Method and system for road defect detection and repair

Abstract

The application provides a road defect detection and repair method and system, comprising collecting road images in a collection range of a driving vehicle and geographical position information corresponding to the road images; identifying defect information of a road surface based on the road images; determining a repair scheme and repair engineering quantity according to the defect information; calculating a repair cost according to the repair engineering quantity and a preset dynamic price database; generating and dispatching a work order based on the repair scheme, the repair cost and the geographical position information; receiving and verifying acceptance images after repair, and generating settlement data based on the repair cost after verification, which realizes full-process automation and precision processing of road defect detection, repair planning, engineering quantity measurement, work order management and cost settlement, and improves the response speed, cost control accuracy and management efficiency of road maintenance.

Description

Technical Field

[0001] This invention relates to the field of road maintenance technology, and in particular to a method and system for detecting and repairing road surface defects. Background Technology

[0002] In the field of road maintenance, especially in the maintenance of temporary gravel roads in wind farms, traditional methods present numerous problems that urgently need to be addressed. These roads, restricted by policy from being paved, are susceptible to various defects caused by the natural environment. Traditional manual inspection methods are inefficient, costly, and unable to achieve real-time defect monitoring. Furthermore, the formulation of repair plans and the estimation of work volume rely excessively on the experience of staff, leading to significant errors. This can cause repair delays, affecting road traffic, or result in resource waste and increased maintenance costs. In addition, the calculation of repair costs lacks a unified and accurate basis, and the work order dispatch and settlement processes are disconnected. There is a lack of systematic technical means to integrate defect identification, work volume calculation, work order management, and cost settlement, severely impacting the overall efficiency and economy of road maintenance.

[0003] Therefore, how to achieve automated management of the entire chain from defect discovery to repair settlement, and improve the response speed, cost control accuracy and management efficiency of road maintenance, is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] This invention provides a method and system for detecting and repairing road surface defects, which enables automated management of the entire chain from defect discovery to repair settlement, thereby improving the response speed, cost control accuracy and management efficiency of road maintenance.

[0005] On the one hand, the present invention provides a method for detecting and repairing road surface defects, comprising: Collect road images within the range of the traveling vehicle and the corresponding geographical location information of the road images; Based on the road images, identify road surface defect information; Based on the defect information, determine the repair plan and the amount of repair work; The repair cost is calculated based on the repair work volume and the preset dynamic price database; Based on the repair plan, the repair cost, and the geographical location information, a work order is generated and dispatched; Receive and verify the repaired acceptance image, and generate settlement data based on the repair cost after successful verification.

[0006] On the other hand, the present invention also provides a road surface defect detection and repair system, which includes: The acquisition module is used to acquire road images within the acquisition range of the driving vehicle and the corresponding geographical location information of the road images; The identification module is used to identify road surface defect information based on the road image; The determination module is used to determine the repair plan and repair work volume based on the defect information; The calculation module is used to calculate the repair cost based on the repair work volume and a preset dynamic price database; The generation module is used to generate and dispatch work orders based on the repair plan, the repair cost, and the geographical location information; The verification module is used to receive and verify the repaired acceptance image, and generate settlement data based on the repair cost after the verification is passed.

[0007] The road surface defect detection and repair method and system provided by this invention collects road images and corresponding geographical location information through vehicle-mounted equipment, identifies road surface defect information using artificial intelligence technology, matches repair plans based on preset rules and calculates repair work volume, calculates repair costs using a dynamic price database, generates and dispatches work orders, verifies and accepts images after repair completion and generates settlement data, realizing fully automated and precise processing of road surface defect detection, repair planning, work volume calculation, work order management and cost settlement, improving the response speed, cost control accuracy and management efficiency of road maintenance. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0009] Figure 1 This is a schematic flowchart of the road surface defect detection and repair method provided in the embodiments of the present invention; Figure 2 This is a schematic diagram of the road surface defect detection and repair system provided in an embodiment of the present invention. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0011] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0012] Figure 1 This is a schematic flowchart of the road surface defect detection and repair method provided in the embodiments of the present invention.

[0013] like Figure 1 As shown, the road surface defect detection and repair method provided in this embodiment of the invention mainly includes the following steps: 101. Collect road images within the collection range of the driving vehicle and the corresponding geographical location information of the road images; In this embodiment, a vehicle-mounted acquisition unit can be formed by deploying 360° high-definition cameras on wind farm production vehicles (such as maintenance vehicles and transport vehicles). This unit integrates a GPS / BeiDou positioning module, which can automatically trigger dynamic shooting during vehicle movement, collect real-time road surface and ditch images, and simultaneously record the geographical location information corresponding to each frame of the image. The acquisition unit features anti-shake, waterproof, and dustproof design, adapting to harsh environments such as sandstorms, rain, and snow, ensuring the clarity and stability of image acquisition.

