Method and system for identifying rolling operation track of road roller

Abstract

This invention relates to the field of road roller compaction technology, and more particularly to a method and system for identifying the compaction trajectory of a road roller. The method includes the following steps: acquiring a target compaction area; collecting geospatial data of the target compaction area to obtain geographical environment data of the work area; locating the road roller to obtain its position coordinates; performing real-time sensing of the road roller's working environment to obtain a three-dimensional model of the working environment; identifying terrain features in the three-dimensional model of the working environment to obtain environmental terrain feature mapping data; performing geographic topology analysis on the target compaction area based on the environmental terrain feature mapping data to obtain a topology model of the work area; and performing matching analysis between the road roller's position coordinates and the topology model of the work area to obtain a candidate set of road roller work paths. This invention reduces the workload of operators who need to frequently stop to check and adjust the road roller's position, making the operation process smoother.

Description

Technical Field

[0001] The present invention relates to the technical field of roller compaction, and in particular to a method and system for identifying a roller compaction operation track. Background Art

[0002] In traditional roller operations, the identification of the operation trajectory mainly relies on the operator's experience and visual judgment. This method is not only inefficient, but also difficult to ensure the accuracy of the operation. Especially in large-scale engineering projects, the operation area is vast and the terrain is complex and changeable. It is difficult for the operator to fully grasp the real-time position and operation progress of the roller. For example, when building a highway through a mountainous area, the roller needs to perform compaction operations on a winding mountain road. Due to the large changes in the slope and curves of the mountain road, it is difficult for the operator to accurately judge whether the roller has covered all the areas that need to be compacted, especially in places where the line of sight is blocked or the terrain is undulating. This not only increases the workload of the operator, but also increases the difficulty of compaction operations. In such complex terrain, the operator often needs to stop frequently to check and adjust the position of the roller to ensure that no area is missed or the same area is compacted repeatedly. This frequent stop and adjustment not only reduces the efficiency of the operation, but also easily leads to uneven compaction, affecting the quality and service life of the road. For example, if the operator fails to find the area that the roller has compacted in time, it will cause the area to be over-compacted, while the adjacent area will sink and crack due to insufficient compaction. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for identifying the rolling operation trajectory of a road roller to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above purpose, a method for identifying a rolling operation track of a road roller comprises the following steps:

[0005] Step S1: Acquire the target rolling area; collect geographic spatial data of the target rolling area to obtain geographic environment data of the working area; locate the roller to obtain the position coordinates of the roller; perceive the working environment of the roller in real time to obtain a three-dimensional model of the working environment;

[0006] Step S2: identifying terrain features of the three-dimensional model of the working environment to obtain environmental terrain feature mapping data; performing geographic topological analysis on the target rolling area based on the environmental terrain feature mapping data to obtain a working area topological model; matching and analyzing the roller position coordinates with the working area topological model to obtain a roller working path candidate set;

[0007] Step S3: selecting a travel path for the roller based on the roller operation path candidate set and the environmental terrain feature mapping data to obtain a rolling operation trajectory path; performing coverage analysis on the rolling operation trajectory path to obtain rolling area integrity assessment data; dynamically adjusting the rolling operation trajectory path according to the rolling area integrity assessment data to obtain an optimized rolling operation trajectory path;

[0008] Step S4: using a vibration sensor to detect the intensity of sound waves according to the optimized rolling operation trajectory path to obtain dynamic monitoring data of the compaction process; performing compaction density and uniformity analysis on the dynamic monitoring data of the compaction process to obtain a road surface compaction quality assessment report; adjusting the optimized rolling operation trajectory path according to the road surface compaction quality assessment report to obtain a compaction quality enhanced operation path;

[0009] Step S5: Based on the compaction quality enhanced operation path and the geographic environment data of the operation area, the operation process of the roller is digitally reconstructed as a twin to obtain a digital mapping model of the operation process; geographic spatial information is extracted from the digital mapping model of the operation process to obtain rolling trajectory coordinate mapping data; the rolling trajectory coordinate mapping data is visualized to obtain a visualization report of the roller operation trajectory.

[0010] The present invention replaces the traditional method that relies on operator experience and visual judgment through automated geospatial data collection and real-time perception technology, reduces human errors, and improves the accuracy and efficiency of operations. By positioning the roller and building a three-dimensional model of the operating environment, the position and operation progress of the roller can be fully and in real time, and accurate control of the operation can be maintained even in an environment with complex terrain or obstructed vision. Through automated path selection and dynamic adjustment, the workload of the operator who needs to frequently stop to check and adjust the position of the roller is reduced, making the operation process smoother. Through coverage analysis and dynamic adjustment of the rolling operation trajectory path, the integrity and uniformity of the rolling area are ensured, and road quality problems caused by uneven compaction are avoided. Through acoustic wave intensity detection and compaction density and uniformity analysis, problems in the compaction process can be discovered in time, and path adjustments can be made according to the pavement compaction quality assessment report, thereby improving the quality and service life of the road. By using vibration sensors to dynamically monitor the compaction process, compaction density and uniformity data can be obtained in real time. Through digital twin reconstruction, the operation process of the roller can be simulated and analyzed to improve the predictability and traceability of the operation. By visualizing the rolling trajectory coordinate mapping data, the roller's operating trajectory can be intuitively displayed.

[0011] Preferably, the present invention further provides a roller rolling operation track recognition system, which is used to execute the roller rolling operation track recognition method as described above, and the roller rolling operation track recognition system comprises:

[0012] The modeling module is used to obtain the target rolling area; collect geospatial data of the target rolling area to obtain the geographical environment data of the working area; locate the roller to obtain the roller's position coordinates; perceive the roller's working environment in real time to obtain a three-dimensional model of the working environment;

[0013] The path candidate set generation module is used to identify the terrain features of the three-dimensional model of the working environment to obtain the environmental terrain feature mapping data; perform geographic topological analysis on the target rolling area based on the environmental terrain feature mapping data to obtain the working area topological model; perform matching analysis on the roller position coordinates and the working area topological model to obtain the roller working path candidate set;

[0014] The path optimization module is used to select the travel path of the roller based on the candidate set of roller operation paths and the environmental terrain feature mapping data to obtain the rolling operation trajectory path; perform coverage analysis on the rolling operation trajectory path to obtain the rolling area integrity assessment data; dynamically adjust the rolling operation trajectory path according to the rolling area integrity assessment data to obtain the optimized rolling operation trajectory path;

[0015] The compaction quality monitoring module is used to detect the intensity of sound waves using a vibration sensor according to the optimized rolling operation trajectory path to obtain dynamic monitoring data of the compaction process; analyze the compaction density and uniformity of the dynamic monitoring data of the compaction process to obtain a road compaction quality assessment report; adjust the optimized rolling operation trajectory path according to the road compaction quality assessment report to obtain a compaction quality enhancement operation path;

[0016] The visualization module is used to digitally reconstruct the operation process of the roller based on the compaction quality enhanced operation path and the geographic environment data of the operation area to obtain a digital mapping model of the operation process; extract geographic spatial information from the digital mapping model of the operation process to obtain rolling trajectory coordinate mapping data; visualize the rolling trajectory coordinate mapping data to obtain a visualization report of the roller operation trajectory.

[0017] The present invention significantly improves the accuracy and efficiency of operations through automation technology, reducing the need for manual operation. The system can perceive the working environment in real time and build a three-dimensional model, promptly identify terrain features, and provide an accurate working path for the roller. The system dynamically selects and optimizes the rolling operation trajectory to ensure the continuity and integrity of the operation. By using vibration sensors to collect data from the compaction process, the system can evaluate the quality of pavement compaction in real time to ensure compliance with standards. The application of digital twin technology digitizes the operation process, improving the predictability and traceability of the operation. The visualization of the operation trajectory makes monitoring and analysis more intuitive and easy to understand. The system also helps to reduce operational risks, improve the safety and reliability of operations, while improving the overall quality of road projects and extending the service life of roads. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent from the detailed description made with reference to the following drawings:

[0019] Figure 1 A schematic flow chart of the steps of a method for identifying a rolling operation trajectory of a road roller according to an embodiment is shown.

[0020] Figure 2 A detailed flow chart of step S26 of an embodiment is shown.

[0021] Figure 3 A detailed flow chart of step S37 of an embodiment is shown. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for identifying a rolling operation track of a road roller, comprising the following steps:

[0026] Step S1: Acquire the target rolling area; collect geographic spatial data of the target rolling area to obtain geographic environment data of the working area; locate the roller to obtain the position coordinates of the roller; perceive the working environment of the roller in real time to obtain a three-dimensional model of the working environment;

[0027] Step S2: identifying terrain features of the three-dimensional model of the working environment to obtain environmental terrain feature mapping data; performing geographic topological analysis on the target rolling area based on the environmental terrain feature mapping data to obtain a working area topological model; matching and analyzing the roller position coordinates with the working area topological model to obtain a roller working path candidate set;

[0028] Step S3: selecting a travel path for the roller based on the roller operation path candidate set and the environmental terrain feature mapping data to obtain a rolling operation trajectory path; performing coverage analysis on the rolling operation trajectory path to obtain rolling area integrity assessment data; dynamically adjusting the rolling operation trajectory path according to the rolling area integrity assessment data to obtain an optimized rolling operation trajectory path;

[0029] Step S4: using a vibration sensor to detect the intensity of sound waves according to the optimized rolling operation trajectory path to obtain dynamic monitoring data of the compaction process; performing compaction density and uniformity analysis on the dynamic monitoring data of the compaction process to obtain a road surface compaction quality assessment report; adjusting the optimized rolling operation trajectory path according to the road surface compaction quality assessment report to obtain a compaction quality enhanced operation path;

[0030] Step S5: Based on the compaction quality enhanced operation path and the geographic environment data of the operation area, the operation process of the roller is digitally reconstructed as a twin to obtain a digital mapping model of the operation process; geographic spatial information is extracted from the digital mapping model of the operation process to obtain rolling trajectory coordinate mapping data; the rolling trajectory coordinate mapping data is visualized to obtain a visualization report of the roller operation trajectory.

