Intelligent vibration flattening system for municipal road construction based on multi-source detection data

Abstract

The present application relates to the technical field of municipal road construction, and particularly relates to a municipal road construction intelligent vibration flattening system based on multi-source detection data. The vibration flattening system comprises a vibration flattening monitoring device, a vibration flattening actuator and an auxiliary moving platform; a data acquisition module acquires multi-source data based on a first sensor group and a second sensor group; a special-shaped area determination module is used to segment and extract the boundary of a special-shaped area; a detection blind area identification module marks a blind area according to a sensor coverage and a coverage benchmark; a time-space prediction compensation module compensates blind area data; a model construction module constructs a three-dimensional digital surface model of a construction area; a regional vibration flattening strategy generation module generates a corresponding vibration flattening strategy for the corresponding area based on the three-dimensional digital surface model; an execution module executes the corresponding strategy; and an analysis module determines the vibration flattening state based on a three-dimensional micro-terrain tolerance and determines relevant parameters accordingly. The present application improves the vibration flattening precision of municipal road construction.

Description

Technical Field

[0001] This invention relates to the field of municipal road construction technology, and in particular to an intelligent vibration leveling system for municipal road construction based on multi-source detection data. Background Technology

[0002] Vibratory leveling is a crucial process in road construction, referring to the compaction and smoothing of paved concrete or asphalt materials using a vibrating device to achieve the designed density and smoothness. Traditional vibratory leveling operations often rely on workers holding vibrating plates or operating simple machinery, resulting in low construction accuracy, poor efficiency, and inconsistent quality. In recent years, with the development of intelligent construction technology, intelligent vibratory leveling systems equipped with GPS / BeiDou positioning, laser sensing, and other detection devices have emerged, achieving a certain degree of automated control of vibratory leveling operations. For example, 3D intelligent paving systems acquire three-dimensional coordinate data of the roadbed through GPS and laser reference stations, driving the paving slab to automatically level; edge detection systems identify the paving edge positions by emitting laser pulse sequences in multiple directions; and vibratory leveling methods for precast concrete components use 3D images to identify the height of the edge molds and automatically adjust the vibratory leveling device for automated leveling.

[0003] However, existing technologies still have significant shortcomings in dealing with the complex construction scenarios of municipal roads. In municipal road construction, irregularly shaped areas such as road edges, around manholes, curb transition zones, and intersections often suffer from blind spots due to limitations in sensor placement and detection range. Specifically, in the central area of ​​the road, the vibratory leveling device can obtain complete multi-source detection data, achieving leveling accuracy down to the millimeter level. However, in the aforementioned irregularly shaped areas, the sensor installation location restricts the acquisition of complete multi-dimensional sensing data, resulting in significantly lower leveling accuracy compared to the central area. This leads to frequent quality defects such as substandard local flatness, severely impacting the overall construction quality and service life of the road. Current technical solutions are mostly localized improvements targeting specific areas. For example, automatic asphalt concrete leveling devices around manholes use a base fixed to the manhole cover for localized leveling, but lack a comprehensive system-level solution to address the leveling blind spots in irregularly shaped areas.

[0004] Chinese Patent Publication No. CN122082329A discloses an automatic road surface smoothness detection system for road construction, relating to the field of road construction quality inspection technology. The system includes: an image acquisition unit for real-time acquisition of original road surface images during asphalt paving and synchronous acquisition of paver vibration characteristic information corresponding to the original road surface images; a data processing module, communicatively connected to the image acquisition unit, for receiving the original road surface images and the paver vibration characteristic information, performing smoothness detection through vibration adaptive image analysis technology, and outputting structured detection results; and a data output unit, communicatively connected to the data processing module, for receiving the structured detection results and realizing real-time display and anomaly warning during the asphalt paving process.

[0005] Therefore, the existing technology has the following problems: the existing vibration leveling system has low vibration leveling accuracy in irregular areas such as road edges and around manholes due to sensor detection blind spots. Summary of the Invention

[0006] To address this issue, the present invention provides an intelligent vibration leveling system for municipal road construction based on multi-source detection data, which overcomes the problem of low vibration leveling accuracy in existing vibration leveling systems in irregular areas such as road edges and around manholes due to sensor detection blind spots.

