Pavement defect monitoring and prediction method and system

Abstract

The present invention relates to the technical field of urban traffic management, and in particular to a pavement defect monitoring and prediction method and system. The method comprises the following steps: constructing a pavement digital twin model of a target pavement; constructing a historical pavement monitoring dataset, and acquiring pavement monitoring indicator precise data and pavement high-definition image data in real time; on the basis of the pavement digital twin model and the pavement monitoring dataset, using a dual-source weight fusion method to obtain an indicator weight of each pavement monitoring indicator; and on the basis of the pavement monitoring indicator precise data, the indicator weight, and the pavement high-definition image data, updating the pavement digital twin model to achieve real-time monitoring and prediction of a target pavement defect, and formulating a pavement maintenance strategy. The present invention is based on the pavement digital twin model, and takes into account the degree of influence of each pavement monitoring indicator on a pavement defect, achieving real-time, accurate, and efficient monitoring and prediction of the pavement defect, thereby formulating the pavement maintenance strategy in a timely manner to ensure the road traffic capacity and safety.

Description

A method and system for monitoring and predicting road defects Technical Field

[0001] This invention relates to the field of urban traffic management technology, and in particular to a method and system for monitoring and predicting road surface defects. Background Technology

[0002] In the rapidly developing modern transportation system, roads, as vital infrastructure connecting cities and rural areas and facilitating economic exchange, directly impact traffic flow and safety. However, with the surge in vehicle numbers and the aging of roads, road surface defects have become increasingly prominent, becoming a key factor restricting traffic efficiency and safety. Cracks, potholes, and other road surface defects not only affect driving comfort but can also trigger traffic accidents, posing a serious threat to people's lives and property.

[0003] Traditional methods for monitoring road surface defects primarily rely on manual inspections and periodic checks. While manual inspections are intuitive, they are limited by labor costs, inspection frequency, and subjective judgment, making efficient and accurate monitoring of large areas of road difficult. Periodic checks, on the other hand, suffer from time lags, often failing to detect and address road surface defects promptly, leading to accumulated problems and exacerbating damage to road structure and traffic safety. Furthermore, with the rise of intelligent transportation systems, the need for real-time monitoring and early warning of road conditions is increasingly urgent. Traditional monitoring methods have significant shortcomings in data processing, information integration, and intelligent analysis, making it difficult to meet the demands of modern traffic management.

[0004] Digital twin technology, an advanced technology that has emerged in recent years, offers a new approach to pavement defect monitoring and prediction. This technology can integrate multiple sensors and monitoring devices to achieve real-time and comprehensive monitoring of pavement conditions. By constructing a digital mirror of the physical world, it can achieve comprehensive, real-time, and dynamic simulation of physical entities and their operating environment, enabling the early detection of potential pavement defects. This provides scientific decision support for road maintenance, effectively reducing maintenance costs and traffic accident risks, and promoting the intelligent development of the transportation sector. Currently, some methods exist for monitoring pavement defects using digital twin technology; however, these methods simply update the digital twin model directly using monitoring data, and the accuracy of pavement defect monitoring and prediction needs improvement. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for monitoring and predicting road surface defects.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for monitoring and predicting pavement defects. The method includes the following steps: constructing a digital twin model of the target pavement; collecting historical pavement monitoring data to construct a historical pavement monitoring dataset, and acquiring accurate data of pavement monitoring indicators and high-resolution pavement image data in real time; obtaining the indicator weights of each pavement monitoring indicator using a dual-source weight fusion method based on the pavement digital twin model and the pavement monitoring dataset; updating the pavement digital twin model based on the accurate data of the pavement monitoring indicators, the indicator weights, and the high-resolution pavement image data to achieve real-time monitoring of defects in the target pavement; predicting the accurate data of the pavement monitoring indicators, and then predicting the defects in the target pavement based on the indicator weights and the pavement digital twin model, and formulating pavement maintenance strategies. The present invention, based on a pavement digital twin model and considering the influence of various pavement monitoring indicators on pavement defects, achieves real-time, accurate, and efficient monitoring and prediction of pavement defects, thereby enabling timely formulation of pavement maintenance strategies to ensure road traffic capacity and safety.

[0007] Optionally, the historical road surface monitoring data includes historical road surface monitoring index data and historical road surface image data;

[0008] The process of collecting historical road surface monitoring data to construct a historical road surface monitoring dataset, and acquiring accurate data on road surface monitoring indicators and high-definition road surface images in real time, includes the following steps:

[0009] Historical road surface monitoring data is collected and preprocessed to construct a historical road surface monitoring dataset.

[0010] Real-time acquisition of road surface monitoring index data and road surface image data, followed by preprocessing, yields accurate data of the road surface monitoring indexes and high-definition image data of the road surface.

[0011] Furthermore, by obtaining the weights of indicators based on historical road surface monitoring datasets, the importance of each road surface monitoring indicator is taken into account when updating road surface information on the road surface digital twin model. In addition, the accurate data of road surface monitoring indicators and high-definition road surface image data can accurately reflect the real-time condition of the road surface, making the road surface defect monitoring and prediction results based on the road surface digital twin model more objective and accurate.

