Asphalt pavement health state monitoring system and method

Abstract

The invention discloses an asphalt pavement health state monitoring system and method, and belongs to the technical field of traffic infrastructure monitoring. The system comprises the following modules: a multi-source data acquisition module used for realizing real-time acquisition of pavement state parameters; the data processing module is used for performing space-time alignment, quality evaluation, exception handling and standardization on the acquired multi-source data; the multi-scale feature extraction module is used for extracting features from the microscopic diseases, the road section states and the network level, and constructing a multi-scale feature representation system; the dynamic graph analysis module is used for constructing a layered dynamic graph structure and realizing unified modeling and analysis of the road network health state; the health assessment module is used for realizing real-time assessment, deterioration trend prediction and risk early warning of the road surface health state; and the decision visualization module is used for displaying the monitoring data, the prediction result and the early warning information, and automatically generating maintenance decision suggestions based on the evaluation result.

Description

Technical Field

[0001] The present application relates to the technical field of transportation infrastructure monitoring, and more specifically, to a system and method for monitoring the health status of an asphalt pavement. Background Art

[0002] With the rapid development of the transportation industry, the widespread use of asphalt pavements has greatly promoted social and economic progress. However, asphalt pavements are prone to aging, cracks, rutting, looseness and other diseases under long-term high-load operation and complex environmental influences. These diseases not only reduce the performance of the pavement, but also threaten driving safety and increase the risk of traffic accidents. At the same time, the repair and maintenance of pavement diseases usually requires a lot of manpower, material and financial resources. How to achieve scientific maintenance management has become a problem that needs to be solved urgently.

[0003] At present, traditional asphalt pavement health monitoring mainly relies on manual inspections and regular testing. This method has defects such as untimely data acquisition, high disease missed detection rate, and low diagnostic efficiency, which makes it difficult to meet the dynamic maintenance needs of modern road networks. In recent years, with the continuous development of sensor technology, artificial intelligence and Internet of Things technology, pavement monitoring technology based on multi-source data collection has gradually emerged. Through static sensors and dynamic acquisition equipment, multi-dimensional data such as static characteristics, dynamic response and environmental impact of the pavement can be obtained in real time, providing rich data support for pavement health status assessment.

[0004] However, the existing monitoring systems and methods still have many shortcomings in practical applications. On the one hand, multi-source data have problems such as heterogeneity, spatiotemporal misalignment and unstable quality during the collection process, which makes it impossible to effectively integrate the data and affects the accuracy of health status assessment. On the other hand, the existing analysis methods usually only focus on the single-scale characteristics of pavement diseases and lack the ability to systematically model multi-scale characteristics at the micro, road section and network levels. At the same time, for the dynamic changes in the health status of the pavement, traditional methods are difficult to effectively capture the spatiotemporal correlation, which limits the comprehensive assessment of the global health status of the road network. In addition, the current monitoring system is still insufficient in risk prediction and maintenance decision-making, and fails to effectively combine multi-dimensional data and evaluation results to provide scientific maintenance recommendations for decision makers.

[0005] In summary, how to build an asphalt pavement health status monitoring system and method that can efficiently collect multi-source data, accurately extract multi-scale features, dynamically analyze the health status of the road network, and realize real-time evaluation, trend prediction and scientific decision support has become a technical problem that needs to be solved urgently. Summary of the invention

[0006] In order to overcome a series of defects in the prior art, the purpose of this application is to provide an asphalt pavement health status monitoring system for the above-mentioned problems, including the following modules.

[0007] Multi-source data acquisition module enables real-time acquisition of road surface status parameters.

[0008] The data processing module performs spatiotemporal alignment, quality assessment, exception processing and standardization on the collected multi-source data.

[0009] The multi-scale feature extraction module extracts features from microscopic defects, road section status and network level to construct a multi-scale feature representation system.

[0010] The dynamic graph analysis module builds a hierarchical dynamic graph structure to achieve unified modeling and analysis of the health status of the road network.

[0011] The health assessment module enables real-time assessment of pavement health status, prediction of degradation trends and risk warning.

[0012] The decision visualization module displays monitoring data, prediction results and warning information, and automatically generates maintenance decision recommendations based on the evaluation results.

[0013] Furthermore, the multi-source data acquisition module includes the following components.

[0014] Static sensor units continuously monitor static changes in pavement structure and materials through sensors installed on the pavement, providing basic pavement health data.

[0015] The dynamic data collection equipment unit uses mobile equipment to collect road surface status data in real time and obtain dynamic load and road surface deformation information.

[0016] Environmental monitoring equipment collects external environmental data related to road surface conditions.

[0017] The vibration sensor unit captures the vibration of the road surface under different loads through vibration sensors.

[0018] The image acquisition unit uses a high-definition camera to capture road surface images in real time.

[0019] The equipment operation monitoring unit monitors the operating status of each data acquisition device, detects equipment failures in a timely manner and performs necessary equipment maintenance.

[0020] Furthermore, the data processing module includes the following components.

[0021] The spatiotemporal alignment unit is responsible for the spatiotemporal alignment of time series data from different data sources to ensure that all types of data can accurately reflect the road surface conditions in the same time and space range.

[0022] The data quality assessment unit is responsible for quality assessment and self-calibration of various types of collected data, and identifying data integrity, accuracy and validity.

[0023] The exception handling unit is responsible for correcting or eliminating abnormal data.

[0024] The data standardization unit is responsible for converting data from different sources into a unified standard format and dimension.

[0025] Data fusion unit, which combines data from multiple sources into a high-precision comprehensive dataset.

[0026] The data synchronization and update unit is used to achieve consistency and real-time update of multi-source data at different processing stages.

[0027] Furthermore, the multi-scale feature extraction module includes the following components.

[0028] The micro-feature extraction unit captures the detailed features of pavement micro-diseases through a high-resolution convolutional layer.

[0029] The road segment feature extraction unit uses a convolutional layer with a medium receptive field to extract state features at the road segment level.

[0030] The network-level feature extraction unit uses a global pooling layer to extract macro features at the road network level.

[0031] The multi-scale feature fusion unit integrates microscopic, section-level and network-level features to construct a unified multi-scale representation system and achieve a comprehensive characterization of the road surface status.

[0032] The scale interaction unit uses a feature pyramid structure to promote information interaction between features of different scales.

[0033] The feature enhancement unit enhances the distinguishability and robustness of features through feature normalization operations to improve the adaptability to complex road conditions.

[0034] Furthermore, the microscopic, section-level and network-level features are integrated to construct a unified multi-scale characterization system to achieve a comprehensive characterization of the road surface status, including the following steps.

[0035] By designing a multi-branch neural network structure, the features at the micro, road segment and network levels are processed respectively, and the attention mechanism is used to learn the importance weights of features at different scales, and the features of the three levels are integrated.

[0036] The fused features are converted into a fixed-dimensional vector representation through mapping, so that it contains not only microscopic behavioral patterns, but also mesoscopic road section status and macroscopic network characteristics, thereby achieving a comprehensive characterization of the road surface status.

[0037] Furthermore, the dynamic graph analysis module includes the following components.

[0038] The graph structure building unit abstracts the road network into a hierarchical dynamic graph structure, where nodes represent road sections and edges represent connection relationships, providing a basic topological structure for modeling the health status of the road network.

[0039] The node feature embedding unit embeds the output results of the multi-scale feature extraction module into the graph nodes to characterize the health status and attribute information of each road segment.

[0040] The edge weight learning unit learns the weights of the edges between nodes through an adaptive mechanism, dynamically reflecting the spatial correlation and influence intensity between road sections.

[0041] The spatiotemporal graph convolution unit uses the spatiotemporal graph convolution network to simultaneously capture the spatial dependency and temporal dynamic changes of the road network, achieving cross-scale feature propagation and fusion.

[0042] The spatiotemporal attention unit introduces the attention mechanism to dynamically assign importance weights to different nodes and time periods.

[0043] The graph pooling unit reduces the dimension of the graph structure through hierarchical pooling operations, extracts global features at the road network level, and realizes the aggregation of health status from local to global.

[0044] Furthermore, the graph structure is reduced in dimension through hierarchical pooling operations, global features at the road network level are extracted, and health status aggregation from local to global is achieved, including the following steps.

[0045] An adjacency matrix is ​​constructed based on the physical connection relationship between road segments, and the initial neighborhood range is defined as the local receptive field.

[0046] Within a predefined neighborhood, a dedicated pooling function is designed to perform preliminary aggregation of node features and map the state information of adjacent road sections into a unified feature representation.

[0047] By iteratively expanding the receptive field of the pooling operation, the features are aggregated and abstracted layer by layer, and finally a global feature representation with greatly reduced dimensions but retaining key semantic information is obtained.

[0048] Furthermore, the health assessment module includes the following components.

[0049] The real-time status analysis unit uses multi-scale feature representation and dynamic graph analysis results to calculate the health score and key performance indicators of the road surface in real time.

[0050] The deterioration trend prediction unit predicts future changes in the pavement health status and identifies potential deterioration risks based on time series analysis and machine learning algorithms.

[0051] The risk warning generation unit automatically generates warning information based on the health status and predicted trends, including the degradation risk level and possible impact range.

[0052] Dynamic comparative analysis unit compares historical data with current assessment results to identify abnormal changes or long-term trends.

[0053] The maintenance needs assessment unit assesses the maintenance needs and urgency of each area based on the health status and risk assessment results.

[0054] Furthermore, the decision visualization module includes the following components.

[0055] The data access unit accesses monitoring data, prediction results and warning information in real time, providing a dynamically updated data source for visualization.

[0056] The map display unit, based on geographic information system technology, intuitively displays the road network health status, disease distribution and warning information in the form of heat maps or layered maps.

[0057] The chart generation unit displays the pavement health index, degradation trend and risk assessment results through line charts or bar charts.

[0058] The early warning prompt unit highlights high-risk sections or sudden hazards in the visual interface, combining color coding and pop-up reminders.

[0059] The decision recommendation unit automatically generates maintenance decision recommendations including regional priority rankings based on health assessment results and maintenance needs assessment, and presents them in structured text or chart form.

[0060] The interactive operation unit provides user interaction functions, supporting managers to view detailed data and adjust decision parameters as needed.