[0007] To achieve the above objectives, the present invention provides an intelligent vibration leveling system for municipal road construction based on multi-source detection data, comprising: The vibration leveling monitoring device includes a vibration leveling actuator for vibrating and leveling roads and an auxiliary mobile platform for acquiring monitoring data of the construction area. The auxiliary mobile platform moves independently of the vibration leveling actuator and is used to acquire three-dimensional point cloud data and surface texture image data of the construction area in advance. The data acquisition module is used to acquire multi-source data, including a first sensor group arranged on the vibratory actuator and a second sensor group arranged on the auxiliary moving platform. The irregular region determination module is used to determine the boundaries of each irregular region, wherein the irregular region boundaries are extracted based on a deep learning semantic segmentation network; The blind spot detection module is used to mark the blind spots in each irregular area based on the sensor coverage and coverage benchmark of each irregular area; The spatiotemporal prediction compensation module is used to perform spatiotemporal prediction compensation on the blind zone data of each of the aforementioned detection blind zones; The model building module is used to build a three-dimensional digital surface model of the construction area based on the generated sub-models. The sub-models include a central model for determining the central area and an irregular model for determining the irregular area. The irregular model is built using data of the irregular area after spatiotemporal prediction compensation. The regional leveling strategy generation module is used to generate corresponding leveling strategies for corresponding regions based on a three-dimensional digital surface model. This includes determining the steering angular velocity and travel speed of the mobile chassis for construction in the irregular region based on the curvature radius, boundary, and geometric features of adjacent leveled regions, and performing construction on the central region with initial operating parameters. The mobile chassis is used to drive the leveling actuator to travel. The execution module is used to execute the stabilization strategy for the corresponding area; The analysis module is used to determine the vibration leveling state of the vibration leveling system based on the obtained three-dimensional micro-geographical difference of the irregular region; the analysis module is also used to determine whether to adjust the coverage reference or the steering angular velocity of the moving chassis based on the vibration leveling state.

[0008] Furthermore, the detection blind spot identification module also includes: a detection window construction submodule, which is used to construct a rectangular detection window based on the position and working width of the vibrating actuator; a statistics submodule, which is used to divide the rectangular detection window into several grid points according to a preset interval, and to count the number of effective grid points, wherein the effective grid points are the grid points with three-dimensional point cloud data acquired by the second sensor group within the rectangular detection window; and a coverage calculation submodule, which is used to determine the sensor coverage based on the number of effective grid points.

[0009] Furthermore, the regional leveling strategy generation module also includes a target elevation value determination submodule, which is used to set the leveling target elevation value of each annular region when there is a manhole cover feature in a single irregular region, so as to ensure that the target elevation change gradient between adjacent annular regions is less than or equal to a preset gradient. The annular region is an area in the irregular region with the center of the manhole cover as the reference and the diameter within the corresponding interval.

[0010] Furthermore, the analysis module is also used to divide the vibration leveling state into a first vibration leveling state and a second vibration leveling state based on the three-dimensional micro-geographical difference; the analysis module also includes: a non-circular area boundary deviation calculation submodule, which is used to determine the non-circular area boundary deviation in the second vibration leveling state, wherein the non-circular area boundary deviation is the maximum value of each elevation deviation, and each elevation deviation is determined by each point on the non-circular area boundary line; a processing submodule, which is used to generate a corresponding processing method based on the non-circular area boundary deviation, including adjusting the coverage reference based on the non-circular area boundary deviation, or adjusting the steering angular velocity of the mobile chassis.

[0011] Furthermore, the analysis module also includes a coverage benchmark first correction submodule, which is used to increase the coverage benchmark based on the ratio of the irregular region boundary deviation to the preset boundary deviation, and the increase in the coverage benchmark is proportional to the ratio.