[0012] Optionally, the real-time acquisition of road surface monitoring index data and road surface image data, and the preprocessing to obtain accurate road surface monitoring index data and high-definition road surface image data, includes the following steps:

[0013] Data cleaning is performed on the road surface monitoring index data to obtain accurate data for the road surface monitoring index;

[0014] The road surface image data is smoothed and denoised, and the contrast is enhanced to obtain high-definition road surface image data.

[0015] Furthermore, by preprocessing the road surface monitoring index data and road surface image data to accurately reflect the real-time condition of the road surface, the updated road surface digital twin model can also accurately reflect the real-time condition of the road surface, thus achieving accurate monitoring of the road surface.

[0016] Optionally, obtaining the index weights of each road monitoring index using the dual-source weight fusion method based on the road surface digital twin model and the road surface monitoring dataset includes the following steps:

[0017] Image recognition is performed on historical road surface image data in the road surface monitoring dataset to obtain road surface defects, including cracks and potholes.

[0018] Based on the image recognition results, calculate the pavement defect evaluation factor value corresponding to each group of pavement monitoring data in the pavement monitoring dataset;

[0019] Based on the pavement monitoring dataset and the pavement defect evaluation factor values, the first weight of the pavement monitoring index is obtained using the ranking importance method.

[0020] Based on the road surface digital twin model, the road surface monitoring dataset, and the road surface defect evaluation factor values, the second weight of the road surface monitoring index is obtained using a step-by-step analysis method.

[0021] The index weights are calculated based on the first weight and the second weight.

[0022] Furthermore, the first weight is obtained based on machine learning methods, and the second weight is obtained based on statistical testing methods. Combining the two to obtain the index weight can avoid the one-sidedness of weights obtained by using a single method and improve the accuracy of pavement defect monitoring and prediction results.

[0023] Optionally, obtaining the second weight of the pavement monitoring index using a step-by-step analysis method based on the pavement digital twin model, the pavement monitoring dataset, and the pavement defect evaluation factor values ​​includes the following steps:

[0024] A set of road monitoring data is randomly selected from the road monitoring dataset as the array to be adjusted, and the remaining sets of road monitoring data are used as the adjustment array.

[0025] For a certain road surface monitoring indicator, the values ​​of the road surface monitoring indicator in the array to be adjusted are replaced sequentially with the values ​​of the road surface monitoring indicator in the adjustment array to obtain multiple sets of adjusted arrays, and the road surface monitoring indicator is marked as the road surface monitoring change indicator.

[0026] The adjusted array is used to update the digital twin model of the road surface, identify road surface defects and calculate the comparison values ​​of multiple road surface defect evaluation factors, and then the second weight of the road surface monitoring change index is calculated by combining the values ​​of the road surface defect evaluation factors.

[0027] Optionally, the second weight satisfies the following relationship:

[0028]

[0029] in, The second weight is N, and the number of elements in the adjustment array is N. This is the comparison value of the i-th pavement defect evaluation factor. The value of the pavement defect evaluation factor is given. The value of the road surface monitoring change index in the i-th adjustment array is... The value of the road surface monitoring change index in the array to be adjusted.

[0030] Optionally, updating the digital twin model of the road surface based on the accurate data of the road surface monitoring indicators, the indicator weights, and the high-definition image data of the road surface to achieve real-time monitoring of defects in the target road surface includes the following steps:

[0031] Calculate weighted road surface monitoring index data based on the accurate data of the road surface monitoring indicators and the weights of the indicators;

[0032] The weighted pavement monitoring index data and the high-definition pavement image data are used to update the pavement digital twin model to obtain a real-time twin pavement, thereby enabling real-time monitoring of the target pavement defects.

[0033] Furthermore, by combining precise data from road surface monitoring indicators with weighted road surface monitoring indicator data, the impact of different road surface monitoring indicators on road surface conditions is fully considered. High-definition road surface image data is also introduced to achieve multi-source data fusion, enabling the digital twin model of the road surface to more comprehensively reflect the actual road surface conditions and improving the real-time and comprehensiveness of monitoring.

[0034] Optionally, the step of predicting accurate data of the road surface monitoring indicators, and then predicting the target road surface defects based on the indicator weights and the road surface digital twin model, and formulating a road surface maintenance strategy, includes the following steps:

[0035] The accurate data of the road surface monitoring indicators are predicted to obtain the future indicator prediction data of each of the road surface monitoring indicators;

[0036] Calculate weighted road surface monitoring indicator prediction data based on the indicator prediction data and the indicator weights;

[0037] The weighted pavement monitoring index prediction data is used to update the real-time twin pavement to obtain the future twin pavement, thereby realizing the prediction of the target pavement defects;

[0038] Develop the current road maintenance strategy based on the weighted road monitoring index data;

[0039] A future road maintenance strategy is formulated based on the real-time twin road surface, the weighted road surface monitoring index prediction data, and the future twin road surface, and the current road surface maintenance strategy is integrated to obtain the road maintenance strategy.

