Asphalt pavement disease intelligent identification and preventive maintenance analysis system

Abstract

The invention relates to the technical field of road engineering operation and maintenance, and discloses an asphalt pavement disease intelligent identification and preventive maintenance analysis system which comprises a material modeling module, a multi-source sensing module, a damping inversion module and a maintenance decision module. The material modeling module constructs a heat and humidity transfer characteristic model based on material attributes and outputs an initial performance state vector; the multi-source sensing module collects field environment excitation, internal structure response and traffic load data; the damping inversion module calculates a functional attenuation index representing micro-pore characteristics by comparing heat and humidity transfer lag differences of a theoretical model and actually measured data, and calculates a comprehensive health degree index in combination with a load, and the maintenance decision-making module identifies whether the pavement is in a functional hidden danger period or a structural fatigue period based on a dual-threshold judgment logic, and determines whether the pavement is in a non-functional hidden danger period or a structural fatigue period. And correspondingly generating a chemical restoration or physical restoration scheme. Quantitative recognition of early-stage hidden water damage is achieved through a heat and humidity damping inversion mechanism, functional attenuation and structural damage are decoupled, and preventive maintenance scheme matching is achieved.

Description

Technical Field

[0001] This invention relates to the field of road engineering operation and maintenance technology, specifically to an intelligent identification and preventive maintenance analysis system for asphalt pavement defects. Background Technology

[0002] Asphalt pavement, as a major form of highway transportation infrastructure, is subject to the combined effects of traffic loads and the natural environment during its long-term service life. Water damage is one of the main causes of early pavement performance degradation. Moisture intrusion into the pavement structure causes asphalt film peeling and mixture loosening, subsequently inducing macroscopic defects such as potholes and cracks, severely shortening the road's service life. Therefore, implementing scientific preventative maintenance is of great significance for maintaining pavement service levels and reducing total life-cycle maintenance costs.

[0003] Current asphalt pavement distress detection technologies primarily rely on manual inspections, vehicle-mounted camera image recognition, and ground-penetrating radar detection. These conventional methods focus on capturing apparent geometric defects on the pavement surface or obvious physical discontinuities within, such as cracks, voids, or obvious loose areas. However, the evolution of pavement water damage is a gradual process from microscopic to macroscopic. Before visible cracks appear or structural strength drops sharply, the microscopic pore structure and hydrophilic / hydrophobic properties of the pavement material have already changed. Existing detection methods lack sufficient sensitivity to this early, hidden material functional degradation, making it difficult to effectively identify the distress during its incubation period. This often leads to the distress being discovered only when it has progressed to the stage of structural damage, thus missing the optimal window for preventative treatment.

[0004] Furthermore, existing pavement condition evaluation systems typically use comprehensive indicators such as the Pavement Condition Index (PCI) to score pavement health. While these aggregated evaluation indicators can reflect the overall service level of the pavement, they struggle to decouple the analysis of the physical properties of the defects. Specifically, existing evaluation methods cannot accurately distinguish whether pavement performance degradation is caused by functional decline at the material level (such as loss of hydrophobicity and microscopic leakage) or by mechanical fatigue at the structural level (such as base course cracking and reduced load-bearing capacity). Due to the lack of precise definition of the evolution stage and essential attributes of defects, maintenance decisions often tend to adopt uniform engineering measures. For example, milling and repaving may be mistakenly chosen when only surface function restoration is needed, or only surface sealing may be applied when substantial structural damage has occurred, resulting in wasted maintenance resources or incomplete engineering remediation. Current technologies lack an analytical system that can combine the material's heat and moisture transfer mechanism, invert microscopic defect characteristics through dynamic response differences, and formulate targeted maintenance strategies based on this classification. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent identification and preventive maintenance analysis system for asphalt pavement defects. This system solves the problems in existing technologies, such as the difficulty in quantitatively identifying early-stage hidden water damage to asphalt pavements and the difficulty in distinguishing between functional degradation and structural fatigue, which leads to delayed maintenance timing and mismatched measures.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent identification and preventive maintenance analysis system for asphalt pavement defects, comprising:

[0007] The materials modeling module is used to construct a heat and moisture transfer characteristic model of the pavement structure based on the material mix data and laboratory mechanical performance indicators of asphalt pavement, and output the initial performance state vector.