[0014] 102. Based on the road image, identify road surface defect information; In this embodiment, for defect identification of road images, the Retinex dynamic image enhancement algorithm can be used to preprocess the acquired images, improving image contrast and eliminating the impact of environmental factors such as dust, rain, and fog on image quality. The preprocessed images are then input into a pre-trained multi-scale feature fusion convolutional neural network (CNN) model. The training dataset of this model covers various typical defect images such as collapses, cracks, and ditch blockages, and covers different lighting and weather conditions. It can accurately identify the type of road surface defect (such as collapses, cracks, ditch blockages, etc.), defect size (such as collapse area, crack length, etc.), and defect severity level (mild / medium / severe), thus completing the identification of road surface defect information. The defect information includes the defect type, defect size, and defect severity level.

[0015] Among them, the multi-scale feature fusion convolutional neural network (CNN) model can be specifically optimized for defect identification in wind farm gravel roads. It can adopt a lightweight encoder-decoder architecture, and its core achieves integrated identification of defect type, size, and severity level through "multi-scale feature capture + accurate fusion", as detailed below: The model aims to adapt to the harsh environment (dust storms, rain and fog) and small-scale defects (fine cracks, small-scale gravel loss) in Northwest China. It extracts defect features at different scales through layered extraction—the shallow layer captures the detailed texture of defects, while the deep layer extracts global semantic information. Attention mechanisms are also incorporated to weaken the interference of road gravel background. After cross-scale feature fusion, detailed and global information are integrated. Finally, through a multi-task output module, defect types such as collapses, cracks, and ditch blockages are identified simultaneously, and key dimensions such as the length, width, and depth of defects are calculated. Combined with the road traffic requirements of wind farms, the model is classified into three levels of severity: light, medium, and severe.

[0016] The model is trained on over 100,000 labeled defect images covering different lighting and weather conditions in Northwest China. By simulating harsh environments, the model enhances its generalization ability and ensures the accuracy of defect identification in complex scenarios, providing a reliable basis for subsequent repair scheme matching and engineering quantity calculation.

[0017] 103. Based on the defect information, determine the repair plan and the amount of repair work; In a specific implementation process, a repair plan can be matched based on a preset repair strategy mapping table, according to the defect type and the defect severity level; wherein, the repair plan includes repair methods, standard construction steps and recommended material types.

[0018] Specifically, the preset repair strategy mapping table is stored in the system's repair standard library. This mapping table establishes the correspondence between defect types, defect severity levels, and repair solutions. For example, when the defect type is "collapse" and the severity level is "severe," the matching repair solution is "gravel filling repair method." The corresponding standard construction steps include cleaning the defect area, compacting the base, filling gravel in layers, and leveling and compacting the surface. The recommended material type is gravel with a particle size that meets the preset standard. When the defect type is "ditch blockage" and the severity level is "moderate," the matching repair solution is "mechanical dredging + manual cleaning method." The standard construction steps include mechanically excavating the silt, manually cleaning the remaining debris, and repairing the inner wall of the ditch. The recommended material type is none (no filling material is required, only cleaning equipment is needed).

[0019] After obtaining the repair plan, the repair work volume can be calculated based on the repair method, the standard construction steps, the recommended material type, and the defect size; wherein, the repair work volume includes material usage, labor hours, and machinery usage time.

[0020] In a specific implementation process, the calculation of material usage includes: a1. Match the corresponding geometric model according to the defect type, input the defect size into the geometric model to calculate the geometric quantity of the defect; Specifically, a database of correspondences between defect types and geometric models can be pre-set, with different defect types corresponding to specific geometric models. For example, collapse defects correspond to frustum cone geometric models, crack defects correspond to cuboid trench geometric models, and ditch blockage defects correspond to column geometric models, etc.

[0021] Once the AI ​​identifies the defect type, it can retrieve the matching geometric model and its calculation formula from the mapping library. The specific defect size parameters identified and output by the AI ​​are then input into the model for calculation. For example, the upper and lower base radii and depth of a collapse are input into the formula for the volume of a frustum to calculate the defect volume; the length, average width, and preset standard depth of a crack are input into the formula for the volume of a cuboid to calculate the initial trench volume; and the length of the ditch blockage is multiplied by the standard cross-sectional area to calculate the theoretical sediment volume. These calculation results represent the geometric quantities of the defect that occupy space.

[0022] a2. According to the preset engineering quantity conversion rules, process the geometric quantities of the defects to generate basic engineering quantities; In a specific implementation process, the geometric quantity of a defect is a theoretical spatial quantity, not equal to the actual material quantity required for construction. Therefore, for different defect types, preset engineering quantity conversion rules can be used to modify the geometric quantity to take into account construction process requirements (such as slope protection, material compaction, trench widening, etc.), thereby outputting a foundation engineering quantity that better reflects the actual project. The preset engineering quantity conversion rules have specific processing logics for the geometric quantities of different defect types. For example, for the volume of collapse-type defects, the volume reduction after base compaction needs to be considered; for the trench volume of crack-type defects, adjustments need to be made based on construction process requirements. After processing the geometric quantity of the defect using these rules, the foundation engineering quantity is generated.