[0061] The report generation unit automatically generates visual reports summarizing monitoring data, evaluation results and decision-making recommendations.

[0062] The purpose of this application is also to provide a method for monitoring the health status of an asphalt pavement, comprising the following steps.

[0063] The static characteristic data and dynamic monitoring data of asphalt pavement are collected in real time through the sensor network.

[0064] The collected heterogeneous data are aligned in time and space, and wavelet transform is used for noise reduction and standardization to construct a multimodal fusion dataset.

[0065] Based on the feature pyramid network, adaptive fusion of multi-scale features is achieved to build a systematic road condition representation system.

[0066] Combining the spatiotemporal graph convolutional network and the self-attention mechanism, the dynamic change characteristics of the road network are extracted, and the multi-level aggregation and representation of features are achieved through the layered graph pooling method.

[0067] Multi-dimensional risk identification is achieved based on historical data and real-time monitoring data, and the priority of maintenance needs is determined through quantitative comparative analysis of multi-dimensional factors.

[0068] Based on the geographic information system platform, the monitoring data, assessment results and early warning information can be visualized, and intelligent suggestions can be provided for maintenance decisions.

[0069] Compared with the prior art, the present application has the following beneficial effects.

[0070] This application realizes real-time monitoring, evaluation and prediction of road conditions through modules such as multi-source data collection, data processing, multi-scale feature extraction, dynamic graph analysis, health assessment and decision visualization. The system can not only capture the microscopic diseases and road section conditions of the road surface, but also conduct unified modeling and analysis at the network level, providing intelligent decision support for road maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a schematic diagram of the structure of an asphalt pavement health status monitoring system disclosed in an embodiment of the present application.

[0072] Figure 2 A flow chart of a method for monitoring the health status of an asphalt pavement disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments.

[0074] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0075] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0076] like Figure 1 As shown, an asphalt pavement health status monitoring system includes the following modules.

[0077] The multi-source data acquisition module builds a multi-source data acquisition network through static sensors, dynamic acquisition equipment and environmental monitoring equipment to achieve real-time acquisition of road condition parameters.

[0078] The data processing module performs spatiotemporal alignment, quality assessment, exception processing and standardization on the collected multi-source data.

[0079] The multi-scale feature extraction module extracts features from microscopic defects, road section status and network level, constructs a multi-scale feature representation system, and achieves a comprehensive characterization of the road surface status.

[0080] The dynamic graph analysis module builds a hierarchical dynamic graph structure and realizes unified modeling and analysis of the health status of the road network through cross-scale feature fusion and spatiotemporal attention mechanism.

[0081] The health assessment module realizes real-time assessment of pavement health status, prediction of degradation trends and risk warning based on multi-scale feature representation and dynamic graph analysis results.

[0082] The decision visualization module provides an intuitive visualization interface to display monitoring data, prediction results and early warning information, and automatically generates maintenance decision recommendations based on the evaluation results to provide managers with a basis for decision-making.

[0083] In this embodiment, the multi-source data acquisition module is the basis of the asphalt pavement health status monitoring system. Its function is to build a multi-level acquisition network through static sensors, dynamic acquisition equipment and environmental monitoring equipment to collect relevant data on the health status of the pavement in real time. Static sensors such as strain gauges, pressure sensors, temperature sensors, etc. can be stably installed at various locations on the pavement for long-term monitoring of changes in different locations. These sensors can obtain parameters such as mechanics and temperature on the surface and inside of the road in real time, and provide accurate pavement status information. Dynamic acquisition equipment such as vehicle-mounted sensors, drones, pavement inspection vehicles, etc. can collect data during movement and obtain small changes on the pavement. These dynamic data are crucial for capturing short-term changes and emergencies that may occur in the pavement during actual use. In addition, environmental monitoring equipment can monitor the influencing factors of the surrounding environment, such as humidity, precipitation, wind speed, etc., which have an important impact on the pavement status. Through the fusion of these multi-source data, it is possible to achieve all-round and real-time status monitoring of the asphalt pavement, providing accurate data support for subsequent analysis and decision-making.

[0084] In this embodiment, the core task of the data processing module is to process and optimize multi-source data to ensure the quality, integrity and validity of the data. First, through the spatiotemporal alignment technology, ensure that the data from different sensors and devices are accurately matched in time and space dimensions. This is because there are differences in the acquisition frequency and spatial coverage of different devices, and the data needs to be effectively aligned for subsequent analysis. Secondly, the quality assessment module screens the collected data, removes noise and incomplete parts, and ensures that subsequent analysis is not interfered by bad data. In this process, anomaly detection technology also plays an important role, which can identify and process abnormal fluctuations in data, such as data errors caused by equipment failure or environmental changes. Finally, data standardization processing converts data from different sources and different types into a unified format and scale, so that all data can be integrated and compared on the same platform, laying the foundation for subsequent feature extraction and health assessment.

[0085] In this embodiment, the multi-scale feature extraction module is designed to comprehensively reflect the health status of the road surface through feature extraction at different levels. From a microscopic perspective, this part focuses on extracting small-scale disease features on the road surface, such as cracks, potholes, and surface defects such as shedding. These microscopic diseases often have a long-term impact on the durability of the road surface, so their detection and analysis are crucial. Next, the extraction of road section status features focuses on larger-scale road surface areas, such as the flatness of the road section, the road surface bearing capacity, and the accumulation of damage. By analyzing the overall health status of the road section, a basis can be provided for the repair and maintenance of the road section. Finally, the network-level feature extraction is a comprehensive assessment of the health status of the entire road network, including factors such as connectivity, traffic capacity, and maintenance requirements between road sections. The feature of this module is that it can characterize the health status of the road surface from multiple scales and multiple dimensions, providing all-round feature support for subsequent dynamic graph analysis.

[0086] In this embodiment, the dynamic graph analysis module realizes unified modeling and analysis of the health status of the road network by constructing a hierarchical dynamic graph structure. The health status of the road surface is not only a time series problem, but also a spatial structured problem. The dynamic graph structure enables each section in the road network to be flexibly modeled in time and space, and can effectively represent the state changes of different sections at different times. In this module, cross-scale feature fusion is one of the core technologies. Through the fusion of microscopic, section and network-level features, the dynamic changes in road health can be fully understood. At the same time, the spatiotemporal attention mechanism helps the system dynamically adjust the focus of attention in different time and space dimensions during the analysis process, so as to better capture the key factors of road health changes. This module can not only analyze a single section, but also conduct a comprehensive health status assessment of the entire road network, providing more accurate support for decision-making and management.

[0087] In this embodiment, the health assessment module uses multi-scale features and dynamic graph analysis results to perform real-time assessment of the health status of the road surface, predict deterioration trends, and provide risk warnings. The real-time assessment function can help managers keep track of the health status of the road surface at any time, detect potential hazards in a timely manner, and make necessary maintenance decisions based on the assessment results. The deterioration trend prediction predicts the health change trend of the road surface in the future by analyzing historical data and current status, helping relevant departments to prepare countermeasures in advance. The risk warning function issues a warning in advance when potential problems occur on the road surface, reminding managers to take timely measures. This module can use intelligent algorithms to evaluate the health of the road surface in real time, and combine the influencing factors of the external environment to make more accurate predictions and decisions.

[0088] In this embodiment, the decision visualization module can convert complex pavement health data and analysis results into graphical information that is easy to understand and operate, such as heat maps, trend maps, early warning prompts, etc. This information can help pavement managers quickly understand the current road conditions, predict future changes, and make corresponding maintenance decisions. Based on the evaluation results, maintenance decision recommendations can be automatically generated to provide managers with a scientific basis to ensure the optimal allocation of maintenance resources, reduce the occurrence of road damage, and extend the service life of the pavement. Through the visualization module, the entire system not only improves the transparency of the data, but also makes pavement health management more intelligent and systematic.

[0089] The above modules work together to form a complete asphalt pavement health status monitoring system. Through multi-source data collection, precise data processing, multi-scale feature extraction and dynamic graph analysis, it can comprehensively and real-time monitor and evaluate the health status of the road surface. Combining the health assessment and decision visualization modules, it not only provides managers with accurate health status assessment and deterioration trend prediction, but also optimizes the allocation of maintenance resources through intelligent decision-making suggestions.

[0090] Furthermore, the multi-source data acquisition module includes the following components.

[0091] Static sensor units continuously monitor static changes in pavement structure and materials through sensors installed on the pavement, providing basic pavement health data.

[0092] The dynamic data collection equipment unit uses mobile equipment to collect road surface status data in real time and obtain dynamic load and road surface deformation information.

[0093] Environmental monitoring equipment collects external environmental data related to road conditions and provides external factor references for changes in road conditions.

[0094] The vibration sensor unit uses vibration sensors to capture the vibration of the road surface under different loads and analyze road damage and potential problems.

[0095] The image acquisition unit uses a high-definition camera to capture road surface images in real time to assist in determining surface damage or aging.

[0096] The equipment operation monitoring unit monitors the operating status of each data acquisition device, detects equipment failures in a timely manner and performs necessary equipment maintenance.

[0097] In this embodiment, the static sensor unit is one of the core components of the multi-source data acquisition module. Its main function is to monitor the static changes of the pavement structure and materials in real time through sensors installed on the pavement. These sensors are usually installed at different depths and positions inside the pavement, including strain gauges, temperature sensors, humidity sensors, etc. These devices can continuously collect basic status data of the pavement during long-term use, such as temperature changes, humidity fluctuations, pavement stress conditions, etc. These data are crucial to understanding the changing trends of the pavement health status, especially for problems such as road aging, settlement, and cracking under long-term use. The advantage of static sensors is that they can collect data stably and continuously without excessive manual intervention, thereby providing a reliable long-term data basis for subsequent analysis. In addition, static sensors can also realize real-time data upload, ensuring instant control of the pavement status. The application of this unit provides data guarantee for accurate assessment of the pavement health status and is the "eye" of the monitoring system.