[0040] Furthermore, by predicting future defects in the target pavement, road maintenance work can be planned in advance to prevent the problems from worsening. When formulating road maintenance strategies, integrating current and future strategies allows for a comprehensive consideration of the current and future state of the pavement, combining long-term planning with short-term responses. This leads to more scientific and rational maintenance strategies, which helps optimize the allocation of maintenance resources, reduce unnecessary waste, and improve the efficiency and effectiveness of maintenance work.

[0041] Optionally, the step of formulating a future pavement maintenance strategy based on the real-time twin pavement, the weighted pavement monitoring index prediction data, and the future twin pavement, and integrating the current pavement maintenance strategy to obtain the pavement maintenance strategy, includes the following steps:

[0042] The weighted road surface monitoring index prediction data are arranged in descending order;

[0043] The smallest data in the weighted road surface monitoring index prediction data is deleted sequentially, and the remaining weighted road surface monitoring index prediction data is used to update the real-time twin road surface after each deletion to obtain the comparison twin road surface, and the similarity between the comparison twin road surface and the future twin road surface is calculated.

[0044] When the similarity is less than the similarity threshold for the first time, the operation of deleting the weighted road surface monitoring index prediction data is stopped, and the remaining weighted road surface monitoring index prediction data after the previous deletion operation is used as the final decision data.

[0045] The road maintenance strategy is derived by formulating a future road maintenance strategy based on the final judgment data and integrating the current road maintenance strategy.

[0046] Furthermore, by sorting the weighted pavement monitoring index prediction data by size and deleting the smallest data one by one, and using the remaining weighted pavement monitoring index prediction data to update the real-time twin pavement, and then calculating the similarity with the future twin pavement, it is possible to more accurately identify the combination of pavement monitoring indicators that has the greatest impact on the future state of the pavement. This allows for the integration of current pavement maintenance strategies to obtain more targeted pavement maintenance strategies, ensuring maintenance effectiveness while minimizing maintenance costs.

[0047] Secondly, the present invention also provides a pavement defect monitoring and prediction system. The system uses a pavement defect monitoring and prediction method provided by the present invention. The system includes: a digital twin model construction module for constructing a pavement digital twin model of the target pavement; a data acquisition and preprocessing module for acquiring historical pavement monitoring data to construct a historical pavement monitoring dataset, and for acquiring accurate data of pavement monitoring indicators and high-definition pavement image data in real time; and a pavement defect monitoring and prediction module for obtaining the indexes of each pavement monitoring indicator using a dual-source weighted fusion method based on the pavement digital twin model and the pavement monitoring dataset. The system includes: a weighted index; updating the digital twin model of the road surface based on the accurate data of the road surface monitoring indicators, the index weights, and the high-definition image data of the road surface, thereby achieving real-time monitoring of target road surface defects; predicting the accurate data of the road surface monitoring indicators, and then predicting the target road surface defects based on the index weights and the digital twin model of the road surface, and formulating road surface maintenance strategies; a data storage module for storing data collected and generated by the data acquisition and preprocessing module, and also for storing data generated by the road surface defect monitoring and prediction module; and an information visualization module for displaying real-time road surface monitoring data and road surface digital twin information, and outputting the road surface maintenance strategies. This system is compatible with the method provided by this invention, can stably execute the method provided by this invention, and improves the practical application capability of this invention. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 is a flowchart illustrating a method for monitoring and predicting road surface defects according to an embodiment of the present invention;

[0050] Figure 2 is a schematic diagram of the framework of a road surface defect monitoring and prediction system according to an embodiment of the present invention. Detailed Implementation

[0051] Specific embodiments of the present invention will now be described in detail. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the invention.

[0052] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0053] It should be noted in advance that, in one alternative embodiment, except for independent descriptions, the same symbols or letters appearing in all formulas have the same meaning and value.

[0054] In an optional embodiment, referring to Figure 1, the present invention provides a method for monitoring and predicting road surface defects, the method comprising the following steps:

[0055] S1. Construct a digital twin model of the target road surface.

[0056] Specifically, in this embodiment, a digital twin model of the road surface is constructed using SketchUp by utilizing the road geometry information, road texture information, and environmental information in the road design CAD drawings.

[0057] Digital twin models of road surfaces can reflect changes in the physical world of road surfaces in real time, providing a real-time view of current road conditions. Based on historical and real-time data, they can simulate and predict road defects, enabling early detection and prevention of cracks and potholes. Furthermore, digital twin models can present complex road conditions in an intuitive and easy-to-understand way. Users can use the model to make various assumptions and tests to evaluate the effectiveness of different maintenance plans, thus making more informed decisions. In addition, building digital twin models of road surfaces can make road management more data-driven and intelligent, improving efficiency and effectiveness.

[0058] Furthermore, in other alternative embodiments, other software such as 3DS MAX, Revit, and Unity3D can also be used to build the digital twin model of the road surface.

[0059] S2. Collect historical road surface monitoring data to construct a historical road surface monitoring dataset, and obtain accurate data of road surface monitoring indicators and high-definition road surface image data in real time.

[0060] Step S2 specifically includes the following steps:

[0061] S21. Collect historical road surface monitoring data and preprocess the historical road surface monitoring data to construct a historical road surface monitoring dataset.