[0023] Specifically, the defect types include at least one of collapse defects, crack defects, and ditch blockage defects; the geometric quantities of the defects include at least one of defect volume, crack length, average crack width, and blockage area and blockage length. The process of processing the geometric quantities of the defects to generate basic engineering quantities according to preset engineering quantity conversion rules may specifically include: a21. Call the engineering quantity conversion logic corresponding to the defect type from the engineering quantity conversion rules; a22. For the aforementioned collapse-type defects, the engineering quantity conversion logic calculates the compacted volume of the space to be filled based on the defect volume, the average slope of the collapse area, and the bottom compaction evaluation parameters, and uses this as the basic engineering quantity. Specifically, for collapse-type defects, the key lies in obtaining the average slope gradient and bottom compaction evaluation parameters of the collapse area. The average slope gradient can be obtained by segmenting the collapse area using a CNN model. An optimized edge detection algorithm is then used to uniformly extract key feature points at the top, bottom, and middle of the slope (covering the complete slope morphology). Combining the 3D point cloud data from the vehicle-mounted LiDAR with GPS / BeiDou positioning, the pixel coordinates of the feature points are converted into precise 3D coordinates (error ≤ ±3cm). The local slope of each pair of corresponding feature points is calculated (based on elevation difference and horizontal distance). After removing outliers, the arithmetic mean is taken as the average slope gradient (accuracy ≤ ±1°).

[0024] The bottom compaction assessment parameters can be obtained as follows: vehicle-mounted vibration sensors collect road vibration data of the collapsed area (extracting core indicators such as frequency and amplitude); AI model analyzes the bottom soil image and determines the degree of looseness by texture density (divided into 3 levels: dense / medium / loose); retrieve historical compaction measurement data of the same soil type in this road section (such as the results of sand cone test); use a pre-trained simple regression model, integrate vibration indicators, looseness level and historical data calibration, and output compaction assessment parameters in the range of 0-1 (the closer to 1, the higher the compaction).

[0025] After obtaining the average slope gradient and bottom compaction parameters of the collapsed area, the compacted volume of the space to be filled can be calculated as follows: a221. Input the average slope gradient into a preset slope stability coefficient mapping table to obtain the corresponding slope trimming coefficient. Specifically, the preset slope stability coefficient mapping table includes the correspondence between the average slope gradient and the slope adjustment coefficient. The steeper the slope, the greater the required slope adjustment work, and the higher the corresponding slope adjustment coefficient. For example, when the average slope gradient is 20°, the corresponding slope adjustment coefficient is 1.1; when the slope is 30°, the coefficient is 1.3. By inputting the average slope gradient obtained through AI image recognition and 3D point cloud reconstruction into this mapping table, the corresponding slope adjustment coefficient can be obtained. This coefficient quantifies the proportion of additional filling material required due to the slope gradient.

[0026] a222. Input the bottom compaction evaluation parameters into a preset soil compression coefficient mapping table to obtain the corresponding volumetric compression coefficient; Specifically, the pre-defined soil compressibility coefficient mapping table includes the correspondence between bottom compaction assessment parameters and volumetric compressibility coefficients. A lower bottom compaction assessment parameter indicates a looser base soil, a greater volume reduction ratio after compaction of the filling material, and a smaller corresponding volumetric compressibility coefficient. For example, when the bottom compaction assessment parameter is 0.7, the volumetric compressibility coefficient is 0.9; when the parameter is 0.8, the coefficient is 0.95. Inputting the calculated bottom compaction assessment parameter into this mapping table yields the corresponding volumetric compressibility coefficient, which characterizes the volume reduction ratio of the filling material after compaction on the collapsed base.

[0027] a223. Based on the defect volume, the slope adjustment coefficient, and the volume compression coefficient, a comprehensive calculation is performed using a preset volume synthesis rule to output the compacted volume of the space to be filled, which is the basic engineering quantity.

[0028] Specifically, the defect volume can be corrected using the slope correction coefficient to obtain the theoretical filling volume including the additional materials required for slope correction; then, the theoretical filling volume is corrected again using the volume compression coefficient, taking into account the volume reduction of the filling material after the base is compacted, and the final calculated volume is the compacted volume of the space to be filled. This volume, as the basic engineering quantity of collapse-type defects, can accurately reflect the actual volume of materials that need to be filled.

[0029] a23. For the crack-type defects, the engineering quantity conversion logic is based on the crack length and the average width, and combined with the obtained standard depth and widening coefficient of the crack repair process, to calculate the volume of the tank to be filled with material, which is used as the basic engineering quantity. In a specific implementation process, this step can be implemented in the following way: a231. Based on the average width and the widening coefficient, determine the planned groove width required for the repair work; Specifically, the planned groove width required for repair work can be calculated by multiplying the average width of the crack by the widening factor. The widening factor is set to ensure that the filling material can fully bond with the pavement on both sides of the crack, thereby improving the repair effect. For example, when the average width is 2 mm and the widening factor is 1.5, the planned groove width is 3 mm.