[0031] In this embodiment, first, an aerial remote sensing scan of the target rolling area is performed using a drone equipped with a high-resolution camera to obtain the geospatial image of the operating area. The flight altitude of the drone is set to 200 meters, and the camera resolution is set to 0.05 meters / pixel. After covering the entire area, the image data is transmitted to the GIS software for processing, including correction, splicing and enhancement, to obtain the geographical environment data of the operating area. The roller is positioned in real time using the GPS and IMU systems to obtain the precise position coordinates of the roller. At the same time, a ground laser scanner (LiDAR) is used to perform a three-dimensional spatial scan of the operating environment to generate a three-dimensional model of the operating environment. A deep learning algorithm is used to identify the terrain features of the three-dimensional model and extract the terrain feature mapping data. Based on these data, a geographic topological analysis is performed to construct a topological model of the operating area. Using the spatial analysis tool of the GIS software, the roller position coordinates are matched and analyzed with the topological model of the operating area, and a candidate set of roller operating paths is intelligently generated. According to the candidate set of operating paths and the environmental terrain feature mapping data, the optimal travel path is selected to obtain the rolling operation trajectory path. The coverage analysis tool of GIS software is used to evaluate the integrity of the rolling area, and the trajectory path is dynamically adjusted to optimize the rolling operation trajectory path. In the actual rolling operation, the vibration sensor installed on the roller is used to detect the intensity of sound waves and collect dynamic monitoring data of the compaction process. These data are input into the data analysis software to analyze the compaction density and uniformity and generate a pavement compaction quality assessment report. According to the assessment report, the rolling operation trajectory path is adjusted and optimized again to enhance the compaction quality. Finally, based on the compaction quality enhancement operation path and the geographical environment data of the operation area, the operation process of the roller is reconstructed in the digital twin platform to obtain a digital mapping model of the operation process. The rolling trajectory coordinate mapping data is extracted through GIS software, and visualized to generate a visualization report of the roller operation trajectory.

[0032] Preferably, step S1 comprises the following steps:

[0033] Step S11: acquiring a target rolling area, and performing an aerial remote sensing scan of the target rolling area by an unmanned aerial vehicle to obtain a geographic spatial image of the operation area;

[0034] Specifically, the target rolling area can be obtained first, and an aerial remote sensing scan of the designated construction area can be performed using a drone equipped with a high-resolution camera. The drone's flight altitude is set to 200 meters, and the flight path is pre-planned to ensure that the drone can cover the entire target area and fly in a grid pattern from north to south and from west to east. During the flight, the drone automatically captures high-resolution geospatial images, and the resolution of these images is set to 0.05 meters / pixel to ensure that the subtle features on the ground can be captured. After shooting, the drone transmits the image data to the computer system of the ground control station. In the computer system, professional geographic information system (GIS) software is used to process the images, including correction, splicing and enhancement, to obtain geospatial images of the work area.

[0035] Step S12: extracting geomorphic features from the geospatial image of the operation area to obtain geomorphic classification data of the operation area;

[0036] Specifically, image processing software can be used to pre-process the geospatial images of the work area, including removing clouds, shadows, and enhancing color contrast. Then, a convolutional neural network (CNN) is used to classify the images. In the training phase, the CNN model is trained using known landform sample data, which includes different types of terrain, such as grass, sand, gravel, etc., with at least 100 training images for each category. After the training is completed, the model is applied to the images of the entire work area, and the landform classification data of the work area is obtained through the classification ability of the model. The classification results mark different landform types with different colors, for example, grass is green, sand is yellow, and gravel is gray.

[0037] Step S13: Performing geographic semantic fusion on the geomorphic classification data of the operation area to obtain geographic environment data of the operation area;

[0038] Specifically, GIS software can be used to overlay and analyze the geomorphic classification data of the working area with other geographic information layers, which include land use data, soil type data, and vegetation cover data of the target rolling area. For example, land use data shows that certain areas are farmland, while soil type data indicates that the soil type in these areas is loam. Through the overlay function of GIS software, these data are combined with the geomorphic classification data to form a comprehensive geographic environment dataset. In this process, appropriate fusion rules are selected, for example, giving priority to farmland areas in land use data because these areas require special compaction treatment. The fused geographic environment dataset will contain detailed geographic semantic information for each pixel, such as soil type, vegetation type, and land use type, which will be stored in the GIS database in the form of attribute tables.

[0039] Step S14: constructing a geographic coordinate system for the target rolling area to obtain geographic reference coordinates of the working area;

[0040] Specifically, you can use a GPS device to conduct field measurements at the four corners and key feature points (such as bridges, culverts, etc.) of the construction site in the target rolling area, record the WGS84 coordinates of each point, import these coordinate data into the GIS software, and create a new geographic coordinate system, select the WGS84 coordinate system as the benchmark, and set the projection parameters in the GIS software, for example, select the UTM (Universal Transverse Mercator) projection, and specify specific areas in the northern and eastern hemispheres, such as UTM zone 45N. In this way, we can convert GPS coordinates into plane coordinates, and finally, use the mapping tools in the GIS software to draw the boundaries of the work area based on the measured coordinate points and generate a geographic reference coordinate map of the work area.

[0041] Step S15: positioning the roller based on the geographic reference coordinates of the working area to obtain the position coordinates of the roller;

[0042] Specifically, a high-precision GPS receiver can be installed on the roller, which can receive signals from at least 4 satellites. The sampling rate of the GPS receiver is set to 1Hz, that is, the position data is updated once per second. At the same time, the IMU provides the pitch, roll and yaw angles of the roller, as well as acceleration and angular velocity information, which are used to assist GPS positioning, especially in environments where satellite signals are blocked. The positioning system transmits the collected data to the ground control center in real time through the wireless communication module. At the ground control center, GIS software is used to receive and process these data, and the GPS and IMU data are matched with the previously established geographic coordinate system to obtain the precise position coordinates of the roller in the working area. These coordinate data include the X coordinate in the east-west direction and the Y coordinate in the north-south direction, as well as the elevation Z coordinate relative to the reference surface, forming a three-dimensional position coordinate system with an accuracy of centimeters.

[0043] Step S16: Perform a three-dimensional spatial scan on the working environment of the road roller to obtain a three-dimensional model of the working environment.

[0044] Specifically, a terrestrial laser scanner can be mounted on a slowly moving survey vehicle and traverse the work area along a preset path. The scanner emits laser pulses and measures the time it takes for the laser pulses to hit the ground and surrounding objects and return, thereby calculating the distance. The laser scanner is set to a horizontal angular resolution of 0.01 degrees, a vertical angular resolution of 0.01 degrees, and a scanning range of 300 meters. The scanner collects data at a rate of 1 million points per second and generates a point cloud containing X, Y, and Z coordinates. These point cloud data are transmitted to data processing software, which uses algorithms to denoise, filter, and segment the point cloud to identify the ground and obstacles. The software converts the processed point cloud data into a 3D mesh model, which represents the elevation changes of the terrain and the spatial location of obstacles in the form of a triangular mesh. Finally, this 3D model is imported into the GIS software, aligned with the geographic reference coordinates, and integrated with other geographic information layers (such as landform classification data and geographic environment data) to form a 3D model of the work environment.

[0045] The present invention improves the efficiency of geospatial data collection through unmanned aerial remote sensing scanning, quickly covers large areas, and is faster than traditional methods. By extracting geomorphic features from geospatial images, detailed geomorphic classification data can be obtained. The availability of data is enhanced through geographic semantic fusion, and the geomorphic classification data is combined with geographic environmental data to provide more comprehensive background information for roller operations. The constructed geographic coordinate system provides an accurate reference framework for roller operations, ensuring the precise alignment of operations and the accuracy of path planning. The position of the roller and environmental changes can be monitored through real-time positioning and three-dimensional spatial scanning.

[0046] Preferably, step S2 comprises the following steps:

[0047] Step S21: semantically segmenting and annotating the three-dimensional model of the working environment to obtain a semantically annotated data set of the working environment;

[0048] Specifically, a pre-trained deep learning network, such as U-Net or DeepLabV3+, which performs well in image segmentation tasks, can be used to convert the point cloud data of the three-dimensional model of the working environment into a series of two-dimensional orthophoto images, which show the terrain of the working environment from different angles. These images are input into the deep learning network for pixel-level semantic segmentation. The network is trained to recognize different terrain features, such as roads, vegetation, water bodies, and buildings. During the training process, a batch of annotated data containing these features is used, with at least 1,000 annotated images for each category. After training, the network can automatically segment and annotate new image maps, assigning each pixel to the corresponding category. The segmentation results are displayed in color-coded form, for example, roads are red, vegetation is green, water bodies are blue, and buildings are gray. These annotated data are stored as a dataset, and each pixel contains its corresponding category label, thus forming a semantic annotation dataset for the working environment.

[0049] Step S22: clustering the terrain features of the working environment semantic annotation dataset to obtain an environment layered terrain feature dataset;

[0050] Specifically, clustering algorithms, such as K-means or DBSCAN, can be used to cluster the pixels in the semantic annotation dataset of the working environment. For example, select the K-means algorithm and set the K value to 5, which represents the number of terrain feature categories that you want to distinguish. The algorithm will group similar pixels according to the semantic labels and spatial location information of the pixels. During the clustering process, some parameters are set for the algorithm, such as the maximum number of iterations is 100 and the distance threshold is 2. After clustering, a hierarchical terrain feature dataset is obtained, and the pixels of each category are organized together to form different terrain feature layers. These layers include but are not limited to road layers, vegetation layers, water layers, and building layers. Each layer contains a set of pixels corresponding to the features, as well as their geometric and spatial information.

