling, the drill rod feed resistance is monitored in real time. When the feed resistance exceeds the safety threshold, the feed is stopped and the hole position is skipped. After each hole is drilled, debris inside the hole is blown out with a preset air pressure and the hole wall is cleaned with a preset rotation speed to obtain the grouting channel.

[0030] Furthermore, the borehole path planning results include: For each target hole coordinate, the corresponding target pose of the robotic arm end effector is solved using an inverse kinematics numerical iterative algorithm. ; Based on the current joint angle of the robotic arm As the initial configuration, with the target pose. To terminate the constraint, an initial joint trajectory from the initial configuration to the target configuration is generated in the joint space using fifth-order polynomial interpolation. Collision detection is performed in the preset configuration space. If the initial joint trajectory interferes with the fastener obstacle model, an artificial potential field is introduced to apply a repulsive force to the trajectory segment where the interference occurs for obstacle avoidance correction. Local trajectory replanning is performed with the optimization objectives of smooth joint velocity and minimum energy consumption to generate the collision-free optimal joint trajectory q(t). The drilling path planning result is formed by splicing the joint trajectories of each segment.

[0031] In embodiment S4, the robot system is controlled to lay grouting pipes in each grouting channel according to the hole coordinates, and the joint edge is sealed to establish a grouting channel network connecting each grouting pipe with the joint cavity; wherein, laying grouting pipes in each grouting channel includes: Match the prefabricated grouting pipes of the corresponding specifications according to the diameter of each grouting hole, and press the grouting pipes into each grouting channel in sequence according to the hole layout order, so that the outer wall of the grouting pipe and the hole wall are sealed, and the pipe opening is higher than the predetermined height of the track slab surface.

[0032] Furthermore, sealing the seam edge includes: The adhesive application path is generated based on the azimuth angle θ, and the sealing adhesive is continuously applied along the outer edge of the seam. The adhesive thickness is controlled to the preset thickness. After the adhesive is applied, the initial curing time of the edge sealing adhesive is calculated based on the current ambient temperature. Heating is started when the ambient temperature is lower than the preset temperature threshold.

[0033] This step aims to establish a closed grouting channel network that connects each grouting pipe to the joint cavity, providing a sealed channel for subsequent grouting operations.

[0034] In this embodiment, S5, grouting is performed hole by hole through the grouting channel network according to the grouting process parameters, and the grouting pressure is adjusted based on the status data until the fullness judgment condition is met, and then the process is switched to the next grouting hole to complete all grouting operations. Adjusting grouting pressure based on status data includes: Based on the current grouting pressure p(t) and cumulative grouting volume V(t) during the grouting process; The current grouting pressure p(t) and the preset grouting pressure benchmark value are used as the reference values. The deviation e(t) between them, and the rate of change of grouting pressure (t) is used as the state input, and the optimal grouting pressure setpoint for the next time step is calculated using an adaptive control law. (t+1), and the actual grouting pressure is made to track the optimal grouting pressure setting value through the PID control algorithm.

[0035] Furthermore, the saturation condition is: the cumulative grouting volume V(t) reaches the estimated grouting volume. The preset ratio; in this embodiment, the pre-review ratio can be set to 85%; Estimated grouting volume Represented as:

[0036] Where α is the shape compensation coefficient. The average width of the seam. This represents the maximum depth of the gap. This is the seam length. This is the loss coefficient of the grouting material.

[0037] It injects grouting material hole by hole through a network of grouting channels. During the grouting process, the grouting pressure deviation and pressure change rate are used as state inputs. An adaptive control law is used to dynamically adjust the grouting pressure setpoint and a PID algorithm is used to track the actual pressure. Combined with the estimated grouting volume based on the joint geometry parameters, a fullness judgment condition is constructed to accurately determine the grouting termination time of each grouting hole. This effectively avoids under-grouting or over-grouting and improves the density and uniformity of the grout filling.

[0038] In embodiment S6, controlling the robot system to cut off the exposed portions of each grouting pipe until they are flush with the surface of the track slab includes: Based on the exposed height data of each grouting pipe, the cutting position is set within a preset height range from the surface of the track slab, and the exposed part of each grouting pipe is removed by rotating circumferential cutting.