[0030] a232. Based on the crack length, the planned slot width, and the standard depth, determine the initial groove volume when processing the crack area into a regular groove structure; Specifically, using the crack length, the calculated planned groove width, and the preset standard depth as parameters, the initial groove volume when the crack area is treated as a regular groove structure is calculated according to the formula for calculating the volume of a cuboid (volume = length × width × depth). This volume reflects the volume of material required to fill a single linear crack under ideal conditions.

[0031] a233. Identify the morphological type of the crack; Specifically, AI image recognition technology can be used to further analyze the morphology of cracks and determine the type of crack morphology, which is mainly divided into single linear cracks (continuous cracks without branches or intersections) and / or network cracks (cracks with multiple branches and intersections).

[0032] a234. If the morphological category is a single linear crack, the initial trench volume shall be used as the basic engineering quantity. Specifically, if the identification result is a single linear crack, since its shape is regular, the initial tank volume can accurately reflect the filling requirements. Therefore, the initial tank volume is directly used as the basic engineering quantity for crack-type defects.

[0033] a235. If the morphological category is the network crack, the corresponding volume magnification factor is obtained from the crack repair process parameter library according to the number and distribution density of the network cracks, and the initial tank volume is multiplied by the volume magnification factor to obtain the final tank volume, which is used as the basic engineering quantity.

[0034] Specifically, if the identification result is a network crack, since it has intersections and branches, the actual filling requirement is greater than the initial tank volume. At this time, the volume magnification factor corresponding to the number and distribution density of the network crack is retrieved from the crack repair process parameter library (the more intersections and the denser the distribution, the larger the magnification factor). The initial tank volume is multiplied by the volume magnification factor to obtain the final tank volume. This volume is the basic engineering volume of the network crack, which can meet the filling requirements under its complex shape.

[0035] a24. For the aforementioned ditch blockage defects, the engineering quantity conversion logic calculates the volume of silt to be removed based on the blockage area and the blockage length, combined with the obtained standard ditch cross-section model, and uses this volume as the basic engineering quantity.

[0036] In a specific implementation process, the calculation of basic engineering quantities can include the following methods: a241. Based on the geographic location information of the aforementioned ditch blockage defects, call the standard ditch cross-section model of the road segment corresponding to the geographic location information; Specifically, based on the geographical location information of the ditch blockage defect, the standard ditch cross-section model of the corresponding road section can be retrieved from the database. The standard ditch cross-section model includes detailed parameters such as the cross-sectional shape (e.g., rectangular, trapezoidal) and cross-sectional dimensions (e.g., width, depth) of the ditch. These parameters are all from the road design drawings and as-built data.

[0037] a242. Based on the blockage length and the standard ditch cross-sectional model, calculate the theoretical volume of the ditch section under a fully unobstructed state; Specifically, the cross-sectional area of ​​the ditch can be calculated based on the retrieved standard ditch cross-sectional model. Then, combined with the blockage length identified by AI, the theoretical volume of the ditch in a fully unobstructed state can be obtained by multiplying the cross-sectional area by the length. This theoretical volume is the maximum volume that the ditch can accommodate.

[0038] a243. Analyze the proportion of the blocked area to the effective flow area of ​​the standard side ditch cross-section model; Specifically, AI image recognition technology can be used to analyze images of blocked areas to determine the blocked area. At the same time, the effective flow area of ​​the ditch (i.e., the cross-sectional area through which water flows when the ditch is draining normally) can be calculated based on a standard ditch cross-sectional model, and then the proportion of the blocked area to the effective flow area can be calculated.

[0039] a244. Based on the preset ratio and siltation rate comparison table, determine the effective siltation coefficient corresponding to the current siltation state; wherein, the effective siltation coefficient is used to characterize the proportion of the actual volume of the ditch occupied by the silt. Specifically, the pre-defined ratio and siltation rate comparison table includes the correspondence between the percentage of blocked area and the effective siltation coefficient. The higher the percentage of blocked area, the more severe the ditch blockage, and the larger the effective siltation coefficient. For example, when the percentage is 60%, the effective siltation coefficient is 0.5; when the percentage is 80%, the coefficient is 0.7. Based on the calculated percentage of blocked area, the corresponding effective siltation coefficient is obtained from the comparison table. This coefficient represents the proportion of the actual volume of the ditch occupied by the silt.

[0040] a245. Multiply the theoretical volume by the effective blockage coefficient to obtain the volume of the silt, which is used as the basic engineering quantity.

[0041] Specifically, the calculated theoretical volume of the ditch can be multiplied by the effective blockage coefficient to obtain the volume of silt that needs to be removed. This volume of silt serves as the basic engineering quantity for ditch blockage defects.

[0042] In this embodiment, the accuracy of the theoretical volume calculation of the ditch is ensured by using a standard ditch cross-section model. The correlation between the proportion of blocked area and the effective blockage coefficient makes the calculation of the actual volume of silt more closely reflect the actual situation of ditch blockage, avoiding errors caused by estimating solely based on the blocked area and length. This helps to rationally plan the dredging scheme, allocate equipment and manpower, and improve the efficiency and economy of ditch dredging work.

