Pavement load spatial distribution positioning method and system based on multi-source heterogeneous data fusion

Abstract

The invention belongs to the technical field of pavement load positioning, and provides a pavement load spatial distribution positioning method and system based on multi-source heterogeneous data fusion in order to solve the problem that the strain distribution of a pavement full-scale space cannot be comprehensively monitored at present. The method comprises the following steps: acquiring road surface laser radar data and road surface mechanical data of a set road section at each moment; fitting the ground from the road surface laser radar data and removing the ground, and based on the road surface laser radar data from which the fitting ground is removed, performing clustering identification on a vehicle type and a corresponding load so as to track a track of the vehicle; according to the method, the vehicle position and the pavement stress are decoupled from the pavement mechanical data by utilizing a finite element mechanical analysis method, and the pavement stress and load distribution diagram in the three-dimensional space is generated by combining the tracked vehicle track, so that the precise real-time identification of the pavement vehicle load space distribution is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of pavement load positioning, and in particular relates to a pavement load spatial distribution positioning method and system by fusing multi-source heterogeneous data. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As highways age, existing pavement structures face problems such as reduced bearing capacity and difficulty in timely detection of defects. Especially under vehicle loads, the risk of structural failure increases, seriously threatening traffic safety. The core of these problems lies in the difficulty of state conversion and connection at various stages in the life cycle of existing pavement structures, which cannot dynamically reflect changes in traffic operation status and pavement performance, resulting in a lack of refined and real-time basis for maintenance management.

[0004] At present, laser radar based on light speed calculation has made progress in traffic flow recognition, but it still lacks comprehensiveness and real-time performance in vehicle load distribution recognition and road mechanics perception. Although distributed fiber optic sensing technology can detect vibration signals in the environment, it is limited by construction conditions and equipment costs and cannot fully monitor the strain distribution of the road surface in all scales and spaces, and accurately locate and monitor the road load in real time. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method and system for spatial distribution positioning of road load based on multi-source heterogeneous data fusion, which is based on the multi-source heterogeneous data fusion method to achieve accurate positioning and real-time monitoring of road load.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A first aspect of the present invention provides a method for locating the spatial distribution of road loads by fusing multi-source heterogeneous data.

[0007] In one or more embodiments, a method for locating the spatial distribution of road loads by fusing multi-source heterogeneous data is provided, including: Obtaining road surface laser radar data and road surface mechanical data at each time of a set road section; wherein the road surface mechanical data is the road surface stress when a vehicle passes by; Fit the ground from the road LiDAR data and remove it, cluster and identify the vehicle type and its location based on the road LiDAR data after removing the fitted ground, and dynamically track the trajectory of the vehicle; Finite element mechanics analysis is used to decouple vehicle position and pavement stress from pavement mechanics data, and then combined with the tracked vehicle trajectory to generate a pavement stress and load distribution map in three-dimensional space.

[0008] As an implementation method, based on the road surface lidar data after removing the fitted ground, the set road section is divided into several continuous cubes, and the point density of each cube is calculated; by comparing the point density of each cube with the point density dynamic threshold, the background and moving vehicles are distinguished.

[0009] As an implementation method, when the point density of any cube is higher than the average point density of all cubes, the point density threshold is increased; wherein, when the adjusted point density threshold = α×initial point density threshold; α>1, it is a preset first adjustment coefficient.

[0010] As an implementation method, when the point density of any cube is lower than the average point density of all cubes and the point density variance of the current cube is less than a preset variance threshold, the point density threshold is lowered; wherein the adjusted point density threshold = β × initial point density threshold; β<1, which is a preset second adjustment coefficient.

[0011] As an implementation mode, by analyzing the change of the point density of each cube, the upper limit and the lower limit of the point density threshold are adaptively adjusted based on the histogram.

