Road maintenance quality inspection system based on intelligent decision-making

Abstract

The present invention relates to the field of road data processing technology, and in particular to a road maintenance quality detection system based on intelligent decision-making, comprising: an image acquisition module, a model calibration module, a maintenance plan module, a monitoring and analysis module, a vehicle monitoring module, an assessment module, and a judgment module. When determining that maintenance abnormalities are found on road sections within a single area, the preset maintenance duration corresponding to the single area is adjusted to a corresponding value, the maintenance thickness of each road section corresponding to the single area is adjusted to a corresponding value, the preset maintenance area is adjusted to a corresponding value, or the amount of road surface image information used to train a built-in model in the model calibration module is adjusted to a corresponding value. After completing road maintenance, the road condition is classified based on the continuously monitored road image information, and subsequent maintenance parameters are adjusted based on the classification results, thereby improving the maintenance efficiency of the road.

Description

Technical Field

[0001] The present invention relates to the technical field of road data processing, and in particular to a road maintenance quality detection system based on intelligent decision-making. Background Art

[0002] With the rapid development and improvement of road construction, road mileage has continued to increase, and road traffic volume has gradually increased in recent years. This, coupled with overloaded roads, has directly led to an increasing number of road diseases, which have a significant impact on road performance. This not only directly affects the overall performance and lifespan of highways, but also directly affects driving safety, comfort, and economy. Therefore, road maintenance is a vital link in maintaining road quality.

[0003] The contradiction between traditional road maintenance and management methods and the current large-scale maintenance needs is becoming increasingly acute. Road inspection and repair work still primarily relies on inspectors using written descriptions of damage locations. This lacks a robust road repair inspection model and consumes significant time and human resources. Due to the extensive and complex scope of road repair projects, manual inspections are subject to significant subjectivity, and different inspectors may produce inconsistent results, complicating decision-making for road repairs.

[0004] Chinese Patent Publication No.: CN117522175B discloses a road maintenance decision-making method and system, which includes determining the PCI of a target road; determining a preliminary decision level for target road maintenance based on the PCI; controlling a road detection device to obtain detection data of the target road; controlling a workstation to determine road damage data based on the detection data; the workstation is a road damage identification and processing platform based on a road damage model; determining a deep decision level for target road maintenance based on the road damage data; and determining a target road maintenance decision model based on the preliminary decision level and the deep decision level for target road maintenance. It can be seen that the above technical solution has the following problems: it does not consider classifying road conditions based on continuously monitored road image information after completing road maintenance, and does not consider adjusting subsequent maintenance parameters based on the classification results, which affects the efficiency of road maintenance. Summary of the Invention

[0005] To this end, the present invention provides a road maintenance quality detection system based on intelligent decision-making to overcome the problem in the prior art that the road conditions are not classified based on the continuously monitored road image information after the completion of road maintenance, and the subsequent maintenance parameters are not adjusted based on the classification results, which affects the road maintenance efficiency.

[0006] To achieve the above objectives, the present invention provides a road maintenance quality detection system based on intelligent decision-making, comprising:

[0007] An image acquisition module includes a plurality of image acquirers respectively arranged at each road section in each road area for acquiring road image information;

[0008] a model calibration module connected to the image acquisition module, for periodically calibrating damaged areas in the road surface image information, and determining damaged areas whose area is larger than a preset maintenance area as areas to be maintained;

[0009] a maintenance planning module connected to the model calibration module, for determining maintenance parameters based on the damaged area calibrated by the model calibration module, including maintenance area, maintenance thickness, and maintenance duration;

[0010] a monitoring and analysis module, connected to the image acquisition module, the model calibration module, and the maintenance plan module, respectively, for determining the flatness based on the road surface image information of the corresponding road section reacquired by the image acquisition module after a preset operating time, on the condition that maintenance of each of the areas to be maintained is completed;

[0011] The vehicle monitoring module is used to count the number of heavy-loaded vehicles passing through each road section in each cycle;

[0012] an assessment module, connected to the monitoring and analysis module and the vehicle monitoring module, respectively, for marking a maintenance label of a corresponding road section based on the flatness of each road section;

[0013] A determination module, which is respectively connected to the assessment module, the maintenance plan module and the model calibration module, is used to determine whether the maintenance of each road section in a single pavement area is qualified based on the statistical number of each type of maintenance labels of each road section in a single pavement area, and when determining that the maintenance of each road section in a single pavement area is abnormal, determine the maintenance time, maintenance thickness or maintenance area of ​​the single pavement area, or determine the number of pavement image information used to train the built-in model in the model calibration module.

[0014] Furthermore, the monitoring and analysis module is used to determine the flatness based on the road surface image information, to obtain the grayscale difference between adjacent pixels in the road surface image information, calculate the standard deviation of each grayscale difference, and obtain the flatness for a single road surface image information;

[0015] The assessment module is used to mark the maintenance label of the corresponding road section based on the flatness, including:

[0016] If the flatness is less than or equal to the first preset flatness, the maintenance label of the single road section is determined as a stable road section;

[0017] If the flatness is less than or equal to the second preset flatness and greater than the first preset flatness, then marking the maintenance label of the single road section in combination with the heavy-load vehicle flow parameter of the single road section;

[0018] If the flatness is greater than a second preset flatness, a maintenance tag of the single road section is marked based on the average rainfall of the road surface area corresponding to the single road section within the preset operating time.

