Road surface settlement disease morphology construction method and device, equipment and storage medium

Abstract

The application discloses a kind of road surface settlement disease form construction method, device, equipment and storage medium, the method includes: by constructing the road disease simulation database including hollow disease parameters and associated road surface settlement response parameters, real road abnormal area feature data is collected and preprocessed, design multi-dimension heuristic factor quantization real and simulation data The comprehensive matching score of data is combined with confidence threshold value to determine real disease area, finally based on the disease parameter of matched road surface settlement disease form is constructed, realize the accurate form construction of road surface settlement disease, effectively excavate the correlation characteristics of road internal hollow disease and road surface settlement, can provide information characteristics for the accurate identification of road internal hollow disease, provide database support for road internal and external integrated disease intelligent detection, provide scientific and accurate basis for road internal and external integrated damage assessment, improve the intelligent and scientific level of road maintenance.

Description

Technical Field

[0001] This invention relates to the field of road engineering, and in particular to a method, apparatus, equipment and storage medium for constructing the morphology of road surface subsidence. Background Technology

[0002] As a core component of transportation infrastructure, roads are subject to multiple factors during long-term service, including repeated vehicle loads, natural environmental erosion, geological subsidence, and rainwater infiltration. As a result, hidden defects such as cavities and voids easily develop inside the road base and surface layers. Because these defects are buried inside the road, they are difficult to detect with the naked eye in the early stages. As the defects develop, they will gradually cause uneven settlement of the road surface, which will not only reduce the comfort of driving, but also bring traffic safety hazards such as vehicle bumps and loss of control. At the same time, continuous settlement will further aggravate the damage to the road structure and significantly shorten the overall service life of the road.

[0003] Currently, road defect investigation mainly relies on non-destructive testing technologies such as ground-penetrating radar. While these technologies can quickly scan roads and identify internal abnormal areas, they can only present the general outline and spatial range of these abnormal areas. They cannot accurately distinguish whether the abnormal area is a real cavity defect or a non-defect-related anomaly such as loose base layer or pipeline misalignment. Furthermore, they cannot efficiently and accurately match key defect parameters with actual defects. Traditional road defect assessment methods lack a systematic road defect simulation data system that can support defect parameter matching. They have not established a correspondence between road structure, internal cavity defects, and road surface settlement response, nor do they have a scientific multi-dimensional matching and evaluation system. Defect assessment relies heavily on human experience, leading to a high rate of misjudgment, frequent omissions, and errors. This not only results in the ineffective waste of road maintenance resources but also easily delays the treatment of real defects, making it difficult to provide accurate and reliable defect parameter basis and data support for refined road maintenance decisions. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, equipment, and storage medium for constructing the morphology of road surface subsidence defects, aiming to solve the technical problems in the prior art of high misjudgment rate of road defects, difficulty in accurately matching key parameters of defects, and inability to effectively construct the real morphology of road surface subsidence defects.

[0005] To achieve the above objectives, the present invention provides a method for constructing the morphology of road surface settlement defects, the method comprising the following steps:

[0006] A road distress simulation database is constructed, which contains distress parameters for multiple distress scenarios. The distress parameters include cavity distress parameters and road surface settlement response parameters associated with the cavity distress parameters.

[0007] Collect raw feature data of abnormal areas of real roads, and preprocess the raw feature data to obtain real feature data;

[0008] Based on multi-dimensional heuristic factors, the comprehensive matching score between the real feature data and the parameters in the simulation database is quantified. The multi-dimensional heuristic factors include volume heuristic factors, depression depth heuristic factors, and three-dimensional position heuristic factors.

[0009] The comprehensive matching score is matched and determined based on a preset confidence threshold, and the abnormal area is determined to be a real disease area based on the determination result.

[0010] If the abnormal area is a real disease area, then the road surface subsidence disease morphology is constructed based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database.

[0011] Optionally, the construction of the road defect simulation database includes:

[0012] Based on the structural design information of typical roads, a three-dimensional model of the road body including road surface potholes is established.

[0013] Different parameters of cavity defects are set inside the three-dimensional model of the road body to form multiple sets of cavity defect parameters for differentiated defect scenarios. The cavity defect parameters include the three-dimensional location parameters and volume parameters of the cavity defects.

[0014] A preset standard load is applied to the pothole area of ​​the road surface in the three-dimensional model of the road body. The secondary settlement distance of the pothole is monitored and recorded by the simulation system. The secondary settlement distance is used as the road surface settlement response parameter associated with the cavity disease parameter. The preset standard load is used to simulate the actual stress conditions of vehicle driving.

[0015] The void defect parameters of each group of differentiated defect scenarios are associated and stored with the corresponding road surface settlement response parameters, and then structured to form a road defect simulation database containing defect parameters of multiple defect scenarios.

[0016] Optionally, the step of collecting raw feature data of abnormal areas of real roads and preprocessing the raw feature data to obtain real feature data includes:

[0017] Collect ground-penetrating radar scan data of real roads, and identify abnormal areas suspected of being defects from the ground-penetrating radar scan data;

[0018] Based on the ground-penetrating radar scan data, determine whether there are potholes above the abnormal area;

[0019] If there are road surface potholes above the abnormal area, the original feature data of the abnormal area is directly measured and supplemented, and the original feature data includes volume parameters, sinking depth parameters and three-dimensional position parameters.

[0020] If there are no potholes above the abnormal area, the road surface directly above the abnormal area is compacted based on a preset compaction strategy.

[0021] If the road surface subsides after compaction, then the steps of direct measurement and supplementary collection of original feature data of the abnormal area are performed.

[0022] If the road surface does not subside after compaction, it is determined that the abnormal area has no valid original feature data. The steps of collecting ground-penetrating radar scan data of the real road and identifying the abnormal area suspected of being a defect from the ground-penetrating radar scan data are returned to re-identify the abnormal area.

[0023] The collected raw feature data is cleaned and verified to obtain the true feature data.

[0024] Optionally, the step of quantifying the comprehensive matching score between the real feature data and the parameters in the simulation database based on multi-dimensional heuristic factors includes:

[0025] Based on the volume parameters in the real feature data and the corresponding cavity disease volume parameters in the simulation database, the volume heuristic factor is calculated, referring to the following formula:

[0026]

[0027] in, Represents the volume heuristic factor. Represents the volume in the true feature data. This represents the corresponding volume parameters of the cavity in the simulation database;

[0028] Based on the subsidence depth parameter in the real feature data and the corresponding road surface settlement response parameter in the simulation database, the subsidence depth heuristic factor is calculated, referring to the following formula:

[0029]

[0030] in, Indicates the sink depth heuristic factor. This represents the depth of depression parameter in the actual feature data. This represents the corresponding road surface settlement response parameters in the simulation database;

[0031] Based on the three-dimensional position parameters in the real feature data and the corresponding three-dimensional position parameters of the cavity disease in the simulation database, the three-dimensional position heuristic factor is calculated.

[0032] The volume heuristic factor, the depression depth heuristic factor, and the three-dimensional position heuristic factor are standardized respectively to obtain the standardized score of each heuristic factor;

[0033] Each heuristic factor is assigned a corresponding weight based on its standardized score, and the combined score and weights are used to calculate the comprehensive matching score between the real feature data and the parameters in the simulation database.