[0043] a3. Based on the recommended material type, query the preset material parameter table to obtain the unit usage, material density and construction loss coefficient of the material corresponding to the recommended material type; In a specific implementation process, the material parameter table stores detailed parameters for various common repair materials, including the unit usage (i.e., the amount of material required per unit of work) of materials such as gravel and fillers of different specifications, material density (the ratio of mass to volume), and construction loss coefficient (the proportion of material loss during construction). Based on the recommended material types determined in the repair plan, the system can retrieve the corresponding parameter data from the material parameter table.

[0044] a4. Based on the basic engineering quantity, the unit usage, the material density, and the construction loss coefficient, determine the material usage.

[0045] In a specific implementation process, the theoretical material requirement can be determined based on the basic engineering quantity and the unit usage; the theoretical material requirement can be converted into the actual material quantity based on the material density; the actual material quantity can be corrected according to the construction loss coefficient to obtain the final material usage; wherein, the construction loss coefficient is dynamically adjusted according to the recommended material type and construction environment.

[0046] Specifically, the determination of theoretical material requirements is based on the basic engineering quantity and the unit usage. The basic engineering quantity is the engineering quantity data that meets the construction requirements after being processed by the engineering quantity conversion rules. The unit usage is the amount of material required per unit of basic engineering quantity. Multiplying the two gives the theoretical amount of material required to complete the repair project, i.e., the theoretical material requirement. This value reflects the basic amount of material required to complete the repair without loss.

[0047] Since theoretical material requirements are usually expressed in either mass or volume units, but actual procurement and construction may require conversion to the other unit, the theoretical material requirements are converted to actual quantities based on the material density obtained from the material parameter table. For example, if the theoretical material requirements are expressed in mass units (kilograms) and the material density is known (kilograms per cubic meter), the actual quantity can be converted to volume units (cubic meters) by dividing the mass by the density, facilitating the measurement of materials during procurement and use.

[0048] Material loss is inevitable during construction, therefore the actual material quantity needs to be adjusted based on a construction loss coefficient. This construction loss coefficient is not a fixed value; it can be dynamically adjusted based on the characteristics of the recommended material type (e.g., gravel is easily lost, while specialized fillers have lower loss) and environmental parameters (e.g., rainy or windy weather increases material loss). For example, if the recommended material is gravel and the construction environment is windy, a higher construction loss coefficient can be applied; conversely, if the recommended material is a specialized filler and the construction environment is favorable, the loss coefficient will be relatively lower. Multiplying the actual material quantity by the dynamically adjusted construction loss coefficient yields the corrected material quantity, which is the final material usage. This usage quantity fully meets construction needs while avoiding waste caused by over-purchasing.

[0049] In a specific implementation process, the calculation of man-hours includes: b1. Based on the standard construction steps, query the preset standard construction process time database to obtain the basic working hours required to complete the standard construction steps under standard working conditions. Specifically, the pre-set standard construction time database stores the basic time data required to complete the standard construction steps for different repair schemes under standard working conditions (i.e., good environmental conditions and no special complexities). For example, the basic time corresponding to the standard construction steps for "gravel filling of collapse defects" is 2 hours / cubic meter. Based on the standard construction steps determined in the repair scheme, the system queries and retrieves the corresponding basic time from this time database.

[0050] b2. Based on the severity level of the defect, obtain the corresponding construction complexity adjustment coefficient from the preset working hour adjustment coefficient table; wherein, the higher the severity level of the defect, the larger the construction complexity adjustment coefficient; Specifically, the preset time adjustment coefficient table includes a construction complexity adjustment coefficient. The construction complexity adjustment coefficient is related to the severity level of the defect. The higher the severity level of the defect, the greater the difficulty of the repair work, the more complex the procedures, and the more time is required. Therefore, the corresponding adjustment coefficient is larger. For example, the adjustment coefficient is 1.0 for minor defects, 1.2 for moderate defects, and 1.5 for severe defects.

[0051] b3. Obtain the environmental parameters during construction, and based on the environmental parameters, obtain the corresponding environmental factor adjustment coefficient from the working hour adjustment coefficient table; Specifically, the preset working time adjustment coefficient table also includes environmental factor adjustment coefficients. These environmental factor adjustment coefficients are related to the environmental parameters during construction. The environmental parameters are obtained through the sensors of the vehicle-mounted equipment and real-time meteorological data, including weather conditions (such as rain, sandstorms), daytime light conditions (such as strong light, weak light), and ambient temperature (too high or too low). Different environmental parameters correspond to different adjustment coefficients. For example, the adjustment coefficient for rainy days is 1.3, and the adjustment coefficient for high-temperature environments (above 35℃) is 1.2.

[0052] b4. Calculate the comprehensive adjustment coefficient based on the construction complexity adjustment coefficient, the environmental factor adjustment coefficient, and their respective weighting coefficients; Specifically, the weighting coefficients of the construction complexity adjustment coefficient and the environmental factor adjustment coefficient can be preset. For example, the weight of the construction complexity adjustment coefficient is 0.6 and the weight of the environmental factor adjustment coefficient is 0.4. Based on these two weighting coefficients, combined with the obtained construction complexity adjustment coefficient and environmental factor adjustment coefficient, the comprehensive adjustment coefficient is calculated by weighted summation, that is, comprehensive adjustment coefficient = (construction complexity adjustment coefficient × 0.6) + (environmental factor adjustment coefficient × 0.4).