[0098] In this embodiment, the dynamic acquisition device unit uses mobile equipment, such as inspection vehicles, drones, intelligent inspection vehicles, etc., to collect status data in real time on the road surface, especially the performance of the road surface under traffic load. Compared with static sensors, dynamic acquisition equipment can obtain information such as dynamic load, road deformation, rutting, cracks, etc. with the help of vehicle driving or other mobile devices. This information has a higher practical significance in reflecting the health status of the road surface, because the state change of the road surface under different loads and traffic conditions is usually the most critical evaluation indicator. For example, in sections with high traffic density, dynamic acquisition can accurately record the deformation of the road surface under the rolling of heavy vehicles, helping to determine the potential risk of road damage. The advantage of dynamic acquisition equipment is that it can cover a wider range of sections, obtain real-time and comprehensive health data, and can be compared with static data to help managers better identify and predict problems. Dynamic acquisition equipment can collect data efficiently and extensively, becoming an important supplement to the analysis of road health status.

[0099] In this embodiment, the environmental monitoring equipment plays a role in providing a reference for external environmental impacts in the multi-source data acquisition module. The health of the road surface is not only affected by changes in its own materials and structures, but also by external environmental factors such as temperature, humidity, precipitation, wind speed, and ultraviolet rays. For example, frequent precipitation or extreme temperature changes will accelerate the aging process of the road surface, especially in asphalt pavements, where environments with large temperature differences may cause cracking or deformation of the road surface. Therefore, the environmental monitoring equipment can provide meteorological data related to changes in the state of the road surface by installing meteorological monitoring instruments (such as temperature sensors, humidity sensors, air pressure sensors, precipitation monitors, etc.). These external data, combined with the road health data, can effectively explain the causes of road damage and provide more accurate background information for formulating maintenance strategies. Through environmental monitoring equipment, external environmental factors can be closely combined with road health data to help analyze the interaction between road damage and environmental conditions, and improve the comprehensiveness and accuracy of monitoring and analysis.

[0100] In this embodiment, the vibration sensor unit is used to capture the vibration of the road surface under different loads, especially the vibration signals generated when traffic vehicles pass. These vibration signals can reflect the stress conditions of the road surface and possible structural problems. For example, when the road surface is subjected to a large load, the vibration sensor can record the corresponding vibration amplitude and frequency. By analyzing these data, it can be determined whether the road surface has structural damage or potential cracks, settlement and other problems. The vibration sensor unit can sensitively detect tiny vibration changes, especially in sections with heavy traffic and frequent load changes, and can promptly detect potential road surface problems. By collecting and analyzing vibration data, possible safety hazards can be warned in advance, providing an accurate basis for maintenance decisions. In addition, the use of vibration sensors does not depend on changes in the external environment, so they have strong stability and reliability.

[0101] In this embodiment, the image acquisition unit uses a high-definition camera or imaging system to capture road surface images in real time, which is an important technical means to assist in judging the damage, aging or other diseases of the road surface through visual means. The high-definition camera can be installed above the road surface or on-board equipment, and through automated image acquisition and analysis, surface damage such as cracks, potholes, shedding, rutting, etc. is detected. These surface damages directly affect the driving safety of the road surface, so they need to be detected accurately and efficiently. The advantages of the image acquisition unit are its high resolution and real-time performance, which can intuitively reflect the subtle damage on the road surface, and can automatically identify and classify different types of damage. In addition, by combining with other sensor data, the image data can be further used to verify or supplement the results of other data acquisition methods to improve the overall accuracy. The unit can capture road surface problems intuitively and in real time, which is an effective supplement to traditional detection methods.

[0102] In this embodiment, the main function of the equipment operation monitoring unit is to monitor the operating status of each data acquisition device in real time, ensure that the equipment operates normally and can respond in time when a failure occurs. With the increase in the use of sensors and dynamic acquisition equipment, the operating status of the equipment is crucial to the data quality and the accuracy of the monitoring results. By integrating various monitoring technologies, such as battery power monitoring, temperature monitoring, signal transmission monitoring, etc., the unit can ensure that the equipment can work normally at any time. When a device fails or its performance degrades, an alarm will be automatically triggered and repairs or replacements will be carried out in time. This unit improves the stability and reliability of data acquisition and ensures the continuous and efficient operation of the monitoring system. The equipment operation monitoring unit provides a guarantee for the long-term stable operation of the entire system and reduces data loss or errors caused by equipment failure.

[0103] In summary, through the collaborative work of the above components, the multi-source data acquisition module can monitor the health status of asphalt pavement in real time efficiently and accurately. The static sensor unit provides basic pavement structure data, the dynamic acquisition equipment unit obtains the pavement performance under actual load, the environmental monitoring equipment provides important reference for external environmental factors, the vibration sensor unit captures potential structural problems by detecting vibration, the image acquisition unit supplements the surface disease information through visual analysis, and the equipment operation monitoring unit ensures the normal operation of the data acquisition equipment. The various components work together to form a comprehensive, accurate and efficient pavement health monitoring system, which provides strong data support for subsequent analysis and decision-making.

[0104] Furthermore, the data processing module includes the following components.

[0105] The spatiotemporal alignment unit is responsible for the spatiotemporal alignment of time series data from different data sources to ensure that all types of data can accurately reflect the road surface conditions in the same time and space range.

[0106] The data quality assessment unit performs quality assessment and self-calibration on various types of collected data, identifies data integrity, accuracy and validity, and ensures data reliability.

[0107] The exception processing unit corrects or removes abnormal data to ensure the accuracy of the final data set and avoid interference with subsequent analysis.

[0108] The data standardization unit converts data from different sources into a unified standard format and dimension, ensuring that multi-source data can be seamlessly integrated and compatible with subsequent analysis.

[0109] The data fusion unit combines data from multiple sources into a high-precision comprehensive dataset based on spatiotemporal alignment and normalization of the data.

[0110] The data synchronization and update unit is used to achieve consistency and real-time update of multi-source data at different processing stages.

[0111] In this embodiment, the spatiotemporal alignment unit is one of the core components of the data processing module, which is mainly responsible for the spatiotemporal alignment of time series data from different data sources to ensure that various data can accurately reflect the road surface status within the same time and space range. Different types of data use different timestamps and spatial positioning methods. Therefore, how to ensure the consistency of various types of data in time and space dimensions is crucial. The spatiotemporal alignment unit accurately aligns the time series data through a variety of algorithms to ensure that the measurement data from different data sources can be synchronized in the time dimension and can match the specific area of ​​road surface monitoring in the spatial position. For example, static sensor data and dynamic acquisition device data will have different sampling frequencies. The spatiotemporal alignment unit will synchronize and align the data through interpolation algorithms, time window methods or spatial interpolation methods. Through this process, the data can be analyzed in a unified spatiotemporal framework, providing an accurate basis for subsequent data processing and health status assessment. The technical effect of the spatiotemporal alignment unit is to eliminate the time differences and spatial errors from different data sources and improve the reliability of multi-source data fusion.

[0112] In this embodiment, during the multi-source data collection process, data anomalies caused by equipment failure, signal interference or other external factors may occur. If not handled, it will affect the accuracy and stability of the entire monitoring system. The data quality assessment unit evaluates the integrity, accuracy and consistency of the data through a variety of algorithms, and automatically corrects or calibrates based on the evaluation results. For example, for missing data, an interpolation algorithm can be used to fill it; for outliers, they can be automatically identified and excluded based on the distribution characteristics of historical data. In addition, the data quality assessment unit can also adjust the collection frequency and collection method in real time according to the specific pattern of the data and environmental conditions to optimize the quality of the data. This unit ensures the reliability of the final data set, avoids the adverse effects of invalid or distorted data on subsequent analysis, and further improves the accuracy of the system.

[0113] In this embodiment, the core function of the exception handling unit is to identify and process abnormal data that occurs during the data collection process to ensure the accuracy and consistency of the final data set. In practical applications, sensors generate erroneous data due to environmental interference, insufficient power, hardware failure or communication problems. If these abnormal data are not removed or corrected in time, they may have a serious impact on subsequent analysis and decision-making. The exception handling unit can automatically identify and classify abnormal data through anomaly detection algorithms, combined with historical patterns of data and current collected data. The processing methods for abnormal values ​​usually include methods such as elimination, replacement and correction. For example, abnormal data far from the normal range can be directly eliminated; for abnormal values ​​that deviate slightly from normal data, a data smoothing algorithm can be used for correction. The exception handling unit can significantly improve the accuracy of the data, reduce the interference of erroneous data on road health assessment, and ensure the effectiveness of subsequent analysis results.

[0114] In this embodiment, the data standardization unit is designed to solve the heterogeneous data formats and dimensional differences from different data sources. Since different acquisition devices and sensors may use different units, dimensions or data representation methods, the role of the data standardization unit is to convert all data from different sources into a unified standard format, so that the data can be seamlessly integrated and used for subsequent analysis. For example, road surface temperature data may be expressed in degrees Celsius, while pressure data may be in Pascals. These data are converted into unified units and dimensions through standardized units to ensure that they are compatible and combined for analysis. Standardization is not limited to unit conversion, but may also include the unification of data scales, conversion of data types, etc., thereby eliminating differences between different data sources and ensuring efficient integration of multi-source data. The data standardization unit provides a unified data processing framework, so that data from various sensors and devices can be compared and analyzed on the same basis, improving the efficiency and accuracy of data processing.

[0115] In this embodiment, the data comes from multiple channels such as static sensors, dynamic data collection equipment, and environmental monitoring equipment. The sources and formats of the data are different. Through the data fusion unit, these scattered data can be effectively integrated into a unified, high-precision data set. For example, the structural data provided by the static sensor and the traffic load data provided by the dynamic data collection equipment can be merged through the data fusion unit, and a complete road health portrait is formed through multi-level analysis and modeling. Data fusion technology includes weighted averaging, Kalman filtering, Bayesian inference and other methods. The most appropriate fusion method is selected according to the characteristics of the data and analysis requirements. This unit improves the accuracy and reliability of the data by accurately fusing multi-source data, providing comprehensive data support for road health status assessment.