[0039] In this embodiment, S7, the repair quality is assessed by combining the detection data of the repaired area, and quality evaluation data is generated; including: Combining the full-coverage image data of the repair area, the continuity of the sealing adhesive and the surface flatness deviation are extracted through image segmentation. When the proportion of missing sealing adhesive is less than the first preset threshold and the surface flatness deviation is less than the second preset threshold, the sealing quality is determined to be qualified. Based on the ultrasonic scanning data of the repair area, the proportion of the interface debonding area is calculated by analyzing the ratio of the reflected wave amplitude to the reference wave amplitude. When the proportion of the interface debonding area is less than the third preset threshold, the interface bonding state is judged to be qualified. When both the edge sealing quality and the interface bonding state are qualified, the comprehensive evaluation result is qualified; otherwise, it is unqualified, and the unqualified location and index deviation value are marked to generate quality evaluation data.

[0040] In this step, the integrity of the sealing adhesive and the surface flatness are detected by full-coverage image data, and the interface bonding status is evaluated by analyzing the reflected wave amplitude through ultrasonic scanning data. The evaluation conclusion of the repair quality is generated by combining the judgment results of the two indicators, thus realizing the objective quantitative assessment of the repair quality.

[0041] Furthermore, it also includes encapsulating all raw sensor data, process parameters, and quality evaluation data generated during the operation into data packets in a unified timestamp format, and uploading them to the remote monitoring platform database via wireless communication.

[0042] The closed-loop grouting operation control method for interlayer gaps in high-speed railway ballastless track in this embodiment integrates gap detection, hole planning, drilling and cleaning, grouting pipe laying and sealing, adaptive grouting, pipe cutting and leveling, and quality evaluation into a data-driven closed-loop operation process. Each step uses the stopping position information, gap geometric parameters, hole coordinates, grouting process parameters, grouting channel network, and detection data as the basis for transmission and execution. This effectively solves the technical problems of discrete procedures, parameter dependence on manual experience, and difficulty in quantifying and tracing repair quality in existing gap repair methods. It enables the complete operation of high-speed railway ballastless track gap repair to be completed independently within a single nighttime track maintenance window, improving the consistency and controllability of repair quality.

[0043] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0044] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling closed-loop grouting operations between interlayer gaps in high-speed railway ballastless track, characterized in that, Includes the following steps: S1. Perform a self-check of the robot system and navigate to the starting point of the target work area; S2. Control the robot system to move along the work section and acquire multimodal sensing data. Based on the multimodal sensing data, extract the joint geometry parameters and generate the hole layout coordinates and grouting process parameters for each grouting hole. S3. Control the robot system to perform drilling and hole cleaning operations according to the hole layout coordinates to obtain grouting channels; S4. Based on the hole coordinates, control the robot system to lay grouting pipes in each grouting channel and seal the edge of the joint, establishing a grouting channel network that connects each grouting pipe with the joint cavity. S5. According to the grouting process parameters, grouting is performed hole by hole through the grouting channel network, and the grouting pressure is adjusted based on the status data until the fullness judgment condition is met, then switch to the next grouting hole to complete all grouting operations. S6. Control the robot system to cut off the exposed part of each grouting pipe until it is flush with the surface of the track slab; S7. Assess the repair quality by combining the detection data of the repaired area and generate quality evaluation data.

2. The method for controlling closed-loop grouting operations between interlayer gaps in high-speed railway ballastless track according to claim 1, characterized in that, In step S2, extracting the gap geometry parameters based on the multimodal sensing data includes: Using the positional pose information as a spatial reference, the extended Kalman filter algorithm is used to perform spatiotemporal synchronous fusion of multimodal sensing data, and output the three-dimensional contour point set of the gap region; the multimodal sensing data includes three-dimensional lidar point cloud, visible light image and infrared thermal image; Based on a plane segmentation and region growing algorithm, the track slab reference plane is fitted from the set of 3D contour points. The projection contour of the gap on the reference plane is extracted, and the geometric parameters of the gap are calculated. The geometric parameters of the gap include the average width. Maximum width Maximum depth Length L and azimuth angle θ.