[0053] b5. Multiply the basic working hours by the comprehensive adjustment coefficient to obtain the labor hours.

[0054] Specifically, the basic working hours obtained from the query can be multiplied by the calculated comprehensive adjustment coefficient. The result is the man-hours required to complete the repair project. The man-hours obtained fully consider the complexity of construction and the impact of environmental factors, making them more consistent with actual construction conditions. In this way, the man-hours obtained are more accurate, providing a reliable basis for manpower planning and cost accounting for the repair project. This helps to rationally allocate human resources, improve construction efficiency, and control labor costs.

[0055] In a specific implementation process, the calculation of machine usage time includes: c1. Based on the standard construction steps and the defect type, determine the type of machinery required to complete the repair and the standard operating time corresponding to the type of machinery; Specifically, the type of machinery required to complete the repair project can be determined based on the standard construction steps and defect type in the repair plan. For example, filling subsidence defects requires excavators and loaders, while clearing blocked ditches requires dredging machines. Simultaneously, the system stores the standard operating times for various types of machinery for different tasks. For instance, the standard operating time for an excavator filling subsidence defects is 1 hour per cubic meter. The corresponding standard operating time can be obtained based on the determined machinery type and workload.

[0056] c2. Based on the severity level of the defect, query the preset mechanical efficiency impact database to obtain the first correction coefficient corresponding to the mechanical type and the severity level of the defect; Specifically, the preset mechanical efficiency impact database stores correction coefficients for different types of machinery under various conditions. These coefficients are determined by combining historical machinery operation data (such as the actual operating efficiency of machinery in similar past projects) and expert experience rules, ensuring high reliability. Based on the severity level of the defect, the database is queried to obtain the first correction coefficient corresponding to the current machinery type and defect severity level. Higher defect severity levels indicate greater operational difficulty and lower efficiency, resulting in a larger first correction coefficient. For example, the first correction coefficient for a minor defect is 1.0, for a moderate defect it is 1.1, and for a severe defect it is 1.3.

[0057] c3. Obtain the geographical environmental parameters of the construction location, including the terrain slope and the type of surface soil; c4. Based on the geographical environment parameters and the type of machinery, query the machinery efficiency impact database to obtain the corresponding second correction coefficient; Specifically, the geographical environmental parameters of the construction site are obtained through GPS / BeiDou positioning combined with a terrain database. These parameters mainly include terrain slope (e.g., gentle, mild, steep) and surface soil type (e.g., soft soil, hard soil, gravelly soil). Based on the obtained geographical environmental parameters and the determined type of machinery, the corresponding second correction coefficient is retrieved from the machinery efficiency impact database. Different geographical environments have different impacts on machinery operation efficiency. For example, the second correction coefficient for excavators on steep slopes is 1.2, while the second correction coefficient for loaders on soft soil is 1.1.

[0058] c5. Based on the standard operating time, the first correction coefficient, and the second correction coefficient, the machine usage time is calculated by weighted average; wherein, the coefficient value of the machine efficiency in the database is determined by combining historical machine operation data and expert experience rules.

[0059] Specifically, the weights of the first and second correction coefficients can be preset, and the standard operating time can be combined with the first and second correction coefficients through weighted calculation. That is, the machine usage time = standard operating time × (first correction coefficient × first weight + second correction coefficient × second weight) to obtain the final machine usage time.

[0060] 104. Calculate the repair cost based on the repair work volume and the preset dynamic price database; Specifically, the dynamic price database stores real-time unit prices of different types of repair materials, labor rates, and machinery rental fees in the local area. Based on the calculated repair workload, the database can be retrieved to retrieve the corresponding price data and automatically calculate the total repair cost according to a preset cost calculation logic. For example, material cost = material usage × corresponding real-time unit price of the material; labor cost = labor hours × local labor rate; machinery cost = machinery usage time × corresponding machinery rental unit price; total repair cost = material cost + labor cost + machinery cost.

[0061] 105. Based on the repair plan, the repair cost, and the geographical location information, generate and dispatch a work order; Specifically, based on the determined repair plan, the calculated repair cost, and the collected defect geographical location information, a work order containing the above information can be generated through the cloud platform. The work order can then be dispatched to the maintenance team closest to the defect location according to the location distribution of the maintenance team. The maintenance team can receive the work order through the Web / APP terminal.

[0062] 106. Receive and verify the repaired acceptance image. After verification, generate settlement data based on the repair cost.