[0008] The multi-source sensing module is deployed at the road service site to collect real-time data on external environmental excitation, internal structural response, and traffic load.

[0009] The damping inversion module is connected to the material modeling module and the multi-source sensing module respectively, and is used to receive the initial performance state vector and the dynamic data collected on site. The damping inversion module calculates the functional attenuation index that characterizes the changes in the micro-pore characteristics of the road surface by comparing the difference between the theoretical heat and moisture transfer model and the actual response data, and calculates the comprehensive health index that characterizes the macro-mechanical performance of the road surface by combining traffic load data.

[0010] The maintenance decision module, connected to the damping inversion module, is used to make a dual threshold judgment based on the functional decay index and the comprehensive health index, identify the current stage of pavement disease evolution, and generate corresponding preventive maintenance plan instructions.

[0011] Preferably, the material modeling module includes a component performance calibration unit, which performs the following calculation logic to generate the initial performance state vector:

[0012] Calculate the water-repellent efficiency factor based on the water absorption rate inhibition ratio of the mixture;

[0013] Calculate the compaction performance factor based on the mapping relationship between water-binder ratio and dynamic modulus;

[0014] Water retention efficiency factor calculated based on extreme shrinkage strain;

[0015] The water-repellent efficiency factor, the density efficiency factor, and the water-retention efficiency factor are encapsulated into the initial performance state vector.

[0016] Preferably, the multi-source sensing module includes:

[0017] An environmental sensing unit is used to collect the external environmental stimulus data, including atmospheric temperature, atmospheric humidity, and rainfall.

[0018] An internal response acquisition unit is used to acquire the base temperature and dielectric constant inside the road structure as the internal structure response data;

[0019] The load monitoring unit is used to collect the cumulative number of axle loads acting on the road surface, which is used as the traffic load data.

[0020] Preferably, the damping inversion module includes a theoretical reference value calculation unit and a dynamic parameter identification unit:

[0021] The theoretical reference value calculation unit is used to input the initial performance state vector into the heat and moisture transfer differential equation and solve it to obtain the theoretical environmental response hysteresis time constant of the pavement structure to the external environmental excitation data under the ideal undamaged state.

[0022] The dynamic parameter identification unit is used to perform cross-correlation analysis on the synchronously collected atmospheric temperature time series and base layer temperature time series to identify the actual lag time constant under the actual service state of the road surface.

[0023] Preferably, the damping inversion module further includes a functional degradation assessment unit:

[0024] The functional degradation assessment unit calculates the deviation between the theoretical environmental response hysteresis time constant and the actual hysteresis time constant, and corrects the deviation using the measured dielectric constant to obtain the functional degradation index.

[0025] The functional decay index is used to quantitatively characterize the changes in the connectivity of the micropore structure inside the pavement material caused by water erosion.

[0026] Preferably, the damping inversion module further includes a comprehensive health evaluation unit:

[0027] The comprehensive health evaluation unit uses grey relational analysis to select the cumulative number of axle loads, dielectric constant, and functional decay index to construct a comparison sequence. Taking the ultimate state of the pavement design life as a reference sequence, the grey relational coefficients of each parameter are calculated and weighted summed to obtain the comprehensive health index.

[0028] Preferably, the maintenance decision module is preset with functional early warning thresholds and structural safety thresholds, and executes the following judgment logic:

[0029] If the functional degradation index is less than the functional warning threshold and the comprehensive health index is greater than the structural safety threshold, the road surface is determined to be in a stable service period.

[0030] If the functional degradation index is greater than or equal to the functional warning threshold, and the comprehensive health index is greater than the structural safety threshold, the road surface is determined to be in a period of functional hazard.

[0031] If the comprehensive health index is less than or equal to the structural safety threshold, the road surface is determined to be in a period of structural fatigue.