[0034] Optionally, the calculation of the three-dimensional location heuristic factor based on the three-dimensional location parameters in the real feature data and the corresponding three-dimensional location parameters of the cavity disease in the simulation database includes:

[0035] A local three-dimensional coordinate system is established with the actual disease center corresponding to the actual feature data as the origin;

[0036] The corresponding cavity disease center in the simulation database is converted into a simulation vector relative to the real disease center;

[0037] Calculate the angle between the simulation vector and the three preset reference direction unit vectors to obtain the angle set, extract the maximum angle and angle range from it, determine the core angle factor based on the maximum angle, and determine the angle refinement factor based on the angle range;

[0038] Calculate the straight-line distance between the actual disease center and the simulated disease center. Combine this straight-line distance, the core angle factor, and the angle refinement factor to calculate the three-dimensional position heuristic factor, which characterizes the three-dimensional positional similarity between the actual and simulated diseases, using the following formula:

[0039]

[0040] in, Represents the three-dimensional position heuristic factor. This represents the straight-line distance between real and simulated diseases. This represents the average straight-line distance between corresponding diseases in the simulation database. Represents the distance factor. Indicates the core angle factor, Indicates the angle refinement factor. , and This represents the weighting coefficient.

[0041] Optionally, the step of performing a matching judgment on the comprehensive matching score based on a preset confidence threshold, and determining whether the abnormal area is a real disease area based on the judgment result, includes:

[0042] Based on the training results of road defect data, a dynamic threshold strategy is adopted to set a preset confidence threshold.

[0043] The comprehensive matching score between the real feature data and each set of parameters in the simulation database is compared with the preset reliability threshold.

[0044] If the overall matching score is greater than or equal to the preset confidence threshold, the set of parameters is marked as matching disease parameters, and the abnormal area is determined to be a real disease area.

[0045] If the overall matching score is less than the preset confidence threshold, the abnormal area is determined to be a normal abnormal area and not a real disease area.

[0046] If the comprehensive matching score between the real feature data and multiple sets of parameters is greater than or equal to the preset confidence threshold, the set of disease parameters with the highest comprehensive matching score is selected as the optimal matching disease parameters, and the road surface subsidence disease morphology is constructed based on the optimal matching disease parameters.

[0047] Optionally, constructing the road surface settlement morphology based on the matching defect parameters corresponding to the abnormal area in the road defect simulation database includes:

[0048] Extract matching disease parameters corresponding to the abnormal area from the road disease simulation database. The matching disease parameters include cavity disease parameters and road surface settlement response parameters.

[0049] The matching disease parameters are then verified a second time by combining ground-penetrating radar scanning data to determine the confidence level of the matching disease parameters;

[0050] When the confidence level value is between the preset confidence threshold and the preset verification parameter threshold, the matching disease parameters are corrected according to the ground penetrating radar scanning data, and the road surface subsidence disease morphology corresponding to the abnormal area is constructed based on the corrected matching disease parameters.

[0051] If the confidence level is greater than or equal to the preset verification parameter threshold, the road surface subsidence morphology corresponding to the abnormal area is directly constructed using the matching lesion parameters.

[0052] Furthermore, to achieve the above objectives, the present invention also proposes a road surface settlement morphology construction device that applies the road surface settlement morphology construction method described above, the road surface settlement morphology construction device comprising:

[0053] The road disease simulation module is used to construct a road disease simulation database. The road disease simulation database contains disease parameters for multiple disease scenarios. The disease parameters include cavity disease parameters and road surface settlement response parameters associated with the cavity disease parameters.

[0054] The data acquisition module is used to collect raw feature data of abnormal areas of real roads and preprocess the raw feature data to obtain real feature data.

[0055] A multidimensional matching module is used to quantify the comprehensive matching score between the real feature data and the parameters in the simulation database based on multidimensional heuristic factors, including volume heuristic factors, depression depth heuristic factors and three-dimensional position heuristic factors.

[0056] The disease identification module is used to match and determine the comprehensive matching score based on a preset confidence threshold, and to determine whether the abnormal area is a real disease area based on the determination result.

[0057] The disease morphology construction module is used to construct the road surface subsidence disease morphology based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database if the abnormal area is a real disease area.

[0058] In addition, to achieve the above objectives, this application also proposes a road surface settlement morphology construction device, the device comprising: a memory, a processor, and a road surface settlement morphology construction program stored in the memory, the processor being used to run the road surface settlement morphology construction program, the computer program being configured to implement the steps of the road surface settlement morphology construction method as described above.

[0059] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the road surface settlement morphology construction method described above.

[0060] Beneficial effects of this invention:

[0061] This invention constructs a road defect simulation database containing defect parameters for multiple defect scenarios, including cavity defect parameters and road surface settlement response parameters associated with these parameters. It collects raw feature data of abnormal areas from real roads and preprocesses this raw feature data to obtain real feature data. Based on multi-dimensional heuristic factors, it quantifies the comprehensive matching score between the real feature data and the parameters in the simulation database. These multi-dimensional heuristic factors include volume heuristic factors, subsidence depth heuristic factors, and three-dimensional position heuristic factors. Based on a preset confidence threshold, it performs a matching judgment on the comprehensive matching score and determines the abnormal area based on the judgment result. Whether the abnormal area is a real disease area; if the abnormal area is a real disease area, then the morphology of road surface settlement disease is constructed based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database, thereby realizing the accurate identification and morphology construction of road surface settlement disease, effectively mining the correlation characteristics between internal road cavity disease and road surface settlement, realizing the accurate morphology construction of road surface settlement disease identification, effectively mining the correlation characteristics between internal road cavity disease and road surface settlement, which can provide information features for the accurate identification of internal road cavity disease, provide database support for intelligent detection of integrated internal and external road diseases, provide a scientific and accurate basis for integrated internal and external road damage assessment, and improve the intelligent and scientific level of road maintenance. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a schematic diagram of the structure of the road surface subsidence morphology construction device in the hardware operating environment involved in the embodiments of the present invention;

[0064] Figure 2 This is a flowchart illustrating the first embodiment of the method for constructing the morphology of road surface subsidence defects according to the present invention.

[0065] Figure 3 This is a flowchart illustrating the second embodiment of the method for constructing the morphology of road surface subsidence defects according to the present invention.

[0066] Figure 4 This is a structural block diagram of the first embodiment of the road surface subsidence morphology construction device of the present invention.

[0067] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0068] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0069] Reference Figure 1 , Figure 1 This is a schematic diagram of the equipment structure for constructing the morphology of road surface subsidence defects in the hardware operating environment involved in the embodiments of the present invention.

[0070] like Figure 1 As shown, the road surface settlement morphology construction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; the user interface 1003 may also include standard wired and wireless interfaces. The network interface 1004 may optionally include standard wired and wireless interfaces (such as Wireless-Fidelity (Wi-Fi) interfaces). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0071] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the road surface settlement morphology construction equipment, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0072] like Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a road surface settlement morphology construction program.

[0073] exist Figure 1In the road surface settlement morphology construction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the road surface settlement morphology construction device of the present invention can be set in the road surface settlement morphology construction device, and the road surface settlement morphology construction device calls the road surface settlement morphology construction program stored in the memory 1005 through the processor 1001 and executes the road surface settlement morphology construction method provided in the embodiment of the present invention.

[0074] This invention provides a method for constructing the morphology of road surface subsidence defects, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the method for constructing the morphology of road surface subsidence defects according to the present invention.