[0012] Furthermore, the analysis module also includes: an error determination submodule, which is used to determine the root mean square error of the true elevation value and the compensated elevation, wherein the true elevation value is obtained by the auxiliary moving platform scanning the corresponding area when the leveling actuator re-levels according to the adjusted coverage benchmark; a blind zone compensation reliability determination submodule, which is used to determine the blind zone compensation reliability based on the root mean square error; and a coverage benchmark second correction submodule, which is used to determine the coverage benchmark based on the difference between the blind zone compensation reliability and the preset allowable error.

[0013] Furthermore, the second correction submodule of the coverage benchmark is also used to reduce the coverage benchmark based on the difference between the blind zone compensation confidence and the preset allowable error, and the reduction of the coverage benchmark is proportional to the difference.

[0014] Furthermore, the analysis module is also used to determine the steering angular velocity of the mobile chassis when the system is in the second vibration level state after adjusting the coverage reference.

[0015] Furthermore, the analysis module also includes: an evaluation submodule, which is used to determine the yaw rate characterization value based on the yaw rate obtained in the vibration leveling actuator and the preset yaw rate, wherein the preset yaw rate is determined based on the travel speed and the radius of curvature in the path planning; and a steering rate correction submodule, which is used to determine the steering rate based on the ratio of the yaw rate characterization value to the preset yaw rate characterization value.

[0016] Furthermore, the steering angular velocity correction submodule is also used to reduce the steering angular velocity based on the ratio of the yaw rate characterization value to the preset yaw rate characterization value, and the reduction in steering angular velocity is proportional to the ratio.

[0017] Compared with existing technologies, the beneficial effects of this invention are as follows: the vibration leveling system of this invention includes a vibration leveling monitoring device containing a vibration leveling execution mechanism and an auxiliary moving platform; a data acquisition module that collects multi-source data based on a first sensor group and a second sensor group; an irregular region determination module for segmenting and extracting the boundaries of irregular regions; a blind spot identification module for marking blind spots based on sensor coverage and coverage benchmarks; a spatiotemporal prediction compensation module for compensating for blind spot data; a model building module for constructing a three-dimensional digital surface model of the construction area; a regional vibration leveling strategy generation module for generating corresponding vibration leveling strategies for corresponding regions based on the three-dimensional digital surface model; an execution module for executing the corresponding strategies; and an analysis module for determining the vibration leveling state based on three-dimensional micro-geographical differences and determining relevant parameters accordingly. This invention improves the vibration leveling accuracy of municipal road construction.

[0018] Furthermore, this invention determines sensor coverage based on the number of effective grid points and the total number of grid points, which can more accurately detect blind spots, thereby enabling more effective spatiotemporal prediction and compensation of blind spot data, and further improving the effectiveness of data in municipal road construction.

[0019] Furthermore, this invention divides concentric annular areas radially outward from the center of the manhole cover, and independently sets a target elevation value for each annular area. At the same time, it constrains the gradient of target elevation changes between adjacent annular areas to not exceed a preset limit. This achieves a gradual and smooth transition of the road surface around the manhole cover, avoiding abrupt changes in elevation or settlement steps between the edge of the manhole cover and the road surface in traditional construction. It ensures uniform compaction and consistent density of the material around the manhole, and reduces early cracks or damage caused by local stress concentration.

[0020] Furthermore, the present invention generates a corresponding processing method for the boundary deviation of the irregular region based on the elevation deviation of each point on the boundary line of the irregular region. This method can more accurately determine the reason for determining the second leveling state, so that the relevant parameters can be adjusted more effectively in the future, thereby further improving the leveling accuracy of municipal roads.

[0021] Furthermore, this invention determines the coverage benchmark based on the ratio of the boundary deviation of the irregular area to the preset boundary deviation, which can more accurately adjust the coverage benchmark, thereby triggering the spatiotemporal prediction compensation mechanism more accurately, and thus providing a more complete three-dimensional digital surface model, further improving the vibration leveling accuracy of municipal roads.

[0022] Furthermore, the present invention determines whether to adjust the coverage benchmark based on the reliability of blind spot compensation. This can further ensure that the elevation error after compensation is still within the allowable range after the coverage benchmark is increased, thereby more effectively constraining the coverage benchmark and further improving the leveling accuracy of municipal roads.