[0116] In this embodiment, the data synchronization and update unit plays an important supporting role in the entire data processing process. Since the real-time requirements of multi-source data are high, and the update frequency and timestamps of different data sources may be different, the data synchronization and update unit is responsible for ensuring the synchronization and consistency of different data sources. The unit monitors the progress of data collection in real time, updates the data in the database in a timely manner, and updates and calibrates the data in real time according to the preset synchronization mechanism. For example, after the time-space alignment, the data synchronization and update unit is responsible for ensuring that the new collected data is merged into the processing flow in a timely manner, and ensuring that the historical data will not be overwritten or lost due to the new data collection. In addition, with the continuous changes in the environment and the road surface state, the data synchronization and update unit can also realize dynamic real-time updates to ensure that the data is always up to date and can adapt to the ever-changing monitoring needs. The technical effect of the data synchronization and update unit is to ensure the real-time, consistency and accuracy of the data, avoid the lag or obsolescence of the data, and improve the response speed of the monitoring system.

[0117] In summary, the data processing module effectively ensures the quality, accuracy and availability of multi-source data through the close collaboration of the above components. The spatiotemporal alignment unit ensures the consistency of data from different sources in time and space; the data quality assessment unit assesses the reliability and validity of the data; the exception handling unit effectively corrects or removes abnormal data; the data standardization unit achieves consistency in data format and unit; the data fusion unit provides accurate pavement health data through efficient integration of multi-source data; the data synchronization and update unit ensures the real-time and consistency of data. The comprehensive application of these functions not only improves the accuracy of the data, but also provides strong data support for real-time assessment, early warning and decision-making of pavement health status.

[0118] Furthermore, the multi-scale feature extraction module includes the following components.

[0119] The micro-feature extraction unit captures the detailed features of pavement micro-diseases through a high-resolution convolutional layer, providing a basis for local damage analysis.

[0120] The road section feature extraction unit uses a convolutional layer with a medium receptive field to extract the state features at the road section level to reflect the overall condition of the local road section.

[0121] The network-level feature extraction unit uses a global pooling layer to extract macro features at the road network level and characterize the global road network status.

[0122] The multi-scale feature fusion unit integrates microscopic, section-level and network-level features to construct a unified multi-scale representation system and achieve a comprehensive characterization of the road surface status.

[0123] The scale interaction unit uses a feature pyramid structure to promote information interaction between features of different scales and improve the coherence of feature expression.

[0124] The feature enhancement unit enhances the distinguishability and robustness of features through feature normalization operations to improve the adaptability to complex road conditions.

[0125] In this embodiment, the microscopic feature extraction unit focuses on capturing the detailed features of microscopic diseases of the road surface through a high-resolution convolution layer, which is the basis for analyzing local damage to the road surface. In asphalt pavement health monitoring, microscopic diseases usually refer to structural damage within a small range such as cracks, pitting, potholes, etc. These problems are not easy to detect in the early stage, but can cause rapid deterioration of road health in a short period of time. Through the high-resolution convolution layer, the microscopic feature extraction unit can accurately capture the subtle damage on the road surface, and identify detailed features such as tiny cracks, peeling, and rutting through meticulous image analysis. These features provide important data support for subsequent local damage analysis, which helps to quickly locate problem areas and take corresponding repair measures. It can be seen that the microscopic feature extraction unit greatly improves the recognition accuracy and speed of local diseases, and can perform accurate diagnosis when the damage is still in the early stage, thereby avoiding further expansion of road diseases, reducing maintenance costs and increasing the service life of the road surface.

[0126] In this embodiment, the road section feature extraction unit processes a larger range than the microscopic feature extraction unit, and focuses on identifying the status of a longer section or area of ​​the road. For example, road section features may include the overall flatness of the road surface, the distribution of lateral and longitudinal cracks, the depth of rutting, uneven compaction, etc. The convolution layer with a medium receptive field can integrate the surrounding road surface information to extract the status characteristics of the entire road section, which helps to detect structural problems in a larger range, rather than just local minor damage. Through the road section feature extraction unit, common problems in the road section can be identified, such as long-term water accumulation, the impact of continuous high-load traffic, and other factors. This unit provides more comprehensive data support for the overall condition assessment at the road section level, ensuring that the monitoring system not only focuses on individual problems, but also captures more complex potential risks that may affect larger areas, thereby achieving accurate judgment and early warning of the health status of the road surface.

[0127] In this embodiment, the network-level feature extraction unit performs an overall assessment of the health status of the entire road network, rather than being limited to a specific road section or area. Through the global pooling layer, the network-level feature extraction unit can extract macro features across multiple road sections or even the entire road network, such as the structural damage distribution of the entire road network, the degree of road aging, and the traffic load distribution. The global pooling layer can effectively capture the health status of large-scale road networks by compressing and summarizing the features within the entire road network, providing decision makers with global information to help them understand the differences in health status between different road sections and promptly identify potential problems that may pose a threat to the entire road network. In terms of technical effects, the network-level feature extraction unit can realize dynamic monitoring and evaluation of the entire road network, promote the intelligence of road maintenance and management, and enable decision makers to formulate more scientific and accurate maintenance strategies to effectively prevent large-scale systemic failures in the road network.

[0128] In this embodiment, since the health status of the road surface involves factors at multiple levels, from microscopic damage to the overall condition of the road section to the macroscopic performance of the entire road network, features at different scales each reflect information at different levels, and features at a single scale often cannot fully describe the health of the road surface. Through the multi-scale feature fusion unit, features at different levels can be effectively combined to form a comprehensive, cross-scale health assessment model. For example, if local microscopic damage occurs on a certain road section, combined with the macroscopic characteristics of the entire road network, the potential impact of the damage on the health of the entire road network can be further assessed. This unit ensures that health information from local to global can be fully utilized through cross-scale fusion. In terms of technical effects, the feature fusion unit significantly improves the perception of complex road conditions, and can accurately depict the overall and local health status of the road surface through the combination of multi-level information, and provide comprehensive data support for subsequent health assessments and decision-making.

[0129] In this embodiment, the scale interaction unit promotes information interaction between features of different scales by using a feature pyramid structure, thereby improving the coherence of feature expression. Features of different scales contain road surface information at different levels, and this information is often interdependent and interactive. For example, microscopic features can reflect local early damage, while section features can reveal whether these local problems have expanded to a larger range, and network-level features provide a global perspective on road health. The scale interaction unit uses a pyramid structure to enable information of different scales to be effectively transmitted to each other, optimize the expression of features, and enable each layer of features to obtain support from other scale information. For example, through the interactive structure, section-level features can more accurately determine the impact of local diseases with the help of microscopic feature information, while global features can help optimize the interpretation of local features. In terms of technical effects, the scale interaction unit greatly improves the correlation between features at different levels, making the entire feature expression system more coherent and comprehensive, thereby providing richer and more accurate basic data for subsequent analysis.

[0130] In this embodiment, the feature enhancement unit enhances the distinguishability and robustness of the features through feature normalization operations, thereby improving the adaptability to complex road conditions. In road health monitoring, data differences caused by different environmental conditions and collection methods are often encountered. The feature enhancement unit enables features of different scales and sources to be compared and analyzed under the same standard through normalization operations. The feature normalization operation not only helps to reduce the deviation caused by different data sources, but also enhances the stability of the features, so that the system has a stronger recognition ability for different types of road damage. In addition, the enhanced features can better adapt to the changes in complex road conditions, and can maintain high accuracy and stability regardless of different climatic conditions or different load conditions. In terms of technical effects, the feature enhancement unit improves the adaptability of the road health status monitoring system to a variety of complex conditions, so that it can maintain efficient detection capabilities in various environments, thereby ensuring the accuracy and reliability of road health status assessment.

[0131] In summary, the multi-scale feature extraction module effectively improves the monitoring and analysis capabilities of road health status through multi-level feature extraction at the micro, segment and network levels, combined with scale interaction and feature enhancement technology. The micro-feature extraction unit captures early diseases in a refined manner, the segment feature extraction unit provides a more comprehensive assessment of local problems, and the network-level feature extraction unit analyzes the health of the road network from a global perspective. The multi-scale feature fusion unit ensures the comprehensive utilization of information at different levels, while the scale interaction unit improves the circulation of information at each scale through a pyramid structure. Finally, the feature enhancement unit optimizes the distinguishability and robustness of the features and improves the adaptability to complex road conditions.

[0132] Furthermore, the detailed features of pavement microscopic defects are captured through a high-resolution convolutional layer, which includes the following steps.

[0133] Perform convolution operation on the processed road image to generate multiple feature maps, which can be expressed as: Y(i,j)=(I*K)(i,j)=∑ m ∑ n I(i+m,j+n)·K(m,n), where Y(i,j) represents the pixel value at position (i,j) in the output feature map after the convolution operation; (i,j) represents the coordinates of the pixel in the image, where i is the row coordinate and j is the column coordinate; I represents the input road image; K is the convolution kernel; * represents the convolution operation; (I*K) represents the result of the convolution operation between the input image I and the convolution kernel K, and the output is a feature map; m and n represent the row and column positions of the convolution kernel K, which are used to index the elements of the convolution kernel K when calculating the convolution; I(i+m,j+n) represents a pixel in the input image I, located at the coordinate (i+m,j+n); K(m,n) represents an element in the convolution kernel K, located at the position (m,n).

[0134] Use different sizes of convolution kernel K 1 ,K 2 ,...,K n , perform multi-scale convolution operations on the processed image to extract multi-scale features, and fuse the multi-scale features through the following formula: Y multi-scale =[(I*K 1 ),(I*K 2 ),...,(I*K n )], where Y multi-scale Represents the fusion result of multi-scale feature maps; (I * K 1 ) represents the input image I and the convolution kernel K 1 The result after convolution operation; (I * K 2 ) represents the input image I and the convolution kernel K 2 The result after convolution operation; (I * K n ) represents the input image I and the convolution kernel K n The result after convolution operation.

[0135] The ReLU activation function is used to activate the convolution feature map to remove invalid features and enhance the response of local damage to highlight the surface details of the road surface. The formula is: A(i,j)=ReLU(Y(i,j)), where A(i,j) represents the activation value of the (i,j)th position in the feature map after being processed by the ReLU function; ReLU(·) represents the ReLU activation function.

[0136] The activated feature map is input into the classification network and then compared with the damage classification weight matrix W. damage Combined with the bias term b, the Softmax function is used to obtain the classification probability distribution of the damage: P damage =Softmax(W damage A+b), where P damage represents the probability distribution of damage classification, which is the result output by the classification layer of the neural network; A represents the feature map after convolution and activation function processing; Softmax(·) represents the Softmax function.