[0032] Preferably, the maintenance decision module includes a scheme generation unit, used to generate instructions based on the judgment result:

[0033] When the road surface is determined to be in the aforementioned functional hazard period, a chemical functional restoration plan instruction is generated, which includes construction parameters for spraying a penetrating water-repellent agent.

[0034] When the road surface is determined to be in the structural fatigue period, a physical structure repair plan instruction is generated, which includes construction parameters for road surface milling and repaving or high-pressure grouting.

[0035] Preferably, the maintenance decision-making module further includes a benefit evaluation unit:

[0036] The benefit evaluation unit is used to calculate the dynamic input-output ratio of the maintenance plan in conjunction with the disease evolution rate;

[0037] The preventive maintenance plan instruction is output only when the dynamic input-output ratio is greater than the preset benefit threshold; otherwise, the road surface is added to the continuous observation queue.

[0038] Preferably, when constructing the differential equation for heat and moisture transfer, the theoretical reference value calculation unit maps the water-repellent efficiency factor in the initial performance state vector to the moisture diffusion coefficient parameter of the equation, maps the density efficiency factor to the thermal conductivity parameter of the equation, and introduces the atmospheric humidity and rainfall data collected by the environmental sensing unit as the dynamic boundary conditions of the equation to construct a theoretical heat transfer model that reflects the specific material properties of the road surface and the real-time environmental humidity.

[0039] This invention provides an intelligent identification and preventive maintenance analysis system for asphalt pavement defects. It has the following beneficial effects:

[0040] 1. This invention uses the deviation in the heat and moisture transfer lag time constant to invert the internal state of the road surface by comparing the differences between the theoretical heat and moisture transfer model and the actual response data. Compared with traditional techniques that rely on visible surface cracks or deformation for judgment, this system can utilize the sensitivity of the material's thermal damping characteristics to detect changes in the connectivity of the road surface's micro-pore structure caused by water erosion before macroscopic structural damage is apparent, thereby achieving early quantitative identification of hidden water damage.

[0041] 2. This invention establishes a dual-threshold judgment logic based on the functional degradation index and the comprehensive health index, enabling refined classification of pavement distress evolution stages. This mechanism effectively solves the problem that existing single evaluation indicators cannot distinguish between the physical and chemical properties of distress, accurately identifying pavements in the functional hazard stage and generating targeted chemical functional restoration plans, thus avoiding resource waste caused by prematurely adopting physical repair methods such as milling and repaving due to confusion of distress types.

[0042] 3. This invention introduces a component performance calibration unit in the material modeling stage, mapping water-repellent, dense, and water-retaining performance factors to coefficients of the heat and moisture transfer equation, and combining real-time environmental data as dynamic boundary conditions. This design enables the theoretical model to adapt to specific material properties and environmental changes in different road sections, improving the accuracy of baseline value calculations; combined with the dynamic input-output ratio calculation of the benefit evaluation unit, it ensures that maintenance instructions are issued only when economically reasonable, preventing excessive intervention in pavements during their stable service life. Attached Figure Description

[0043] Figure 1 This is a system framework diagram of the present invention;

[0044] Figure 2 This is a schematic diagram of the logical structure of the material modeling module of the present invention;

[0045] Figure 3 This is a schematic diagram of the logical structure of the multi-source sensing module of the present invention;

[0046] Figure 4 This is a schematic diagram of the logic structure of the damping inversion module of the present invention;

[0047] Figure 5 This is a schematic diagram of the hierarchical early warning logic of the maintenance decision module of the present invention.

[0048] Among them, 100 is the material modeling module; 200 is the multi-source sensing module; 300 is the damping inversion module; and 400 is the maintenance decision module. Detailed Implementation

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Please see the appendix Figure 1 This invention provides an intelligent identification and preventive maintenance analysis system for asphalt pavement defects, comprising:

[0051] The material modeling module 100 is configured to establish a digital material model of the target pavement. It receives the chemical composition parameters and laboratory mechanical performance indicators of high-toughness crack-resistant cement-stabilized crushed stone material, and maps the parameters and indicators into an initial performance state vector. The initial performance state vector includes a water-repellent efficiency factor characterizing hydrophobicity, a dense efficiency factor characterizing crystal density, and a water-retaining efficiency factor characterizing water adsorption capacity.