[0051] Step S23: performing terrain classification encoding on the environment layered terrain feature data set to obtain a terrain complexity assessment data set;

[0052] Specifically, a set of terrain classification standards can be defined based on factors such as terrain slope, elevation change, and land cover type. For example, the slope is divided into five levels: 0-5%, 5-15%, 15-30%, 30-45%, and above 45%, and each level corresponds to a code value, such as 1, 2, 3, 4, and 5. The elevation change is divided into three levels based on the relative height difference: 0-5 meters, 5-10 meters, and above 10 meters, with code values ​​of 1, 2, and 3 respectively. The land cover type (such as grassland, forest, and water) is also assigned different code values. Using the terrain analysis tool in the GIS software, the slope and elevation of each terrain feature layer are analyzed, and the corresponding code value is automatically assigned to each pixel or grid. These code values ​​reflect the complexity of the terrain. For example, areas with steeper slopes require the roller to slow down or use special operating techniques, while areas with large elevation changes require additional soil removal or filling work. Finally, a terrain complexity assessment dataset is obtained, which contains the terrain complexity code value of each area.

[0053] Step S24: performing geological structural association on the terrain complexity assessment data set to obtain environmental terrain feature mapping data, and performing spatial structure reconstruction on the environmental terrain feature mapping data to obtain an environmental geographic topological connectivity model;

[0054] Specifically, geological structure data of the target rolling area can be collected, including geological maps, seismic data, and drilling data. These geological structure data are superimposed and analyzed with the terrain complexity assessment dataset using GIS software to identify the impact of geological structures on terrain features. For example, knowing that the terrain near the fault line will be more fragmented and complex, a higher complexity value will be assigned to the terrain features in these areas. Spatial analysis tools are used to reconstruct the spatial structure of the terrain feature mapping data to identify the spatial relationship and connectivity between terrain features. Minimum cost path analysis is used to determine the best connection path between different terrain features, or network analysis is used to identify the connectivity pattern of terrain features. Through these analyses, environmental terrain feature mapping data can be obtained, which not only contains the spatial location of terrain features, but also contains the spatial relationship and connectivity information between them. Finally, an environmental geographic topological connectivity model is constructed, which shows the connectivity between terrain features in the form of a graph. In this model, each terrain feature is a node, and the lines between nodes represent the connectivity between terrain features. The weight of the line reflects the cost or complexity of the path.

[0055] Step S25: dividing the target rolling area into operating areas based on the environmental geographic topological connectivity model to obtain an operating area topological model;

[0056] Specifically, the environmental geo-topological connectivity model can be imported into the GIS software, and then the density-based DBSCAN algorithm is selected to identify natural partitions in the connectivity model. Parameters are set for the DBSCAN algorithm, such as selecting a suitable neighborhood radius (e.g., a radius of 10 meters) and setting a minimum point threshold (e.g., at least 30 points in an area). These parameters help the algorithm identify areas that are closely connected in space, which have similar characteristics in topography and geological structure and are suitable as a single working area. Run the clustering algorithm, and the GIS software will automatically divide the target rolling area into multiple working areas according to the set parameters. Each working area is assigned a unique identifier, and the nodes and links within each area are marked as belonging to the area. The terrain characteristics of each working area, such as slope, elevation, and surface cover type, are further analyzed to determine the difficulty of each area and the required compaction strategy. For example, one work area contains steep slopes and loose soil, requiring the use of specific compaction equipment and techniques; while another area is relatively flat and can be worked with a standard roller. The final result is a work area topology model that describes in detail the boundaries, internal structure and characteristics of each work area, as well as the connectivity between them.

[0057] Step S26: performing matching analysis on the roller position coordinates and the operating area topology model to obtain a candidate set of roller operating paths.

[0058] Specifically, please refer to the sub-steps of step S26 for the detailed implementation process of this embodiment.

[0059] The present invention realizes accurate identification and distinction of different elements in the working environment through environmental understanding. A layered terrain feature data set is formed by clustering terrain features, which simplifies the understanding and application process. The quantitative assessment of terrain complexity helps to identify construction difficulties and risks. The understanding of the relationship between terrain features and geological structures is deepened through geological structure association, and the generated environmental terrain feature mapping data provides deeper geographic information for work path planning. The environmental geographic topological connectivity model is further constructed through the reconstruction and topological analysis of the spatial structure. Based on this model, the working area can be accurately divided, and a topological model of the working area can be formed to provide the best working path selection for the roller. Through the matching analysis of the roller position coordinates and the working area topological model, the roller working path candidate set is intelligently generated to optimize the working process and improve the working efficiency.

[0060] Preferably, step S26 comprises the following steps:

[0061] Step S261: Associating the roller position coordinates with the topological model of the working area to obtain preliminary working path matching data;

[0062] Specifically, the working area topology model can be loaded and a buffer radius, such as 50 meters, can be set. This buffer is used to determine the relationship between the current position of the roller and each node in the working area topology model. When the roller position coordinates fall into the buffer of a certain working area, the area is identified as the current working area of ​​the roller. The central control software uses the spatial query function of GIS, such as "Query within radius", to identify the working area node closest to the current position of the roller, and record this information to form preliminary working path matching data.

[0063] Step S262: Calculate the shortest path and the optimal channel based on the preliminary operation path matching data to obtain operation path feasibility assessment data;

[0064] Specifically, the preliminary operation path matching data can be loaded into the GIS software. These data include the association information between the current position of the roller and the nodes in the operation area. The appropriate network analysis algorithm, such as the Dijkstra algorithm, is selected to calculate the shortest path. The calculation of the optimal channel needs to consider factors such as the length, slope, curvature and road conditions of the path. Weight parameters are set for the algorithm. For example, the weight of the path with a slope greater than 10% is increased by 1.5 times, and the weight of the path with a curvature radius less than 15 meters is increased by 2 times. These weight parameters help the algorithm identify the optimal channel under the current operating conditions. When the network analysis algorithm is run, the GIS software will automatically calculate the shortest path and the optimal channel from the current position of the roller to each node in the operation area according to the set weight parameters. The results of the algorithm include information such as the length of each path, the estimated travel time, and the complexity of the terrain. This information is used to evaluate the feasibility of the operation path. Finally, the operation path feasibility evaluation data is obtained, which describes in detail the advantages and disadvantages of each candidate operation path.

[0065] Step S263: constructing a feature vector for the operation path feasibility assessment data to obtain a candidate operation path feature space;

[0066] Specifically, a series of features can be defined that describe the key attributes of each candidate operation path, such as path length, average slope, maximum curvature, road material, estimated travel time, and energy consumption. For each candidate path in the operation path feasibility assessment data, GIS software and vehicle performance database are used to extract the specific values ​​of these features. For example, a specific path is found to be 1.5 kilometers long, with an average slope of 3%, a maximum curvature of 15 meters, a road material of asphalt, an estimated travel time of 10 minutes, and an energy consumption of 20 liters of diesel. These values ​​are constructed as a feature vector, such as [1.5, 0.03, 15, "asphalt", 10, 20]. Such feature vectors are constructed for all candidate operation paths and stored in a feature space, each vector representing a candidate path. Use machine learning libraries, such as Python's scikit-learn, to construct and operate feature spaces. Features need to be normalized to ensure that numerical features are on the same scale, such as using MinMaxScaler to scale all features to the range of 0 to 1.

[0067] Step S264: extracting path constraint boundary extreme values ​​from the candidate operation path feature space to obtain a set of operation path feasibility constraint conditions;

[0068] Specifically, the constraints of the operation path can be determined first, including the maximum allowable slope, the minimum curvature radius, the road material restrictions, and the operation time window. For example, the maximum allowable slope is set to 10%, the minimum curvature radius is set to 20 meters, only asphalt or concrete roads can be passed, and the operation time window is from 7 am to 5 pm. Each feature vector in the feature space is analyzed using GIS software and programming scripts to extract the paths that meet these constraints. For each candidate path, check whether the slope value in its feature vector is less than or equal to 10%, whether the curvature is greater than or equal to 20 meters, whether the road material is asphalt or concrete, and whether the estimated travel time falls within the operation time window. If a path meets all these constraints, it is marked as feasible and its feature vector is added to the set of feasibility constraints for the operation path. In this way, a set of candidate operation paths that meet all constraints can be obtained.

[0069] Step S265: performing adaptability evaluation of the operation path based on the feasibility constraint condition set of the operation path to obtain a preliminary adaptability index of the operation path;

[0070] Specifically, criteria for adaptability assessment can be defined, which include the safety, efficiency, and environmental impact of the path. A weighted scoring system is used, in which each criterion is assigned a weight that reflects their relative importance in the overall assessment. For example, safety accounts for 50%, efficiency accounts for 30%, and environmental impact accounts for 20%. GIS software and a customized evaluation algorithm are used to calculate the adaptability index of each path. For safety, the slope, curvature, and traffic volume of the path are considered; for efficiency, the path length and estimated travel time are considered; for environmental impact, sensitive ecological areas and noise restrictions around the path are considered. Each criterion of each path is scored, and then a comprehensive adaptability index is calculated based on the respective weights. For example, a path scored 8 points for safety, 7 points for efficiency, and 6 points for environmental impact, and the comprehensive adaptability index is calculated as 0.5×8+0.3×7+0.2×6=7.10.5×8+0.3×7+0.2×6=7.1. This index provides a score of 0 to 10 for each path, where 10 indicates full adaptability. This index is calculated for all candidate paths and used as the preliminary fitness index.

[0071] Step S266: Perform Monte Carlo risk simulation on the preliminary adaptability index of the operation path to obtain an operation path risk assessment report, and perform path robustness intelligent screening on the preliminary operation path matching data based on the operation path risk assessment report to obtain a candidate set of roller operation paths.