[0012] As an implementation method, in the process of generating a pavement stress and load distribution diagram in three-dimensional space, time synchronization and spatial association are used to ensure that the pavement lidar data and the pavement mechanical data are aligned on the same time axis, and the point cloud in the pavement lidar data is matched with the stress data in the pavement mechanical data through the vehicle's position information.

[0013] As an implementation method, a data fusion algorithm combining Kalman filtering and particle filtering is used to process the decoupled vehicle position and road surface stress and vehicle trajectory to generate a road surface stress and load distribution map in three-dimensional space.

[0014] The second aspect of the present invention provides a road load spatial distribution positioning system that integrates multi-source heterogeneous data.

[0015] In one or more embodiments, a road load spatial distribution positioning system based on multi-source heterogeneous data fusion includes: A multi-source heterogeneous data acquisition module, which is used to obtain road surface lidar data and road surface mechanical data at each time of a set road section; wherein the road surface mechanical data is the road surface stress when a vehicle passes by; The vehicle identification and tracking module is used to fit the ground from the road LiDAR data and remove it, cluster and identify the vehicle type and its location based on the road LiDAR data after removing the fitted ground, and dynamically track the trajectory of the vehicle; The stress and load distribution diagram generation module uses the finite element mechanics analysis method to decouple the vehicle position and road stress from the road mechanics data, and then combines the tracked vehicle trajectory to generate the road stress and load distribution diagram in three-dimensional space.

[0016] As an implementation mode, in the vehicle identification and tracking module, the set road section is divided into a number of continuous cubes based on the road surface lidar data after removing the fitted ground, and the point density of each cube is calculated; by comparing the point density of each cube with the point density dynamic threshold, the background and the moving vehicle are distinguished.

[0017] In another embodiment, a multi-source heterogeneous data fusion road load spatial distribution positioning system includes: a laser radar, a distributed optical fiber sensor and a data processor; The laser radar is used to collect road surface laser radar data at each time of a set road section and transmit it to a data processor; The distributed optical fiber sensor is buried under the roadbed of a set road section and is used to collect pavement mechanical data of the set road section at various times; wherein the pavement mechanical data is the pavement stress when a vehicle passes by; The data processor is configured to execute the steps in the method for locating the spatial distribution of road load by fusing multi-source heterogeneous data as described above.

[0018] Compared with the prior art, the present invention has the following beneficial effects: (1) Based on the road LiDAR data after removing the fitted ground, the present invention clusters and identifies the vehicle type and its position, dynamically tracks the vehicle trajectory, and then combines the vehicle position and road stress decoupled from the road mechanical data to generate a road stress and load distribution map in three-dimensional space. By combining LiDAR data with distributed fiber optic sensor data and performing mechanical analysis and decoupling processing, the present invention makes up for the deficiency of a single data source in identifying the vehicle load position and intensity, and significantly improves the recognition accuracy.

[0019] (2) The present invention automatically learns the cube point density threshold. By analyzing the density of the laser radar scanning data, the point density of each cube of the road surface laser radar data is compared with the point density dynamic threshold, thereby ensuring the efficiency and accuracy of real-time data processing, eliminating background noise points, reducing the interference of redundant data, and achieving the effect of accurately distinguishing the background from moving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0021] Figure 1It is a flow chart of a method for locating the spatial distribution of road loads by fusion of multi-source heterogeneous data according to an embodiment of the present invention; Figure 2 A schematic diagram of a radar point cloud data plane when processing laser radar data according to an embodiment of the present invention; Figure 3 The working principle of the distributed optical fiber sensor used in the embodiment of the present invention; Figure 4 A schematic diagram of sensor layout of a road structure cross section according to an embodiment of the present invention; Figure 5 It is a schematic diagram of decoupling the spatial distribution of vehicle load by using mechanical derivation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0024] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0025] Embodiment 1 Figure 1 The flowchart of the method for locating the spatial distribution of road load by fusion of multi-source heterogeneous data in the present embodiment is as follows. Figure 1 , a road load spatial distribution positioning method based on multi-source heterogeneous data fusion in this embodiment includes: S100: Acquire road surface laser radar data and road surface mechanical data at each time of a set road section; wherein the road surface mechanical data is the road surface stress when a vehicle passes by; S200: fitting the ground from the road surface laser radar data and removing it, clustering and identifying the vehicle type and its position based on the road surface laser radar data after removing the fitted ground, and dynamically tracking the trajectory of the vehicle; S300: Use finite element mechanics analysis to decouple vehicle position and pavement stress from pavement mechanics data, and then combine the tracked vehicle trajectory to generate a pavement stress and load distribution map in three-dimensional space.