[0023] Furthermore, the present invention adjusts the coverage benchmark based on the difference between the blind spot compensation reliability and the preset allowable error, which can more accurately adjust the coverage benchmark, thereby more effectively avoiding compensation distortion caused by an excessively high coverage benchmark, and further improving the leveling accuracy of municipal roads.

[0024] Furthermore, the present invention determines the reason for the second leveling state based on the yaw rate characterization value, which can more accurately determine whether the lateral force exceeds the standard and the material is pushed due to improper setting of the steering angular velocity, thus making the leveling state unqualified. Based on the reason, the relevant parameters can be adjusted more effectively to further improve the leveling accuracy of municipal roads.

[0025] Furthermore, the present invention adjusts the steering angular velocity based on the ratio of the yaw rate characterization value to the preset yaw rate characterization value, which can more accurately determine the steering angular velocity, thereby causing the actual yaw rate to fall back to the expected value, thereby eliminating the damage of lateral force to the material flatness and further improving the vibration leveling accuracy of municipal roads. Attached Figure Description

[0026] Figure 1 This is a structural block diagram of the intelligent vibration leveling system for municipal road construction based on multi-source detection data, as described in an embodiment of the present invention. Figure 2 This is a flowchart illustrating the steps of the intelligent vibration leveling method for municipal road construction based on multi-source detection data, as described in an embodiment of the present invention. Figure 3 This is a flowchart illustrating the steps of determining the three-dimensional micro-geographic difference and the preset three-dimensional micro-geographic difference in an embodiment of the present invention. Figure 4 This is a flowchart illustrating the steps for determining failure based on boundary deviation of irregular regions in an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0028] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0029] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0030] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0031] Please see Figure 1The diagram shown is a structural block diagram of an intelligent vibration leveling system for municipal road construction based on multi-source detection data, according to an embodiment of the present invention. The embodiment of the present invention includes: The vibration leveling monitoring device includes a vibration leveling actuator for vibrating and leveling roads and an auxiliary mobile platform for acquiring monitoring data of the construction area. The auxiliary mobile platform moves independently of the vibration leveling actuator and is used to acquire three-dimensional point cloud data and surface texture image data of the construction area in advance. The data acquisition module is connected to the vibration leveling monitoring device and is used to collect multi-source data, including a first sensor group arranged on the vibration leveling actuator and a second sensor group arranged on the auxiliary moving platform. Specifically, the vibratory leveling actuator includes a mobile chassis for carrying and driving movement, a vibratory plate movably connected to the mobile chassis to perform road vibratory leveling operations, a height adjustment actuator connected at one end to the mobile chassis and at the other end to the vibratory plate to drive the vibratory plate to rise and fall, an eccentric vibration motor fixedly installed on the vibratory plate to generate excitation force, and a local controller electrically connected to the drive system of the height adjustment actuator, the eccentric vibration motor and the mobile chassis respectively, to adjust the height, pitch angle and vibration frequency of the vibratory plate in real time according to the vibratory leveling strategy.

[0032] It is understood that the auxiliary mobile platform is a tracked autonomous mobile robot or a follower telescopic extension boom installed on the vibratory actuator. This embodiment does not impose any restrictions, as long as the auxiliary mobile platform can move independently of the vibratory actuator and acquires three-dimensional point cloud data and surface texture image data of the construction area, especially the irregular area, from different perspectives before or during the operation of the vibratory actuator, in order to supplement the detection blind spots of the vibratory actuator's own sensors.

[0033] The irregular region determination module is connected to the data acquisition module and is used to determine the boundaries of each irregular region. The irregular region boundaries are extracted based on a deep learning semantic segmentation network to divide the central region and the irregular region. The detection blind zone identification module is connected to the data acquisition module and the irregular region determination module respectively, and is used to mark the detection blind zone in each irregular region based on the sensor coverage and coverage benchmark of each irregular region. Specifically, the blind spot detection module further includes: The detection window construction submodule is used to construct a rectangular detection window based on the position and working width of the vibratory actuator; The statistics submodule is used to divide the rectangular detection window into several grid points according to a preset interval, and to count the number of valid grid points, wherein the valid grid points are the grid points with three-dimensional point cloud data acquired by the second sensor group within the rectangular detection window. The coverage calculation submodule is used to determine the sensor coverage based on the ratio of the number of effective grid points to the total number of grid points; The detection blind zone determination submodule is used to determine the area corresponding to the rectangular detection window as the detection blind zone when the sensor coverage is less than a preset threshold.