[0062] Specifically, in this embodiment, the historical pavement monitoring data includes historical pavement monitoring index data and historical pavement image data. The pavement monitoring indexes include the target pavement's stress, strain, displacement, smoothness, compaction, rut depth, friction coefficient, temperature, humidity, average monthly rainfall, average daily traffic flow, average annual daily truck traffic volume, and cumulative standard axle load application times. The historical pavement image data refers to historical pavement images, and each historical pavement image has the same number of pixels. The specific method for obtaining the pavement monitoring index data can refer to existing technologies.

[0063] Furthermore, the historical pavement monitoring data is preprocessed. Specific preprocessing methods can be found in subsequent step S22. Preprocessing the historical pavement monitoring data ensures that the data accurately reflects the pavement condition, providing a reliable data foundation for subsequent calculation of index weights, thereby improving the accuracy of pavement defect monitoring and prediction.

[0064] S22. Real-time acquisition of road surface monitoring index data and road surface image data, and preprocessing to obtain accurate data of the road surface monitoring index and high-definition image data of the road surface.

[0065] Specifically, step S22 includes the following steps:

[0066] S221. Perform data cleaning on the road surface monitoring index data to obtain accurate data for the road surface monitoring index.

[0067] Specifically, in this embodiment, data cleaning includes missing value processing, outlier processing, duplicate value processing, and data consistency processing. Data cleaning ensures that the obtained pavement monitoring index data accurately reflects the real-time condition of the target pavement, guaranteeing the real-time performance and accuracy of subsequent monitoring of the target pavement using a pavement digital twin model.

[0068] S222. The road surface image data is smoothed and noise reduced, and the contrast is enhanced to obtain the high-definition road surface image data.

[0069] Specifically, in this embodiment, the mean offset filtering algorithm is used to smooth and reduce noise in the road surface image data, and the CLAHE algorithm is used to enhance the contrast of the road surface image data. This makes the road surface image clearer and smoother, and the details of cracks and potholes are more prominent. At the same time, the edges of cracks and potholes are clearer, so that the obtained high-definition road surface image data can accurately reflect the real-time condition of the target road surface. This ensures the real-time performance and accuracy of subsequent monitoring of the target road surface using the road surface digital twin model, and also improves the accuracy of subsequent road surface defect identification.

[0070] S3. Based on the road surface digital twin model and the road surface monitoring dataset, the index weights of each road surface monitoring index are obtained using the dual-source weight fusion method.

[0071] Step S3 specifically includes the following steps:

[0072] S31. Perform image recognition on the historical road surface image data in the road surface monitoring dataset to obtain road surface defects, including cracks and potholes.

[0073] Specifically, in this embodiment, the YOLOv7 algorithm is used to identify cracks and potholes on historical road surface images, while recording the number of pixels in the historical road surface images that are defects.

[0074] S32. Calculate the pavement defect evaluation factor value corresponding to each group of pavement monitoring data in the pavement monitoring dataset based on the image recognition results.

[0075] Specifically, in this embodiment, the road surface defect evaluation factor value is the ratio of the number of pixels of the road surface defect to the number of pixels of the road surface image. The road surface defect evaluation factor value can intuitively reflect the severity of the road surface defect.

[0076] S33. Based on the road surface monitoring dataset and the road surface defect evaluation factor values, the first weight of the road surface monitoring index is obtained using the importance ranking method.

[0077] S34. Based on the road surface digital twin model, the road surface monitoring dataset, and the road surface defect evaluation factor values, the second weight of the road surface monitoring index is obtained using the item-by-item analysis method.

[0078] Specifically, step S34 includes the following steps:

[0079] S341. Randomly select a set of road monitoring data from the road monitoring dataset as the array to be adjusted, and use the remaining sets of road monitoring data as the adjustment array.

[0080] Specifically, in this embodiment, the array to be adjusted is denoted as... , Let be the value of the j-th road monitoring indicator in the array to be adjusted, and n be the number of road monitoring indicators; denoted as . , Let be the value of the j-th road monitoring indicator in the k-th adjustment array, where k = 1, 2, 3, ..., N, and N is the number of adjustment arrays.

[0081] S342. For a certain road surface monitoring indicator, the values ​​of the road surface monitoring indicator in the array to be adjusted are replaced sequentially with the values ​​of the road surface monitoring indicator in the adjustment array to obtain multiple sets of adjusted arrays, and the road surface monitoring indicator is marked as a road surface monitoring change indicator.

[0082] Specifically, in this embodiment, it is assumed that... The corresponding road surface monitoring indicators are used as road surface monitoring change indicators, and then they are used sequentially. , , ... replace This yields N adjusted arrays, i.e. , , ... Since there are n road surface monitoring indicators, we can eventually obtain n×N adjusted arrays.

[0083] S343. Update the road digital twin model using the adjusted array, identify road defects and calculate the comparison values ​​of multiple road defect evaluation factors, and then calculate the second weight of the road monitoring change index by combining the values ​​of the road defect evaluation factors.