[0019] Furthermore, the assessment module is used to mark the maintenance label of a single road section based on the heavy-load vehicle flow parameters of the single road section, including:

[0020] Obtain the number of heavy-loaded vehicles passing through a single road section in several cycles, calculate the variance of the number of heavy-loaded vehicles passing through each cycle, and obtain the heavy-loaded vehicle flow parameters;

[0021] If the heavy-load vehicle flow parameter is less than or equal to the first preset flow parameter, the maintenance label of the single road section is determined as a stable road section;

[0022] If the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the maintenance label of the single road section is determined as a fluctuating road section;

[0023] If the heavy-load vehicle flow parameter is greater than the second preset flow parameter, a maintenance label of the single road section is marked based on the average rainfall of the road surface area corresponding to the single road section within the preset operating time.

[0024] Furthermore, the assessment module is used to mark the maintenance label of a single road section based on the average rainfall of the road surface area corresponding to the single road section within a preset operating time, including:

[0025] If the average rainfall is less than or equal to the first preset rainfall, marking the maintenance label of the single road section based on the flatness difference parameter between the single road section and the adjacent road sections;

[0026] If the average rainfall is less than or equal to the second preset rainfall and greater than the first preset rainfall, the maintenance label of the single road section is determined as a sensitive road section;

[0027] If the average rainfall is greater than the second preset rainfall, the maintenance label of the single road section is determined as a weak road section.

[0028] Furthermore, the assessment module is used to mark the maintenance label of a single road section based on the flatness difference parameter between the single road section and adjacent road sections, including:

[0029] Calculating the difference between the flatness of the single road section and the obtained flatness of the single road section connected to the single road section to obtain a flatness difference;

[0030] Calculate the average of the flatness differences between two road sections connected to a single road section to obtain a flatness difference parameter;

[0031] If the flatness difference parameter is less than or equal to the preset difference parameter, the maintenance label of the single road section is determined as a sensitive road section;

[0032] If the flatness difference parameter is greater than the preset difference parameter, the maintenance label of the single road section is determined as a vulnerable road section.

[0033] Furthermore, the determination module is configured to determine whether the maintenance of each road section in the single road surface area is qualified based on the number of each type of maintenance labels of each road section in the single road surface area, including:

[0034] Count the number of maintenance tags of each type in a single pavement area and identify the maintenance tag with the largest number as the problem tag;

[0035] If the problem label is a stable road section, the maintenance of each road section in the single road surface area is determined to be qualified, and each module is controlled to continue to operate using the current operating parameters;

[0036] If the problem label is a fluctuating road section, the maintenance anomaly of each road section in the single road surface area is determined, and the preset maintenance duration corresponding to the single road surface area is adjusted to the corresponding value based on the average value of the heavy-load vehicle flow parameters of each fluctuating road section in the single road surface area;

[0037] If the problem label is a sensitive road section, the maintenance abnormality of each road section in the single road surface area is determined, and the maintenance thickness of each road section corresponding to the single road surface area is adjusted to the corresponding value based on the average flatness of each sensitive road section in the single road surface area;

[0038] If the problem label is a vulnerable road section, the maintenance anomaly of each road section in the single road surface area is determined, and the preset maintenance area is adjusted to the corresponding value based on the average value of the flatness difference parameter of each vulnerable road section in the single road surface area;

[0039] If the problem label is a weak road section, the maintenance abnormalities of each road section in the single road surface area are determined, and the amount of road surface image information used to train the built-in model in the model calibration module is adjusted to the corresponding value based on the average rainfall in the single road surface area.

[0040] Furthermore, the determination module is used to adjust the preset maintenance time corresponding to the single road surface area to a corresponding value based on the average value of the heavy-load vehicle flow parameters of each fluctuating road section in the single road surface area, wherein:

[0041] The average value of the heavy-load vehicle flow parameters in each fluctuating section within a single road surface area is recorded as the average flow rate;

[0042] The reduction in the preset maintenance time is proportional to the average flow rate.

[0043] Furthermore, the determination module is used to adjust the repair thickness of each road section corresponding to the single road surface area to a corresponding value based on the average value of the flatness of each sensitive road section in the single road surface area, wherein:

[0044] The average value of the smoothness of each sensitive road section in a single road surface area is recorded as the mean smoothness value;

[0045] The increase in the repair thickness of each road section corresponding to a single pavement area is proportional to the mean flatness.

[0046] Furthermore, the determination module is used to adjust the preset maintenance area to a corresponding value based on the average value of the flatness difference parameter of each vulnerable road section in a single road surface area, wherein:

[0047] The average value of the roughness difference parameters of each vulnerable road section in a single road surface area is recorded as the average difference;

[0048] The reduction in the preset maintenance area is proportional to the average difference.

[0049] Furthermore, the determination module is used to adjust the amount of road surface image information used to train the built-in model in the model calibration module to a corresponding value based on the average rainfall in a single road surface area, wherein:

[0050] The amount of road surface image information used to train the built-in model in the model calibration module increases in direct proportion to the average rainfall.

[0051] Compared with the prior art, the beneficial effects of the present invention lie in that an image acquisition module, a model calibration module, a maintenance plan module, a monitoring and analysis module, a vehicle monitoring module, an evaluation module and a judgment module are set to mark the maintenance labels of the corresponding road sections based on the flatness of each road section; whether the maintenance of each road section in a single pavement area is qualified is determined based on the statistical number of maintenance labels of each type of each road section in a single pavement area; and when determining that the maintenance of each road section in a single pavement area is abnormal, the maintenance time, maintenance thickness or maintenance area of ​​the single pavement area is determined, or the number of pavement image information used to train the built-in model in the model calibration module is determined; after completing the road maintenance, the road conditions are classified according to the continuously monitored road image information, and the subsequent maintenance parameters are adjusted according to the classification results, thereby improving the maintenance efficiency of the road.