[0137] In summary, a complete microscopic disease detection process is constructed through high-resolution convolutional layers, convolution operations of different scales, ReLU activation functions, and damage classification networks. The convolution operation can extract local features of the pavement image to ensure the capture of detailed damage; the multi-scale convolution operation enhances the adaptability to diseases of different scales and improves the accuracy of overall detection; the ReLU activation function effectively removes invalid features and strengthens the response of disease features; and the damage classification provides accurate classification and probability distribution for pavement diseases through the Softmax function. The combination of these technical means makes the detection of pavement microscopic diseases more efficient, accurate and reliable, providing strong data support for intelligent maintenance decisions and pavement health management.

[0138] Furthermore, a global pooling layer is used to extract macro features at the road network level and characterize the global road network status, including the following steps.

[0139] A multi-layer convolutional neural network is designed, starting from the bottom-level road segment features, and gradually increasing road network structural features are extracted through layer-by-layer convolution operations, ultimately forming a multi-scale representation of the road network.

[0140] A global pooling operation is introduced after the convolutional layer to compress the multi-scale road network representation into a feature vector of fixed dimension, realizing the conversion from local features to global features.

[0141] The fully connected layer performs nonlinear transformation and dimensionality reduction on the pooled feature vector, integrates the multi-dimensional features of the road network, and generates a low-dimensional compact representation that effectively characterizes the overall road network status.

[0142] In summary, by designing a multi-layer convolutional neural network, introducing global pooling operations and fully connected layers for nonlinear transformation and dimensionality reduction, macro features at the road network level can be effectively extracted and characterized. This process extracts rich road network structure information from local to global, providing strong data support for road network health assessment. The hierarchical feature extraction of the convolutional neural network can capture road network features at different levels, while global pooling ensures the effective retention of global information by compressing feature maps. The dimensionality reduction and nonlinear transformation of the fully connected layer further enhance the feature abstraction capability, and ultimately output a concise and effective low-dimensional representation, which is suitable for subsequent road network status assessment and prediction tasks.

[0143] Furthermore, the microscopic, section-level and network-level features are integrated to construct a unified multi-scale characterization system to achieve a comprehensive characterization of the road surface status, including the following steps.

[0144] By designing a multi-branch neural network structure, the features at the micro, road section and network levels are processed respectively, and the attention mechanism is used to learn the importance weights of features at different scales. The features at the three levels are then fused to achieve the optimal combination of features.

[0145] The fused features are converted into a fixed-dimensional vector representation through mapping, so that it contains not only microscopic behavioral patterns, but also mesoscopic road section status and macroscopic network characteristics, thereby achieving a comprehensive characterization of the road surface status.

[0146] In summary, by designing a multi-branch neural network, introducing an attention mechanism, and a strategy of feature fusion and mapping conversion, it is possible to effectively integrate information from different scales, thereby comprehensively characterizing the road surface condition. The multi-branch network ensures the accurate extraction of features at different levels, and the attention mechanism gives each scale feature a dynamic importance weight on this basis, further optimizing the feature fusion process. Finally, the fused features are compressed into a vector of a fixed dimension through mapping conversion, which not only retains the detailed information of the road surface condition, but also improves the computational efficiency. Overall, this multi-scale feature fusion method improves the accuracy and flexibility of road surface condition assessment, and provides strong technical support for road health monitoring in intelligent transportation systems.

[0147] Furthermore, the dynamic graph analysis module includes the following components.

[0148] The graph structure building unit abstracts the road network into a hierarchical dynamic graph structure, where nodes represent road sections and edges represent connection relationships, providing a basic topological structure for modeling the health status of the road network.

[0149] The node feature embedding unit embeds the output results of the multi-scale feature extraction module into the graph nodes to characterize the health status and attribute information of each road segment.

[0150] The edge weight learning unit learns the weights of the edges between nodes through an adaptive mechanism, dynamically reflecting the spatial correlation and influence intensity between road sections.

[0151] The spatiotemporal graph convolution unit uses the spatiotemporal graph convolution network to simultaneously capture the spatial dependency and temporal dynamic changes of the road network, achieving cross-scale feature propagation and fusion.

[0152] The spatiotemporal attention unit introduces an attention mechanism to dynamically assign importance weights to different nodes and time periods, focusing on changes in health status at key sections and key time points.

[0153] The graph pooling unit reduces the dimension of the graph structure through hierarchical pooling operations, extracts global features at the road network level, and realizes the aggregation of health status from local to global.

[0154] In this embodiment, the goal of the graph structure construction unit is to abstract the complex road network into a hierarchical dynamic graph structure to facilitate subsequent health status analysis. Nodes in this graph structure represent various sections of the road network, while edges represent the connection relationship between these sections. In this way, the topological structure of the road network can be formally represented, which is convenient for modeling and analyzing its health status. Specifically, the graph structure provides a basic framework for subsequent dynamic graph analysis, allowing us to model the road network in spatial and temporal dimensions. For example, a section of the road network will be affected by traffic flow, environmental factors, maintenance history, and other factors, and these influences can be modeled through the edges between nodes. In terms of technical effects, the graph structure enables the health status of the road network to be comprehensively modeled at different levels, including from local sections to the hierarchical structure of the entire road network, which improves the accuracy and flexibility of road network status analysis. By constructing a hierarchical dynamic graph, the analysis strategy can be dynamically adjusted according to the actual topological structure of the road network, thereby enhancing the adaptability and scalability of the model.

[0155] In this embodiment, the task of the node feature embedding unit is to embed the output results obtained from the multi-scale feature extraction module into each node of the graph, so as to provide health status and attribute information for each road section. The core of this embedding process is to map high-dimensional features to low-dimensional representations of each node through learning, so as to facilitate subsequent graph convolution operations. These features can include information such as microscopic damage to the road section, health status at the road section level, traffic flow, maintenance records, etc. In terms of technical effect, this unit enhances the richness of node representation, so that each road section can not only express its geometric features, but also contain comprehensive information about its health status, usage, and other dimensions. Through this embedding mechanism, the influence of different road sections in the graph structure can be adaptively adjusted according to their characteristics, which improves the accuracy and meticulousness of the health status analysis of the entire road network. This unit also lays the foundation for subsequent spatiotemporal analysis, so that the dynamic graph can be transformed from static topology to dynamic state, better reflecting the actual operation and health changes of the road network.

[0156] In this embodiment, the edge weight learning unit learns the edge weights according to the actual relationship and influence between the road sections through an adaptive mechanism. For example, the connection between two road sections will be affected by many factors, such as traffic flow, road conditions, traffic accidents, etc., which will change the intensity of their mutual influence. Therefore, the edge weight learning unit enables the edges of the graph to dynamically reflect the actual spatial relationship and interaction between the road sections by modeling these factors. In terms of technical effects, edge weight learning enables the graph structure to flexibly adapt to the complex dynamic behavior of the road network, and provides accurate spatial structure information for spatiotemporal graph convolution and subsequent analysis. The weight of the edge can not only reflect the spatial compactness, but also adaptively adjust the time changes through the learning mechanism, enhance the dynamic modeling ability of the graph, and thus improve the comprehensiveness and accuracy of the analysis of the health status of the road network.

[0157] In this embodiment, the task of the spatiotemporal graph convolution unit is to use the spatiotemporal graph convolution network (ST-GCN) to simultaneously capture the spatial dependency and temporal dynamic changes of the road network. In practical applications, the health status of the road network is not only affected by the interaction between road sections in space, but also by dynamic changes in time, such as seasonal changes, changes in traffic flow during the day and night, etc. Therefore, the spatiotemporal graph convolution unit can capture the dependency and change rules of the road network in both spatial and temporal dimensions through the convolution operation of spatiotemporal data. This convolution operation enables the network to propagate and fuse features across scales, thereby comprehensively characterizing the state of the road network. In terms of technical effect, the spatiotemporal graph convolution enables the model to flexibly adapt to temporal changes while capturing the spatial structure, thereby improving the ability to dynamically model the health status of the road network.

[0158] In this embodiment, in the road network health assessment, the degree of influence of different sections and different time periods is different. Some sections may show significant health changes in specific time periods, while other sections may be relatively stable. Through the attention mechanism, it is possible to automatically identify which sections are more critical in the current analysis task and which time period changes are more influential on the assessment of the overall health status. This dynamic weighting method can adaptively adjust the attention of features and improve the accuracy and pertinence of the analysis. In terms of technical effects, the spatiotemporal attention mechanism enhances the flexibility of the network, enabling it to dynamically adjust the priority of features for different analysis tasks. This mechanism not only improves the robustness and generalization ability of the model, but also makes the road network health status assessment more refined and accurate.

[0159] In this embodiment, the graph pooling unit reduces the dimension of the graph structure through a hierarchical pooling operation, extracts global features at the road network level, and finally realizes the aggregation of health status from local to global. The graph pooling operation reduces the scale of the graph layer by layer by gradually merging adjacent nodes and edges, and maintains the main information of the graph structure at each layer. Ultimately, the pooled graph structure will extract a low-dimensional representation representing the health status of the overall road network. The core of this operation is to enable the model to better extract global information from local features by aggregating node information. In terms of technical effects, the graph pooling unit enables the model to process large-scale road network data and effectively extract global features, avoiding the problem of information loss caused by the large scale of the road network. Through the pooling operation, important information can be maintained while reducing the dimension, providing strong support for the final health status assessment and prediction.

[0160] The above components work together in different ways to enhance the model's modeling capabilities in spatial and temporal dimensions. From graph structure construction, node feature embedding to edge weight learning, to spatiotemporal graph convolution, spatiotemporal attention, and graph pooling operations, they all provide strong technical support in their specific fields and can comprehensively and accurately characterize changes in the health status of the road network. Ultimately, through this multi-dimensional and dynamic analysis framework, real-time monitoring and prediction of the health status of the road network can be achieved, providing an important basis for traffic management and decision-making.