[0026] This embodiment utilizes multi-source heterogeneous data fusion of road surface lidar data and road surface mechanics data to perceive the physical state of the road surface and vehicle load and map the spatial distribution of vehicle load. It can not only dynamically feedback the operating status of the road surface structure, but also deduce the service status of the road surface in real time, providing accurate decision support.

[0027] In step S100, the road surface LiDAR data is measured by a LiDAR, wherein the LiDAR is installed at a fixed position on the road, bridge or tunnel, such as a central green belt or a tunnel vault. In road areas with street lamps, the street lamps can be used as support poles, and the LiDAR can be installed on top of them to save costs. In the tunnel, the LiDAR can be fixed on the vault, and the distributed fiber optic sensor can be buried along the bottom of the tunnel to achieve all-round monitoring. Depending on the traffic environment, the frame number of the 16-beam LiDAR can be set between 1500 and 3000 frames. If it is 32 or 64 lines, the frame number can be reduced to ensure the efficiency and accuracy of real-time data processing.

[0028] Road surface lidar data contains a large number of three-dimensional coordinate points that represent the surface of the vehicle's surroundings. Figure 2 A schematic diagram of the radar point cloud data plane when processing laser radar data in this embodiment is given.

[0029] The pavement mechanical data of this embodiment is detected by using distributed optical fiber sensors buried under the roadbed.

[0030] Distributed fiber optic sensors use fiber Bragg grating technology to sense tiny strain and temperature changes. When a vehicle passes by, the distributed fiber optic sensor monitors the strain of the road surface in real time and records the strain data. Through the principle of optical reflection, the strain data is converted into electrical signals, such as Figure 3 shown.

[0031] Figure 4 The sensor layout diagram of the road structure cross section of this embodiment is given. Distributed optical fiber sensors are buried in the road surface to monitor the physical changes such as strain and vibration when vehicles pass by in real time and detect the load intensity of the road surface. The data processor is responsible for analyzing the sensor signal, determining the load size and its action point, using the Brillouin device to perform spectrum analysis on the scattered signals at different positions of the optical fiber, and using Gaussian fitting to determine the Brillouin frequency shift. :

[0032] in, It's strain. is the temperature change, and are the sensitivity coefficients of strain and temperature, respectively.

[0033] Preferably, the strain and temperature are measured separately by the dual wavelength method to decouple (strain).

[0034] Based on the strain in the optical fiber, the load magnitude is estimated using mechanical formulas.

[0035] Strain and Load The relationship is: ;in, is the elastic modulus of the optical fiber material, is the cross-sectional area of ​​the optical fiber.

[0036] Assuming that the optical fiber is installed on the road surface where the vehicle passes, the estimated load can be approximately considered as a part of the vehicle load. Through the strain distribution, the area with the largest strain in the optical fiber is determined, and then the load application point is determined.

[0037] In step S200, a ground segmentation algorithm RANSAC (Random Sample Consensus) may be used to fit the ground and remove it. In other embodiments, other existing segmentation algorithms may also be used to fit the ground and remove it.

[0038] In this embodiment, based on the road surface lidar data after removing the fitted ground, Euclidean Cluster Extraction is used to cluster the points according to the distance between them. Each group of clustered points represents an object, and clustering identifies the vehicle type and its location.