[0075] In this embodiment, the method for constructing the morphology of road surface subsidence includes the following steps:

[0076] Step S10: Construct a road defect simulation database, which contains defect parameters for multiple defect scenarios.

[0077] It should be understood that the executing entity of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a terminal electronic device capable of performing the above functions. The following description uses a road defect identification and processing device (hereinafter referred to as the processing device) as an example to illustrate this embodiment and the following embodiments.

[0078] It should be noted that the disease parameters are quantitative indicators that describe the basic characteristics of road internal diseases and are used to characterize attributes such as the scale, morphology, and location of the diseases; the disease parameters include cavity disease parameters and road surface settlement response parameters associated with the cavity disease parameters.

[0079] Cavity defects parameters are parameters used to describe cavities inside roads, including specific quantitative indicators such as the volume, shape, burial depth, and planar location of the cavities.

[0080] Road surface settlement response parameters refer to quantitative data related to settlement of the road surface under the influence of cavities and defects when there are cavities and defects inside the road. These include indicators such as settlement amount, settlement range, and settlement gradient, and are related to the cavity and defect parameters.

[0081] In some embodiments, the processing device uses road defect simulation software to simulate road internal defect scenarios under different working conditions, covering cavities of different scales, locations, and forms. For each set of simulation scenarios, corresponding defect parameters are set and road surface settlement response data are collected. The parameters and response data of all scenarios are classified, organized, and standardized to establish a structured database that supports retrieval and matching by defect parameter type, response characteristics, and other dimensions.

[0082] It is understandable that this embodiment constructs a standardized and comprehensive road defect simulation database to provide sufficient reference samples and data support for the subsequent identification and morphological construction of real road defects, avoiding identification deviations caused by insufficient real defect samples or missing parameters. At the same time, it realizes the association storage of defect parameters and road surface settlement response parameters, providing a data foundation for subsequent matching calculations.

[0083] Furthermore, in order to accurately cover disease scenarios of different scales and locations and ensure the comprehensiveness of the database samples, step S10 above may include:

[0084] Step S101: Based on the structural design information of typical roads, establish a three-dimensional model of the road body including road surface potholes.

[0085] It should be noted that the structural design information of typical roads refers to the official design data of representative roads (such as urban arterial roads and expressways), including core information such as road layer structure, material parameters, dimensional specifications, and design loads.

[0086] A three-dimensional model of a road can be a digital model constructed using three-dimensional modeling software based on road structural design information. It can reproduce the actual layered structure and surface condition (including potholes) of the road and is used to simulate internal road defects and surface settlement response.

[0087] Potholes refer to localized damage and depressions on the road surface. They are a common form of road surface damage and an area where road surface settlement is easily manifested due to cavitation. In this embodiment, they are used as a monitoring medium for settlement response.

[0088] Step S102: Set different parameters for cavities within the three-dimensional model of the road body to form multiple sets of cavities parameters for differentiated cavities scenarios. The cavities parameters include the three-dimensional location parameters and volume parameters of the cavities.

[0089] It should be noted that the three-dimensional location parameters of the cavity are quantitative indicators used to describe the spatial location of the cavity within the three-dimensional model of the road body. They mainly include the planar coordinates (X and Y axis coordinates) and burial depth (Z axis coordinate) of the cavity, which are used to accurately locate the cavity inside the road.

[0090] The volume parameters of cavitation are quantitative indicators used to describe the scale of cavitation. They are usually calculated from the length, width and height of the cavity (volume = length × width × height) and are used to characterize the size of the cavity.

[0091] In some embodiments, the processing device can set up multiple sets of differentiated cavities in the base layer or subgrade of the three-dimensional model of the road body, based on the common types of cavities in road maintenance. Each set of cavities has different three-dimensional location parameters (planar coordinates, burial depth) and volume parameters (length, width, height). For example, cavities with a burial depth of 0.5m and a volume of 1m³ can be set up, as well as cavities with a burial depth of 1.0m and a volume of 2m³. Each set of parameters corresponds to an independent cavity scenario, ensuring coverage of cavities of different scales and locations, and forming a comprehensive set of cavity parameter sets.

[0092] Step S103: Apply a preset standard load to the pothole area of ​​the road surface in the three-dimensional model of the road body, monitor and record the secondary settlement distance of the pothole through the simulation system, and use the secondary settlement distance as the road surface settlement response parameter associated with the cavity disease parameter. The preset standard load is used to simulate the actual stress conditions of vehicle driving.

[0093] It should be noted that the preset standard load refers to the load value used to simulate the actual stress conditions of vehicle driving. Its magnitude and action form are close to the actual road vehicle traffic conditions. It is used to trigger the secondary settlement of road surface potholes and realize the collection of settlement response parameters.

[0094] Secondary settlement distance refers to the additional settlement distance of a pothole under a preset standard load due to the influence of internal road voids. It is different from the initial depression depth of the pothole itself and is used to reflect the degree of influence of voids on road surface settlement.

[0095] In the specific implementation, a preset standard load F is applied to the pothole area on the road surface to simulate actual stress conditions such as vehicle driving. The simulation system monitors and records the sinking distance D of the pothole under the load.

[0096] Step S104: Associate and store the cavity disease parameters of each group of differentiated disease scenarios with the corresponding road surface settlement response parameters, and organize them in a structured manner to form a road disease simulation database containing disease parameters of multiple disease scenarios.

[0097] In the specific implementation, the disease parameters (three-dimensional location, volume V) of each scenario are associated and stored with the corresponding road surface settlement response (sinking distance D) to form a structured simulation database. Each data entry contains complete information of "disease three-dimensional location - disease volume - sinking distance".

[0098] Step S20: Collect the original feature data of the abnormal area of ​​the real road, and preprocess the original feature data to obtain the real feature data.

[0099] It should be noted that abnormal areas on a real road refer to localized areas of the road surface that show signs of subsidence or are suspected of having internal defects, as identified through preliminary inspections. These areas are the focus of subsequent inspections and analyses.

[0100] Raw feature data can be road-related data directly collected by ground-penetrating radar without any processing. Real feature data can be standardized data that has been preprocessed and retains the characteristics of road defects and road surface settlement.

[0101] In some embodiments, the processing device may employ multi-source detection equipment (such as ground-penetrating radar GPR, laser pavement detector, UAV aerial photography equipment, etc.) to comprehensively detect road areas suspected of having road surface settlement, collect raw feature data of the area, including raw pavement settlement data, road internal structure reflection data, pavement smoothness data, etc.; preprocess the collected raw feature data, for example, preprocessing includes data denoising (removing abnormal data caused by detection equipment errors and environmental interference), data normalization (unifying data of different dimensions and magnitudes to a unified standard), data alignment (spatially aligning internal structure data with pavement settlement data), and invalid data removal, finally obtaining standardized real feature data.

[0102] Furthermore, in order to improve data quality and avoid invalid data collection, step S20 above may include:

[0103] Step S201: Collect ground-penetrating radar scan data of real roads, and identify abnormal areas suspected of being defects from the ground-penetrating radar scan data.

[0104] It should be noted that ground-penetrating radar (GPR) scanning data refers to waveform data obtained by scanning a real road with GPR equipment, which reflects the internal structure and media distribution of the road, including feature information of the road surface, base layer, subgrade, and internal abnormal areas.