[0072] Specifically, the risk of each path can be assessed using a Monte Carlo simulation method. In this process, a probability distribution is defined for each factor that affects the suitability of the path (such as slope, curvature, etc.), which reflects the uncertainty and variability of these factors. For example, the slope varies in a normal distribution with a mean of 5% and a standard deviation of 1%. A simulation script is written to randomly generate values ​​for these factors and calculate the fitness index of each path under these conditions. This process is repeated, for example, 1000 times, to generate a distribution of fitness indices. By analyzing this distribution, it is possible to estimate the performance of each path under different conditions and identify those that perform well in most situations. Based on the simulation results, a risk assessment report is calculated for each path, including the average fitness index, the worst-case fitness index, and the standard deviation of the fitness index. This information helps assess the robustness of each path. Those paths that perform stably in the simulation and have high fitness indexes are selected as candidate sets of roller operation paths. For example, those paths with an average fitness index higher than 7 and a standard deviation lower than 0.5 are selected. In this way, a set of robust and low-risk operation path candidate sets can be obtained.

[0073] The present invention realizes efficient operation path planning through path matching and optimized path selection. By calculating the shortest path and the optimal channel, the feasibility of the path is evaluated, so as to select the most efficient operation route. The constructed operation path feature vector can identify and quantify the key features of the path. By extracting the boundary extreme value, the path constraint is enhanced to ensure that the path planning meets the actual operation requirements. Adaptability evaluation helps to identify the path that best suits the current operation conditions, thereby improving the flexibility of the operation. By using Monte Carlo risk simulation, potential risks can be predicted, and operation paths with high robustness can be intelligently screened out to enhance the stability and reliability of the path.

[0074] Preferably, step S3 comprises the following steps:

[0075] Step S31: constructing a terrain topology constraint model for the roller's travel path based on the roller's work path candidate set and the environmental terrain feature mapping data to obtain a work path topology constraint model;

[0076] Specifically, GIS software can be used to integrate the roller operation path candidate set with the environmental terrain feature mapping data. The roller operation path candidate set is loaded into the GIS as a layer, and the environmental terrain feature mapping data, including the slope, elevation, soil type and vegetation cover of the terrain, is loaded into the GIS as another layer. Use the spatial analysis tools of GIS to identify the interaction between the path and the terrain features. For example, set the slope threshold to 15% to identify all areas with slopes exceeding this value and mark them as potential high-risk areas. Similarly, identify areas with low soil bearing capacity or areas where dense vegetation affects roller operation. Through these analyses, a terrain topology constraint model is constructed, which contains the spatial relationship and interaction between the path candidate set and the terrain features. This model helps understand which paths are feasible and which need to be adjusted or avoided. For example, if a path candidate set passes through a high slope area, the model will prompt that the path needs to be replanned.

[0077] Step S32: analyzing the constraint conditions of the operation path topology constraint model to obtain a set of terrain adaptability constraint indicators;

[0078] Specifically, a series of terrain suitability constraints can be defined, including the maximum allowable slope, minimum radius of curvature, soil type suitability score, and vegetation coverage. Use the query and analysis tools of the GIS software to extract the specific values ​​of these constraints. For example, if the maximum allowable slope is set to 10%, the GIS software will automatically extract all areas with slopes exceeding this value and mark them as unsuitable areas. Areas with insufficient soil bearing capacity can be identified based on the soil type suitability score, or areas that require additional cleaning can be identified based on the vegetation coverage. Through these analyses, a set of terrain suitability constraint indicators can be obtained, which includes all terrain constraints that affect the operation of the roller. These indicators include the specific values ​​and spatial distribution of slope, curvature, soil type suitability score, and vegetation coverage. For example, if a path passes through an area with a low soil type suitability score, then the path needs additional soil improvement measures or needs to be replanned to avoid these areas.

[0079] Step S33: mapping the topological constraint information of the terrain adaptability constraint index set to obtain a geographic space adaptive constraint matrix, and screening the roller operation path candidate set according to the geographic space adaptive constraint matrix to obtain an initial rolling operation trajectory path;

[0080] Specifically, a set of terrain adaptability constraint indicators can be loaded into GIS, including slope, curvature, soil type, and vegetation coverage, and the spatial analysis tools of GIS can be used to create a topological relationship table that describes the spatial relationship between each path candidate set and the terrain features. For example, it is found that path candidate set 1 intersects an area with a slope greater than 15%, and path candidate set 2 passes through an area with a soil type suitability score less than 3. The GIS software maps this information into a matrix, where each cell represents a combination of a path candidate set and a terrain feature, and the value of the cell indicates whether the combination satisfies the topological constraint (for example, 1 means it satisfies and 0 means it does not satisfy). Specific parameter values ​​are set to define these constraints, for example, areas with a slope greater than 15% are marked as unsuitable, and areas with a soil type suitability score less than 3 are also marked as unsuitable. The GIS software automatically fills in the matrix based on these parameters to create a geospatial adaptive constraint matrix. This matrix helps understand which path candidate sets are feasible and which need to be excluded. Use this matrix to screen the working path candidate sets of the roller. The GIS software automatically selects the paths that meet all topological constraints based on the values ​​in the matrix, and these paths constitute the initial rolling operation trajectory path. For example, if all the cell values ​​of the path candidate set 3 in the matrix are 1, then it is selected as part of the initial rolling operation trajectory path, and finally a set of initial rolling operation trajectory paths that meet all terrain adaptability constraints are obtained.

[0081] Step S34: performing a topological connectivity evaluation on the initial rolling operation trajectory path to obtain an operation path connectivity index;

[0082] Specifically, GIS software can be used to analyze the connectivity of the path to ensure that the roller does not encounter obstacles or disconnected paths when moving from one area to another. First, the initial rolling operation trajectory paths are loaded in the GIS, which include the paths that meet the terrain adaptability constraints screened out in step S33. Use the network analysis tool of GIS, the topology analysis function, to evaluate the connectivity between the paths. Set parameters, for example, define the maximum allowable distance between two path nodes as 10 meters to ensure that they are considered connected. The GIS software automatically detects the distance between path nodes and marks nodes that exceed this distance, which represent potential connectivity problems. Through analysis, the operation path connectivity indicators can be obtained, which include the connectivity status of each path segment and the location that needs to be improved. For example, it is found that path A and path B are not connected at node C because the distance between them exceeds 10 meters.

[0083] Step S35: Calculate the steering angle and curvature constraints of the operation path connectivity index to obtain the operation path smoothness evaluation data.

[0084] Specifically, the work path connectivity indicators can be loaded into the road design software, which include the geometric data and connectivity information of the path. Use the analysis tools of the road design software to calculate the turning angle and curvature of each path segment. Set parameters, for example, specify a maximum turning angle of 45 degrees and a maximum curvature of 100 meters. The software automatically calculates the actual turning angle and curvature of each path segment and compares them with these parameters. Based on these calculations, the work path smoothness evaluation data can be obtained, which includes the turning angle and curvature values ​​of each path segment and whether they meet the set constraints. For example, it is found that the turning angle of a segment of path D is 50 degrees, which exceeds the set maximum value, indicating that the path segment needs to be adjusted to reduce sharp turns. Similarly, if the curvature radius of a path segment is less than 100 meters, it will also be marked as needing optimization.

[0085] Step S36: reconstructing the path morphology of the initial rolling operation track path based on the operation path smoothness evaluation data to obtain the rolling operation track path;

[0086] Specifically, the smoothness assessment data of the working path can be imported into the road design software. These data include the turning angle and curvature values ​​of each path segment and whether they meet the set constraints. For example, it is found that the curvature radius of a certain segment of path E is 80 meters, which is lower than the set 100-meter standard and needs to be adjusted. Use the software's path editing tool to reconstruct these path segments that do not meet the standard. For path E, the radius of curvature is increased by adjusting the geometry of the path to meet the 100-meter standard. This involves moving part of the path so that it follows a smoother curve, or adding transition curves to the path to reduce changes in turning angles and curvature. During the reconstruction process, other factors need to be considered, such as terrain, surrounding environment, and construction restrictions. For example, if path F needs to be adjusted to avoid passing through a sensitive ecological area, the path needs to be replanned to bypass the area while maintaining the required curvature radius and turning angle. Finally, a set of optimized rolling operation trajectory paths is obtained.

[0087] Step S37: Perform coverage analysis on the rolling operation trajectory path to obtain rolling area integrity assessment data, and dynamically adjust the rolling operation trajectory path according to the rolling area integrity assessment data to obtain an optimized rolling operation trajectory path.

[0088] Specifically, please refer to the sub-steps of step S37 for the detailed implementation process of this embodiment.

[0089] The present invention enhances the adaptability of the roller to complex terrain by constructing a terrain topology constraint model, ensures the precise matching of the working path with the terrain features, and improves the safety of the operation. The most suitable working path can be automatically screened out by applying the geospatial adaptive constraint matrix. The continuity of the operation is guaranteed and interruptions are avoided by evaluating the connectivity of the working path. The smoothness of the path is further improved by calculating the constraints of the steering angle and curvature, which reduces mechanical wear and improves the working efficiency. The working trajectory path is morphologically reconstructed based on the smoothness evaluation data to optimize the path quality. The integrity of the working area is ensured by coverage analysis, which avoids missed compaction and repeated compaction and improves the working quality. The dynamic path adjustment can optimize the path in real time according to the working area integrity evaluation data, adapt to changes in the working process, and ensure the working effect. The present invention reduces unnecessary mechanical mobilization and repeated operations.