[0052] Furthermore, a maintenance tag is assigned to a corresponding road section based on its smoothness. By obtaining the grayscale differences between adjacent pixels in the road surface image information and calculating the standard deviation of each grayscale difference, the grayscale difference reflects the road surface's undulations; a larger standard deviation indicates worse road surface smoothness. This improves the accuracy and real-time performance of smoothness detection. When the smoothness is less than or equal to a first preset smoothness, the standard deviation of the grayscale differences between adjacent pixels is in a low range, indicating that the road surface has little noticeable undulations or damage and good smoothness, and the section is marked as stable. When the smoothness is less than or equal to a second preset smoothness and greater than the first preset smoothness, the road surface exhibits some unevenness, but it is not severe. In this case, further evaluation is required in conjunction with the heavy-load vehicle flow parameter. The maintenance tag for each road section is assigned based on the heavy-load vehicle flow parameter for that section. When the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the heavy-load vehicle traffic is relatively stable, with relatively little impact on the road surface, and the section is marked as stable. When the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the number of heavy-load vehicles passing through fluctuates, and the pressure on the road surface also varies. This road section is marked as a fluctuating section. This refined classification of road conditions provides an accurate basis for subsequent determination of the condition of the corresponding road area, enabling automatic identification and detection of road damage, improving detection efficiency, reducing the workload and subjectivity of manual inspections, and increasing the accuracy of detection results, further enhancing road maintenance efficiency.

[0053] Furthermore, the maintenance label of each road section is assigned based on the average rainfall in the corresponding road area over a preset operating period. When the average rainfall is less than or equal to a first preset rainfall amount, the impact of rainfall on the road surface is relatively small. In this case, a further evaluation is performed based on the flatness difference parameter with adjacent road sections. When the average rainfall is greater than the first preset rainfall amount but less than or equal to a second preset rainfall amount, the road surface is more susceptible to rain erosion and the section is marked as a sensitive section. When the average rainfall is greater than the second preset rainfall amount, the road surface is significantly affected by rain and the model calibration module fails to identify the section in a timely manner, resulting in an excessively high flatness and low recognition accuracy of road damage in the current environment, and the section is marked as a weak section. The maintenance label for individual road sections is assigned based on the roughness difference parameter compared to adjacent sections. When the roughness difference parameter is less than or equal to a preset difference parameter, the roughness difference between the section and adjacent sections is small, and due to the unevenness caused by overall environmental factors, the section is marked as sensitive. When the roughness difference parameter is greater than the preset difference parameter, the smoothness of the individual road section differs significantly from that of adjacent sections. The vibration and pressure generated by vehicles passing over adjacent damaged roads are transferred to the current section, making it more susceptible to damage, and thus the section is marked as vulnerable. Road sections are classified and labeled based on multiple factors, including roughness, heavy vehicle flow parameters, rainfall parameters, and roughness difference parameters, enabling a comprehensive assessment of road conditions. This allows for refined classification of road conditions, provides an accurate basis for subsequent maintenance decisions, and improves road maintenance efficiency.

[0054] Furthermore, the number of maintenance tags of each type within a single pavement area is counted, and the maintenance tags with the largest number are identified as problem tags. Based on the different problem tags, the causes of maintenance anomalies are analyzed, and parameters such as the preset maintenance duration, repair thickness, preset maintenance area, and the number of images used in the training model are adjusted accordingly. This enables dynamic adjustment of maintenance management, optimizing maintenance parameters based on actual road conditions and maintenance results, improving the scientific nature and effectiveness of road maintenance. If the problem tag is a fluctuating section, the road surface is prone to damage due to the frequent travel of heavy-loaded vehicles in a single pavement area. In this case, the preset maintenance duration corresponding to the individual pavement area is adjusted to the corresponding value to adjust the maintenance cycle and promptly detect road anomalies. When the problem label is a sensitive section, the repair thickness of each section within the individual road area is adjusted to a corresponding value to reduce maintenance frequency, as each section within the individual road area is prone to damage. When the problem label is a fragile section, the vibration and pressure generated by vehicles passing through adjacent damaged sections affect the current section, making it more susceptible to damage. In this case, the preset maintenance area is adjusted to ensure timely treatment when a section breaks. When the problem label is a weak section, the individual road area is easily damaged by rain, and the current model cannot effectively identify the damage characteristics of the current road working environment. In this case, the model training amount is increased to ensure that even minor damage is promptly identified and maintained. The amount of road surface image information used to train the built-in model in the model calibration module is adjusted to a corresponding value. This enables the built-in model in the model calibration module to better adapt to road conditions under different rainfall conditions, improving the model's ability to identify road damage characteristics and thus improving road maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a module block diagram of a road maintenance quality detection system based on intelligent decision-making according to an embodiment of the present invention;

[0056] Figure 2 This is a logic decision diagram of the evaluation module according to an embodiment of the present invention based on the maintenance label of the road section corresponding to the flatness mark;

[0057] Figure 3 A logical decision diagram for marking a maintenance label of a single road section based on the heavy-load vehicle flow parameters of the single road section by the evaluation module according to an embodiment of the present invention;

[0058] Figure 4 This is a logical decision diagram for marking the maintenance label of a single road section by the evaluation module according to an embodiment of the present invention based on the average rainfall of the road surface area corresponding to the single road section within a preset operating time. DETAILED DESCRIPTION

[0059] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0060] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0061] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0062] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0063] See also Figure 1 、 Figure 2 、 Figure 3 as well as Figure 4 As shown, they are respectively a module block diagram of a road maintenance quality detection system based on intelligent decision-making according to an embodiment of the present invention, a logical decision diagram for an assessment module to mark a maintenance label of a corresponding road section based on flatness, a logical decision diagram for an assessment module to mark a maintenance label of a single road section based on heavy-load vehicle flow parameters of the single road section, and a logical decision diagram for an assessment module to mark a maintenance label of a single road section based on the average rainfall of the road surface area corresponding to the single road section within a preset operating time. A road maintenance quality detection system based on intelligent decision-making according to an embodiment of the present invention comprises:

[0064] An image acquisition module includes a plurality of image acquirers respectively arranged at each road section in each road area for acquiring road image information;

[0065] a model calibration module connected to the image acquisition module, for periodically calibrating damaged areas in the road surface image information, and determining damaged areas whose area is larger than a preset maintenance area as areas to be maintained;

[0066] a maintenance planning module connected to the model calibration module, for determining maintenance parameters based on the damaged area calibrated by the model calibration module, including maintenance area, maintenance thickness, and maintenance duration;

[0067] a monitoring and analysis module, connected to the image acquisition module, the model calibration module, and the maintenance plan module, respectively, for determining the flatness based on the road surface image information of the corresponding road section reacquired by the image acquisition module after a preset operating time, on the condition that maintenance of each of the areas to be maintained is completed;

[0068] The vehicle monitoring module is used to count the number of heavy-loaded vehicles passing through each road section in each cycle;

[0069] an assessment module, connected to the monitoring and analysis module and the vehicle monitoring module, respectively, for marking a maintenance label of a corresponding road section based on the flatness of each road section;

[0070] A determination module is respectively connected to the evaluation module, the maintenance plan module and the model calibration module, and is used to determine whether the maintenance of each road section in a single pavement area is qualified based on the statistical number of each type of maintenance labels of each road section in the single pavement area, and when it is determined that the maintenance of each road section in the single pavement area is abnormal, adjust the preset maintenance time corresponding to the single pavement area to a corresponding value, adjust the maintenance thickness of each road section corresponding to the single pavement area to a corresponding value, adjust the preset maintenance area to a corresponding value, or adjust the number of pavement image information used to train the built-in model in the model calibration module to a corresponding value.

[0071] Specifically, the specific structure of the model calibration module is not described, and it can be any logical component. It can be understood that the road surface image information can be input into the model calibration module, and the model calibration module can select the damaged area in the input image information. This will not be repeated.

[0072] Specifically, the image acquirers in the image acquisition module are distributed in various sections within each road area. The specific structure of the image acquirer is not limited. It can be a high-definition camera installed at a location such as a street light pole or a traffic monitoring pole. It can be understood that it is sufficient to ensure that the road conditions of the entire road section can be covered. This will not be repeated.

[0073] Specifically, the model calibration module is a deep learning model. The model calibration module learns a large amount of road image data to identify damaged areas such as cracks and potholes on the road surface, and marks these areas. The deep learning model can be a convolutional neural network (CNN).

[0074] Specifically, the model calibration module trains the model using road imagery as a training set. Images in the training set are annotated with damaged areas so the model can learn the characteristics of these areas. The trained model is then deployed to the model calibration module to process real-time road imagery.

[0075] Specifically, the maintenance parameters in the maintenance plan module are determined as follows:

[0076] The specific method for determining the repair area is not limited. Based on the damaged area selected by the model calibration module, the pixel area of ​​that area in the image is calculated. Then, combined with the image acquisition parameters, shooting height, and angle, the pixel area is converted into the actual repair area. Using the known image resolution and shooting height, the actual ground area corresponding to each pixel is calculated, resulting in the actual area of ​​the repair area in square meters. This is a prior art technique and will not be further described.

[0077] There is no limitation on the method for determining the repair thickness. The repair thickness can be determined based on the repair area. In this embodiment, the repair thickness can be selected within the interval [2 cm, 8 cm]. , H is the maintenance thickness, S is the maintenance area, and D is the average grayscale of the area to be maintained. It can be understood that the average grayscale of this embodiment is an unsigned integer, α is the first thickness coefficient, β is the second thickness coefficient, α is 0.001, and β is 0.01. This is the existing technology and will not be repeated here.

[0078] There is no limitation on the method of determining the maintenance time. The maintenance time is proportional to the maintenance area and maintenance thickness. A maintenance time calculation model can be established based on historical maintenance data. The maintenance area and maintenance thickness can be substituted into the calculation model to obtain the maintenance time. In this embodiment, optionally, , T is the maintenance time, the unit is hours, H0 is the unit thickness, set H0=1cm, S0 is the unit area, set S0=1cm 2 This is prior art and will not be described in detail.

[0079] Specifically, the image acquisition module collects pavement image information for each road section at set time intervals and transmits it to the model calibration module. The model calibration module processes the input pavement image information, identifies damaged areas, marks them, and then transmits the marked information to the maintenance planning module. The maintenance planning module determines the repair area, repair thickness, and repair duration based on the marked information and generates a maintenance plan. Maintenance personnel maintain the road surface according to the maintenance plan. After maintenance is completed, the monitoring and analysis module triggers the image acquisition module to reacquire pavement image information for the corresponding road section after a preset operating time, analyzes the road surface flatness, and evaluates the maintenance quality.

[0080] Specifically, there is no limitation on the specific method by which the vehicle monitoring module counts the number of heavy-loaded vehicles passing through each road section in each cycle. The vehicle monitoring module may include a high-definition monitoring camera installed on the road section for taking images and videos of the vehicle, obtaining the outline of the vehicle captured by the high-definition monitoring camera, and marking vehicles with an outline area greater than a preset outline area as heavy-loaded vehicles to count the number of heavy-loaded vehicles passing through each road section in each cycle. This is existing technology and will not be repeated here.

[0081] Specifically, a single road surface area includes several road segments.