[0084] Specifically, in this embodiment, the adjusted array is used to update the digital twin model of the road surface to obtain the twin road surface corresponding to the adjusted array. Then, the road surface image in the twin road surface is extracted and the YOLOv7 algorithm is used to identify road surface defects.

[0085] Furthermore, the number of pixels in the extracted twin road surface image should be the same as the number of pixels in the historical road surface image.

[0086] More specifically, the second weight satisfies the following relationship:

[0087]

[0088] in, As the second weight, This represents the comparison value of the i-th pavement defect evaluation factor. These are the numerical values ​​for road surface defect evaluation factors. Let i be the value of the road surface monitoring change index in the i-th adjustment array. The values ​​of the road surface monitoring change indicators in the array to be adjusted.

[0089] S35. Calculate the index weight based on the first weight and the second weight.

[0090] Specifically, in this embodiment, the index weight is the average of the first weight and the second weight. The first weight is obtained based on machine learning methods, and the second weight is obtained based on statistical testing methods. Combining the two to obtain the index weight can avoid the one-sidedness of weights obtained by using a single method and improve the accuracy of pavement defect monitoring and prediction results.

[0091] S4. Update the digital twin model of the road surface based on the accurate data of the road surface monitoring indicators, the indicator weights, and the high-definition image data of the road surface to achieve real-time monitoring of defects in the target road surface.

[0092] Step S4 specifically includes the following steps:

[0093] S41. Calculate weighted road surface monitoring index data based on the accurate data of the road surface monitoring index and the index weight.

[0094] Specifically, in this embodiment, the weighted road surface monitoring index data is the product of the accurate road surface monitoring index data and the corresponding index weights.

[0095] S42. Update the digital twin model of the road surface using the weighted road surface monitoring index data and the high-definition image data of the road surface to obtain a real-time twin road surface, thereby realizing real-time monitoring of the defects of the target road surface.

[0096] Specifically, in this embodiment, by calculating weighted road surface monitoring index data, the influence of different road surface monitoring indicators on road surface condition is fully considered, and high-definition road surface image data is introduced to achieve multi-source fusion of quantitative data and image data, so that the road surface digital twin model can more comprehensively reflect the actual road surface condition and improve the real-time and comprehensiveness of monitoring.

[0097] S5. Predict the accurate data of the road surface monitoring indicators, and then predict the target road surface defects based on the indicator weights and the road surface digital twin model, and formulate a road surface maintenance strategy.

[0098] Step S5 specifically includes the following steps:

[0099] S51. Predict the accurate data of the road surface monitoring indicators to obtain the future indicator prediction data of each of the road surface monitoring indicators.

[0100] Specifically, in this embodiment, a BP neural network is used to construct a prediction model for each road monitoring indicator based on the road monitoring dataset, and the established prediction model is used to obtain indicator prediction data.

[0101] Furthermore, in other alternative embodiments, the predicted data for road surface monitoring indicators such as temperature, humidity, and average monthly rainfall can also be obtained based on the weather forecast for the location of the target road surface.

[0102] S52. Calculate the weighted road surface monitoring index prediction data based on the index prediction data and the index weights.

[0103] Specifically, in this embodiment, the method for calculating the weighted pavement monitoring index prediction data is the same as the method for calculating the weighted pavement monitoring index data.

[0104] S53. Update the real-time twin road surface using the weighted road surface monitoring index prediction data to obtain the future twin road surface, thereby realizing the prediction of the target road surface defects.

[0105] Specifically, in this embodiment, the weighted pavement monitoring index prediction data is used to update the real-time twin pavement to obtain the future twin pavement. Then, the future pavement image in the future twin pavement is extracted and the YOLOv7 algorithm is used to identify pavement defects, thereby achieving the prediction of target pavement defects.

[0106] Furthermore, the number of pixels in future road surface images should be the same as the number of pixels in historical road surface images.

[0107] S54. Formulate the current road maintenance strategy based on the weighted road surface monitoring index data.

[0108] Specifically, in this embodiment, based on expert opinions, the weighted pavement monitoring index data corresponding to each pavement monitoring index are divided into three levels from highest to lowest: below normal, normal, and above normal. Then, different response plans are retrieved and formulated for different levels of weighted pavement monitoring index data, thereby forming a pavement maintenance plan library. Finally, based on the weighted pavement monitoring index data, the corresponding response plan is queried in the pavement maintenance plan library to form the current pavement maintenance strategy.

[0109] S55. Based on the real-time twin pavement, the weighted pavement monitoring index prediction data, and the future twin pavement, formulate a future pavement maintenance strategy, and integrate the current pavement maintenance strategy to obtain the pavement maintenance strategy.

[0110] Specifically, step S55 includes the following steps:

[0111] S551. Arrange the weighted road surface monitoring index prediction data in descending order.

[0112] Specifically, in this embodiment, the weighted pavement monitoring index prediction data arranged in descending order is denoted as the weighted pavement monitoring index prediction data sequence, and is further denoted as... , This refers to the j-th weighted pavement monitoring indicator prediction data in the weighted pavement monitoring indicator prediction data sequence.