[0161] Furthermore, cross-scale feature propagation and fusion are achieved through the following formula: r (t)=σ(∑ k∈N(r) W rk ·h k (t)+W t ·h r (t-1)+∑ s=1 S α s ·H s ), where h r(t) represents the feature vector of node r at time t; σ is the activation function, which is used to perform nonlinear transformation on the result after convolution operation; N(r) represents the set of neighbor nodes of node r; W rk is the spatial relationship weight between node r and node k; h k (t) represents the feature vector of node k at time t; W t is the weight matrix of time convolution, which reflects the influence of the state of node r at time t-1 on the state at the current time; h r (t-1) represents the feature vector of node r at time t-1; S represents the number of scales of cross-scale feature fusion; α s is the weighting coefficient of scale s; H s Represents the feature vector of the s-th scale.

[0162] The above cross-scale feature propagation and fusion formula successfully combines the advantages of spatiotemporal graph convolutional networks by introducing spatial relationship weights, temporal convolution weights, and cross-scale feature weighted fusion mechanisms, improving the accuracy and flexibility of the model in dealing with dynamic road network health status. rk and the temporal convolution weights W t The introduction of enables the model to effectively capture spatial and temporal dependencies, while cross-scale feature fusion enables the network to simultaneously consider the mutual influence between local road segment features and global road network features through multi-scale information aggregation. Ultimately, this cross-scale feature propagation and fusion framework not only improves the performance of the model, but also provides a new solution for the health assessment of complex road networks in the future.

[0163] Furthermore, the graph structure is reduced in dimension through hierarchical pooling operations, global features at the road network level are extracted, and health status aggregation from local to global is achieved, including the following steps.

[0164] An adjacency matrix is ​​constructed based on the physical connection relationship between road segments, and the initial neighborhood range is defined as the local receptive field.

[0165] Within a predefined neighborhood, a dedicated pooling function is designed to perform preliminary aggregation of node features and map the state information of adjacent road sections into a unified feature representation.

[0166] By iteratively expanding the receptive field of the pooling operation, the features are aggregated and abstracted layer by layer, and finally a global feature representation with greatly reduced dimensions but retaining key semantic information is obtained.

[0167] In this embodiment, the hierarchical pooling operation provides powerful information aggregation and feature extraction capabilities for the graph neural network. Through the construction of the adjacency matrix and the definition of the local receptive field, it is possible to focus on the important features of the local area; and the pooling function further simplifies and refines the features by summarizing the node features. In the process of expanding the receptive field of the pooling operation layer by layer, it is possible not only to capture local information more finely, but also to gradually abstract the global road network features, and finally obtain a low-dimensional global feature representation. Overall, the hierarchical pooling operation improves the efficiency and performance of the model through the feature aggregation process from local to global, enabling it to efficiently handle complex road network health status assessment tasks, and provides strong support for the optimization and decision-making of intelligent transportation systems.

[0168] Furthermore, the health assessment module includes the following components.

[0169] The real-time status analysis unit uses multi-scale feature representation and dynamic graph analysis results to calculate the health score and key performance indicators of the road surface in real time and provide current status assessment.

[0170] The deterioration trend prediction unit predicts future changes in the pavement health status and identifies potential deterioration risks based on time series analysis and machine learning algorithms.

[0171] The risk warning generation unit automatically generates warning information based on health status and predicted trends, including degradation risk level and possible impact range, to support rapid response decision-making.

[0172] The dynamic comparative analysis unit compares historical data with current assessment results, identifies abnormal changes or long-term trends, and provides data support for diagnosing the cause of degradation.

[0173] The maintenance needs assessment unit assesses the maintenance needs and urgency of each area based on the health status and risk assessment results.

[0174] In this embodiment, the core function of the real-time status analysis unit is to calculate the health score and key performance indicators of the road surface in real time. By combining multi-scale feature representation and dynamic graph analysis results, the health status of the road network at different levels and time scales can be captured. This unit first processes data from different perception layers, combines local features, road section features and global features at the network level, and provides a comprehensive health assessment for each road section, road network area and even the entire network. In terms of technical effects, it can not only evaluate the immediate health status of the current road section, but also take into account the dynamic changes of the road network structure, such as the impact of factors such as traffic flow, weather changes, and accidents on the road surface state. Based on these multi-dimensional information inputs, the real-time status analysis unit can generate high-precision health scores and provide data support for subsequent decision-making. In addition, through dynamic graph analysis, the unit can capture the spatial correlation and temporal dynamic changes between road sections, thereby ensuring that the health status assessment is timely and dynamically adaptable. Ultimately, accurate and timely assessment results are provided for road maintenance, traffic management and decision-making.

[0175] In this embodiment, the degradation trend prediction unit can not only effectively identify potential health degradation risks, but also warn of potential problems in advance. For example, the machine learning model can capture the trend of gradually increasing surface damage of a road section, and predict the health status at a certain point in the future based on historical data and existing assessment results. In this way, timely warnings can be issued before the problem becomes serious, providing forward-looking guidance for maintenance work. More importantly, the prediction algorithm can self-optimize and continuously adjust the prediction model based on new data to ensure the accuracy and timeliness of the prediction results.

[0176] In this embodiment, through comprehensive analysis of real-time health status and predicted trends, the risk warning generation unit can promptly identify risk points in the road network and provide clear decision-making basis. In terms of technical effect, the risk warning generation unit enables intelligent traffic management to achieve the transition from passive response to active warning. Through the fusion and analysis of multi-dimensional data, risk warnings of different levels can be output, and corresponding response measures can be generated according to the risk level, such as temporary closure of road sections, repair plans, etc. At the same time, the risk warning generation unit is highly flexible and can adjust the warning standards according to various factors such as specific road conditions, traffic flow, climate change, etc., to ensure the accuracy and pertinence of the warning information.

[0177] In this embodiment, the dynamic comparative analysis unit first collects historical health assessment data and compares it with the health status of the current road network, and uses differential analysis technology to identify potential health anomalies. For example, it is found that a certain section of the road surface has shown an obvious deterioration trend in the past period of time, and this trend has not appeared in the historical data. In terms of technical effect, the role of this unit is to provide data support for the causes of road damage and reveal potential factors that affect the health status of the road network, such as sudden natural disasters, excessive traffic loads, and inadequate maintenance. Through comparative analysis, potential long-term trends can also be discovered. For example, some areas may gradually show obvious health decline due to long-term neglect of maintenance, which provides a basis for management agencies to prioritize maintenance. In the end, the dynamic comparative analysis unit not only improves the accuracy of road health management, but also helps maintenance decision makers find the root cause of the problem.

[0178] In this embodiment, the maintenance needs assessment unit can realize the precise scheduling of road network maintenance work, optimize resource allocation, and improve maintenance efficiency. Compared with traditional maintenance methods, this unit can dynamically adjust the maintenance plan to ensure timely response to changes in road health. In addition, the maintenance needs assessment unit can also comprehensively evaluate the urgency of maintenance based on factors such as the frequency of use of the road section and traffic flow. For example, some frequently used urban trunk roads may show more serious health problems due to long-term accumulation of traffic loads and need to be repaired first in a short period of time. This data-driven maintenance assessment method can greatly improve the efficiency and effectiveness of maintenance work and reduce resource waste.

[0179] In summary, the various components of the health assessment module work closely together to build a comprehensive and efficient road network health management system. The real-time status analysis unit ensures accurate assessment of the health status, the degradation trend prediction unit provides forward-looking warnings for future risks, and the risk warning generation unit can provide warning information for decision-making in a timely manner. The dynamic comparative analysis unit can provide data support for the causes of degradation, while the maintenance demand assessment unit helps optimize the allocation of maintenance resources. This comprehensive assessment system not only improves the accuracy of road health management, but also greatly improves the efficiency of road network maintenance, providing strong data support and decision-making basis for traffic management departments. Through the collaborative work of these components, all-round and dynamic management from problem detection, risk prediction to resource optimization and scheduling can be achieved.

[0180] Furthermore, the future trend of road health status is predicted by the following formula: Y(τ)=μ+∑ g=1 p δ g Y(τ-g)+∑ e=1 q θ eε(τ-e)+ε(τ), where Y(τ) represents the road health score at time τ; μ is a constant term, representing the offset of the time series; p is the order of the autoregressive part; δ g represents the influence of the health status Y(τ-g) at the g-th moment on the current health status Y(τ); Y(τ-g) represents the road health status data at the time τ-g, that is, the health status value lagged by g steps; q is the order of the moving average part; θ e It represents the influence of the error term ε(τ-e) at the e-th moment on the current health state Y(τ); ε(τ-e) represents the error term at time τ-e; ε(τ) represents the error term at time τ.

[0181] The potential degradation risk is identified by the following formula: R(τ)=1 / [1+exp(-γ·(Y(τ)-Y threshold ))], where R(τ) represents the pavement deterioration risk index at time τ, which is used to quantify the potential deterioration risk. The larger the value, the higher the risk. Y threshold represents the threshold of the health state, which is used to distinguish between the healthy and deteriorated states; γ is the sensitivity parameter of the risk index, which is used to control the pavement health state Y(τ) and the threshold Y threshold The degree of influence of the differences between them on the risk index R(τ).

[0182] In summary, the model combining autoregression and moving average makes the prediction of health status not only historically dependent, but also flexible in responding to changes in environmental factors. At the same time, the degradation risk identification method provides managers with an intuitive risk assessment tool by dynamically calculating the risk index, which helps them identify potential road problems at an early stage and respond in a timely manner. In addition, it can also achieve all-round intelligent management from health status assessment, trend prediction to risk identification, thereby providing scientific decision-making support for road maintenance work, reducing maintenance costs, and improving road safety and operational efficiency.

[0183] Furthermore, the decision visualization module includes the following components.

[0184] The data access unit accesses monitoring data, prediction results and warning information in real time, providing a dynamically updated data source for visualization.

[0185] The map display unit, based on geographic information system technology, intuitively displays the road network health status, disease distribution and warning information in the form of heat maps or layered maps.

[0186] The chart generation unit displays the pavement health index, degradation trend and risk assessment results through line charts or bar charts, allowing managers to quickly grasp the overall status.

[0187] The early warning prompt unit highlights high-risk sections or sudden hazards in the visual interface, and combines color coding and pop-up reminders to ensure that early warning information is conveyed in a timely manner.