[0082] Specifically, an image acquisition module, a model calibration module, a maintenance plan module, a monitoring and analysis module, a vehicle monitoring module, an evaluation module and a judgment module are set to mark the maintenance labels of the corresponding road sections based on the flatness of each road section; whether the maintenance of each road section in a single pavement area is qualified is determined based on the statistical number of each type of maintenance labels of each road section in a single pavement area; and when it is determined that the maintenance of each road section in a single pavement area is abnormal, the preset maintenance time corresponding to the single pavement area is adjusted to a corresponding value, the maintenance thickness of each road section corresponding to the single pavement area is adjusted to a corresponding value, the preset maintenance area is adjusted to a corresponding value, or the number of pavement image information used to train the built-in model in the model calibration module is adjusted to a corresponding value; after completing the road maintenance, the road condition is classified according to the continuously monitored road image information, and the subsequent maintenance parameters are adjusted according to the classification results, thereby improving the maintenance efficiency of the road.

[0083] Specifically, the monitoring and analysis module is used to determine the flatness based on the road surface image information, to obtain the grayscale difference between adjacent pixels in the road surface image information, calculate the standard deviation of each grayscale difference, and obtain the flatness for a single road surface image information;

[0084] The assessment module is used to mark the maintenance label of the corresponding road section based on the flatness, including:

[0085] If the flatness is less than or equal to the first preset flatness, the maintenance label of the single road section is determined as a stable road section;

[0086] If the flatness is less than or equal to the second preset flatness and greater than the first preset flatness, then marking the maintenance label of the single road section in combination with the heavy-load vehicle flow parameter of the single road section;

[0087] If the flatness is greater than a second preset flatness, a maintenance tag of the single road section is marked based on the average rainfall of the road surface area corresponding to the single road section within the preset operating time.

[0088] Specifically, the first preset flatness is selected within the interval [0.17, 0.22], and the second preset flatness is selected within the interval [0.53, 0.64].

[0089] Specifically, the assessment module is used to mark the maintenance label of a single road section based on the heavy-load vehicle flow parameters of the single road section, including:

[0090] Obtain the number of heavy-loaded vehicles passing through a single road section in several cycles, calculate the variance of the number of heavy-loaded vehicles passing through each cycle, and obtain the heavy-loaded vehicle flow parameters;

[0091] If the heavy-load vehicle flow parameter is less than or equal to the first preset flow parameter, the maintenance label of the single road section is determined as a stable road section;

[0092] If the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the maintenance label of the single road section is determined as a fluctuating road section;

[0093] If the heavy-load vehicle flow parameter is greater than the second preset flow parameter, a maintenance label of the single road section is marked based on the average rainfall of the road surface area corresponding to the single road section within the preset operating time.

[0094] Specifically, the first preset flow parameter is selected within the interval [7, 10], and the second preset flow parameter is selected within the interval [18, 20].

[0095] Specifically, the maintenance label for a corresponding road section is assigned based on its roughness. By obtaining the grayscale differences between adjacent pixels in the road surface image information, the standard deviation of each grayscale difference is calculated. The grayscale difference reflects the road surface's undulations; a larger standard deviation indicates worse road surface smoothness. This improves the accuracy and real-time performance of roughness detection. When the flatness is less than or equal to a first preset flatness, the standard deviation of the grayscale differences between adjacent pixels is in a low range, indicating that the road surface exhibits few noticeable undulations or damage and good smoothness, and the section is marked as stable. When the flatness is less than or equal to a second preset flatness and greater than the first preset flatness, the road surface exhibits some unevenness, but it is not severe. In this case, further evaluation is required in conjunction with the heavy-load vehicle flow parameter. The maintenance label for each road section is assigned based on the heavy-load vehicle flow parameter for that section. When the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the heavy-load vehicle traffic is relatively stable, with relatively little impact on the road surface, and the section is marked as stable. When the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the number of heavy-load vehicles passing through fluctuates, and the pressure on the road surface also varies. This road section is marked as a fluctuating section. This refined classification of road conditions provides an accurate basis for subsequent determination of the condition of the corresponding road area, enabling automatic identification and detection of road damage, improving detection efficiency, reducing the workload and subjectivity of manual inspections, and increasing the accuracy of detection results, further enhancing road maintenance efficiency.

[0096] Specifically, the assessment module is used to mark the maintenance label of a single road section based on the average rainfall of the road surface area corresponding to the single road section within a preset operating period, including:

[0097] If the average rainfall is less than or equal to the first preset rainfall, marking the maintenance label of the single road section based on the flatness difference parameter between the single road section and the adjacent road sections;

[0098] If the average rainfall is less than or equal to the second preset rainfall and greater than the first preset rainfall, the maintenance label of the single road section is determined as a sensitive road section;

[0099] If the average rainfall is greater than the second preset rainfall, the maintenance label of the single road section is determined as a weak road section.

[0100] Specifically, the first preset rainfall amount is selected within the interval [17 mm, 20 mm], and the second preset rainfall amount is selected within the interval [27 mm, 30 mm].

[0101] Specifically, the assessment module is used to mark the maintenance label of a single road section based on the flatness difference parameter between the single road section and adjacent road sections, including:

[0102] Calculating the difference between the flatness of the single road section and the obtained flatness of the single road section connected to the single road section to obtain a flatness difference;

[0103] Calculate the average of the flatness differences between two road sections connected to a single road section to obtain a flatness difference parameter;

[0104] If the flatness difference parameter is less than or equal to the preset difference parameter, the maintenance label of the single road section is determined as a sensitive road section;

[0105] If the flatness difference parameter is greater than the preset difference parameter, the maintenance label of the single road section is determined as a vulnerable road section.

[0106] Specifically, the preset difference parameter is selected within the interval [0.15, 0.22].