[0105] An abnormal area suspected of being a disease can be a local area of ​​the road where abnormal waveforms are found through analysis of ground-penetrating radar scan data, suggesting the presence of internal cavities, but which has not yet been verified.

[0106] Step S202: Determine whether there are road surface potholes above the abnormal area based on the ground penetrating radar scan data.

[0107] In practice, the processing equipment can combine the road surface reflection waveform in the ground penetrating radar scan data to observe whether there are potholes, damage, cracks, or other features on the road surface above the abnormal area. If the surface reflection signal in the scan waveform is discontinuous and there are waveform features corresponding to depressions, and the on-site inspection confirms the existence of road surface potholes, then it is determined that there are road surface potholes above the abnormal area. If the surface of the scan waveform is continuous and there are no abnormal depression features, and the on-site inspection does not find any road surface damage, then it is determined that there are no road surface potholes.

[0108] Step S203: If there are potholes above the abnormal area, directly measure and supplement the original feature data of the abnormal area. The original feature data includes volume parameters, sinking depth parameters and three-dimensional position parameters.

[0109] In the specific implementation, for abnormal areas with potholes, a laser rangefinder is used to measure the sinking depth of the potholes (i.e., the vertical distance between the lowest point of the pothole and the flat part of the road surface) as the sinking depth parameter; a GPS locator is used to collect the three-dimensional coordinates (X, Y, Z axes) of the abnormal area as the three-dimensional position parameter; through ground-penetrating radar data inversion, combined with on-site sampling assistance, the volume of suspected cavities inside the abnormal area is inferred as the volume parameter; the above three types of parameters are integrated to complete the supplementary collection of original feature data.

[0110] Step S204: If there are no potholes above the abnormal area, compact the road surface directly above the abnormal area based on a preset compaction strategy.

[0111] It should be noted that the preset compaction strategy refers to the compaction operation specifications set in advance with reference to road maintenance industry standards. These specifications include parameters such as compaction equipment, compaction pressure, and number of compaction cycles. They are used to simulate the compaction effect of long-term vehicle driving on the road surface and to help determine whether there are internal cavities or defects in abnormal areas.

[0112] In practice, the preset compaction strategy can be set as follows: 3-5 compaction passes, slow compaction speed, and moderate compaction weight (to avoid damaging the road structure).

[0113] Step S205: If the road surface subsides after compaction, perform the step of direct measurement and supplementary collection of original feature data of the abnormal area.

[0114] In practice, after the compaction process is completed, a laser rangefinder is used to measure the subsidence of the road surface directly above the abnormal area. If the measurement results show that there is significant subsidence (i.e., the subsidence is greater than the preset small threshold, such as 0.5mm), it indicates that there is likely a cavity defect in the area. Step S203 is then executed immediately to measure and collect volume parameters, subsidence depth parameters, and three-dimensional position parameters to complete the collection of original feature data.

[0115] Step S206: If there is no subsidence on the road surface after compaction, it is determined that there is no valid original feature data in the abnormal area. The step of collecting ground-penetrating radar scan data of the real road and identifying the abnormal area suspected of being a defect from the ground-penetrating radar scan data is returned to re-identify the abnormal area.

[0116] In practice, if after compaction the road surface is measured and no subsidence is found or the subsidence is less than the preset small threshold, it indicates that the abnormal area may be caused by non-disease factors such as uneven road structure or debris accumulation, and there is no effective original feature data related to the disease. At this time, the area is abandoned, the ground penetrating radar scanning process is restarted, and the process returns to step S201 to scan other areas of the road and re-identify the abnormal areas suspected of being diseases, so as to ensure that the original feature data collected are all related to the actual diseases.

[0117] Step S207: Perform data cleaning and verification processing on the collected raw feature data to obtain real feature data.

[0118] In some embodiments, the collected volume parameters, subsidence depth parameters, and three-dimensional position parameters are cleaned to remove outliers caused by measurement errors and equipment interference (such as volume and depth data that exceed reasonable ranges). A cross-validation method is used to compare the ground penetrating radar inversion data with the field measurement data to verify the consistency and accuracy of the data. Data with large deviations are remeasured and corrected. Finally, the qualified data are standardized to obtain true feature data that can truly reflect the characteristics of the disease in the abnormal area.

[0119] Step S30: Based on multi-dimensional heuristic factors, quantify the comprehensive matching score between the real feature data and the parameters in the simulation database.

[0120] It should be noted that the multi-dimensional heuristic factors refer to multiple core indicators used to measure the degree of matching between real feature data and disease parameters in the simulation database. They reflect the degree of fit between the two from different dimensions and jointly support the calculation of the comprehensive matching score. The multi-dimensional heuristic factors include volume heuristic factors, subsidence depth heuristic factors, and three-dimensional position heuristic factors.

[0121] The volume heuristic factor is used to quantify the degree of matching between the inferred internal cavity volume of anomaly areas in real roads and the cavity volume in the simulation database.

[0122] The subsidence depth heuristic factor is used to quantify the degree of matching between the road surface subsidence depth in real road anomaly areas and the road surface settlement depth in simulation scenarios.

[0123] The three-dimensional location heuristic factor is used to quantify the degree of matching between the spatial three-dimensional location (planar location, burial depth, etc.) of the abnormal area of ​​the real road and the spatial location of the simulated disease scene.

[0124] It should be noted that the comprehensive matching score is a quantitative value calculated based on multi-dimensional heuristic factors through weighted fusion and other methods. It is used to intuitively reflect the degree of matching between real feature data and a set of disease parameters in the simulation database. The higher the score, the higher the matching degree.

[0125] In some embodiments, the volume heuristic factor is calculated based on the similarity between the internal cavity volume inferred from the real feature data and the cavity volume in the simulation database; the subsidence depth heuristic factor is calculated based on the deviation between the real road surface subsidence depth and the road surface settlement depth in the simulation scenario; and the three-dimensional position heuristic factor is calculated based on the fit between the spatial position of the real abnormal area and the spatial position of the simulated disease scenario. Then, weights are set according to the importance of each heuristic factor, and algorithms such as weighted summation are used to fuse the calculation results of the three heuristic factors to obtain the comprehensive matching score of each set of disease parameters between the real feature data and the simulation database, thereby quantifying the degree of matching between the two.

[0126] Step S40: Based on a preset confidence threshold, perform a matching judgment on the comprehensive matching score, and determine whether the abnormal area is a real disease area based on the judgment result.

[0127] It should be noted that the pre-set reliability threshold can be a critical value set in advance based on engineering practice, data verification, etc. It is the core standard for judging the effectiveness of the matching between real feature data and simulated disease parameters, and is used to distinguish between real diseases and non-disease anomalies.

[0128] A true defect area refers to a road abnormality area that has been confirmed through matching and judgment to have internal road defects (such as cavities) and whose surface settlement is caused by these internal defects.

[0129] It is understood that this embodiment uses a pre-set confidence threshold for matching and judgment to effectively distinguish between real diseased areas and non-diseased abnormal areas, reduce the probability of misjudgment and missed judgment, and improve the accuracy of disease identification.