[0052] The multi-source sensing module 200 is configured to collect dynamic data during the service of the road surface, including external environmental excitation data such as atmospheric temperature, atmospheric relative humidity and rainfall, internal structural response data including the internal temperature and dielectric constant of the base layer, and traffic load data including the cumulative number of axle loads.

[0053] The damping inversion module 300 is connected to the material modeling module 100 and the multi-source sensing module 200 respectively. It is configured to calculate the theoretical environmental response lag time constant based on the initial performance state vector, identify the actual lag time constant based on external environmental excitation data and internal structural response data, calculate the functional decay index based on the deviation between the theoretical lag time constant and the actual lag time constant, and calculate the comprehensive health index in combination with the grey relational analysis model.

[0054] The maintenance decision module 400, connected to the damping inversion module 300, is configured to receive the functional attenuation index and the comprehensive health index. It compares these against a preset decision logic library to determine whether the pavement is in a functional hazard period, a micro-crack propagation period, or a structural fatigue period, and generates a chemical function restoration plan or a physical structure repair plan accordingly.

[0055] The following sections will elaborate on each of the above modules in conjunction with specific computational logic and control strategies.

[0056] See attached document Figure 2 , Figure 2 This is a schematic diagram of the logical structure of a material modeling module according to an embodiment of the present invention.

[0057] The material modeling module 100 includes a data input unit, a component performance calibration unit, and a feature vector generation unit. The material modeling module 100 is used to convert the physicochemical properties of high-toughness, crack-resistant cement-stabilized crushed stone materials into initial performance state vectors that can be computed by the computer system.

[0058] The data entry unit is configured to receive material proportioning data and admixture component data for the target pavement base course. The admixture component data includes the mass percentage or dosage information of specific chemical components in the high-toughness composite admixture. These specific chemical components include methyl allyl alcohol polyoxyethylene ether, methacrylic acid, cellulose, polymer nanomaterials, and propylene glycol. The data entry unit also receives basic mechanical performance indicators based on this material proportion, measured in a laboratory environment. These basic mechanical performance indicators include at least the unconfined compressive strength, flexural tensile strength, maximum dry density, and optimum moisture content under standard curing conditions.

[0059] The component performance calibration unit calculates the water-repellent performance factor based on the content of copolymers formed by the condensation of organosilicones and acrylates in the high-toughness composite admixture and the water absorption inhibition ratio. During the calculation, the saturated water absorption rate of the baseline mixture without the admixture was obtained over the standard test duration. The saturated water absorption rate of the mixture with this additive under the same conditions is... . The computational logic satisfies the following relationship:

[0060] ;

[0061] In the formula, This indicates the saturated water absorption rate of the baseline mixture without this admixture during the standard test duration. This indicates the saturated water absorption rate of the mixture containing this additive under the same conditions. The first correction factor is used to eliminate calculation errors caused by differences in aggregate porosity, and its value ranges from 0.85 to 1.15. In this embodiment, when the water absorption rate of coarse aggregate is less than 1.0%, The value is 1.0; when the water absorption rate of coarse aggregate is greater than or equal to 1.0%, The value is 1.05.

[0062] The component performance calibration unit calculates the density performance factor based on the water-reducing effect and crystal density of polycarboxylic acid substances. The component performance calibration unit combines the water-cement ratio reduction rate and the rebound modulus improvement rate for comprehensive calculation. The calculation logic is based on the following formula:

[0063] ;

[0064] In the formula, The water-cement ratio is the baseline mixing ratio. This is the actual water-cement ratio after adding admixtures. The 7-day or 28-day compressive resilience modulus of the reference material. The compressive resilient modulus of the modified material. and Assign coefficients to the weights, and satisfy the following conditions: In this embodiment, the focus is on considering the material's density to counteract the effects of thermal shrinkage, and the following settings are made: The value is 0.6. The value is 0.4.