[0039] In the process of clustering and identifying vehicle types, the set road section is divided into several continuous cubes based on the road surface lidar data after removing the fitted ground, and the point density of each cube is calculated; the point density of each cube is compared with the point density dynamic threshold to distinguish between the background and moving vehicles.

[0040] When the point density of any cube is higher than the average point density of all cubes, the point density threshold is increased; wherein, when the adjusted point density threshold = α×initial point density threshold; α>1, it is the preset first adjustment coefficient.

[0041] When the point density of any cube is lower than the average point density of all cubes, and the point density variance of the current cube is less than the preset variance threshold, the point density threshold is lowered; wherein, the adjusted point density threshold = β × initial point density threshold; β<1, which is the preset second adjustment coefficient.

[0042] By analyzing the changes in the point density of each cube, the upper and lower limits of the point density threshold are adaptively adjusted based on the histogram.

[0043] By analyzing the local density changes, the upper and lower limits of the threshold are dynamically adjusted to ensure adaptive response to density changes in different areas and avoid excessive background noise interference. A common strategy is to use a histogram-based adaptive threshold, that is, to perform histogram statistics on the point density of each local area and select the inflection point in the histogram distribution as the new threshold.

[0044] In step S300, the process of decoupling the vehicle position and the road surface stress from the road surface mechanical data by using the finite element mechanical analysis method is a prior art.

[0045] In step S300, in the process of generating the pavement stress and load distribution diagram in three-dimensional space, time synchronization and spatial association are used to ensure that the pavement lidar data and the pavement mechanical data are aligned on the same time axis, and the point cloud in the pavement lidar data is matched with the stress data in the pavement mechanical data through the vehicle's position information. Figure 5 A schematic diagram of decoupling the spatial distribution of vehicle loads using mechanical derivation is given in an embodiment.

[0046] Specifically, a data fusion algorithm combining Kalman filtering and particle filtering is used to fuse the decoupled vehicle position and road stress with the tracked vehicle trajectory to generate a road stress and load distribution map in three-dimensional space.

[0047] Assume the system status is , including: vehicle position, vehicle speed and acceleration, and load distribution.

[0048] State transfer equation:

[0049] in, is the state transfer function, is the system noise, which is assumed to be Gaussian distributed.

[0050] Among them, the state transfer function describes the state at the previous moment and calculates the state at the current moment.

[0051] In vehicle and road stress analysis, the state transfer function is usually given by the vehicle's dynamic model or load propagation model. For the modeling of vehicle position, velocity and acceleration, the vehicle's motion can be described by the classical equations of motion, such as:

[0052] in, is the time interval; The vehicle is The location at the moment; The vehicle is The location at the moment; The vehicle is at time speed; The vehicle is The speed of the moment; The vehicle is The acceleration at the moment. As for the load distribution, it may be affected by factors such as road surface type, vehicle speed, and vehicle mass.

[0053] Assume that the position of the vehicle on the two-dimensional plane is , the position of the fixed object is , then the distance measured by the lidar can be obtained through the following observation function get:

[0054] Assuming that the load stress is proportional to the acceleration of the vehicle, the observation equation of the distributed optical fiber sensor is expressed in the following form:

[0055]

[0056] in, is the observed state matrix, including but not limited to vehicle position, velocity, acceleration and stress; is the proportionality coefficient, which expresses the relationship between acceleration and load stress, is the observation noise. and are the observation functions of LiDAR and distributed fiber optic sensor, and is the corresponding noise.

[0057] Kalman filtering is suitable for processing linear and Gaussian systems and is used to estimate the dynamic information of the vehicle (position, speed, etc.). The process consists of two steps: Prediction stage: based on the state of the previous moment , use the state transition equation to predict the current state :

[0058] in, is the state transfer function; Forecast Error Covariance :

[0059] in, is the state transition matrix, is the covariance matrix of the process noise; Represents the transpose of a matrix; express The error covariance at time .

[0060] Using LiDAR observations To update:

[0061] Update state estimate :

[0062] Updated error covariance :

[0063] in, is the state estimate before the update; is the Kalman gain, is the observation matrix, is the observation noise covariance.