[0034] The spatiotemporal prediction compensation module is connected to the data acquisition module and the detection blind zone identification module respectively, and is used to perform spatiotemporal prediction compensation on the blind zone data of each detection blind zone; In this embodiment of the invention, the spatiotemporal prediction compensation module further includes: The blind zone data compensation submodule is used to perform spatiotemporal prediction compensation of blind zone data based on multi-source data and geometric constraints from surrounding non-blind zone areas, using interpolation methods to make the blind zone data more complete. The model building module, which is connected to the data acquisition module, the irregular region determination module, and the spatiotemporal prediction compensation module, is used to build a three-dimensional digital surface model of the construction area based on the generated sub-model. The sub-model includes a central model for determining the central region and an irregular model for determining the irregular region. The irregular model is constructed from the data of the irregular region after spatiotemporal prediction compensation. Specifically, the model building module is also used to fuse the preprocessed multi-source data based on the extended Kalman filter to generate a three-dimensional digital surface model, wherein the preprocessing includes timestamp alignment and spatial coordinate system transformation.

[0035] A regional leveling strategy generation module, which is connected to the data acquisition module and the model construction module, is used to generate a corresponding leveling strategy for a corresponding region based on a three-dimensional digital surface model. This includes determining the steering angular velocity and travel speed of the mobile chassis for construction in the irregular region based on the curvature radius, boundary, and geometric features of adjacent leveled regions of the irregular region, and performing construction on the central region with initial operating parameters. The mobile chassis is used to drive the leveling actuator to travel. Specifically, the regional leveling strategy generation module includes: The irregular area leveling strategy generation submodule is used to determine the steering angular velocity and travel speed of the mobile chassis under the construction situation of irregular area, so that the difference between the leveling elevation value of the construction area of ​​the irregular area and the leveling elevation value between the adjacent leveled areas is less than the target elevation difference. The central area vibration leveling strategy generation submodule is used to adjust the height and vibration frequency of the vibrating plate by comparing the deviation between the current construction elevation and the target elevation, so as to generate a closed-loop control strategy for the target elevation. An execution module, which is connected to the region leveling strategy generation module, is used to execute the leveling strategy for the corresponding region; An analysis module, connected to the execution module, is used to determine the vibration leveling state of the vibration leveling system based on the obtained three-dimensional micro-geographical difference of the irregular region; the analysis module is also used to determine whether to adjust the coverage reference or the steering angular velocity of the mobile chassis based on the vibration leveling state.