[0130] In some embodiments, a reasonable confidence threshold (a critical value used to determine the validity of the match) is set by combining road maintenance engineering experience and simulation data verification results. The comprehensive matching score is compared with the preset confidence threshold. If the comprehensive matching score is higher than or equal to the confidence threshold, the abnormal area is determined to match the corresponding defect scene in the simulation database and is identified as a real defect area. If the comprehensive matching score is lower than the confidence threshold, the match is determined to be invalid and the abnormal area does not belong to a real defect area (it may be caused by non-defect factors such as road wear and temporary settlement).

[0131] Furthermore, to improve the accuracy of identifying actual diseased areas and avoid misjudgments, step S40 above may include:

[0132] Step S401: Based on the training results of road defect data, a dynamic threshold strategy is used to set a preset confidence threshold;

[0133] Step S402: Compare the comprehensive matching score between the real feature data and each set of parameters in the simulation database with the preset reliability threshold;

[0134] Step S403: If the comprehensive matching score is greater than or equal to the preset confidence threshold, mark the group of parameters as matching disease parameters and determine that the abnormal area is a real disease area;

[0135] Step S404: If the overall matching score is less than the preset confidence threshold, the abnormal area is determined to be a normal abnormal area and not a real disease area.

[0136] Step S405: When the comprehensive matching score between the real feature data and multiple sets of parameters is greater than or equal to the preset confidence threshold, select the set of disease parameters with the highest comprehensive matching score as the optimal matching disease parameters, and construct the road surface subsidence disease morphology based on the optimal matching disease parameters.

[0137] It should be noted that the training results of road disease data can be obtained by collecting historical disease detection data, simulation verification data, and field measurement data, constructing a dataset, and training it with machine learning algorithms. The results include the correlation between the comprehensive matching score and the authenticity of the disease, threshold adjustment rules, and other results.

[0138] Dynamic threshold strategy refers to a strategy that dynamically adjusts the preset confidence threshold based on the data training results, taking into account differences in road type, disease type, detection scenario, etc., to ensure the rationality and adaptability of the threshold setting.

[0139] Ordinary abnormal areas refer to road abnormal areas where the comprehensive matching score does not reach the preset reliability threshold, the road surface abnormalities are not caused by internal cavities or defects, and are only caused by non-defect factors, and there is no need to construct defect morphology.

[0140] In some embodiments, the processing device can collect historical road defect detection data, simulation database verification data, and field-measured defect data to construct a training dataset, which includes comprehensive matching score samples of real defect areas and ordinary abnormal areas. Machine learning algorithms (such as logistic regression and random forest) are used to train the dataset, analyze the correlation between the comprehensive matching score and the authenticity of the defects, and determine dynamic threshold adjustment rules. Considering the differences in different road types (such as urban arterial roads and rural roads) and defect types (such as shallow cavities and deep cavities), a dynamic threshold strategy is adopted to set pre-set confidence thresholds for different scenarios (within a range of 0-1, such as 0.75 for urban arterial roads and 0.7 for rural roads, which can be dynamically fine-tuned according to the actual scenario), ensuring that the threshold settings conform to the actual defect judgment needs and avoiding misjudgments and missed judgments caused by fixed thresholds.

[0141] Step S50: If the abnormal area is a real disease area, then construct the road surface settlement disease morphology based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database.

[0142] It should be noted that the matching disease parameters refer to the set of disease parameters with the highest comprehensive matching score with the real feature data of the actual disease area in the road disease simulation database, which are used to construct the morphology of road surface subsidence disease.

[0143] The morphology of road surface settlement can be presented in a three-dimensional model or visualization form that intuitively shows the spatial morphology, distribution, degree of settlement, and relationship with internal defects in the actual defect area through methods such as three-dimensional modeling.

[0144] In the specific implementation, once an abnormal area is identified as a real disease area, the set of disease parameters with the highest comprehensive matching score with that area (i.e., matching disease parameters) is extracted from the road disease simulation database. Combined with the real feature data of the real disease area, the matching disease parameters are fine-tuned to make the parameters more in line with the real scene. Using 3D modeling technology (such as BIM modeling, 3D point cloud modeling, etc.), a 3D morphological model of the road surface settlement disease is constructed based on the corrected matching disease parameters, clearly presenting the core information such as the settlement range, settlement degree, internal voids and the correlation between road surface settlement and other core information.

[0145] Furthermore, in order to accurately transform the abstract parameters into an intuitive three-dimensional model and clearly present the relationship between internal cavities and road surface settlement, the above step S50 may include:

[0146] Step S501: Extract the matching disease parameters corresponding to the abnormal area from the road disease simulation database. The matching disease parameters include cavity disease parameters and road surface settlement response parameters.

[0147] Step S502: Perform secondary verification of the matched disease parameters by combining ground penetrating radar scanning data to determine the confidence level value of the matched disease parameters;

[0148] Step S503: When the confidence value is between the preset confidence threshold and the preset verification parameter threshold, the matching disease parameters are corrected according to the ground penetrating radar scanning data, and the road surface subsidence disease morphology corresponding to the abnormal area is constructed based on the corrected matching disease parameters.

[0149] Step S504: If the confidence level value is greater than or equal to the preset verification parameter threshold, the road surface subsidence morphology corresponding to the abnormal area is directly constructed using the matching disease parameters.

[0150] It should be noted that the matched disease parameters refer to the simulated disease parameters that, after matching and judgment, effectively match the real feature data of the real disease area (comprehensive matching score ≥ preset confidence threshold). These parameters include cavity disease parameters (three-dimensional location, volume, etc.) and road surface settlement response parameters (secondary subsidence distance, etc.), and are the core reference for constructing the morphology of road surface settlement disease.

[0151] It should be noted that secondary verification refers to the process of re-examining the reliability and fit of the parameters after extracting and matching disease parameters, combined with ground-penetrating radar scanning data. This is used to improve the accuracy of the parameters and avoid distortion of morphological construction due to matching deviations.

[0152] The confidence score is a quantitative index (ranging from 0 to 1) calculated through secondary verification. It is used to characterize the degree of fit between the matched disease parameters and the actual state of the disease. The higher the score, the stronger the reliability of the parameters.

[0153] In practical implementation, if the overall matching score is considered... The abnormal area was determined to be a real disease, with a confidence level of [value missing]. Its key parameters (three-dimensional position, volume, and depression depth) are directly taken from the parameter values ​​of the corresponding simulation data.

[0154] like The abnormal area was determined to be a normal abnormal area (not a real disease), with a confidence level lower than [missing information]. No further extraction of disease parameters is required.

[0155] For results determined to be genuine diseases, a secondary verification is performed using raw ground-penetrating radar data. If the confidence level is... Between these steps, the disease parameters need to be fine-tuned based on the actual test data; if the confidence level is ≥0.9, the parameters obtained from the matching should be used directly to ensure the accuracy and reliability of the results.

[0156] In some embodiments, the raw ground-penetrating radar scan data and preprocessed real feature data of the abnormal area collected in the early stage are retrieved, and the feature signals reflecting internal cavities in the ground-penetrating radar waveform (such as amplitude change range and waveform phase shift) are extracted. The extracted feature signals are compared and analyzed with the cavity disease parameters (such as three-dimensional location and volume) in the matching disease parameters. The correlation analysis algorithm is used to calculate the degree of fit between the two, and then converted into the confidence value of the matching disease parameters (value range 0-1). The higher the confidence value, the higher the degree of fit between the matching disease parameters and the actual state of the real disease, and the stronger the reliability of the parameters.