[0113] S552. Delete the smallest data in the weighted road surface monitoring index prediction data in sequence, and update the real-time twin road surface using the remaining weighted road surface monitoring index prediction data after each deletion to obtain the comparison twin road surface, and calculate the similarity between the comparison twin road surface and the future twin road surface.

[0114] Specifically, in this embodiment, taking the first deletion of the smallest data in the weighted road surface monitoring index prediction data as an example, the data to be deleted is... ,get Then use The real-time twin pavement is updated to obtain a comparison twin pavement. Next, the comparison pavement image of the comparison twin pavement is extracted, and then the similarity between the comparison pavement image and the future pavement image extracted in step S53 is calculated. The calculated result is used as the similarity between the comparison twin pavement and the future twin pavement. By sorting the weighted pavement monitoring index prediction data by size and deleting the smallest data one by one, and updating the real-time twin pavement with the remaining weighted pavement monitoring index prediction data, and then calculating the similarity with the future twin pavement, the combination of pavement monitoring indicators that has the greatest impact on the future state of the pavement can be more accurately identified. This facilitates the subsequent integration of the current pavement maintenance strategy to obtain a more targeted pavement maintenance strategy, ensuring maintenance effectiveness while minimizing maintenance costs.

[0115] Furthermore, the number of pixels in the road surface image to be compared should be the same as the number of pixels in the historical road surface image. In addition, this embodiment uses a structural similarity index to represent the similarity between the compared road surface image and the future road surface image.

[0116] S553. When the similarity is less than the similarity threshold for the first time, stop deleting the weighted road surface monitoring index prediction data, and use the remaining weighted road surface monitoring index prediction data after the previous deletion operation as the final decision data.

[0117] Specifically, in this embodiment, the similarity threshold is set to 0.92.

[0118] S554. Formulate a future road maintenance strategy based on the final judgment data, and integrate the current road maintenance strategy to obtain the road maintenance strategy.

[0119] Specifically, in this embodiment, based on the obtained final judgment data, a future road maintenance strategy is formulated using the method for formulating the current road maintenance strategy, and then the current road maintenance strategy and the future road maintenance strategy are merged to obtain the road maintenance strategy.

[0120] More specifically, the process of integrating the current pavement maintenance strategy with the future pavement maintenance strategy is as follows: For a certain pavement monitoring indicator, determine whether the level range of its corresponding weighted pavement monitoring indicator data is not lower than the level range of its corresponding weighted pavement monitoring indicator prediction data. If so, the response plan for that pavement monitoring indicator in the current pavement maintenance strategy remains unchanged. If not, the response plan for that pavement monitoring indicator in the future pavement maintenance strategy is used to replace the response plan for that pavement monitoring indicator in the current pavement maintenance strategy. After completing the judgment for all pavement monitoring indicators, the modified current pavement maintenance strategy, i.e., the final pavement maintenance strategy, can be obtained.

[0121] When formulating road maintenance strategies, integrating current and future road maintenance strategies allows for a comprehensive consideration of the current and future condition of the road surface. This approach combines long-term planning with short-term responses, resulting in more scientific and rational maintenance strategies. This helps optimize the allocation of maintenance resources, reduce unnecessary waste, and improve the efficiency and effectiveness of maintenance work.

[0122] It should be noted that in some cases, the actions described in the specification can be performed in different orders and still achieve the desired results. In this embodiment, the order of steps is given only to make the embodiment clearer and easier to explain, and not to limit it.

[0123] In an optional embodiment, referring to Figure 2, the present invention provides a pavement defect monitoring and prediction system. The system uses a pavement defect monitoring and prediction method provided by the present invention. The system includes a digital twin model construction module A1, a data acquisition and preprocessing module A2, a pavement defect monitoring and prediction module A3, a data storage module A4, and an information visualization module A5.

[0124] The digital twin model building module A1 is used to build a digital twin model of the target road surface.

[0125] Specifically, in this embodiment, the digital twin model construction module A1 is electrically connected to the road surface defect monitoring and prediction module A3 and the information visualization module A5, respectively. The digital twin model construction module A1 is based on SketchUp software and uses road geometry information, road texture information and environmental information from road design CAD drawings to construct a road surface digital twin model.

[0126] The data acquisition and preprocessing module A2 is used to collect historical road surface monitoring data to construct a historical road surface monitoring dataset, and to acquire accurate data of road surface monitoring indicators and high-definition road surface image data in real time.

[0127] Specifically, in this embodiment, the data acquisition and preprocessing module A2 performs the content described in step S2.

[0128] More specifically, the data acquisition and preprocessing module A2 includes a digital display screen and various sensors for collecting road surface monitoring data. These sensors transmit information to the data acquisition and preprocessing module A2 via the Internet of Things (IoT). Data that cannot be obtained using sensors can be input into the data acquisition and preprocessing module A2 through the digital display screen.

[0129] The pavement defect monitoring and prediction module A3 is used to obtain the index weights of each pavement monitoring index using a dual-source weight fusion method based on the pavement digital twin model and the pavement monitoring dataset; update the pavement digital twin model based on the accurate data of the pavement monitoring indexes, the index weights, and the high-definition pavement image data to achieve real-time monitoring of target pavement defects; predict the accurate data of the pavement monitoring indexes, and then predict the target pavement defects based on the index weights and the pavement digital twin model, and formulate pavement maintenance strategies.