[0188] The decision recommendation unit automatically generates maintenance decision recommendations including regional priority rankings based on health assessment results and maintenance needs assessment, and presents them in structured text or chart form.

[0189] The interactive operation unit provides user interaction functions, supporting managers to view detailed data and adjust decision parameters as needed.

[0190] The report generation unit automatically generates visual reports that summarize monitoring data, assessment results and decision-making recommendations for easy archiving and sharing.

[0191] In this embodiment, the core role of the data access unit is to ensure the dynamic update and timeliness of the data to support the real-time monitoring and evaluation functions of the decision visualization platform. Specifically, the data access unit can summarize and integrate information from different sensors (such as road condition sensors, meteorological sensors, etc.) and external data sources (such as traffic flow data, weather forecasts, etc.). The unit ensures that decisions can be made in real time based on the latest data to prevent decision errors caused by data delays or distortions. For example, if a section of the road surface is suddenly damaged or the weather changes, the unit can promptly transmit this information to the decision maker to ensure that response suggestions can be provided in the shortest time and reduce the potential impact of the emergency. In addition, the unit can also ensure data synchronization across platforms and devices, and ensure the flexibility and scalability of data access.

[0192] In this embodiment, the core technical effect of the map display unit is to convert complex health status information into an intuitive and easy-to-understand visual display in a graphical way, which greatly enhances the user's perception of the health status of the road network. The heat map uses color depth to show changes in health status, thereby helping managers quickly identify sections of road with poor health or greater potential risks, making it easier to formulate targeted maintenance plans. The layered map can display different information through different layers. For example, one layer displays the health index of a section of road, and another layer displays the type and location of the disease, further enhancing the readability of the data and the accuracy of the decision. The unit also supports dynamic updates, and can automatically refresh the map when new data is received to maintain the real-time and accuracy of the data. In terms of technical effects, this geographic information display method not only improves the interactivity of the data, but also helps managers quickly grasp the overall situation and make more timely and effective decisions.

[0193] In this embodiment, by combining historical data and predicted data, the line graph can clearly show the trend of the road health index over time, which helps to identify potential health problems in a timely manner. The bar graph is suitable for displaying the health assessment results and risk assessments of different sections or areas. By comparing the data of different areas, it can help managers clearly know which sections or areas are in poor health and need priority treatment. In terms of technical effects, the chart generation unit can convert large amounts of complex data information into concise and clear charts, significantly improving the efficiency of data analysis and the accuracy of decision-making. In addition, the chart generation unit supports a variety of graphic display formats and personalized customization to meet the diverse requirements of different management levels and decision-making needs.

[0194] In this embodiment, the core function of the early warning prompt unit is to display high-risk road sections or sudden disease conditions in a timely manner to ensure that managers can quickly respond to potential dangers. For example, when a road section has a disease or the road health index is lower than a predetermined threshold, an early warning will be automatically issued, and a red highlight mark, pop-up window or sound prompt will be used to provide a significant reminder to ensure that managers pay attention to key issues as soon as possible. In terms of technical effects, the early warning prompt unit helps managers distinguish different types of risks through different colors and visual effects, and can automatically generate early warnings through set thresholds, improving the response speed and accuracy of the entire system.

[0195] In this embodiment, the core technical effect of the decision-making suggestion unit is to automatically generate maintenance decision suggestions through data analysis and model prediction, reduce manual intervention, and improve the scientificity and efficiency of decision-making. The unit combines multiple factors, such as road health, potential risk level, traffic flow, historical maintenance records, etc., calculates the priority of different road sections, and generates an operational maintenance plan. The generated decision suggestions can be presented in the form of charts or reports to help managers clearly understand the maintenance needs of each area, and can allocate resources and arrange maintenance according to priority. In terms of technical effects, this automated decision support greatly improves the accuracy and planning of maintenance work, helps to optimize resource allocation and avoid waste of resources. At the same time, the decision-making suggestion unit can flexibly adjust the decision suggestions based on real-time updated data, so that maintenance work can keep up with changes in the health status of the road network in a timely manner.

[0196] In this embodiment, the interactive operation unit allows the user to interact with the system through the interface, flexibly select the area, time period or data dimension of interest, and perform customized query and analysis. For example, the manager can select a section of road surface for detailed viewing, analyze its historical health status, predict future trends, or view relevant early warning information. At the same time, the interactive operation unit also allows the user to adjust some parameters, such as early warning thresholds, maintenance priority standards, etc., to meet different management needs. In terms of technical effects, the interactive operation unit improves the flexibility of decision-making and user experience, allowing managers to customize the operation process according to their own needs and obtain personalized data analysis results.

[0197] In this embodiment, the report generation unit can generate reports in different formats according to management needs, including PDF reports, Excel tables or PowerPoint presentations, summarize various types of data and present them clearly. Through the generation of reports, it is possible to easily view, print or share the generated analysis results, providing strong data support for subsequent work or reporting to superiors. In terms of technical effects, the report generation unit greatly improves the efficiency and accuracy of report generation through automated operations, avoiding errors or omissions that may occur in the manual report writing process. At the same time, the standardized format of the report also improves the clarity and consistency of information transmission, which helps to improve the transparency of the decision-making process.

[0198] In summary, the decision visualization module realizes the visualization of functions such as road health assessment, early warning, and maintenance suggestions through the collaborative work of various components, significantly improving managers' control over the health status of the road network. The data access unit ensures the real-time update and accuracy of data, the map display unit improves the readability of information through graphical methods, and the chart generation unit makes data analysis more intuitive and easy to understand. The early warning prompt unit and the decision suggestion unit reduce the errors and delays of manual operations through automated early warning and decision support, while the interactive operation unit provides flexible customized query functions, and the report generation unit improves the efficiency of information archiving and sharing. Through the synergy of this series of components, the decision visualization module provides efficient and accurate intelligent decision support for the health management of the road network, helping managers make timely and effective maintenance decisions, optimize resource allocation, and improve the safety and economy of road operation.

[0199] like Figure 2 As shown, a method for monitoring the health status of an asphalt pavement includes the following steps.

[0200] The static characteristic data and dynamic monitoring data of asphalt pavement are collected in real time through the sensor network.

[0201] The collected heterogeneous data are aligned in time and space, and wavelet transform is used for noise reduction and standardization to construct a multimodal fusion dataset.

[0202] Based on the feature pyramid network, adaptive fusion of multi-scale features is achieved to build a systematic road condition representation system.

[0203] Combining the spatiotemporal graph convolutional network and the self-attention mechanism, the dynamic change characteristics of the road network are extracted, and the multi-level aggregation and representation of features are achieved through the layered graph pooling method.

[0204] Multi-dimensional risk identification is achieved based on historical data and real-time monitoring data, and the priority of maintenance needs is determined through quantitative comparative analysis of multi-dimensional factors.

[0205] Based on the geographic information system platform, the monitoring data, assessment results and early warning information can be visualized, and intelligent suggestions can be provided for maintenance decisions.

[0206] In this embodiment, the sensor network can realize dynamic monitoring with full coverage at all times. The collected data includes not only conventional static characteristic data (such as temperature, humidity, pavement structural characteristics, etc.), but also dynamic data related to traffic flow (such as load changes, pavement vibration, etc.), which provides all-round data support for a comprehensive understanding of the health of the pavement. Since the pavement status will change with factors such as weather and traffic flow, the collection of real-time data can reflect these changes in a timely manner, providing higher timeliness and accuracy for subsequent analysis. In addition, the distributed characteristics of the sensor network make the monitoring system highly scalable, and monitoring points can be added or adjusted at any time according to demand to meet the needs of monitoring road networks of different scales.

[0207] In this embodiment, in order to achieve effective data fusion, it is necessary to perform spatiotemporal alignment processing on these heterogeneous data. Spatiotemporal alignment mainly unifies the time and space dimensions of the collected data for subsequent analysis and fusion. For example, different types of sensors have different sampling frequencies and timestamps, which requires the use of algorithms to synchronize the data so that the states of data from different sensors at the same time and the same position can accurately correspond. In addition, data denoising and standardization are to improve data quality, reduce noise interference that may occur during the acquisition process, and ensure the availability of data. Wavelet transform, as a powerful signal processing method, can effectively perform data denoising. Through wavelet transform, the signal can be decomposed into multiple scales, and the noise at different scales can be removed respectively, thereby retaining the effective information in the original signal. The standardized processing of data ensures the dimensional consistency of different data sources, so that different types of data can be effectively compared and fused.

[0208] In this embodiment, the adaptive fusion of multi-scale features based on the feature pyramid network (FPN) is one of the key steps in the health status monitoring of asphalt pavement. The assessment of the health status of asphalt pavement needs to comprehensively consider the feature information of different scales, and these feature information may involve different time and space scales. For example, there may be small-scale pavement cracks in the short term, while there may be more serious settlement or structural damage in the long term. The feature pyramid network can adaptively extract valuable information from features of different scales, effectively fuse features at different scales, and construct a systematic pavement status characterization system. Specifically, FPN can jointly model pavement damage or health status of different scales through multi-level feature extraction and fusion, and realize the full-scale characterization of complex pavement structures. In terms of technical effect, this process can improve the sensitivity and accuracy of the pavement health status monitoring system, especially in the face of complex and changeable pavement health status, FPN can perform reasonable feature extraction and weighted fusion at different scale levels, thereby improving the accuracy of health assessment and ensuring that pavement damage can be effectively identified in the early stage.

[0209] In this embodiment, the health status of the road network is not only related to a single road section, but often has spatiotemporal correlation, that is, the health status of the road section is affected by factors such as the surrounding environment and traffic flow. The spatiotemporal graph convolutional network can effectively capture this spatiotemporal dependency, and perform information propagation and feature extraction on the spatiotemporal graph structure through graph convolution, thereby mining the interaction and influence between the sections in the road network. At the same time, the self-attention mechanism can automatically adjust the weight according to the importance of the data, strengthen the expression of key features, and suppress the influence of irrelevant features. This technical combination can not only extract the dynamic change characteristics of the road health status, but also predict the health status of different regions and time points according to the characteristics of the spatiotemporal graph network. In terms of technical effects, through the combination of the spatiotemporal graph convolutional network and the self-attention mechanism, the correlation and dynamic change trend between the sections in the road network can be more accurately identified, providing more accurate feature input for subsequent health assessment and risk prediction, and improving the system's prediction ability and real-time response ability.