[0064] Particle filtering is used to process nonlinear and non-Gaussian systems and is suitable for load distribution information fed back by fiber optic sensors. Particle filtering uses multiple particles to represent the probability distribution of system states.

[0065] Initialize particles: Generate Particles , each particle represents a possible state, and the initial particles are generated based on the prior information of the load distribution.

[0066] Particle weight update: based on the observations of distributed fiber optic sensors The observation prediction corresponding to each particle , update the weight of each particle :

[0067] in, is the observation likelihood function for a given particle state, indicating the degree of match between the observed data and the particle state; is the weight of each particle before updating.

[0068] Resampling: In order to avoid particle degradation (i.e. the weights of most particles approach zero), the particle set needs to be resampled. Particles with high weights are retained, and particles with low weights are eliminated to generate a new particle set.

[0069] State estimation: The weighted average of particles is used to estimate the load distribution state at the current moment : .

[0070] In this embodiment, the Kalman filter is responsible for the linear part (such as vehicle dynamics), and the particle filter handles the nonlinear part (such as load distribution). The predicted output of the Kalman filter can provide prior information for the particle filter, and the result of the particle filter is used to further correct the Kalman filter's estimate. Through the fusion of the Kalman filter and the particle filter, the system can obtain an accurate estimate of the vehicle load distribution and dynamically track the vehicle's movement trajectory. These data are further used to construct the load distribution model.

[0071] Embodiment 2 In one or more embodiments, a road load spatial distribution positioning system based on multi-source heterogeneous data fusion includes: A multi-source heterogeneous data acquisition module, which is used to obtain road surface lidar data and road surface mechanical data at each time of a set road section; wherein the road surface mechanical data is the road surface stress when a vehicle passes by; The vehicle identification and tracking module is used to fit the ground from the road LiDAR data and remove it, cluster and identify the vehicle type and its location based on the road LiDAR data after removing the fitted ground, and dynamically track the trajectory of the vehicle; The stress and load distribution diagram generation module uses the finite element mechanics analysis method to decouple the vehicle position and road stress from the road mechanics data, and then combines the tracked vehicle trajectory to generate the road stress and load distribution diagram in three-dimensional space.

[0072] In the vehicle identification and tracking module, the set road section is divided into several continuous cubes according to the road surface lidar data after removing the fitted ground, and the point density of each cube is calculated; the point density of each cube is compared with the point density dynamic threshold to distinguish the background and the moving vehicle.

[0073] It should be noted here that the various modules in the road load spatial distribution positioning system based on multi-source heterogeneous data fusion correspond one-to-one to the various steps in the road load spatial distribution positioning method based on multi-source heterogeneous data fusion in the above-mentioned embodiment 1, and the specific implementation process is the same and will not be described in detail here.

[0074] Embodiment 3 In this embodiment, a road load spatial distribution positioning system with multi-source heterogeneous data fusion is provided, which includes: a laser radar, a distributed optical fiber sensor and a data processor; The laser radar is used to collect road surface laser radar data at each time of a set road section and transmit it to a data processor; The distributed optical fiber sensor is buried under the roadbed of a set road section and is used to collect pavement mechanical data of the set road section at various times; wherein the pavement mechanical data is the pavement stress when a vehicle passes by; The data processor is configured to execute the steps in the method for locating the spatial distribution of road load by fusing multi-source heterogeneous data as described in the first embodiment.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for locating the spatial distribution of road loads by fusion of multi-source heterogeneous data, characterized in that: include: Obtaining road surface laser radar data and road surface mechanical data at each time of a set road section; wherein the road surface mechanical data is the road surface stress when a vehicle passes by; Fit the ground from the road LiDAR data and remove it, cluster and identify the vehicle type and its location based on the road LiDAR data after removing the fitted ground, and dynamically track the trajectory of the vehicle; Finite element mechanics analysis is used to decouple vehicle position and pavement stress from pavement mechanics data, and then combined with the tracked vehicle trajectory to generate a pavement stress and load distribution map in three-dimensional space.