[0130] Specifically, in this embodiment, the road surface defect monitoring and prediction module A3 is electrically connected to the digital twin model construction module A1, the data acquisition and preprocessing module A2, the data storage module A4, and the information visualization module A5, respectively. The specific execution of steps S3-S5 by the road surface defect monitoring and prediction module A3 will not be elaborated here.

[0131] The data storage module A4 is used to store the data collected and generated by the data acquisition and preprocessing module A2, and can also store the data generated by the road surface defect monitoring and prediction module A3.

[0132] Specifically, in this embodiment, the data storage module A4 is electrically connected to the data acquisition and preprocessing module A2, the road surface defect monitoring and prediction module A3, and the information visualization module A5, respectively.

[0133] Furthermore, the data storage module A4 also stores a road maintenance solution library.

[0134] The information visualization module A5 is used to display real-time road surface monitoring data and road surface digital twin information, and can output the road surface maintenance strategy.

[0135] In summary, the method provided by this invention, by constructing a digital twin model of the road surface, presents complex road conditions in an intuitive and easy-to-understand manner, enabling the monitoring and prediction of road defects. This method preprocesses road monitoring index data and road image data to accurately reflect the real-time condition of the road surface, thus ensuring that the updated digital twin model also accurately reflects the real-time condition, achieving accurate road monitoring. When updating the digital twin model, this method combines precise data from road monitoring indicators with indicator weights to calculate weighted road monitoring index data, fully considering the influence of different road monitoring indicators on the road surface condition. This allows the digital twin model to more comprehensively reflect the actual road surface situation, improving the real-time performance, comprehensiveness, and accuracy of monitoring. The indicator weights are obtained by fusing the first and second weights, avoiding the one-sidedness of weights obtained from a single method, further improving the accuracy of road defect monitoring and prediction results. After monitoring and predicting road defects, this method can also formulate corresponding road maintenance strategies, ensuring maintenance effectiveness while minimizing maintenance costs, which helps extend the service life of the road surface and improve road safety and traffic capacity. Furthermore, the system provided by this invention is compatible with the method provided by this invention, and can stably execute the method provided by this invention, thereby enhancing the practical application capability of this invention.

[0136] 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for monitoring and predicting road surface defects, characterized in that, Includes the following steps: Construct a digital twin model of the target road surface; Historical road surface monitoring data is collected to construct a historical road surface monitoring dataset, and accurate data of road surface monitoring indicators and high-definition road surface image data are obtained in real time; Based on the road surface digital twin model and the road surface monitoring dataset, the index weights of each road surface monitoring index are obtained using the dual-source weight fusion method. The digital twin model of the road surface is updated based on the accurate data of the road surface monitoring indicators, the indicator weights, and the high-definition image data of the road surface, so as to realize real-time monitoring of the defects of the target road surface. The accurate data of the road surface monitoring indicators are predicted, and then the defects of the target road surface are predicted based on the indicator weights and the road surface digital twin model, and a road surface maintenance strategy is formulated.

2. The method for monitoring and predicting road surface defects according to claim 1, characterized in that: The historical road surface monitoring data includes historical road surface monitoring index data and historical road surface image data; The process of collecting historical road surface monitoring data to construct a historical road surface monitoring dataset, and acquiring accurate data on road surface monitoring indicators and high-definition road surface images in real time, includes the following steps: Historical road surface monitoring data is collected and preprocessed to construct a historical road surface monitoring dataset. Real-time acquisition of road surface monitoring index data and road surface image data, followed by preprocessing, yields accurate data of the road surface monitoring indexes and high-definition image data of the road surface.

3. The method for monitoring and predicting road surface defects according to claim 2, characterized in that, The process of acquiring road surface monitoring index data and road surface image data in real time, and preprocessing them to obtain accurate road surface monitoring index data and high-definition road surface image data includes the following steps: Data cleaning is performed on the road surface monitoring index data to obtain accurate data for the road surface monitoring index; The road surface image data is smoothed and denoised, and the contrast is enhanced to obtain high-definition road surface image data.

4. The method for monitoring and predicting road surface defects according to claim 2, characterized in that, The step of obtaining the index weights of each road monitoring index using the dual-source weight fusion method based on the road digital twin model and the road monitoring dataset includes the following steps: Image recognition is performed on historical road surface image data in the road surface monitoring dataset to obtain road surface defects, including cracks and potholes. Based on the image recognition results, calculate the pavement defect evaluation factor value corresponding to each group of pavement monitoring data in the pavement monitoring dataset; Based on the pavement monitoring dataset and the pavement defect evaluation factor values, the first weight of the pavement monitoring index is obtained using the ranking importance method. Based on the road surface digital twin model, the road surface monitoring dataset, and the road surface defect evaluation factor values, the second weight of the road surface monitoring index is obtained using a step-by-step analysis method. The index weights are calculated based on the first weight and the second weight.