[0090] Preferably, step S37 includes the following steps:

[0091] Step S371: Calculate the area coverage rate of the rolling operation track path to obtain preliminary statistical data of the rolling coverage rate;

[0092] Specifically, the rolling operation trajectory paths can be loaded into the GIS as vector data. These paths represent the areas that the roller actually rolled. The boundaries of the target rolling area can be loaded into the GIS as another vector layer. This boundary can be the planned boundary of the road project or the ground area that needs to be compacted. Using the area analysis tool of the GIS software, the area covered by each rolling operation trajectory path is calculated and compared with the total area of ​​the target rolling area. For example, it is found that the area actually rolled by the roller is 5,000 square meters, while the total area of ​​the target rolling area is 10,000 square meters. The GIS software automatically calculates the coverage rate, which is the ratio of the actual rolling area divided by the area of ​​the target area. In this example, the coverage rate is 50%. These calculation results provide preliminary statistical data on the area coverage of the rolling operation trajectory paths.

[0093] Step S372: performing spatial interpolation and regional gap filling on the preliminary statistical data of rolling coverage to obtain preliminary assessment data of coverage area integrity;

[0094] Specifically, preliminary statistics of rolling coverage can be attached as attribute data to the vector layer of each rolling operation track path. Using the spatial analysis tools of the GIS software, the uncovered or insufficiently covered areas are identified and spatially interpolated. For example, the inverse distance weighted (IDW) interpolation method is used to predict the coverage of the uncovered area, and a power parameter of 2 is selected during interpolation to enhance the influence of neighboring points. Through interpolation, a continuous coverage surface can be obtained, which shows the predicted coverage at each location. Fill the identified gap areas. Using the buffer analysis tool of the GIS software, a buffer is created for each rolling operation track path, and the buffer distance is set to half the roller rolling width, such as 2 meters. This buffer helps identify uncovered areas adjacent to the existing path, which require additional rolling operations to fill the gaps. Through spatial interpolation and regional gap filling, preliminary assessment data on the completeness of the coverage area can be obtained. These data include the predicted coverage at each location and the area that requires additional rolling. For example, it is found that in a certain area, the predicted coverage is less than 95%, which indicates that additional rolling operations are needed in this area to ensure complete coverage.

[0095] Step S373: performing rolling uniformity assessment based on the preliminary assessment data of coverage area integrity to obtain a rolling area uniformity assessment index;

[0096] Specifically, preliminary assessment data of coverage area integrity, including predicted coverage and buffer analysis results, can be used as input data. Using the raster analysis tool of the GIS software, the predicted coverage surface is overlaid with the actual rolling path to identify the variability of coverage. For example, it is found that the coverage of some areas is much higher or lower than that of the surrounding areas, which indicates that there is unevenness in the rolling operation. Set a standard deviation threshold, such as 5%, to define the acceptable range of variation in coverage. The statistical analysis tool calculates the standard deviation between the coverage of each grid cell and the average coverage to evaluate the uniformity of coverage. If the standard deviation of an area exceeds the set threshold, the area is marked as a potential uneven coverage area. Finally, the rolling area uniformity assessment indicators are obtained, which include the standard deviation value of each area and the comparison results with the threshold.

[0097] Step S374: performing rolling integrity assessment on the target rolling area based on the rolling area uniformity assessment index to obtain rolling area integrity assessment data;

[0098] Specifically, the spatial query function of GIS software can be used to identify all areas that do not meet the uniformity standards by combining uniformity assessment indicators and preliminary assessment data. For example, it was found that in the northwest of the target compaction area, the standard deviation of coverage exceeded the threshold of 5%, indicating that the compaction coverage in this area was uneven. These uneven areas are analyzed in detail to determine whether additional compaction operations are required. The hotspot analysis tool of GIS software is used to identify areas with high and low coverage. These hotspot areas indicate areas of over-compaction or under-compaction. Finally, the compaction area integrity assessment data is obtained, which includes the uniformity assessment results and hotspot analysis results for each area.

[0099] Step S375: performing constraint parameter matching on the compaction area integrity assessment data to obtain area compaction optimization correction parameters;

[0100] Specifically, the compaction area integrity assessment data can be loaded into GIS, which includes the uniformity assessment results and hot spot analysis results of each area. According to the assessment data, the parameters that need to be optimized are determined, such as areas where the number of compaction passes needs to be increased, areas where the compaction speed needs to be adjusted, or areas where the compaction direction needs to be changed. Specific constraint values ​​are set for these parameters. For example, for areas with insufficient compaction density, it is decided to add 2 rolling passes to ensure that the compaction degree reaches more than 95%. Using the project management software, a correction task is created for each area that needs to be optimized, and the corresponding correction parameters are assigned. For example, for a specific area, the correction parameter is set to "add 2 rolling passes and reduce the speed to 3km / h". These correction parameters are recorded in the project management software and associated with the corresponding GIS layers so that the construction team can adjust the operation according to these parameters. Finally, a set of regional compaction optimization correction parameters are obtained, which provide specific adjustment guidance for each area that needs to be optimized.

[0101] Step S376: Adjust the rolling operation trajectory path based on the regional rolling optimization correction parameters to obtain a preliminary optimized rolling operation trajectory path, and perform boundary constraints on the preliminary optimized rolling operation trajectory path to obtain an optimized rolling operation trajectory path.

[0102] Specifically, the regional compaction optimization correction parameters can be loaded into the GIS and associated with the compaction operation trajectory path layer. Use the editing tools of the GIS software to adjust the compaction operation trajectory path according to the correction parameters. For example, for areas that need to add 2 passes of compaction, copy the corresponding path segment in the GIS and superimpose the additional passes on the original path. Use CAD software to perform precise geometric design of the adjusted path, fine-tune the path to avoid conflicts with obstacles, and ensure that the path meets construction requirements. For example, the path needs to be adjusted to bypass a large rock or a protected vegetation area. Finally, the preliminary optimized compaction operation trajectory path is bounded. Use the buffer analysis tool of the GIS software to create a buffer for each adjusted path segment to ensure that the path does not exceed the predetermined construction boundary. For example, set a 2-meter buffer to ensure that the roller does not roll into unauthorized areas. Through these steps, the final optimized compaction operation trajectory path can be obtained.

[0103] The present invention calculates the regional coverage of the rolling operation trajectory path to provide a data basis for subsequent analysis, thereby improving the accuracy of the coverage. The continuity of coverage is enhanced by spatial interpolation and regional gap filling, and the uncovered or repeatedly covered areas are reduced. Based on the integrity assessment data, the rolling uniformity is evaluated to ensure the consistency of the compaction quality in the operating area. The integrity assessment ensures that no area that needs compaction is missed, thereby improving the comprehensiveness of the operation. By matching the constraint parameters of the rolling area integrity assessment data, the regional rolling optimization correction parameters are obtained. Dynamic path adjustment is performed based on these parameters, which improves the adaptability and optimization of the operating path, and ensures that the path adjustment meets the operating requirements through boundary constraint optimization.

[0104] Preferably, step S4 comprises the following steps:

[0105] Step S41: performing rolling operation on the target rolling area based on the optimized rolling operation trajectory path, and using a vibration sensor to detect the sound wave intensity to obtain operation dynamic sound wave intensity data;

[0106] Specifically, a roller equipped with a real-time data acquisition system can be used for the operation. The system includes multiple vibration sensors that are installed near the roller of the roller to measure and record the intensity of sound waves generated when the roller contacts the ground. Select a suitable vibration sensor, such as an accelerometer with a measurement range of ±10g and a sampling frequency of 1000Hz. After the rolling operation begins, the sensor collects sound wave intensity data in real time. These parameters are recorded as dynamic sound wave intensity data of the operation, which reflect the rolling effect of the roller in different areas. For example, when rolling an area with insufficient compaction, the sensor records a higher sound wave intensity, while a lower sound wave intensity is recorded in an area with good compaction.

[0107] Step S42: performing spectrum decomposition on the operation dynamic sound wave intensity data to obtain the operation sound wave vibration spectrum data;

[0108] Specifically, the dynamic sound wave intensity data of the operation can be imported into the signal processing software. Select Fast Fourier Transform (FFT) to convert the time domain signal into a frequency domain signal. Set the parameters of FFT, for example, select a suitable window size (such as 1024 points) and overlap ratio (such as 50%) to ensure the accuracy and efficiency of spectral decomposition. The software automatically executes the FFT algorithm to decompose the sound wave intensity data into spectral data of different frequency components. These spectral data include the amplitude and phase information of each frequency component, which reflects the frequency characteristics of the sound wave intensity data. For example, it is found that the amplitude is higher in the low-frequency area (such as 0-100Hz), while the amplitude is lower in the high-frequency area (such as 100-1000Hz).

[0109] Step S43: extracting spectrum features from the operation sound wave vibration spectrum data to obtain operation sound wave spectrum feature data;

[0110] Specifically, the operating acoustic vibration spectrum data can be imported into the software. These data include the amplitude and phase information of different frequency components. Select a suitable spectrum feature extraction method, such as by identifying key features such as peak frequency, valley frequency, and spectrum energy distribution in the spectrum. Set parameters, such as selecting a frequency range (such as 0-1000Hz) to focus on the frequency band most relevant to the compaction effect. The software automatically calculates and identifies the peaks and valleys in the spectrum, as well as their frequencies and amplitudes. For example, a peak frequency of 500Hz is identified, and the corresponding amplitude is 0.8G², which indicates that the vibration energy at this frequency is high and has a strong correlation with the compaction effect. The statistical features of the spectrum, such as mean, standard deviation, skewness, and kurtosis, can also be calculated to fully describe the characteristics of the spectrum. These features are extracted to form the operating acoustic spectrum feature data.