[0107] Specifically, the maintenance label of a single road section is assigned based on the average rainfall over a preset operating time within the corresponding road area. When the average rainfall is less than or equal to a first preset rainfall amount, the impact of rainfall on the road surface is relatively small, and a further evaluation is performed based on the flatness difference parameter with adjacent road sections. When the average rainfall is greater than the first preset rainfall amount but less than or equal to a second preset rainfall amount, the road surface is more susceptible to rain erosion and the section is marked as a sensitive section. When the average rainfall is greater than the second preset rainfall amount, the road surface is significantly affected by rain, and the model calibration module fails to identify the section in a timely manner, resulting in an excessively high flatness and low accuracy in identifying road damage under the current environment, marking the section as a weak section. The maintenance label for individual road sections is assigned based on the roughness difference parameter compared to adjacent sections. When the roughness difference parameter is less than or equal to a preset difference parameter, the roughness difference between the section and adjacent sections is small, and due to the unevenness caused by overall environmental factors, the section is marked as sensitive. When the roughness difference parameter is greater than the preset difference parameter, the smoothness of the individual road section differs significantly from that of adjacent sections. The vibration and pressure generated by vehicles passing over adjacent damaged roads are transferred to the current section, making it more susceptible to damage, and thus the section is marked as vulnerable. Road sections are classified and labeled based on multiple factors, including roughness, heavy vehicle flow parameters, rainfall parameters, and roughness difference parameters, enabling a comprehensive assessment of road conditions. This allows for refined classification of road conditions, provides an accurate basis for subsequent maintenance decisions, and improves road maintenance efficiency.

[0108] Specifically, the determination module is used to determine whether the maintenance of each road section in the single road surface area is qualified based on the statistical number of each type of maintenance labels of each road section in the single road surface area, including:

[0109] Count the number of maintenance tags of each type in a single pavement area and identify the maintenance tag with the largest number as the problem tag;

[0110] If the problem label is a stable road section, the maintenance of each road section in the single road surface area is determined to be qualified, and each module is controlled to continue to operate using the current operating parameters;

[0111] If the problem label is a fluctuating road section, the maintenance anomaly of each road section in the single road surface area is determined, and the preset maintenance duration corresponding to the single road surface area is adjusted to the corresponding value based on the average value of the heavy-load vehicle flow parameters of each fluctuating road section in the single road surface area;

[0112] If the problem label is a sensitive road section, the maintenance abnormality of each road section in the single road surface area is determined, and the maintenance thickness of each road section corresponding to the single road surface area is adjusted to the corresponding value based on the average flatness of each sensitive road section in the single road surface area;

[0113] If the problem label is a vulnerable road section, the maintenance anomaly of each road section in the single road surface area is determined, and the preset maintenance area is adjusted to the corresponding value based on the average value of the flatness difference parameter of each vulnerable road section in the single road surface area;

[0114] If the problem label is a weak road section, the maintenance abnormalities of each road section in the single road surface area are determined, and the amount of road surface image information used to train the built-in model in the model calibration module is adjusted to the corresponding value based on the average rainfall in the single road surface area.

[0115] Specifically, the model is fine-tuned using the re-identified training set.

[0116] Specifically, under the condition that the problem label is a weak road section, the road surface image information used to train the built-in model in the model calibration module is selected from road surface image information obtained in a road surface area with an average rainfall greater than a second preset rainfall.

[0117] Specifically, the various types of maintenance labels for each road section in a single pavement area include stable sections, fluctuating sections, sensitive sections, vulnerable sections, and weak sections.

[0118] Specifically, the number of maintenance tags of each type within a single pavement area is counted, and the maintenance tags with the largest number are identified as problem tags. Based on the different problem tags, the causes of maintenance anomalies are analyzed, and parameters such as the preset maintenance duration, repair thickness, preset maintenance area, and the number of images used to train the model are adjusted accordingly. This enables dynamic adjustment of maintenance management, optimizing maintenance parameters in a timely manner based on actual road conditions and maintenance results, improving the scientific nature and effectiveness of road maintenance. If the problem tag is a fluctuating section, the road surface is prone to damage due to the frequent travel of heavy-loaded vehicles in a single pavement area. In this case, the preset maintenance duration corresponding to the single pavement area is adjusted to the corresponding value to adjust the maintenance cycle and promptly detect road anomalies. When the problem label is a sensitive section, the repair thickness of each section within the individual road area is adjusted to a corresponding value to reduce maintenance frequency, as each section within the individual road area is prone to damage. When the problem label is a fragile section, the vibration and pressure generated by vehicles passing through adjacent damaged sections affect the current section, making it more susceptible to damage. In this case, the preset maintenance area is adjusted to ensure timely treatment when a section breaks. When the problem label is a weak section, the individual road area is easily damaged by rain, and the current model cannot effectively identify the damage characteristics of the current road working environment. In this case, the model training amount is increased to ensure that even minor damage is promptly identified and maintained. The amount of road surface image information used to train the built-in model in the model calibration module is adjusted to a corresponding value. This enables the built-in model in the model calibration module to better adapt to road conditions under different rainfall conditions, improving the model's ability to identify road damage characteristics and thus improving road maintenance efficiency.

[0119] Specifically, the determination module is used to adjust the preset maintenance time corresponding to a single road surface area to a corresponding value based on the average value of the heavy-load vehicle flow parameters of each fluctuating road section in the single road surface area, wherein:

[0120] The average value of the heavy-load vehicle flow parameters in each fluctuating section within a single road surface area is recorded as the average flow rate;

[0121] The reduction in the preset maintenance time is proportional to the average flow rate.