[0157] This embodiment constructs a road defect simulation database, which contains defect parameters for multiple defect scenarios. These parameters include cavity defect parameters and road surface settlement response parameters associated with the cavity defect parameters. Raw feature data of abnormal areas on real roads is collected and preprocessed to obtain real feature data. Based on multi-dimensional heuristic factors, a comprehensive matching score is quantified between the real feature data and the parameters in the simulation database. These multi-dimensional heuristic factors include volume heuristic factors, subsidence depth heuristic factors, and three-dimensional position heuristic factors. A matching determination is made based on a preset confidence threshold for the comprehensive matching score. If it is determined whether the abnormal area is a real disease area, and if the abnormal area is a real disease area, then the morphology of road surface settlement disease is constructed based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database. This achieves accurate morphological construction of road surface settlement disease, effectively explores the correlation characteristics between internal road cavity disease and road surface settlement, and can provide information features for accurate identification of internal road cavity disease. The constructed morphology of road surface settlement disease can provide a scientific and accurate basis for road maintenance, help to carry out targeted maintenance work, reduce the waste of resources caused by blind maintenance, and at the same time provide data support for the prediction and prevention of road diseases, and improve the intelligence and scientific level of road maintenance.

[0158] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the method for constructing the morphology of road surface subsidence defects according to the present invention.

[0159] Based on the first embodiment described above, in this embodiment, step S30 further includes:

[0160] Step S301: Calculate the volume heuristic factor based on the volume parameters in the real feature data and the corresponding void disease volume parameters in the simulation database.

[0161] It should be noted that the volume heuristic factor is used to measure the volume similarity between the real anomaly area and the simulated defect. The closer the value of this factor is to 1, the higher the degree of volume matching between the two. Refer to the following formula:

[0162]

[0163] in, Represents the volume heuristic factor. Represents the volume in the true feature data. This represents the volume parameters of the corresponding void defect in the simulation database.

[0164] Step S302: Based on the subsidence depth parameters in the real feature data and the corresponding road surface settlement response parameters in the simulation database, calculate the subsidence depth heuristic factor.

[0165] It should be noted that the subsidence depth heuristic factor is used to measure the similarity between the subsidence depth of the actual road and the subsidence depth of the simulated road defects. The closer the value of this factor is to 1, the higher the degree of matching between the two subsidence depths, as shown in the following formula:

[0166]

[0167] in, Indicates the sink depth heuristic factor. This represents the depth of depression parameter in the actual feature data. This represents the corresponding road surface settlement response parameters in the simulation database.

[0168] Step S303: Based on the three-dimensional position parameters in the real feature data and the corresponding three-dimensional position parameters of the cavity disease in the simulation database, calculate the three-dimensional position heuristic factor.

[0169] In some embodiments, three-dimensional position parameters are extracted from real feature data, and three-dimensional position parameters of cavitation defects are retrieved from the simulation database; the spatial Euclidean distance method is used to calculate the position similarity, which is then converted into a three-dimensional position heuristic factor; through calculation, the three-dimensional position heuristic factor corresponding to each set of simulation parameters is obtained, with a value of 0-1. The closer the value is to 1, the better the spatial position of the real and simulated defects matches.

[0170] Furthermore, in order to accurately calculate the three-dimensional position heuristic factor and achieve multi-dimensional quantization of position matching, step S303 above may include:

[0171] Step S3031: Establish a local three-dimensional coordinate system with the actual disease center corresponding to the actual feature data as the origin.

[0172] It should be noted that the true disease center refers to the geometric center of the suspected cavity disease within the actual abnormal area of ​​the road. It is obtained by calibration of the three-dimensional position parameters in the actual feature data and serves as the origin reference for establishing the local three-dimensional coordinate system.

[0173] The local three-dimensional coordinate system is a three-dimensional coordinate system with the center of the actual disease as the origin and the coordinate axis directions (X-axis along the road direction, Y-axis perpendicular to the road, Z-axis perpendicular to the road surface) set according to the actual road structure. It is used to accurately represent the relative positional relationship between the real and simulated diseases.

[0174] Step S3032: Convert the corresponding cavity disease center in the simulation database into a simulation vector relative to the real disease center.

[0175] It should be noted that the simulation vector is a vector formed by taking the center of the real disease as the origin and the relative coordinates of the simulated disease center. It is used to quantify the positional offset direction and offset amount of the simulated disease relative to the real disease.

[0176] In practical implementation, the actual disease center is used. Establish a local three-dimensional coordinate system with the origin as the center, and simulate the center of the disease. Transformed into relative vector All angle calculations revolve around the vector. It unfolds in three-dimensional space.

[0177] Step S3033: Calculate the angle between the simulation vector and the three preset reference direction unit vectors, obtain the angle set, extract the maximum angle and angle range from it, determine the core angle factor based on the maximum angle, and determine the angle refinement factor based on the angle range.

[0178] It should be noted that the reference direction unit vector can be a preset unit vector (with a magnitude of 1) corresponding to the three coordinate axes of the local three-dimensional coordinate system, used as the reference for angle calculation and to quantify the directional deviation of the simulation vector.

[0179] The included angle set refers to the set of three included angles calculated from the simulation vector and the three reference direction unit vectors, which is used to reflect the directional distribution characteristics of the simulation vector.

[0180] It should be noted that the core angle factor is a matching index calculated based on the maximum angle in the set of included angles. It is used to characterize the maximum directional deviation between the simulation vector and the reference direction. The value ranges from 0 to 1. The smaller the deviation, the higher the factor value.

[0181] The angle refinement factor is a matching index calculated based on the angle range of the included angle set. It is used to characterize the concentration of the simulated vector direction. The smaller the angle range, the higher the factor value, and the more accurate the position matching.

[0182] Step S3034: Calculate the straight-line distance between the real disease center and the simulated disease center. Combine the straight-line distance, the core angle factor, and the angle refinement factor to calculate the three-dimensional position heuristic factor that characterizes the three-dimensional position similarity between the real disease and the simulated disease.

[0183] It should be noted that the calculation of the 3D position heuristic factor is based on the following formula:

[0184]

[0185] in, Represents the three-dimensional position heuristic factor. This represents the straight-line distance between real and simulated diseases. This represents the average straight-line distance between corresponding diseases in the simulation database. Represents the distance factor. , and This represents the weighting coefficient.

[0186] It refers to the maximum angle between the centers of real and simulated diseases, representing the similarity of the core direction;

[0187] Definition: In a local coordinate system with the actual disease center as the origin, calculate all the angles between the simulated disease center vector and the preset reference directions (such as the road length direction X-axis, width direction Y-axis, and depth direction Z-axis), and take the maximum value among them.

[0188] Three reference directions (X, Y, Z) are preset, and vectors are calculated for each. Angle with each reference direction (Using the vector product formula:) ,in (It is the unit vector of the reference direction); take The maximum value is ;

[0189] Core Angle Factor The cosine function in The interval is monotonically decreasing. The smaller, The larger the value, the higher the similarity in the core directions;

[0190] The angle refinement factor refers to the angular range between the center of the real and simulated disease, which is used to refine the assessment of directional similarity.

[0191] Definition: In the same local coordinate system mentioned above, the difference between the maximum angle and the minimum angle is taken after calculating the angle between the simulated disease center vector and all preset reference directions.