[0111] Step S44: performing compaction process monitoring modeling based on the operation sound wave spectrum characteristic data to obtain compaction process dynamic monitoring data;

[0112] Specifically, the operating sound wave spectrum feature data can be used as input features, and other relevant monitoring data such as rolling speed, number of rolling passes, and material type can be collected at the same time. Select random forest or gradient boosting machine (GBM) to build a compaction process monitoring model. Set model parameters, such as the number of trees is 100 and the maximum depth is 10. Using these parameters, the model learns the relationship between spectral features and compaction effects, and can predict key indicators in the compaction process, such as compaction degree and uniformity. After the model training is completed, the spectral feature data collected in real time is input into the model, and the model automatically outputs the prediction results of the compaction process, forming dynamic monitoring data for the compaction process. For example, the model predicts that the compaction degree of a certain area is 92%, indicating that additional rolling passes are required.

[0113] Step S45: Analyze the compaction density and uniformity of the dynamic monitoring data of the compaction process to obtain a road surface compaction quality assessment report, and adjust the optimized rolling operation trajectory path according to the road surface compaction quality assessment report to obtain a compaction quality enhanced operation path.

[0114] Specifically, the dynamic monitoring data of the compaction process can be imported into the construction management system. These data include the compaction prediction results obtained from step S44 and other related parameters, such as the number of compaction passes and material moisture in each area. Use the built-in data analysis tool of the system to perform statistical analysis on these data and calculate the overall and local compaction density and uniformity indicators. For example, the average compaction degree of a certain area is calculated to be 90%, but there is a situation where the compaction degree of a local area is less than 85%, which indicates that there is a problem of uneven compaction. Based on these analysis results, the system automatically generates a pavement compaction quality assessment report. The report lists in detail the compaction degree, uniformity evaluation of each area and the comparison results with the standard specifications. For example, the report points out that although the overall compaction degree meets the requirements, specific areas (such as the edge of the roadbed) require additional rolling to improve uniformity. According to the pavement compaction quality assessment report, the path optimization tool in the construction management system is used to adjust the optimized rolling operation trajectory path. Set adjustment parameters, for example, for areas with compaction below the standard, decide to add 1 to 2 rolling passes. The system automatically plans a new rolling operation path based on these parameters and the original operation trajectory path. For example, a new path is planned so that the roller makes an extra round trip at the edge of the roadbed, resulting in an operation path with enhanced compaction quality.

[0115] The present invention monitors the intensity of sound waves in real time through vibration sensors, provides direct physical feedback for the compaction process, and analyzes the operation sound wave vibration data through spectrum decomposition to reveal the compaction characteristics. The key features of the spectrum are extracted to provide accurate data for monitoring modeling, and dynamic monitoring of the compaction process is achieved, thereby enhancing the control of compaction quality. By analyzing the compaction density and uniformity, quantitative indicators are provided for the compaction quality of the road surface, and the operation path is adjusted according to the quality assessment report to optimize the compaction quality. The present invention helps to improve the compaction quality of the road surface, reduce the cost of later maintenance, and extend the service life of the road.

[0116] Preferably, step S45 includes the following steps:

[0117] Step S451: extracting the gravity center frequency feature of the dynamic monitoring data of the compaction process to obtain the gravity center frequency feature vector of the compaction process;

[0118] Specifically, you can choose Fast Fourier Transform (FFT) to analyze the dynamic monitoring data of the compaction process. Set the FFT parameters, select a suitable window size (such as 2048 points) and overlap ratio (such as 75%), and the software will automatically execute the FFT algorithm to convert the time domain signal into a frequency domain signal and calculate the amplitude of each frequency component. Next, calculate the center of gravity frequency, which is the weighted average of all frequency components, with the weight being the respective amplitude. For example, if a spectrum is obtained in which the amplitude is 0.5G² at a frequency of 300Hz, 0.8G² at a frequency of 500Hz, and 0.3G² at a frequency of 700Hz, the center of gravity frequency is calculated as This centroid frequency value forms part of the centroid frequency feature vector of the compaction process, which also includes other key frequency features such as the peak frequency of the spectrum, bandwidth, etc.

[0119] Step S452: evaluating the non-uniformity of compaction density in the target rolling area based on the gravity center frequency characteristic vector of the compaction process, obtaining a preliminary evaluation index of compaction density, and interpolating the preliminary evaluation index of compaction density to obtain pavement compaction density distribution data;

[0120] Specifically, the centroid frequency feature vector can be associated with the geographic location of the target compaction area, and the spatial interpolation function of the GIS software can be used to predict the compaction density of the entire area. Select an appropriate interpolation method, such as Kriging, and set parameters such as the variogram (such as a spherical model) and the search radius (such as 30 meters). Kriging takes into account spatial autocorrelation and provides an estimate of the compaction density at each location and its uncertainty. For example, it was found that at a particular location, the estimated value of the compaction density was 85%, while at another location, the estimated value was 90%. These estimates form a preliminary evaluation index of the compaction density. Using the interpolation tool of the GIS software, these discrete evaluation indicators are converted into a continuous compaction density distribution map. The interpolation results provide a spatial distribution of the pavement compaction density, helping to identify areas with high and low compaction density, as well as uneven areas that require additional attention.

[0121] Step S453: performing regional uniformity mapping on the road surface compaction density distribution data to obtain a compaction regional uniformity distribution map;

[0122] Specifically, the pavement compaction density distribution data can be loaded into the GIS as a raster layer. These data contain the estimated compaction density of each raster cell. Use the standard deviation or coefficient of variation (CV) calculation function of the raster analysis tool of the GIS software to evaluate the compaction density uniformity of each raster cell and its neighboring cells. Set parameters, such as selecting a 3x3 window size, to calculate the standard deviation or coefficient of variation of the compaction density within each window. These statistical indicators reflect the uniformity of the compaction density in each local area. Based on the calculation results, a compaction area uniformity distribution map is generated, in which different colors or shades represent different uniformity levels. For example, areas with a standard deviation below 5% are marked as green (indicating good uniformity), areas with a standard deviation between 5% and 10% are marked as yellow (indicating average uniformity), and areas with a standard deviation above 10% are marked as red (indicating poor uniformity).

[0123] Step S454: performing consistency evaluation based on the compaction area uniformity distribution map to obtain compaction uniformity evaluation data, and performing constraint matching on the compaction uniformity evaluation data to obtain key indicators of pavement compaction quality;

[0124] Specifically, the uniformity distribution map can be converted into numerical data, where the uniformity level of each grid cell is converted into a numerical index, for example, the green area is 1, the yellow area is 2, and the red area is 3. Use statistical analysis tools, such as descriptive statistical analysis, to calculate the overall and local uniformity assessment data, for example, calculate the average uniformity index and standard deviation of the entire area. Set constraints on compaction uniformity according to industry standards or project requirements. For example, it is stipulated that the average uniformity index of the entire area shall not exceed 2, or that the uniformity index of more than 75% of the area shall not exceed 1. Compare the actual uniformity assessment data with these constraints to determine whether the pavement compaction quality meets the requirements. Finally, the key indicators of pavement compaction quality are obtained, which include the overall uniformity assessment results and the proportion of areas that meet or do not meet the constraints. For example, if it is found that the uniformity index of more than 25% of the areas exceeds 2, it is necessary to increase the number of rolling passes or adjust the rolling equipment in these areas to improve the compaction uniformity.

[0125] Step S455: integrating and correlating key indicators of pavement compaction quality to obtain a pavement compaction quality assessment report;

[0126] Specifically, key indicators of pavement compaction quality can be imported into the quality management software. These data include uniformity grade numerical indicators for each grid unit, as well as overall and local uniformity assessment data, such as average uniformity indicators and standard deviations. At the same time, other key compaction quality indicators, such as compaction density, material ratio, and water content, are also imported into the software. These indicators are comprehensively analyzed using the data analysis module of the software. For example, it is found that there is a positive correlation between water content and compaction density, that is, an increase in water content leads to a decrease in compaction density. The software automatically calculates their weighted average to generate a comprehensive compaction quality score. Set weight parameters, for example, compaction uniformity accounts for 40% of the total score, compaction density accounts for 30%, and material ratio and water content each account for 15%. Based on these weight parameters and the actual indicator values, the software calculates a comprehensive score and generates a detailed pavement compaction quality assessment report. The report includes the values ​​of each key indicator, their contribution to the overall quality score, and a comparative analysis with historical data. For example, the report noted that although compaction uniformity was good, the compaction density was slightly below standard due to high moisture content, resulting in a lower overall score.

[0127] Step S456: Perform performance mapping on the pavement compaction quality assessment report to obtain key characteristic parameters of compaction quality, and perform parameter constraints on the key characteristic parameters of compaction quality to obtain pavement compaction quality enhancement parameters;

[0128] Specifically, the key indicators in the pavement compaction quality assessment report can be used as input features, and a machine learning model can be used to predict the performance of the compaction quality. Select a suitable model, such as a support vector machine (SVM), and set the parameters. Select the radial basis function (RBF) as the kernel function, set the regularization parameter C to 1.0, and the model learns the relationship between the key indicators and the compaction quality performance, and can predict the compaction quality under different conditions. Parameter constraints are imposed on the performance predicted by the model to obtain the pavement compaction quality enhancement parameters. For example, a constraint condition is set that the compaction density must not be lower than 92%. If the compaction density predicted by the model is lower than this value, the input parameters will be adjusted, such as increasing the number of rolling passes or adjusting the material ratio to increase the compaction density. Finally, the pavement compaction quality enhancement parameters are obtained. For example, if the model prediction shows that adding one rolling pass can increase the compaction density to 95%, the construction team is recommended to add one rolling pass in a specific area in the assessment report.

[0129] Step S457: Parameter mapping is performed on the optimized rolling operation trajectory path based on the pavement compaction quality enhancement parameters to obtain a compaction quality enhancement operation path.