[0122] In this embodiment, optionally,

[0123] comparing the average flow rate with a first preset average flow rate and a second preset average flow rate;

[0124] If the average flow rate is less than or equal to the first preset average flow rate, the preset maintenance time corresponding to the single road surface area is adjusted to 0.92 times the initial preset maintenance time;

[0125] If the average flow rate is less than or equal to the second preset average flow rate and greater than the first preset average flow rate, the preset maintenance time corresponding to the single road surface area is adjusted to 0.83 times the initial preset maintenance time;

[0126] If the average flow rate is greater than the second preset average flow rate, the preset maintenance time corresponding to the single road surface area is adjusted to 0.73 times the initial preset maintenance time;

[0127] The first preset average flow rate is 12, and the second preset average flow rate is 16.

[0128] Specifically, the determination module is used to adjust the repair thickness of each road section corresponding to a single road surface area to a corresponding value based on the average flatness of each sensitive road section in the single road surface area, wherein:

[0129] The average value of the smoothness of each sensitive road section in a single road surface area is recorded as the mean smoothness value;

[0130] The increase in the repair thickness of each road section corresponding to a single pavement area is proportional to the mean flatness.

[0131] In this embodiment, optionally,

[0132] Comparing the flatness average with a first preset flatness average and a second preset flatness average;

[0133] If the average flatness value is less than or equal to the first preset average flatness value, the repair thickness of each road section corresponding to the single road surface area is adjusted to 1.1 times the initial repair thickness;

[0134] If the average flatness value is less than or equal to the second preset average flatness value and greater than the first preset average flatness value, the repair thickness of each road section corresponding to the single road surface area is adjusted to 1.2 times the initial repair thickness;

[0135] If the average flatness value is greater than the second preset average flatness value, the repair thickness of each road section corresponding to the single road surface area is adjusted to 1.3 times the initial repair thickness;

[0136] The first preset flatness average is 0.4, and the second preset flatness average is 0.8.

[0137] Specifically, the determination module is used to adjust the preset maintenance area to a corresponding value based on the average value of the flatness difference parameter of each vulnerable road section in a single road surface area, wherein:

[0138] The average value of the roughness difference parameters of each vulnerable road section in a single road surface area is recorded as the average difference;

[0139] The reduction in the preset maintenance area is proportional to the average difference.

[0140] In this embodiment, optionally,

[0141] comparing the average difference with a first predetermined average difference and a second predetermined average difference;

[0142] If the average difference is less than or equal to the first preset average difference, the preset maintenance area is adjusted to 0.94 times the initial preset maintenance area;

[0143] If the average difference is less than or equal to the second preset average difference and greater than the first preset average difference, the preset maintenance area is adjusted to 0.87 times the initial preset maintenance area;

[0144] If the average difference is greater than the second preset average difference, the preset maintenance area is adjusted to 0.77 times the initial preset maintenance area;

[0145] The first preset average difference is 0.24, and the second preset average difference is 0.28.

[0146] Specifically, the determination module is used to adjust the amount of road surface image information used to train the built-in model in the model calibration module to a corresponding value based on the average rainfall in a single road surface area, wherein:

[0147] The amount of road surface image information used to train the built-in model in the model calibration module increases in direct proportion to the average rainfall.

[0148] In this embodiment, optionally,

[0149] Comparing the average rainfall with a first preset rainfall comparison threshold and a second preset rainfall comparison threshold;

[0150] If the average rainfall is less than or equal to the first preset rainfall comparison threshold, the amount of road surface image information of the training model is adjusted to 1.14 times the initial amount;

[0151] If the average rainfall is less than or equal to the second preset rainfall comparison threshold and greater than the first preset rainfall comparison threshold, the amount of road surface image information of the training model is adjusted to 1.25 times the initial amount;

[0152] If the average rainfall is greater than the second preset rainfall comparison threshold, the amount of road surface image information of the training model is adjusted to 1.32 times the initial amount;

[0153] The first preset rainfall comparison threshold is 32 mm, and the second preset rainfall comparison threshold is 37 mm.

[0154] Specifically, the maintenance cycle is dynamically adjusted based on fluctuations in heavy-load vehicle traffic. When heavy-load vehicle traffic fluctuates significantly, maintenance frequency is increased to promptly identify and address road surface issues, improving road safety and service life. This avoids the potential for untimely or excessive maintenance that can occur with fixed maintenance cycles.

[0155] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0156] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A road maintenance quality detection system based on intelligent decision-making, characterized in that: include: An image acquisition module includes a plurality of image acquirers respectively arranged at each road section in each road area for acquiring road image information; a model calibration module connected to the image acquisition module, for periodically calibrating damaged areas in the road surface image information, and determining damaged areas whose area is larger than a preset maintenance area as areas to be maintained; a maintenance planning module connected to the model calibration module, for determining maintenance parameters based on the damaged area calibrated by the model calibration module, including maintenance area, maintenance thickness, and maintenance duration; a monitoring and analysis module, connected to the image acquisition module, the model calibration module, and the maintenance plan module, respectively, for determining the flatness based on the road surface image information of the corresponding road section reacquired by the image acquisition module after a preset operating time, on the condition that maintenance of each of the areas to be maintained is completed; The vehicle monitoring module is used to count the number of heavy-loaded vehicles passing through each road section in each cycle; an assessment module, connected to the monitoring and analysis module and the vehicle monitoring module, respectively, for marking a maintenance label of a corresponding road section based on the flatness of each road section; A determination module, connected to the assessment module, the maintenance plan module, and the model calibration module, is configured to determine whether the maintenance of each road section in a single road surface area is qualified based on the number of maintenance labels of each type for each road section in the single road surface area, including: Count the number of maintenance tags of each type in a single pavement area and identify the maintenance tag with the largest number as the problem tag; If the problem label is a stable road section, the maintenance of each road section in the single road surface area is determined to be qualified, and each module is controlled to continue to operate using the current operating parameters; If the problem label is a fluctuating road section, the maintenance anomaly of each road section in the single road surface area is determined, and the preset maintenance duration corresponding to the single road surface area is adjusted to the corresponding value based on the average value of the heavy-load vehicle flow parameters of each fluctuating road section in the single road surface area; If the problem label is a sensitive road section, the maintenance abnormality of each road section in the single road surface area is determined, and the maintenance thickness of each road section corresponding to the single road surface area is adjusted to the corresponding value based on the average flatness of each sensitive road section in the single road surface area; If the problem label is a vulnerable road section, the maintenance anomaly of each road section in the single road surface area is determined, and the preset maintenance area is adjusted to the corresponding value based on the average value of the flatness difference parameter of each vulnerable road section in the single road surface area; If the problem label is a weak road section, the maintenance abnormalities of each road section in the single road surface area are determined, and the amount of road surface image information used to train the built-in model in the model calibration module is adjusted to the corresponding value based on the average rainfall in the single road surface area.