3. The method for controlling closed-loop grouting operations between layers of ballastless track in high-speed railways according to claim 1, characterized in that, In step S2, the coordinates of each grouting hole and the grouting process parameters are generated, including: Based on maximum width Determine the gap level and output the gap level indicator G; The hole arrangement is determined according to the gap level identifier G. Based on the gap length L and the hole arrangement, the minimum safe distance between each hole and the fastener is used as a constraint to generate the hole coordinates of each grouting hole, so that the grouting holes are arranged along the gap direction. The diameter of each grouting hole is determined according to the joint level identifier G, and the maximum joint depth is determined according to the joint level identifier G. Determine the depth of each grouting hole; determine the grouting pressure range based on the joint level identifier G, as a grouting process parameter.

4. The method for controlling closed-loop grouting operations between interlayer gaps in high-speed railway ballastless track according to claim 1, characterized in that, S3 includes: The drilling operation motion path is planned based on the hole layout coordinates, and the drilling path planning result is obtained; According to the drilling path planning results, the machine moves sequentially to each hole location and performs drilling according to the hole diameter and depth corresponding to each grouting hole. During drilling, the drill rod feed resistance is monitored in real time. When the feed resistance exceeds the safety threshold, the feed is stopped and the hole position is skipped. After each hole is drilled, debris inside the hole is blown out with a preset air pressure and the hole wall is cleaned with a preset rotation speed to obtain the grouting channel.

5. The method for controlling closed-loop grouting operations between layers of ballastless track in high-speed railways according to claim 1, characterized in that, The obtained borehole path planning results include: For each target hole coordinate, the corresponding target pose of the robotic arm end effector is solved using an inverse kinematics numerical iterative algorithm. ; Based on the current joint angle of the robotic arm As the initial configuration, with the target pose. To terminate the constraint, an initial joint trajectory from the initial configuration to the target configuration is generated in the joint space using fifth-order polynomial interpolation. Collision detection is performed in the preset configuration space. If the initial joint trajectory interferes with the fastener obstacle model, an artificial potential field is introduced to apply a repulsive force to the trajectory segment where the interference occurs for obstacle avoidance correction. Local trajectory replanning is performed with the optimization objectives of smooth joint velocity and minimum energy consumption to generate the collision-free optimal joint trajectory q(t). The drilling path planning result is formed by splicing the joint trajectories of each segment.

6. The method for controlling closed-loop grouting operations between layers of ballastless track in high-speed railways according to claim 1, characterized in that, In step S5, adjusting the grouting pressure based on the status data includes: Based on the current grouting pressure p(t) and cumulative grouting volume V(t) during the grouting process; The current grouting pressure p(t) and the preset grouting pressure benchmark value are used as the reference values. The deviation e(t) between them, and the rate of change of grouting pressure (t) is used as the state input, and the optimal grouting pressure setpoint for the next time step is calculated using an adaptive control law. (t+1), and the actual grouting pressure is made to track the optimal grouting pressure setting value through the PID control algorithm.

7. The method for controlling closed-loop grouting operations between interlayer gaps in high-speed railway ballastless track according to claim 1, characterized in that, In S5, the saturation determination condition is: the cumulative grouting volume V(t) reaches the estimated grouting volume. The preset ratio; The estimated grouting volume Represented as: Where α is the shape compensation coefficient. The average width of the seam. This represents the maximum depth of the gap. This is the seam length. This is the loss coefficient of the grouting material.

8. The method for controlling closed-loop grouting operations between layers of ballastless track in high-speed railways according to claim 1, characterized in that, S7 includes: Combining the full-coverage image data of the repair area, the continuity of the sealing adhesive and the surface flatness deviation are extracted through image segmentation. When the proportion of missing sealing adhesive is less than the first preset threshold and the surface flatness deviation is less than the second preset threshold, the sealing quality is determined to be qualified. Based on the ultrasonic scanning data of the repair area, the proportion of the interface debonding area is calculated by analyzing the ratio of the reflected wave amplitude to the reference wave amplitude. When the proportion of the interface debonding area is less than the third preset threshold, the interface bonding state is judged to be qualified. When both the edge sealing quality and the interface bonding state are qualified, the comprehensive evaluation result is qualified; otherwise, it is unqualified, and the unqualified location and index deviation value are marked to generate quality evaluation data.