[0036] Please see Figure 2 The diagram shown is a flowchart illustrating the steps of an intelligent vibration leveling method for municipal road construction based on multi-source detection data, according to an embodiment of the present invention. The method includes: S1, the data acquisition module collects multi-source data based on the first sensor group arranged on the vibratory leveling actuator and the second sensor group arranged on the auxiliary moving platform. The auxiliary moving platform moves independently of the vibratory leveling actuator to pre-acquire the three-dimensional point cloud data and surface texture image data of the construction area. S2, the boundary of each irregular region is determined by the irregular region determination module connected to the data acquisition module, wherein the irregular region boundary is extracted based on a deep learning semantic segmentation network to divide the central region and the irregular region; S3, the detection blind zone identification module, which is connected to the data acquisition module and the anisotropic region determination module respectively, marks the detection blind zone in each anisotropic region based on the sensor coverage and coverage benchmark of each anisotropic region; S4, the spatiotemporal prediction compensation module, which is connected to the data acquisition module and the detection blind zone identification module respectively, performs spatiotemporal prediction compensation on the blind zone data of each detection blind zone; S5, a three-dimensional digital surface model of the construction area is constructed based on the generated sub-model by a model building module connected to the data acquisition module, the irregular region determination module, and the spatiotemporal prediction compensation module respectively. The sub-model includes a central model for determining the central region and an irregular model for determining the irregular region. The irregular model is constructed using the data of the irregular region after spatiotemporal prediction compensation. S6, the region leveling strategy generation module connected to the data acquisition module and the model construction module generates a corresponding leveling strategy for the corresponding region based on the three-dimensional digital surface model. This includes determining the steering angular velocity and travel speed of the mobile chassis for construction in the irregular region based on the curvature radius, boundary and geometric features of the adjacent leveled regions, and performing construction in the central region with the initial operating parameters. The mobile chassis is used to drive the leveling actuator to travel. S7, the balancing strategy for the corresponding region is executed by the execution module connected to the region balancing strategy generation module; S8, the analysis module connected to the execution module determines the vibration leveling state of the vibration leveling system based on the obtained three-dimensional micro-geographical difference of the irregular region, and determines whether to adjust the coverage reference or the steering angular velocity of the mobile chassis based on the vibration leveling state.

[0037] Specifically, the analysis module includes: The plane fitting submodule is used to fit several point cloud data in the irregular region into a single plane based on the least squares method. The three-dimensional micro-geographical deviation calculation submodule is used to determine the three-dimensional micro-geographical deviation based on the standard deviation of the elevation residuals of each point on the plane, so as to determine the micro-unevenness of the road surface inside the irregular area. The larger the value, the more severe the local undulation of the road surface and the worse the micro-smoothness.

[0038] In this embodiment of the invention, the analysis module further includes: The irregular region boundary deviation calculation submodule is used to determine the irregular region boundary deviation under the second leveling state. The irregular region boundary deviation is the maximum value of each elevation deviation, which is determined by each point on the irregular region boundary line. This determines the maximum deviation between the actual elevation on the irregular region boundary line after leveling and the design target elevation. The larger the irregular region boundary deviation, the more distorted the terrain information on which the leveling strategy is based, and the lower the accuracy of the three-dimensional digital surface model. The smaller the irregular region boundary deviation, the greater the lateral force, the greater the material deformation, and the greater the trajectory deviation.

[0039] In this embodiment of the invention, the analysis module further includes: The error determination submodule is used to determine the root mean square error between the true elevation value obtained by the auxiliary moving platform's backscan after the leveling is completed and the compensation elevation determined by the spatiotemporal prediction compensation module. The blind zone compensation reliability determination submodule is used to determine the blind zone compensation reliability based on the ratio of the root mean square error to the preset interpolation error, so as to determine the accuracy of the spatiotemporal prediction compensation module in performing elevation interpolation on the detection blind zone. The lower the blind zone compensation reliability, the more accurate the interpolation result, and the higher the accuracy of the spatiotemporal prediction compensation module in performing elevation interpolation on the detection blind zone.

[0040] Please see Figure 3 The diagram shown is a flowchart illustrating the steps of determining the three-dimensional micro-geographic difference and the preset three-dimensional micro-geographic difference according to an embodiment of the present invention, including: The analysis module calculates the three-dimensional micro-geographical discrepancy; The analysis module determines the leveling status of municipal roads based on the three-dimensional micro-geographical difference; The analysis module, based on the determination that the vibration leveling state is the second vibration leveling state, determines whether to adjust the coverage benchmark based on the ratio of the heterogeneous region boundary deviation to a preset boundary deviation, according to the boundary deviation of the heterogeneous region. The ratio of the boundary deviation of the heterogeneous area to the preset boundary deviation determines the degree of the current boundary deviation exceeding the standard. The larger the ratio, the more heterogeneous areas are misjudged as non-blind zones and data compensation is not initiated, making the data of the 3D digital surface model sparser near the boundary, the more the leveling strategy deviates from the ideal trajectory, the greater the height difference between the road surface and the edge of the manhole cover or the edge of the road, and the worse the flatness quality. The first correction submodule based on the coverage benchmark determines the coverage benchmark to determine the boundary for marking the corresponding area as a detection blind zone and initiating spatiotemporal prediction compensation. The greater the increase in the coverage benchmark, the fewer irregular areas are misjudged as non-blind zones and data compensation is not initiated. The blind zone compensation reliability determination submodule in the analysis module adjusts the coverage benchmark based on the difference between the blind zone compensation reliability and the preset allowable error after leveling based on the adjusted coverage benchmark. The difference between the blind zone compensation reliability and the preset allowable error determines the severity of the distortion in the current spatiotemporal prediction compensation. The larger the difference, the more significant the deviation of the root mean square error between the actual elevation and the compensated elevation in the blind zone from the maximum allowable interpolation error. The larger the blind zone, the greater the dependence of interpolation, the lower the reliability of the compensation data, and the more severe the interpolation distortion. The coverage benchmark is determined based on the second correction submodule. The greater the reduction in the coverage benchmark, the smaller the blind zone range and the higher the reliability of the compensation data.