[0063] Specifically, after the maintenance team completes the repair work, they need to take images of the repaired site as acceptance images and upload them to the system. The system compares the acceptance images with the images of defects before repair and verifies whether the repair effect meets the standards, such as a smooth surface after filling the collapse and no siltation in the ditches. If the verification is successful, settlement data is automatically generated based on the previously calculated repair costs, providing a basis for cost settlement. Throughout the entire process of generating settlement data, relevant data is recorded using blockchain technology to ensure that the data is tamper-proof and guarantees transparent and traceable settlement.

[0064] The road surface defect detection and repair method in this embodiment collects road images and corresponding geographical location information through vehicle-mounted equipment, identifies road surface defect information using artificial intelligence technology, matches repair plans based on preset rules and calculates repair work volume, calculates repair costs using a dynamic price database, generates and dispatches work orders, verifies and accepts images after repair completion and generates settlement data, realizing fully automated and precise processing of road surface defect detection, repair planning, work volume calculation, work order management and cost settlement, improving the response speed, cost control accuracy and management efficiency of road maintenance.

[0065] Based on the same general inventive concept, this invention also protects a road surface defect detection and repair system. The road surface defect detection and repair system provided by this invention will be described below. The road surface defect detection and repair system described below can be referred to in correspondence with the road surface defect detection and repair method described above.

[0066] Figure 2 This is a schematic diagram of the road surface defect detection and repair system provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the road surface defect detection and repair system of this embodiment includes a data acquisition module 21, an identification module 22, a determination module 23, a calculation module 24, a generation module 25, and a verification module 26.

[0067] The acquisition module 21 is used to acquire road images within the acquisition range of the driving vehicle and the geographical location information corresponding to the road images; The identification module 22 is used to identify road surface defect information based on the road image; The determination module 23 is used to determine the repair plan and repair work volume based on the defect information; Calculation module 24 is used to calculate the repair cost based on the repair work volume and a preset dynamic price database; The generation module 25 is used to generate and dispatch work orders based on the repair plan, the repair cost, and the geographical location information; The verification module 26 is used to receive and verify the repaired acceptance image, and generate settlement data based on the repair cost after the verification is passed.

[0068] It should be noted that all relevant information that may be involved in the various embodiments of the present invention is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and is information that users actively provide or generate during the use of the product / service, as well as information obtained with user authorization.

[0069] The information processed by this invention may vary depending on the specific product / service scenario and should be based on the specific scenario in which the user uses the product / service. This may involve user account information, device information, or other related information. This invention will treat the relevant information and its processing with the utmost diligence.

[0070] This invention places great emphasis on the security of relevant information and has adopted reasonable and feasible security protection measures that comply with industry standards to protect user information and prevent unauthorized access, public disclosure, use, modification, damage or loss of relevant information.

[0071] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0072] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting and repairing road surface defects, characterized in that, include: Collect road images within the range of the traveling vehicle and the corresponding geographical location information of the road images; Based on the road images, identify road surface defect information; Based on the defect information, determine the repair plan and the amount of repair work; The repair cost is calculated based on the repair work volume and the preset dynamic price database; Based on the repair plan, the repair cost, and the geographical location information, a work order is generated and dispatched; Receive and verify the repaired acceptance image, and generate settlement data based on the repair cost after successful verification.

2. The method for detecting and repairing road defects according to claim 1, characterized in that, The defect information includes the defect type, defect size, and defect severity level; Based on the defect information, the repair plan and repair work volume are determined, including: Based on a preset repair strategy mapping table, a repair plan is matched according to the defect type and the defect severity level; wherein, the repair plan includes a repair method, standard construction steps and recommended material types; The repair work volume is calculated based on the repair method, the standard construction steps, the recommended material type, and the defect size; wherein, the repair work volume includes material usage, labor hours, and machinery usage time.

3. The method for detecting and repairing road defects according to claim 2, characterized in that, The calculation process for the material usage includes: Based on the defect type, match the corresponding geometric model, input the defect size into the geometric model, and calculate the geometric quantity of the defect; According to the preset engineering quantity conversion rules, the geometric quantities of the defects are processed to generate basic engineering quantities; Based on the recommended material type, query the preset material parameter table to obtain the unit dosage, material density and construction loss coefficient of the material corresponding to the recommended material type; The material usage is determined based on the basic engineering quantity, the unit usage, the material density, and the construction loss coefficient.

4. The method for detecting and repairing road defects according to claim 3, characterized in that, Based on the aforementioned basic engineering quantity, the aforementioned unit usage, the aforementioned material density, and the aforementioned construction loss coefficient, the material usage is determined, including: Based on the aforementioned basic engineering quantities and unit usage quantities, the theoretical material requirements are determined. Based on the material density, the theoretical material requirement is converted into actual material quantity; The actual material quantity is corrected based on the construction loss coefficient to obtain the final material usage; wherein, the construction loss coefficient is dynamically adjusted according to the recommended material type and construction environment.