[0192] Continue The calculation results; .

[0193] Step S304: Standardize the volume heuristic factor, the depression depth heuristic factor, and the three-dimensional position heuristic factor respectively to obtain the standardized score of each heuristic factor.

[0194] In the specific implementation, the volume normalization score is:

[0195]

[0196] in, The closer to 1, The closer it is to 1, the higher the volume matching degree.

[0197] Depression Depth Standardized Score:

[0198]

[0199] in, The closer to 1, The closer it is to 1, the higher the matching degree of settlement noise reduction.

[0200] 3D position standardized score:

[0201]

[0202] in, The smaller, The closer it is to 1, the higher the positional match.

[0203] Weight assignment: The weights of each factor are determined using the analytic hierarchy process (AHP) to satisfy the following conditions: .

[0204] in, Represents volume weight, Indicates the depth weight of the depression. This represents the weight of the three-dimensional location, and the weight can be dynamically adjusted (for pit-type defects, the depth of the depression is emphasized). It can be set to 0.4; for cavitary diseases, the focus is on location and volume. , Each is set to 0.35).

[0205] Step S305: Assign corresponding weights to the standardized scores of each heuristic factor, and calculate the comprehensive matching score between the real feature data and the parameters in the simulation database by combining the weights and the standardized scores.

[0206] In the specific implementation, based on road maintenance engineering experience and the degree of damage impact, corresponding weights are assigned to the standardized scores of the three heuristic factors (the sum of the weights is 1). Among them, the three-dimensional position heuristic factor has the highest weight (e.g., 0.4), followed by the volume heuristic factor (e.g., 0.3), and the subsidence depth heuristic factor has a weight of 0.3 (which can be adjusted according to the actual scenario). A weighted summation algorithm is used to calculate the comprehensive matching score between the real feature data and each set of damage parameters in the simulation database. The score ranges from 0 to 1. The higher the score, the higher the overall matching degree between the two, as shown in the following formula:

[0207]

[0208] in The value range is 0-1. The closer the value is to 1, the higher the overall fit between the real data and the simulation data.

[0209] This embodiment uses multi-dimensional heuristic factors to perform matching and quantification from three core dimensions: volume, depression depth, and three-dimensional position. This avoids the bias caused by single-dimensional matching and improves the comprehensiveness and accuracy of the matching. Through standardization, the scale differences of different heuristic factors are eliminated, ensuring that multi-dimensional indicators can be effectively integrated. This makes the comprehensive matching score more in line with the actual disease judgment needs and can truly reflect the overall matching degree between real diseases and simulation scenarios, thereby improving the accuracy and standardization of disease identification.

[0210] Furthermore, this embodiment of the invention also proposes a computer-readable storage medium storing a road surface settlement morphology construction program, which, when executed by a processor, implements the steps of the road surface settlement morphology construction method described above.

[0211] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0212] The aforementioned computer-readable storage medium may be included in the road surface settlement morphology construction device; or it may exist independently and not be assembled into the road surface settlement morphology construction device.

[0213] Furthermore, this invention also proposes a computer program product, including a road surface settlement morphology construction program, which, when executed by a processor, implements the steps of the road surface settlement morphology construction method described above.

[0214] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-mentioned method for constructing the morphology of road surface subsidence disease, and will not be repeated here.

[0215] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the road surface subsidence morphology construction device of the present invention.

[0216] like Figure 4 As shown, the road surface subsidence morphology construction device proposed in this embodiment of the invention includes:

[0217] The road disease simulation module 10 is used to construct a road disease simulation database. The road disease simulation database contains disease parameters for multiple disease scenarios. The disease parameters include cavity disease parameters and road surface settlement response parameters associated with the cavity disease parameters.

[0218] The data acquisition module 20 is used to acquire raw feature data of abnormal areas of real roads and preprocess the raw feature data to obtain real feature data.

[0219] The multidimensional matching module 30 is used to quantify the comprehensive matching score between the real feature data and the parameters in the simulation database based on multidimensional heuristic factors, including volume heuristic factors, depression depth heuristic factors and three-dimensional position heuristic factors.

[0220] Disease identification module 40 is used to match and determine the comprehensive matching score based on a preset confidence threshold, and determine whether the abnormal area is a real disease area based on the determination result;

[0221] The disease morphology construction module 50 is used to construct the road surface subsidence disease morphology based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database if the abnormal area is a real disease area.

[0222] This embodiment constructs a road defect simulation database containing defect parameters for multiple defect scenarios. These parameters include cavity defect parameters and associated pavement settlement response parameters. Raw feature data of abnormal areas on real roads is collected and preprocessed to obtain real feature data. A comprehensive matching score between the real feature data and the parameters in the simulation database is quantified based on multi-dimensional heuristic factors, including volume heuristic factors, subsidence depth heuristic factors, and three-dimensional position heuristic factors. The comprehensive matching score is then used to determine the abnormal area based on a preset confidence threshold. Whether the abnormal area is a real disease area; if the abnormal area is a real disease area, then the morphology of road surface settlement disease is constructed based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database, thereby realizing the accurate identification and morphology construction of road surface settlement disease, effectively mining the correlation characteristics between internal road cavity disease and road surface settlement, realizing the accurate morphology construction of road surface settlement disease identification, effectively mining the correlation characteristics between internal road cavity disease and road surface settlement, which can provide information features for the accurate identification of internal road cavity disease, provide database support for intelligent detection of integrated internal and external road diseases, provide a scientific and accurate basis for integrated internal and external road damage assessment, and improve the intelligent and scientific level of road maintenance.

[0223] The road surface settlement morphology construction device provided in this application, employing the road surface settlement morphology construction method in the above embodiments, can solve the technical problem of road surface settlement morphology construction. Compared with the prior art, the beneficial effects of the road surface settlement morphology construction device provided in this application are the same as those of the road surface settlement morphology construction method provided in the above embodiments, and other technical features in the road surface settlement morphology construction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0224] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0225] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0226] In addition, for technical details not described in detail in this embodiment, please refer to the method for constructing the morphology of road surface subsidence disease provided in any embodiment of the present invention, which will not be repeated here.