[0130] Specifically, the pavement compaction quality enhancement parameters, such as the increased number of rolling passes or the adjusted material mix, can be imported into the GIS software as input conditions. These parameters are associated with specific areas or road sections, indicating that these areas require special compaction work. The path planning tool of the GIS software is used to adjust the optimized rolling operation trajectory path in combination with the pavement compaction quality enhancement parameters. For example, if an area requires additional rolling passes, this area is marked as high priority and the corresponding number of passes is added in the path planning. The Dijkstra algorithm is used to calculate the shortest or optimal path, while considering the impact of additional rolling passes on the path length and compaction effect. During the path planning process, specific parameter values ​​are set, such as the maximum turning radius of the roller is 10 meters and the maximum climbing angle is 10 degrees to ensure that the path planning meets the operating limitations of the roller. The GIS software automatically adjusts the path based on these parameters to avoid areas that are not suitable for rolling and ensure that all areas that require enhanced compaction are covered. Finally, the compaction quality enhancement operation path is obtained.

[0131] The present invention provides key data for compaction quality by extracting the center of gravity frequency feature, thereby evaluating the non-uniformity of the compaction density in the target rolling area, and obtaining comprehensive pavement compaction density distribution data by interpolating the preliminary evaluation indicators. A compaction area uniformity distribution map is generated through regional uniformity mapping to intuitively display the compaction quality, and key indicators of pavement compaction quality are extracted through consistency evaluation. By extracting the key characteristic parameters of compaction quality and performing parameter constraints, pavement compaction quality enhancement parameters are obtained. Based on these parameters, the rolling operation trajectory path can be optimized to improve the compaction effect.

[0132] Preferably, step S5 comprises the following steps:

[0133] Step S51: constructing a digital twin coordinate system based on the compaction quality enhancement operation path and the geographical environment data of the operation area to obtain a digital twin reference coordinate;

[0134] Specifically, the compaction quality enhancement operation path can be loaded into the GIS software as vector data, and the geographic environment data of the operation area, including terrain elevation, landform type, and soil type, can be loaded into the GIS software as another layer. Use the spatial analysis function of the GIS software to match the operation path with the geographic environment data, set the coordinate transformation parameters, for example, select the WGS84 coordinate system as the benchmark, and project all data into the UTM coordinate system, and use 3D modeling tools such as Autodesk Revit or Bentley Systems to build a digital twin model of the operation area. In this model, each operation path point is assigned 3D coordinates, including X, Y, and Z coordinates, which correspond to the geographic environment data in the GIS. Set the accuracy parameters of the model, for example, the coordinate accuracy reaches the centimeter level, and finally obtain the digital twin reference coordinates.

[0135] Step S52: extracting the operation parameter features of the operation process of the road roller to obtain a digital feature vector set of the operation process, and reconstructing the time-space dimension of the digital feature vector set of the operation process to obtain operation parameter time series mapping data;

[0136] Specifically, a data acquisition system can be installed on the roller, which can record key parameters in the operation process in real time, such as rolling speed, number of rolling passes, compaction density and ambient temperature. These parameters are recorded as digital feature vectors, each of which contains a series of parameter values ​​related to a specific operation moment. Use data analysis software, such as Python with the Pandas library, to process these digital feature vectors. Timestamp each operation parameter and reconstruct them into time series data. For example, record the speed of the roller at a specific time point as 5km / h and the compaction density as 92%. Mark these data points in the form of [timestamp, speed, compaction density], such as [20240324T1430, 5, 92], and finally obtain the operation parameter time series mapping data.

[0137] Step S53: simulating the operation process based on the digital twin reference coordinates and the operation parameter time series mapping data to obtain a digital mapping model of the operation process;

[0138] Specifically, the digital twin reference coordinates can be imported into the simulation software, and the operating parameter time series mapping data, including parameters such as rolling speed and compaction density, can be associated with the corresponding time and space positions. Use the simulation software to simulate the movement and compaction process of the roller in the operating area. Set the simulation parameters, for example, select a suitable time step (such as 1 second) and spatial resolution (such as 0.1 meters). The simulation software calculates the position change and compaction effect of the roller at each time step based on the input parameters and physical model. During the simulation process, the software records the roller position and compaction parameters at each time step to generate a digital mapping model of the operating process. This model describes in detail the movement trajectory and compaction effect of the roller in the operating area.

[0139] Step S54: spatially marking the digital mapping model of the operation process to obtain geographic spatial information annotation data, and associating the digital mapping model of the operation process with a coordinate system based on the geographic spatial information annotation data to obtain rolling track coordinate mapping data;

[0140] Specifically, each event or operation in the digital mapping model of the operation process can be associated with geospatial information. For example, the position and compaction parameters of the roller at a specific time are associated with specific coordinate points in the operation area. Use the spatial tagging tool of the GIS software to add a geographic tag to each roller position in the digital mapping model, including longitude, latitude and elevation information. These geospatial information annotation data are stored in the database and associated with the corresponding events in the digital mapping model of the operation process. Finally, the rolling trajectory coordinate mapping data is obtained, which associates the movement trajectory and compaction parameters of the roller with the geospatial coordinate system of the operation area.

[0141] Step S55: Visualize the rolling track coordinate mapping data to obtain a visualized report of the roller operation track.

[0142] Specifically, the rolling track coordinate mapping data can be imported into the GIS software, and a new layer can be created using the layer management function of the GIS software to display the roller's operating track. Choose appropriate symbolization methods to represent different compaction parameters, for example, use different colors to represent different compaction levels, and use line width to represent the number of rolling passes. For example, areas with a compaction degree higher than 90% are displayed in green, areas with a compaction degree between 80% and 90% are displayed in yellow, and areas with a compaction degree lower than 80% are displayed in red. Use the query and analysis tools of the GIS software to identify and highlight specific track features, such as turning points, repeated rolling areas, and unrolled areas. Set query parameters, for example, choose to display all areas with compaction below the standard value and highlight them in red on the map. Finally, use the mapping function of the GIS software to generate a visual report of the roller's operating track.

[0143] The present invention provides a basis for the digital representation of the operation process by constructing a digital twin coordinate system and extracting deep features of the operation parameters, thereby enhancing the understanding of the operation process. Digital simulation makes operation planning and review more efficient, while the precise annotation of geographic spatial information and the visualization of the operation trajectory make the operation process and results intuitive and easy to understand. The digital mapping model enhances the traceability and transparency of the operation process, optimizes resource allocation, reduces waste, and improves operation safety, taking measures in advance by predicting potential risks and problems.

[0144] Preferably, the present invention further provides a roller rolling operation track recognition system, which is used to execute the roller rolling operation track recognition method as described above, and the roller rolling operation track recognition system comprises:

[0145] The modeling module is used to collect geographic spatial data of the target rolling area to obtain the geographic environment data of the working area; locate the roller to obtain the roller's position coordinates; perceive the roller's working environment in real time to obtain a three-dimensional model of the working environment;

[0146] The path candidate set generation module is used to identify the terrain features of the three-dimensional model of the working environment to obtain the environmental terrain feature mapping data; perform geographic topological analysis on the target rolling area based on the environmental terrain feature mapping data to obtain the working area topological model; perform matching analysis on the roller position coordinates and the working area topological model to obtain the roller working path candidate set;

[0147] The path optimization module is used to select the travel path of the roller based on the candidate set of roller operation paths and the environmental terrain feature mapping data to obtain the rolling operation trajectory path; perform coverage analysis on the rolling operation trajectory path to obtain the rolling area integrity assessment data; dynamically adjust the rolling operation trajectory path according to the rolling area integrity assessment data to obtain the optimized rolling operation trajectory path;

[0148] The compaction quality monitoring module is used to detect the intensity of sound waves using a vibration sensor according to the optimized rolling operation trajectory path to obtain dynamic monitoring data of the compaction process; analyze the compaction density and uniformity of the dynamic monitoring data of the compaction process to obtain a road compaction quality assessment report; adjust the optimized rolling operation trajectory path according to the road compaction quality assessment report to obtain a compaction quality enhancement operation path;

[0149] The visualization module is used to digitally reconstruct the operation process of the roller based on the compaction quality enhanced operation path and the geographic environment data of the operation area to obtain a digital mapping model of the operation process; extract geographic spatial information from the digital mapping model of the operation process to obtain rolling trajectory coordinate mapping data; visualize the rolling trajectory coordinate mapping data to obtain a visualization report of the roller operation trajectory.

[0150] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0151] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for identifying a rolling operation track of a road roller, characterized in that: The following steps are involved: Step S1: Obtain the target rolling area; Collect geospatial data of the target rolling area to obtain geographical environment data of the operation area; Position the roller to obtain the roller's position coordinates; perceive the roller's working environment in real time to obtain a three-dimensional model of the working environment; Step S2: identifying terrain features of the three-dimensional model of the working environment to obtain environmental terrain feature mapping data; performing geographic topological analysis on the target rolling area based on the environmental terrain feature mapping data to obtain a working area topological model; matching and analyzing the roller position coordinates with the working area topological model to obtain a roller working path candidate set; Step S3: selecting a travel path for the roller based on the roller operation path candidate set and the environmental terrain feature mapping data to obtain a rolling operation trajectory path; performing coverage analysis on the rolling operation trajectory path to obtain rolling area integrity assessment data; The rolling operation trajectory path is dynamically adjusted according to the rolling area integrity assessment data to obtain an optimized rolling operation trajectory path; wherein step S3 includes the following steps: Step S31: constructing a terrain topology constraint model for the roller's travel path based on the roller's work path candidate set and the environmental terrain feature mapping data to obtain a work path topology constraint model; Step S32: analyzing the constraint conditions of the operation path topology constraint model to obtain a set of terrain adaptability constraint indicators; Step S33: mapping the topological constraint information of the terrain adaptability constraint index set to obtain a geographic space adaptive constraint matrix, and screening the roller operation path candidate set according to the geographic space adaptive constraint matrix to obtain an initial rolling operation trajectory path; Step S34: performing a topological connectivity evaluation on the initial rolling operation trajectory path to obtain an operation path connectivity index; Step S35: Calculate the steering angle and curvature constraints of the operation path connectivity index to obtain the operation path smoothness evaluation data. Step S36: reconstructing the path morphology of the initial rolling operation track path based on the operation path smoothness evaluation data to obtain the rolling operation track path; Step S37: performing coverage analysis on the rolling operation trajectory path to obtain rolling area integrity assessment data, and dynamically adjusting the rolling operation trajectory path according to the rolling area integrity assessment data to obtain an optimized rolling operation trajectory path; Step S4: using a vibration sensor to detect the intensity of sound waves according to the optimized rolling operation trajectory path to obtain dynamic monitoring data of the compaction process; performing compaction density and uniformity analysis on the dynamic monitoring data of the compaction process to obtain a road surface compaction quality assessment report; adjusting the optimized rolling operation trajectory path according to the road surface compaction quality assessment report to obtain a compaction quality enhanced operation path; Step S5: Based on the compaction quality enhanced operation path and the geographic environment data of the operation area, the operation process of the roller is digitally reconstructed as a twin to obtain a digital mapping model of the operation process; geographic spatial information is extracted from the digital mapping model of the operation process to obtain rolling trajectory coordinate mapping data; the rolling trajectory coordinate mapping data is visualized to obtain a visualization report of the roller operation trajectory.