2. The method for spatial distribution positioning of road load by fusion of multi-source heterogeneous data as claimed in claim 1, characterized in that: According to the road surface lidar data after removing the fitted ground, the set road section is divided into several continuous cubes, and the point density of each cube is calculated; by comparing the point density of each cube with the point density dynamic threshold, the background and moving vehicles can be distinguished.

3. The method for spatial distribution positioning of road load by fusion of multi-source heterogeneous data as claimed in claim 2 is characterized in that: When the point density of any cube is higher than the average point density of all cubes, the point density threshold is increased; wherein, when the adjusted point density threshold = α×initial point density threshold; α>1, it is the preset first adjustment coefficient.

4. The method for spatial distribution positioning of road load by fusion of multi-source heterogeneous data as claimed in claim 2, characterized in that: When the point density of any cube is lower than the average point density of all cubes, and the point density variance of the current cube is less than the preset variance threshold, the point density threshold is lowered; wherein, the adjusted point density threshold = β × initial point density threshold; β<1, which is the preset second adjustment coefficient.

5. The method for spatial distribution positioning of road load by fusion of multi-source heterogeneous data as claimed in claim 2, characterized in that: By analyzing the changes in the point density of each cube, the upper and lower limits of the point density threshold are adaptively adjusted based on the histogram.

6. The method for spatial distribution positioning of road load by fusion of multi-source heterogeneous data as claimed in claim 1, characterized in that: In the process of generating the pavement stress and load distribution diagram in three-dimensional space, time synchronization and spatial association are used to ensure that the pavement lidar data and the pavement mechanics data are aligned on the same time axis, and the point cloud in the pavement lidar data is matched with the stress data in the pavement mechanics data through the vehicle's position information.

7. The method for spatial distribution positioning of road load by fusion of multi-source heterogeneous data as claimed in claim 1, characterized in that: The data fusion algorithm combining Kalman filtering and particle filtering is used to process the decoupled vehicle position, road stress and vehicle trajectory to generate a road stress and load distribution map in three-dimensional space.

8. A road load spatial distribution positioning system based on multi-source heterogeneous data fusion, characterized in that: include: A multi-source heterogeneous data acquisition module, which is used to obtain road surface lidar data and road surface mechanical data at each time of a set road section; wherein the road surface mechanical data is the road surface stress when a vehicle passes by; The vehicle identification and tracking module is used to fit the ground from the road LiDAR data and remove it, cluster and identify the vehicle type and its location based on the road LiDAR data after removing the fitted ground, and dynamically track the trajectory of the vehicle; The stress and load distribution diagram generation module uses the finite element mechanics analysis method to decouple the vehicle position and road stress from the road mechanics data, and then combines the tracked vehicle trajectory to generate the road stress and load distribution diagram in three-dimensional space.

9. The road load spatial distribution positioning system based on multi-source heterogeneous data fusion as claimed in claim 8 is characterized in that: In the vehicle identification and tracking module, the set road section is divided into several continuous cubes according to the road surface lidar data after removing the fitted ground, and the point density of each cube is calculated; the point density of each cube is compared with the point density dynamic threshold to distinguish the background and the moving vehicle.

10. A road load spatial distribution positioning system based on multi-source heterogeneous data fusion, characterized in that: include: LiDAR, distributed fiber optic sensors, and data processors; The laser radar is used to collect road surface laser radar data at each time of a set road section and transmit it to a data processor; The distributed optical fiber sensor is buried under the roadbed of a set road section and is used to collect pavement mechanical data of the set road section at various times; wherein the pavement mechanical data is the pavement stress when a vehicle passes by; The data processor is configured to execute the steps in the method for locating the spatial distribution of road load by fusing multi-source heterogeneous data as described in any one of claims 1 to 7.

Images