5. The method for detecting and repairing road defects according to claim 3, characterized in that, The defect types include at least one of the following: collapse defects, crack defects, and ditch blockage defects; The geometric quantities of the defect include at least one of the following: defect volume, crack length, average crack width, and plugging area and plugging length. According to preset engineering quantity conversion rules, the geometric quantities of the defects are processed to generate basic engineering quantities, including: Call the engineering quantity conversion logic corresponding to the defect type from the engineering quantity conversion rules; For the aforementioned collapse-type defects, the engineering quantity conversion logic calculates the compacted volume of the space to be filled based on the defect volume, the average slope of the collapse area, and the bottom compaction degree evaluation parameters, and uses this as the basic engineering quantity. For the aforementioned crack-type defects, the engineering quantity conversion logic is based on the crack length and the average width, and combined with the obtained standard depth and widening coefficient of the crack repair process, to calculate the volume of the tank to be filled with material, which is used as the basic engineering quantity. For the aforementioned ditch blockage defects, the engineering quantity conversion logic calculates the volume of silt to be removed based on the blockage area and the blockage length, combined with the obtained standard ditch cross-section model, and uses this volume as the basic engineering quantity.

6. The method for detecting and repairing road defects according to claim 5, characterized in that, Based on the defect volume, the average slope of the collapsed area, and the bottom compaction evaluation parameters, the compacted volume of the space to be filled is calculated, including: The average slope gradient is input into a preset slope stability coefficient mapping table to obtain the corresponding slope adjustment coefficient; the slope adjustment coefficient is used to quantify the additional material filling requirements caused by the slope gradient. The bottom compaction evaluation parameters are input into a preset soil compression coefficient mapping table to obtain the corresponding volume compression coefficient; the volume compression coefficient is used to characterize the volume reduction ratio of the filling material after compaction on the collapsed base; Based on the defect volume, the slope adjustment coefficient, and the volume compression coefficient, a comprehensive calculation is performed using a preset volume synthesis rule to output the compacted volume of the space to be filled, which is used as the basic engineering quantity.

7. The method for detecting and repairing road defects according to claim 5, characterized in that, Based on the crack length and the average width, and combined with the standard depth and widening coefficient of the crack repair process, the volume of the tank to be filled with material is calculated, including: Based on the average width and the widening coefficient, determine the planned groove width required for the repair work; Based on the crack length, the planned slot width, and the standard depth, determine the initial groove volume when treating the crack area as a regular groove structure; Identify the morphological category of the crack; wherein the morphological category includes single linear cracks and / or network cracks; If the morphology is a single linear crack, the initial trench volume is taken as the basic engineering quantity. If the morphological category is the network crack, the corresponding volume magnification factor is obtained from the crack repair process parameter library according to the number and distribution density of the network cracks, and the initial tank volume is multiplied by the volume magnification factor to obtain the final tank volume, which is used as the basic engineering quantity.

8. The method for detecting and repairing road defects according to claim 5, characterized in that, Based on the blocked area and the blocked length, and combined with the obtained standard ditch cross-sectional model, the volume of silt to be removed is calculated as the basic engineering quantity, including: Based on the geographic location information of the aforementioned ditch blockage defects, the standard ditch cross-section model of the road segment corresponding to the geographic location information is invoked; Based on the blockage length and the standard ditch cross-sectional model, calculate the theoretical volume of this ditch section under a fully unobstructed state; Analyze the proportion of the blocked area relative to the effective flow area of ​​the standard side ditch cross-section model; Based on a preset ratio and siltation rate comparison table, the effective siltation coefficient corresponding to the current siltation state is determined; wherein, the effective siltation coefficient is used to characterize the proportion of the actual volume of the ditch occupied by the silt. Multiply the theoretical volume by the effective blockage coefficient to obtain the volume of the silt, which is used as the basic engineering quantity.

9. The method for detecting and repairing road surface defects according to any one of claims 2-8, characterized in that, The calculation process for the labor hours includes: Based on the standard construction steps, the preset standard construction process time database is queried to obtain the basic time required to complete the standard construction steps under standard working conditions. Based on the severity level of the defect, the corresponding construction complexity adjustment coefficient is obtained from a preset work hour adjustment coefficient table; wherein, the higher the severity level of the defect, the larger the construction complexity adjustment coefficient. Obtain environmental parameters during construction, and based on these environmental parameters, obtain the corresponding environmental factor adjustment coefficients from the working hour adjustment coefficient table; wherein, the environmental parameters include at least weather conditions, daytime light conditions, and ambient temperature; Based on the construction complexity adjustment coefficient, the environmental factor adjustment coefficient, and their respective weighting coefficients, a comprehensive adjustment coefficient is calculated. The basic working hours are multiplied by the comprehensive adjustment coefficient to obtain the labor hours.

10. A road surface defect detection and repair system, characterized in that, include: The acquisition module is used to acquire road images within the acquisition range of the driving vehicle and the corresponding geographical location information of the road images; The identification module is used to identify road surface defect information based on the road image; The determination module is used to determine the repair plan and repair work volume based on the defect information; The calculation module is used to calculate the repair cost based on the repair work volume and a preset dynamic price database; The generation module is used to generate and dispatch work orders based on the repair plan, the repair cost, and the geographical location information; The verification module is used to receive and verify the repaired acceptance image, and generate settlement data based on the repair cost after the verification is passed.

Images