[0041] Specifically, the analysis module also includes: The evaluation submodule is used to determine the yaw rate characterization value based on the difference between the yaw rate obtained from the vibration actuator and the preset yaw rate, and the ratio of the preset yaw rate to a very small positive number, wherein the preset yaw rate is determined based on the ratio of the travel speed to the radius of curvature in the path planning. In this embodiment of the invention, the yaw rate characterization value is used to determine the extent to which the actual steering rate of the quantized oscillating actuator exceeds the expected steering rate during turning or detouring in an irregular area.

[0042] Please see Figure 4 As shown, it is a flowchart of the steps for determining failure based on boundary deviation of irregular region in an embodiment of the present invention, including: The analysis module determines failure based on the boundary deviation of the irregular region and determines the steering angular velocity based on the ratio of the yaw rate characterization value to the preset yaw rate characterization value. Failure due to boundary deviation of the irregular region includes situations where the leveling state is in the second leveling state after adjusting the coverage reference, and situations where the boundary deviation of the irregular region is less than or equal to the preset boundary deviation. The ratio of the yaw rate characterization value to the preset yaw rate characterization value determines the degree to which the actual yaw rate exceeds the expected yaw rate. The larger the ratio, the greater the excessive lateral force on the vibrating plate, the more obvious the lateral displacement of the material, the more the trajectory deviates from the design arc, and the more severe the deterioration of the three-dimensional micro-geometry. The steering angular velocity is determined by the steering angular velocity correction submodule to determine the steering rate of the mobile chassis when turning or detouring in irregular areas. The greater the reduction in steering angular velocity, the smoother the chassis steering, the smaller the lateral acceleration generated, the less disturbance to the uncured road surface material, and the higher the leveling accuracy.

[0043] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0044] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart vibration leveling system for municipal road construction based on multi-source detection data, characterized in that, include: The vibration leveling monitoring device includes a vibration leveling actuator for vibrating and leveling roads and an auxiliary mobile platform for acquiring monitoring data of the construction area. The auxiliary mobile platform moves independently of the vibration leveling actuator and is used to acquire three-dimensional point cloud data and surface texture image data of the construction area in advance. The data acquisition module is used to acquire multi-source data, including a first sensor group arranged on the vibratory actuator and a second sensor group arranged on the auxiliary moving platform. The irregular region determination module is used to determine the boundaries of each irregular region, wherein the irregular region boundaries are extracted based on a deep learning semantic segmentation network; The blind spot detection module is used to mark the blind spots in each irregular area based on the sensor coverage and coverage benchmark of each irregular area; The spatiotemporal prediction compensation module is used to perform spatiotemporal prediction compensation on the blind zone data of each of the aforementioned detection blind zones; The model building module is used to build a three-dimensional digital surface model of the construction area based on the generated sub-models. The sub-models include a central model for determining the central area and an irregular model for determining the irregular area. The irregular model is built using data of the irregular area after spatiotemporal prediction compensation. The regional leveling strategy generation module is used to generate corresponding leveling strategies for corresponding regions based on a three-dimensional digital surface model. This includes determining the steering angular velocity and travel speed of the mobile chassis for construction in the irregular region based on the curvature radius, boundary, and geometric features of adjacent leveled regions of the irregular region, and performing construction on the central region with initial operating parameters. The mobile chassis is used to drive the leveling actuator to travel. The execution module is used to execute the stabilization strategy for the corresponding area; The analysis module is used to determine the vibration leveling state of the vibration leveling system based on the obtained three-dimensional micro-geographical difference of the irregular region; the analysis module is also used to determine whether to adjust the coverage reference or the steering angular velocity of the moving chassis based on the vibration leveling state.

2. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 1, characterized in that, The blind spot detection module also includes: The detection window construction submodule is used to construct a rectangular detection window based on the position and working width of the vibratory actuator; The statistics submodule is used to divide the rectangular detection window into several grid points according to a preset interval, and to count the number of valid grid points, wherein the valid grid points are the grid points with three-dimensional point cloud data acquired by the second sensor group within the rectangular detection window; The coverage calculation submodule is used to determine the sensor coverage based on the number of effective grid points.

3. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 2, characterized in that, The regional leveling strategy generation module also includes a target elevation value determination submodule, which is used to set the leveling target elevation value of each annular region when there is a manhole cover feature in a single irregular region, so as to ensure that the target elevation change gradient between adjacent annular regions is less than or equal to a preset gradient. The annular region is an area in the irregular region with the center of the manhole cover as the reference and the diameter within the corresponding interval.

4. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 3, characterized in that, The analysis module is also used to divide the vibration leveling state into a first vibration leveling state and a second vibration leveling state based on the three-dimensional micro-geographical difference. The analysis module also includes: The irregular region boundary deviation calculation submodule is used to determine the irregular region boundary deviation under the second vibration leveling state. The irregular region boundary deviation is the maximum value of each elevation deviation, and each elevation deviation is determined by each point on the irregular region boundary line. The processing submodule is used to generate a corresponding processing method based on the boundary deviation of the irregular region, including adjusting the coverage reference based on the boundary deviation of the irregular region, or adjusting the steering angular velocity of the mobile chassis.

5. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 4, characterized in that, The analysis module also includes a coverage benchmark first correction submodule, which is used to increase the coverage benchmark based on the ratio of the irregular region boundary deviation to the preset boundary deviation, and the increase in the coverage benchmark is proportional to the ratio.

6. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 5, characterized in that, The analysis module also includes: The error determination submodule is used to determine the true elevation value and the root mean square error of the compensated elevation. The true elevation value is obtained by the auxiliary moving platform scanning the corresponding area when the leveling actuator re-levels the area according to the adjusted coverage benchmark. The blind zone compensation confidence determination submodule is used to determine the blind zone compensation confidence based on the root mean square error; The second correction submodule for coverage benchmark is used to determine the coverage benchmark based on the difference between the blind zone compensation confidence and the preset allowable error.

7. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 6, characterized in that, The second correction submodule of the coverage benchmark is also used to reduce the coverage benchmark based on the difference between the blind zone compensation confidence and the preset allowable error, and the reduction of the coverage benchmark is proportional to the difference.

8. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 7, characterized in that, The analysis module is also used to determine the steering angular velocity of the mobile chassis when the system is in the second vibration leveling state after the coverage benchmark is determined.

9. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 8, characterized in that, The analysis module also includes: The evaluation submodule is used to determine the yaw rate characterization value based on the yaw rate obtained from the vibration actuator and the preset yaw rate, wherein the preset yaw rate is determined based on the travel speed and the radius of curvature in the path planning. The steering angular velocity correction submodule is used to determine the steering angular velocity based on the ratio of the yaw rate characterization value to the preset yaw rate characterization value.

10. The intelligent vibration leveling system for municipal road construction based on multi-source detection data according to claim 9, characterized in that, The steering angular velocity correction submodule is also used to reduce the steering angular velocity based on the ratio of the yaw rate characterization value to the preset yaw rate characterization value, and the reduction in steering angular velocity is proportional to the ratio.

Images