[0227] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0228] It should be noted that the user information (including but not limited to user device information, user personal information, user location information, user behavior information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0229] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0230] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0231] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for constructing the morphology of road surface settlement defects, characterized in that, The method for constructing the morphology of road surface subsidence defects includes: A road distress simulation database is constructed, which contains distress parameters for multiple distress scenarios. The distress parameters include cavity distress parameters and road surface settlement response parameters associated with the cavity distress parameters. Collect raw feature data of abnormal areas of real roads, and preprocess the raw feature data to obtain real feature data; Based on multi-dimensional heuristic factors, the comprehensive matching score between the real feature data and the parameters in the simulation database is quantified. These multi-dimensional heuristic factors include volume heuristic factors, depression depth heuristic factors, and three-dimensional position heuristic factors. The calculation methods for these multi-dimensional heuristic factors include: Based on the volume parameters in the real feature data and the corresponding cavity disease volume parameters in the simulation database, the volume heuristic factor is calculated, referring to the following formula: in, Represents the volume heuristic factor. Represents the volume in the true feature data. This represents the corresponding volume parameters of the cavity in the simulation database; Based on the subsidence depth parameter in the real feature data and the corresponding road surface settlement response parameter in the simulation database, the subsidence depth heuristic factor is calculated, referring to the following formula: in, Indicates the sink depth heuristic factor. This represents the depth of depression parameter in the actual feature data. This represents the corresponding road surface settlement response parameters in the simulation database; A local three-dimensional coordinate system is established with the actual disease center corresponding to the actual feature data as the origin; The corresponding cavity disease center in the simulation database is converted into a simulation vector relative to the real disease center; Calculate the angle between the simulation vector and the three preset reference direction unit vectors to obtain the angle set, extract the maximum angle and angle range from it, determine the core angle factor based on the maximum angle, and determine the angle refinement factor based on the angle range; Calculate the straight-line distance between the actual disease center and the simulated disease center. Combine this straight-line distance, the core angle factor, and the angle refinement factor to calculate the three-dimensional position heuristic factor, which characterizes the three-dimensional positional similarity between the actual and simulated diseases, using the following formula: in, Represents the three-dimensional position heuristic factor. This represents the straight-line distance between real and simulated diseases. This represents the average straight-line distance between corresponding diseases in the simulation database. Represents the distance factor. Indicates the core angle factor, Indicates the angle refinement factor. , and Indicates the weighting coefficient; The comprehensive matching score is matched and determined based on a preset confidence threshold, and the abnormal area is determined to be a real disease area based on the determination result. If the abnormal area is a real disease area, then the road surface subsidence disease morphology is constructed based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database.

2. The method for constructing the morphology of road surface subsidence as described in claim 1, characterized in that, The construction of the road defect simulation database includes: Based on the structural design information of typical roads, a three-dimensional model of the road body including road surface potholes is established. Different parameters of cavity defects are set inside the three-dimensional model of the road body to form multiple sets of cavity defect parameters for differentiated defect scenarios. The cavity defect parameters include the three-dimensional location parameters and volume parameters of the cavity defects. A preset standard load is applied to the pothole area of ​​the road surface in the three-dimensional model of the road body. The secondary settlement distance of the pothole is monitored and recorded by the simulation system. The secondary settlement distance is used as the road surface settlement response parameter associated with the cavity disease parameter. The preset standard load is used to simulate the actual stress conditions of vehicle driving. The void defect parameters of each group of differentiated defect scenarios are associated and stored with the corresponding road surface settlement response parameters, and then structured to form a road defect simulation database containing defect parameters of multiple defect scenarios.

3. The method for constructing the morphology of road surface subsidence as described in claim 1, characterized in that, The process of collecting raw feature data of abnormal areas of real roads and preprocessing the raw feature data to obtain real feature data includes: Collect ground-penetrating radar scan data of real roads, and identify abnormal areas suspected of being defects from the ground-penetrating radar scan data; Based on the ground-penetrating radar scan data, determine whether there are potholes above the abnormal area; If there are road surface potholes above the abnormal area, the original feature data of the abnormal area is directly measured and supplemented, and the original feature data includes volume parameters, sinking depth parameters and three-dimensional position parameters. If there are no potholes above the abnormal area, the road surface directly above the abnormal area is compacted based on a preset compaction strategy. If the road surface subsides after compaction, then the steps of direct measurement and supplementary collection of original feature data of the abnormal area are performed. If the road surface does not subside after compaction, it is determined that the abnormal area has no valid original feature data. The steps of collecting ground-penetrating radar scan data of the real road and identifying the abnormal area suspected of being a defect from the ground-penetrating radar scan data are returned to re-identify the abnormal area. The collected raw feature data is cleaned and verified to obtain the true feature data.

4. The method for constructing the morphology of road surface subsidence as described in claim 1, characterized in that, The method of quantifying the comprehensive matching score between the real feature data and the parameters in the simulation database based on multi-dimensional heuristic factors includes: The volume heuristic factor, the depression depth heuristic factor, and the three-dimensional position heuristic factor are standardized to obtain the standardized scores of each heuristic factor. Each heuristic factor is assigned a corresponding weight based on its standardized score, and the combined score and weights are used to calculate the comprehensive matching score between the real feature data and the parameters in the simulation database.

5. The method for constructing the morphology of road surface subsidence defects as described in any one of claims 1 to 4, characterized in that, The process of matching the comprehensive matching score based on a preset confidence threshold, and determining whether the abnormal area is a real disease area based on the determination result, includes: Based on the training results of road defect data, a dynamic threshold strategy is adopted to set a preset confidence threshold. The comprehensive matching score between the real feature data and each set of parameters in the simulation database is compared with the preset reliability threshold. If the overall matching score is greater than or equal to the preset confidence threshold, the set of parameters is marked as matching disease parameters, and the abnormal area is determined to be a real disease area. If the overall matching score is less than the preset confidence threshold, the abnormal area is determined to be a normal abnormal area and not a real disease area. If the comprehensive matching score between the real feature data and multiple sets of parameters is greater than or equal to the preset confidence threshold, the set of disease parameters with the highest comprehensive matching score is selected as the optimal matching disease parameters, and the road surface subsidence disease morphology is constructed based on the optimal matching disease parameters.

6. The method for constructing the morphology of road surface subsidence defects as described in any one of claims 1 to 4, characterized in that, The construction of road surface subsidence morphology based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database includes: Extract matching disease parameters corresponding to the abnormal area from the road disease simulation database. The matching disease parameters include cavity disease parameters and road surface settlement response parameters. The matching disease parameters are then verified a second time by combining ground-penetrating radar scanning data to determine the confidence level of the matching disease parameters; When the confidence level value is between the preset confidence threshold and the preset verification parameter threshold, the matching disease parameters are corrected according to the ground penetrating radar scanning data, and the road surface subsidence disease morphology corresponding to the abnormal area is constructed based on the corrected matching disease parameters. If the confidence level is greater than or equal to the preset verification parameter threshold, the road surface subsidence morphology corresponding to the abnormal area is directly constructed using the matching lesion parameters.

7. A road surface settlement morphology construction device using the road surface settlement morphology construction method according to any one of claims 1 to 6, characterized in that, The device includes: The road disease simulation module is used to construct a road disease simulation database. The road disease simulation database contains disease parameters for multiple disease scenarios. The disease parameters include cavity disease parameters and road surface settlement response parameters associated with the cavity disease parameters. The data acquisition module is used to collect raw feature data of abnormal areas of real roads and preprocess the raw feature data to obtain real feature data. A multidimensional matching module is used to quantify the comprehensive matching score between the real feature data and the parameters in the simulation database based on multidimensional heuristic factors, including volume heuristic factors, depression depth heuristic factors and three-dimensional position heuristic factors. The disease identification module is used to match and determine the comprehensive matching score based on a preset confidence threshold, and to determine whether the abnormal area is a real disease area based on the determination result. The disease morphology construction module is used to construct the road surface subsidence disease morphology based on the matching disease parameters corresponding to the abnormal area in the road disease simulation database if the abnormal area is a real disease area.

8. A device for constructing the morphology of road surface subsidence defects, characterized in that, The road surface settlement morphology construction device includes: a memory, a processor, and a road surface settlement morphology construction program stored in the memory. The processor is used to run the road surface settlement morphology construction program, and the road surface settlement morphology construction program is configured to implement the road surface settlement morphology construction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a road surface settlement morphology construction program, which, when executed by a processor, implements the road surface settlement morphology construction method as described in any one of claims 1 to 6.

Images