[0210] In this embodiment, through the comprehensive analysis of historical data and real-time monitoring data, the risk status of different road sections can be fully identified. The multi-dimensional risk identification method quantitatively evaluates the health of the road surface by considering multiple factors, such as traffic flow, weather changes, load conditions, etc., so as to accurately identify potential high-risk sections. In terms of technical effect, this step can determine the priority of maintenance needs through quantitative comparative analysis of factors of different dimensions. For example, some sections may need to be repaired first due to large traffic flow and heavy load, while other sections may only require routine maintenance. Through this precise risk identification, strong support can be provided for maintenance decisions, ensuring that maintenance resources can be reasonably allocated according to the actual needs of the road section to avoid waste of resources.

[0211] In this embodiment, the Geographic Information System (GIS) platform can intuitively present complex road health status information in the form of a map, so that managers can clearly see the health status of different road sections, the distribution of potential diseases and early warning information. This geographic information display method allows managers to directly view the specific conditions of the road section on the map, and conduct spatial analysis and decision support. In addition, the GIS platform can also provide managers with intelligent maintenance decision-making suggestions based on system analysis results. In terms of technical effects, the visual presentation of the GIS platform can not only improve the intuitiveness and ease of use of information, but also enhance the transparency of data analysis and decision-making. Combined with real-time monitoring data and historical analysis results, managers can be provided with accurate maintenance suggestions and early warning information to help them optimize maintenance plans according to actual conditions and improve the efficiency and economy of road maintenance.

[0212] In summary, this asphalt pavement health status monitoring method realizes the whole process monitoring from data collection to health assessment, risk identification and decision support by combining advanced sensor networks, data processing technology and deep learning models. The sensor network provides comprehensive and real-time data support, data preprocessing ensures data quality, the combination of feature pyramid network and spatiotemporal graph convolution network improves the accuracy and dynamic response capability of the system, risk identification and maintenance demand assessment ensure the optimal allocation of resources, and the visualization display of GIS platform improves the transparency and efficiency of decision-making. Through this systematic approach, asphalt pavement health status monitoring can provide accurate and intelligent maintenance decision support to ensure the safety and reliability of the pavement during its service life cycle.

[0213] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An asphalt pavement health status monitoring system, characterized in that: Includes the following modules: Multi-source data acquisition module, used to obtain road surface status parameters in real time; Data processing module, used for spatiotemporal alignment, quality assessment, exception handling and standardization of collected multi-source data; Multi-scale feature extraction module, which is used to extract features from microscopic damage, road section status and network level, and build a multi-scale feature representation system; Dynamic graph analysis module, used to build a hierarchical dynamic graph structure to achieve unified modeling and analysis of road network health status; Health assessment module, used to achieve real-time assessment of pavement health status, deterioration trend prediction and risk warning; The decision visualization module is used to display monitoring data, prediction results and early warning information, and automatically generate maintenance decision recommendations based on the evaluation results.

2. The asphalt pavement health status monitoring system according to claim 1, characterized in that: The multi-source data acquisition module includes the following components: Static sensor unit, which continuously monitors the static changes of pavement structure and materials through sensors installed on the pavement, providing basic pavement health data; Dynamic collection equipment unit, which uses mobile equipment to collect road surface status data in real time and obtain dynamic load and road surface deformation information; Environmental monitoring equipment, which collects external environmental data related to the road surface condition; A vibration sensor unit, which uses vibration sensors to capture the vibration of the road surface under different loads; An image acquisition unit uses a high-definition camera to capture road surface images in real time; The equipment operation monitoring unit monitors the operating status of each data acquisition device, detects equipment failures in a timely manner and performs necessary equipment maintenance.

3. The asphalt pavement health status monitoring system according to claim 1, characterized in that: The data processing module includes the following components: The spatiotemporal alignment unit is responsible for spatiotemporal alignment of time series data from different data sources to ensure that all types of data can accurately reflect the road surface status in the same time and space range; Data quality assessment unit, responsible for quality assessment and self-calibration of various types of collected data, identifying data integrity, accuracy and validity; The exception handling unit is responsible for correcting or eliminating abnormal data; Data standardization unit, responsible for converting data from different sources into a unified standard format and dimension; A data fusion unit that combines data from multiple sources into a high-precision comprehensive dataset; The data synchronization and update unit is used to achieve consistency and real-time update of multi-source data at different processing stages.

4. The asphalt pavement health status monitoring system according to claim 1, characterized in that: The multi-scale feature extraction module includes the following components: Microscopic feature extraction unit, which captures the detailed features of pavement microscopic diseases through high-resolution convolutional layers; The road segment feature extraction unit uses a convolutional layer with a medium receptive field to extract state features at the road segment level; The network-level feature extraction unit uses a global pooling layer to extract macro features at the road network level; Multi-scale feature fusion unit, which integrates microscopic, section-level and network-level features to build a unified multi-scale representation system and achieve a comprehensive description of the road surface status; Scale interaction unit, using feature pyramid structure to promote information interaction between features of different scales; The feature enhancement unit enhances the distinguishability and robustness of features through feature normalization operations to improve the adaptability to complex road conditions.

5. The asphalt pavement health status monitoring system according to claim 4, characterized in that: The microscopic, segment and network-level features are integrated to build a unified multi-scale characterization system to achieve a comprehensive characterization of the road surface state, including the following steps: By designing a multi-branch neural network structure, the features at the micro, road segment and network levels are processed respectively, and the importance weights of features at different scales are learned using the attention mechanism, and the features at the three levels are integrated; The fused features are converted into a fixed-dimensional vector representation through mapping, so that it contains not only microscopic behavioral patterns, but also mesoscopic road section status and macroscopic network characteristics, thereby achieving a comprehensive characterization of the road surface status.

6. The asphalt pavement health status monitoring system according to claim 1, characterized in that: The dynamic graph analysis module includes the following components: The graph structure building unit abstracts the road network into a hierarchical dynamic graph structure, where nodes represent road sections and edges represent connection relationships, providing a basic topological structure for modeling the health status of the road network; The node feature embedding unit embeds the output results of the multi-scale feature extraction module into the graph nodes to represent the health status and attribute information of each road segment; The edge weight learning unit learns the weights of the edges between nodes through an adaptive mechanism, dynamically reflecting the spatial correlation and influence intensity between road sections; The spatiotemporal graph convolution unit uses the spatiotemporal graph convolution network to simultaneously capture the spatial dependency and temporal dynamic changes of the road network, achieving cross-scale feature propagation and fusion; The spatiotemporal attention unit introduces an attention mechanism to dynamically assign importance weights to different nodes and time periods; The graph pooling unit reduces the dimension of the graph structure through hierarchical pooling operations, extracts global features at the road network level, and realizes the aggregation of health status from local to global.

7. The asphalt pavement health status monitoring system according to claim 6, characterized in that: The graph structure is reduced in dimension through hierarchical pooling operations, global features at the road network level are extracted, and health status aggregation from local to global is achieved, including the following steps: Construct an adjacency matrix based on the physical connection relationship between road segments, and define the initial neighborhood range as the local receptive field; In the predefined neighborhood, a dedicated pooling function is designed to perform preliminary aggregation of node features and map the state information of adjacent road sections into a unified feature representation. By iteratively expanding the receptive field of the pooling operation, the features are aggregated and abstracted layer by layer, and finally a global feature representation with greatly reduced dimensions but retaining key semantic information is obtained.

8. The asphalt pavement health status monitoring system according to claim 1, characterized in that: The health assessment module includes the following components: Real-time status analysis unit, which uses multi-scale feature representation and dynamic graph analysis results to calculate the health score and key performance indicators of the road surface in real time; Deterioration trend prediction unit, based on time series analysis and machine learning algorithms, predicts future trends in pavement health and identifies potential deterioration risks; The risk warning generation unit automatically generates warning information based on the health status and predicted trends, including the degradation risk level and possible impact range; Dynamic comparative analysis unit, which compares historical data with current assessment results to identify abnormal changes or long-term trends; The maintenance needs assessment unit assesses the maintenance needs and urgency of each area based on the health status and risk assessment results.

9. The asphalt pavement health status monitoring system according to claim 1, characterized in that: The decision visualization module includes the following components: Data access unit, which accesses monitoring data, prediction results and warning information in real time, and provides a dynamically updated data source for visualization; The map display unit, based on geographic information system technology, visually displays the health status of the road network, disease distribution and warning information in the form of heat maps or layered maps; A chart generation unit that displays the pavement health index, deterioration trend, and risk assessment results through line charts or bar charts; Early warning unit, which highlights high-risk sections or sudden damage in a visual interface, combining color coding and pop-up reminders; The decision-making recommendation unit automatically generates maintenance decision recommendations including regional priority rankings based on health assessment results and maintenance needs assessment, and presents them in the form of structured text or charts; Interactive operation unit, which provides user interaction functions and supports managers to view detailed data and adjust decision parameters as needed; The report generation unit automatically generates visual reports summarizing monitoring data, evaluation results and decision-making recommendations.

10. A method for monitoring the health status of an asphalt pavement, implemented based on an asphalt pavement health status monitoring system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Collect static characteristic data and dynamic monitoring data of asphalt pavement in real time through sensor network; The collected heterogeneous data are aligned in time and space, and the wavelet transform is used for noise reduction and standardization to construct a multimodal fusion data set; Adaptive fusion of multi-scale features is achieved based on feature pyramid network, and a systematic road condition representation system is constructed; Combine the spatiotemporal graph convolutional network and the self-attention mechanism to extract the dynamic change characteristics of the road network, and realize the multi-level aggregation and representation of the features through the layered graph pooling method; Achieve multi-dimensional risk identification based on historical data and real-time monitoring data, and determine the priority of maintenance needs through quantitative comparative analysis of multi-dimensional factors; Based on the geographic information system platform, the monitoring data, assessment results and early warning information can be visualized, and intelligent suggestions can be provided for maintenance decisions.

Images