2. The method for identifying the rolling operation track of a road roller according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: acquiring a target rolling area, and performing an aerial remote sensing scan of the target rolling area by an unmanned aerial vehicle to obtain a geographic spatial image of the operation area; Step S12: extracting geomorphic features from the geospatial image of the operation area to obtain geomorphic classification data of the operation area; Step S13: Performing geographic semantic fusion on the geomorphic classification data of the operation area to obtain geographic environment data of the operation area; Step S14: constructing a geographic coordinate system for the target rolling area to obtain geographic reference coordinates of the working area; Step S15: positioning the roller based on the geographic reference coordinates of the working area to obtain the position coordinates of the roller; Step S16: Perform a three-dimensional spatial scan on the working environment of the road roller to obtain a three-dimensional model of the working environment.

3. The method for identifying the rolling operation track of a road roller according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: semantically segmenting and annotating the three-dimensional model of the working environment to obtain a semantically annotated data set of the working environment; Step S22: clustering the terrain features of the working environment semantic annotation dataset to obtain an environment layered terrain feature dataset; Step S23: performing terrain classification encoding on the environment layered terrain feature data set to obtain a terrain complexity assessment data set; Step S24: performing geological structural association on the terrain complexity assessment data set to obtain environmental terrain feature mapping data, and performing spatial structure reconstruction on the environmental terrain feature mapping data to obtain an environmental geographic topological connectivity model; Step S25: dividing the target rolling area into operating areas based on the environmental geographic topological connectivity model to obtain an operating area topological model; Step S26: performing matching analysis on the roller position coordinates and the operating area topology model to obtain a candidate set of roller operating paths.

4. The method for identifying the rolling operation track of a road roller according to claim 3, characterized in that: Step S26 includes the following steps: Step S261: Associating the roller position coordinates with the topological model of the operation area to obtain preliminary operation path matching data; Step S262: Calculate the shortest path and the optimal channel based on the preliminary operation path matching data to obtain operation path feasibility assessment data; Step S263: constructing a feature vector for the operation path feasibility assessment data to obtain a candidate operation path feature space; Step S264: extracting path constraint boundary extreme values ​​from the candidate operation path feature space to obtain a set of operation path feasibility constraint conditions; Step S265: performing adaptability evaluation of the operation path based on the feasibility constraint condition set of the operation path to obtain a preliminary adaptability index of the operation path; Step S266: Perform Monte Carlo risk simulation on the preliminary adaptability index of the operation path to obtain an operation path risk assessment report, and perform path robustness intelligent screening on the preliminary operation path matching data based on the operation path risk assessment report to obtain a candidate set of roller operation paths.

5. The method for identifying the rolling operation track of a road roller according to claim 1, characterized in that: Step S37 includes the following steps: Step S371: Calculate the area coverage rate of the rolling operation track path to obtain preliminary statistical data of the rolling coverage rate; Step S372: performing spatial interpolation and regional gap filling on the preliminary statistical data of rolling coverage to obtain preliminary assessment data of coverage area integrity; Step S373: performing rolling uniformity assessment based on the preliminary assessment data of coverage area integrity to obtain a rolling area uniformity assessment index; Step S374: performing rolling integrity assessment on the target rolling area based on the rolling area uniformity assessment index to obtain rolling area integrity assessment data; Step S375: performing constraint parameter matching on the compaction area integrity assessment data to obtain area compaction optimization correction parameters; Step S376: Adjust the rolling operation trajectory path based on the regional rolling optimization correction parameters to obtain a preliminary optimized rolling operation trajectory path, and perform boundary constraints on the preliminary optimized rolling operation trajectory path to obtain an optimized rolling operation trajectory path.

6. The method for identifying the rolling operation track of a road roller according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing rolling operation on the target rolling area based on the optimized rolling operation trajectory path, and using a vibration sensor to detect the sound wave intensity to obtain operation dynamic sound wave intensity data; Step S42: performing spectrum decomposition on the operation dynamic sound wave intensity data to obtain operation sound wave vibration spectrum data; Step S43: extracting spectrum features from the operation sound wave vibration spectrum data to obtain operation sound wave spectrum feature data; Step S44: performing compaction process monitoring modeling based on the operation sound wave spectrum characteristic data to obtain compaction process dynamic monitoring data; Step S45: Analyze the compaction density and uniformity of the dynamic monitoring data of the compaction process to obtain a road surface compaction quality assessment report, and adjust the optimized rolling operation trajectory path according to the road surface compaction quality assessment report to obtain a compaction quality enhanced operation path.

7. The method for identifying the rolling operation track of a road roller according to claim 6, characterized in that: Step S45 includes the following steps: Step S451: extracting the gravity center frequency feature of the dynamic monitoring data of the compaction process to obtain the gravity center frequency feature vector of the compaction process; Step S452: evaluating the non-uniformity of compaction density in the target rolling area based on the gravity center frequency characteristic vector of the compaction process, obtaining a preliminary evaluation index of compaction density, and interpolating the preliminary evaluation index of compaction density to obtain pavement compaction density distribution data; Step S453: performing regional uniformity mapping on the road surface compaction density distribution data to obtain a compaction regional uniformity distribution map; Step S454: performing consistency evaluation based on the compaction area uniformity distribution map to obtain compaction uniformity evaluation data, and performing constraint matching on the compaction uniformity evaluation data to obtain key indicators of pavement compaction quality; Step S455: integrating and correlating key indicators of pavement compaction quality to obtain a pavement compaction quality assessment report; Step S456: Perform performance mapping on the pavement compaction quality assessment report to obtain key characteristic parameters of compaction quality, and perform parameter constraints on the key characteristic parameters of compaction quality to obtain pavement compaction quality enhancement parameters; Step S457: Parameter mapping is performed on the optimized rolling operation trajectory path based on the pavement compaction quality enhancement parameters to obtain a compaction quality enhancement operation path.

8. The method for identifying the rolling operation track of a road roller according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: constructing a digital twin coordinate system based on the compaction quality enhancement operation path and the geographical environment data of the operation area to obtain a digital twin reference coordinate; Step S52: extracting the operation parameter features of the operation process of the road roller to obtain a digital feature vector set of the operation process, and reconstructing the time-space dimension of the digital feature vector set of the operation process to obtain time series mapping data of the operation parameters; Step S53: simulating the operation process based on the digital twin reference coordinates and the operation parameter time series mapping data to obtain a digital mapping model of the operation process; Step S54: spatially marking the digital mapping model of the operation process to obtain geographic spatial information annotation data, and associating the digital mapping model of the operation process with a coordinate system based on the geographic spatial information annotation data to obtain rolling track coordinate mapping data; Step S55: Visualize the rolling track coordinate mapping data to obtain a visualized report of the roller operation track.

9. A system for identifying the rolling track of a road roller, characterized in that: The method for identifying the rolling track of a road roller according to claim 1, wherein the identification system for the rolling track of a road roller comprises: The modeling module is used to obtain the target rolling area; collect geospatial data of the target rolling area to obtain the geographical environment data of the working area; locate the roller to obtain the roller's position coordinates; perceive the roller's working environment in real time to obtain a three-dimensional model of the working environment; The path candidate set generation module is used to identify the terrain features of the three-dimensional model of the working environment to obtain the environmental terrain feature mapping data; perform geographic topological analysis on the target rolling area based on the environmental terrain feature mapping data to obtain the working area topological model; perform matching analysis on the roller position coordinates and the working area topological model to obtain the roller working path candidate set; The path optimization module is used to select the travel path of the roller based on the candidate set of roller operation paths and the environmental terrain feature mapping data to obtain the rolling operation trajectory path; perform coverage analysis on the rolling operation trajectory path to obtain the rolling area integrity assessment data; dynamically adjust the rolling operation trajectory path according to the rolling area integrity assessment data to obtain the optimized rolling operation trajectory path; The compaction quality monitoring module is used to detect the intensity of sound waves using a vibration sensor according to the optimized rolling operation trajectory path to obtain dynamic monitoring data of the compaction process; analyze the compaction density and uniformity of the dynamic monitoring data of the compaction process to obtain a road compaction quality assessment report; adjust the optimized rolling operation trajectory path according to the road compaction quality assessment report to obtain a compaction quality enhancement operation path; The visualization module is used to digitally reconstruct the operation process of the roller based on the compaction quality enhanced operation path and the geographic environment data of the operation area to obtain a digital mapping model of the operation process; extract geographic spatial information from the digital mapping model of the operation process to obtain rolling trajectory coordinate mapping data; visualize the rolling trajectory coordinate mapping data to obtain a visualization report of the roller operation trajectory.

Images