2. The road maintenance quality detection system based on intelligent decision-making according to claim 1 is characterized in that: The monitoring and analysis module is configured to determine the flatness based on the road surface image information of the corresponding road section reacquired by the image acquisition module after a preset running time, upon completion of the maintenance of each of the areas to be maintained, including: obtaining grayscale differences between adjacent pixel points in the road surface image information of the corresponding road section reacquired by the image acquisition module after the preset running time, calculating the standard deviation of each grayscale difference, and obtaining the flatness of each piece of road surface image information; The assessment module is used to mark the maintenance label of the corresponding road section based on the flatness, including: If the flatness is less than or equal to the first preset flatness, the maintenance label of the single road section is determined as a stable road section; If the flatness is less than or equal to the second preset flatness and greater than the first preset flatness, then marking the maintenance label of the single road section in combination with the heavy-load vehicle flow parameter of the single road section; If the flatness is greater than a second preset flatness, a maintenance tag of the single road section is marked based on the average rainfall of the road surface area corresponding to the single road section within the preset operating time.

3. The road maintenance quality detection system based on intelligent decision-making according to claim 2 is characterized in that: The assessment module is used to mark the maintenance label of a single road section in combination with the heavy-load vehicle flow parameters of the single road section, including: Obtain the number of heavy-loaded vehicles passing through a single road section in several cycles, calculate the variance of the number of heavy-loaded vehicles passing through each cycle, and obtain the heavy-loaded vehicle flow parameters; If the heavy-load vehicle flow parameter is less than or equal to the first preset flow parameter, the maintenance label of the single road section is determined as a stable road section; If the heavy-load vehicle flow parameter is less than or equal to the second preset flow parameter and greater than the first preset flow parameter, the maintenance label of the single road section is determined as a fluctuating road section; If the heavy-load vehicle flow parameter is greater than the second preset flow parameter, a maintenance label of the single road section is marked based on the average rainfall of the road surface area corresponding to the single road section within the preset operating time.

4. The road maintenance quality detection system based on intelligent decision-making according to claim 3 is characterized in that: The assessment module is used to mark the maintenance label of a single road section based on the average rainfall of the road surface area corresponding to the single road section within a preset operating time, including: If the average rainfall is less than or equal to the first preset rainfall, marking the maintenance label of the single road section based on the flatness difference parameter between the single road section and the adjacent road sections; If the average rainfall is less than or equal to the second preset rainfall and greater than the first preset rainfall, the maintenance label of the single road section is determined as a sensitive road section; If the average rainfall is greater than the second preset rainfall, the maintenance label of the single road section is determined as a weak road section.

5. The road maintenance quality detection system based on intelligent decision-making according to claim 4 is characterized in that: The assessment module is used to mark the maintenance label of a single road section based on the flatness difference parameter between the single road section and adjacent road sections, including: Calculating the difference between the flatness of the single road section and the obtained flatness of the single road section connected to the single road section to obtain a flatness difference; Calculate the average of the flatness differences between two road sections connected to a single road section to obtain a flatness difference parameter; If the flatness difference parameter is less than or equal to the preset difference parameter, the maintenance label of the single road section is determined as a sensitive road section; If the flatness difference parameter is greater than the preset difference parameter, the maintenance label of the single road section is determined as a vulnerable road section.

6. The road maintenance quality detection system based on intelligent decision-making according to claim 5 is characterized in that: The determination module is used to adjust the preset maintenance time corresponding to a single road surface area to a corresponding value based on the average value of the heavy-load vehicle flow parameters of each fluctuating road section in the single road surface area, wherein: The average value of the heavy-load vehicle flow parameters in each fluctuating section within a single road surface area is recorded as the average flow rate; The reduction in the preset maintenance time is proportional to the average flow rate.

7. The road maintenance quality detection system based on intelligent decision-making according to claim 6 is characterized in that: The determination module is used to adjust the repair thickness of each road section corresponding to a single road area to a corresponding value based on the average flatness of each sensitive road section in the single road area, wherein: The average value of the smoothness of each sensitive road section in a single road surface area is recorded as the mean smoothness value; The increase in the repair thickness of each road section corresponding to a single pavement area is proportional to the mean flatness.

8. The road maintenance quality detection system based on intelligent decision-making according to claim 7 is characterized in that: The determination module is used to adjust the preset maintenance area to a corresponding value based on the average value of the flatness difference parameters of each vulnerable road section in a single road surface area, wherein: The average value of the roughness difference parameters of each vulnerable road section in a single road surface area is recorded as the average difference; The reduction in the preset maintenance area is proportional to the average difference.

9. The road maintenance quality detection system based on intelligent decision-making according to claim 8 is characterized in that: The determination module is used to adjust the amount of road surface image information used to train the built-in model in the model calibration module to a corresponding value based on the average rainfall in a single road surface area, wherein, The amount of road surface image information used to train the built-in model in the model calibration module increases in direct proportion to the average rainfall.

Images