5. The method for monitoring and predicting road surface defects according to claim 4, characterized in that, The step of obtaining the second weight of the pavement monitoring index using a step-by-step analysis method based on the pavement digital twin model, the pavement monitoring dataset, and the pavement defect evaluation factor values ​​includes the following steps: A set of road monitoring data is randomly selected from the road monitoring dataset as the array to be adjusted, and the remaining sets of road monitoring data are used as the adjustment array. For a certain road surface monitoring indicator, the values ​​of the road surface monitoring indicator in the array to be adjusted are replaced sequentially with the values ​​of the road surface monitoring indicator in the adjustment array to obtain multiple sets of adjusted arrays, and the road surface monitoring indicator is marked as the road surface monitoring change indicator. The adjusted array is used to update the digital twin model of the road surface, identify road surface defects and calculate the comparison values ​​of multiple road surface defect evaluation factors, and then the second weight of the road surface monitoring change index is calculated by combining the values ​​of the road surface defect evaluation factors.

6. The method for monitoring and predicting road surface defects according to claim 5, characterized in that, The second weight satisfies the following relationship: ， in, The second weight is N, and the number of elements in the adjustment array is N. This is the comparison value of the i-th pavement defect evaluation factor. The value of the pavement defect evaluation factor is given. The value of the road surface monitoring change index in the i-th adjustment array is... The value of the road surface monitoring change index in the array to be adjusted.

7. The method for monitoring and predicting road surface defects according to claim 1, characterized in that, The process of updating the digital twin model of the road surface based on the accurate data of the road surface monitoring indicators, the indicator weights, and the high-definition image data of the road surface to achieve real-time monitoring of defects in the target road surface includes the following steps: Calculate weighted road surface monitoring index data based on the accurate data of the road surface monitoring indicators and the weights of the indicators; The weighted pavement monitoring index data and the high-definition pavement image data are used to update the pavement digital twin model to obtain a real-time twin pavement, thereby enabling real-time monitoring of the target pavement defects.

8. The method for monitoring and predicting road surface defects according to claim 7, characterized in that, The process of accurately predicting the pavement monitoring indicators, and then predicting the target pavement defects based on the indicator weights and the pavement digital twin model, and formulating a pavement maintenance strategy, includes the following steps: The accurate data of the road surface monitoring indicators are predicted to obtain the future indicator prediction data of each of the road surface monitoring indicators; Calculate weighted road surface monitoring indicator prediction data based on the indicator prediction data and the indicator weights; The weighted pavement monitoring index prediction data is used to update the real-time twin pavement to obtain the future twin pavement, thereby realizing the prediction of the target pavement defects; Develop the current road maintenance strategy based on the weighted road monitoring index data; A future road maintenance strategy is formulated based on the real-time twin road surface, the weighted road surface monitoring index prediction data, and the future twin road surface, and the current road surface maintenance strategy is integrated to obtain the road maintenance strategy.

9. The method for monitoring and predicting road surface defects according to claim 8, characterized in that, The process of formulating a future pavement maintenance strategy based on the real-time twin pavement, the weighted pavement monitoring index prediction data, and the future twin pavement, and then integrating the current pavement maintenance strategy to obtain the pavement maintenance strategy, includes the following steps: The weighted road surface monitoring index prediction data are arranged in descending order; The smallest data in the weighted road surface monitoring index prediction data is deleted sequentially, and the remaining weighted road surface monitoring index prediction data is used to update the real-time twin road surface after each deletion to obtain the comparison twin road surface, and the similarity between the comparison twin road surface and the future twin road surface is calculated. When the similarity is less than the similarity threshold for the first time, the operation of deleting the weighted road surface monitoring index prediction data is stopped, and the remaining weighted road surface monitoring index prediction data after the previous deletion operation is used as the final decision data. The road maintenance strategy is derived by formulating a future road maintenance strategy based on the final judgment data and integrating the current road maintenance strategy.

10. A pavement defect monitoring and prediction system, wherein the system uses a pavement defect monitoring and prediction method according to any one of claims 1-9, characterized in that, The system includes: A digital twin model building module, which is used to build a digital twin model of the target road surface; The data acquisition and preprocessing module is used to collect historical road surface monitoring data to construct a historical road surface monitoring dataset, and to acquire accurate data of road surface monitoring indicators and high-definition road surface image data in real time. A pavement defect monitoring and prediction module is used to obtain the index weights of each pavement monitoring index using a dual-source weight fusion method based on the pavement digital twin model and the pavement monitoring dataset; update the pavement digital twin model based on the accurate data of the pavement monitoring indexes, the index weights, and the high-definition pavement image data to achieve real-time monitoring of target pavement defects; predict the accurate data of the pavement monitoring indexes, and then predict the target pavement defects based on the index weights and the pavement digital twin model, and formulate pavement maintenance strategies. A data storage module is used to store the data collected and generated by the data acquisition and preprocessing module, and can also store the data generated by the road surface defect monitoring and prediction module. The information visualization module is used to display real-time road surface monitoring data and road surface digital twin information, and can output the road surface maintenance strategy.

Images