[0065] The component performance calibration unit calculates the water retention efficiency factor based on the water retention effect of polysaccharide polymers and polyethylene graft copolymers and the attenuation rate of limiting shrinkage strain. The limiting shrinkage strain when the water loss rate of the reference material reaches 100% is set as follows. The limiting shrinkage strain of the modified material is , The calculation follows the following definition:

[0066] ;

[0067] In the formula, Indicates water retention efficiency factor, This represents the ultimate drying shrinkage strain of the reference material. This represents the limiting shrinkage strain of the modified material.

[0068] It is directly related to the stability of the internal humidity gradient of the material. The higher the value, the stronger the material's ability to retain moisture in a dry environment and the better its ability to resist drying shrinkage cracks.

[0069] The eigenvector generation unit receives the eigenvectors calculated by the component performance calibration unit. , and And encapsulate it into an initial performance state vector. .

[0070] The feature vector generation unit generates the initial performance state vector. The data is stored in the system database and sent as static reference parameters to the damping inversion module 300 for subsequent calculation of the theoretical values ​​of the environmental response damping characteristics.

[0071] See attached document Figure 3 , Figure 3 This is a schematic diagram of the logical structure of a multi-source sensing module according to an embodiment of the present invention.

[0072] The multi-source sensing module 200 is configured to collect dynamic data of the road surface during its service process in real time and periodically, including external environmental stimulus data. Internal structural response data and traffic load data The multi-source sensing module includes an environmental sensing unit, an internal response acquisition unit, and a load monitoring unit.

[0073] The environmental sensing unit is configured to acquire external environmental stimulus data. The aforementioned These are the boundary conditions that induce the thermal and wet response of the road surface, which include at least atmospheric temperature. Relative humidity of the atmosphere and rainfall The environmental sensing unit can utilize meteorological monitoring nodes deployed along the road or acquire real-time data from the Highway Weather Monitoring System (RWIS) via a data interface. In this embodiment, the environmental sensing unit integrates a platinum resistance temperature sensor, a polymer humidity sensor, and a tipping bucket rain gauge. The environmental sensing unit collects data at preset time intervals, timestamps the data, and synchronously sends it to the damping inversion module 300.

[0074] The load monitoring unit is configured to collect traffic load data. Traffic load data The cumulative number of axle load applications is a crucial input for calculating pavement fatigue damage. The load monitoring unit performs real-time monitoring using a dynamic weighing sensor array, piezoelectric sensors, or bending plate sensors installed on the pavement. The load monitoring unit identifies the vehicle type and converts the axle load data based on the collected axle load data, and then calculates the cumulative number of applications for each standard axle. The format is periodically updated to the damping inversion module 300.

[0075] The internal response acquisition unit is configured to acquire response data of the internal structure of the base layer. The aforementioned As a real-time indicator characterizing the functional state and internal physical changes of a material, it should at least include the internal temperature of the base layer. and the dielectric constant of the base layer Internal temperature of the base layer The hysteresis effect used to invert heat transfer; the dielectric constant inside the substrate. This is directly related to the material's moisture content and is used to monitor its water-repellent properties. The actual degradation situation. The internal response acquisition unit provides two optional implementation methods:

[0076] First implementation method: Direct measurement based on pre-embedded sensors.

[0077] The internal response acquisition unit acquires data by embedding an integrated sensor array during the construction of the road base course. The sensor array includes MEMS temperature sensors or fiber Bragg grating temperature sensors, configured to measure the temperature at specific depths of the base course (e.g., 5cm and 15cm from the top surface of the base course). The array includes both frequency-domain reflectometry and time-domain transmission-type moisture content sensors for measuring the dielectric constant of the substrate material. The sensor array uploads the collected data at a specified sampling frequency (e.g., once every 15 minutes) via wired or wireless means.

[0078] Second implementation method: Indirect measurement based on surface inversion.

[0079] The internal response acquisition unit acquires road surface internal response data through non-contact methods, utilizing vehicle-mounted equipment or drones equipped with infrared thermal imagers and high-frequency ground-penetrating radar.

[0080] Regarding the internal temperature of the base layer The internal response acquisition unit uses infrared thermal imaging technology to acquire the instantaneous temperature field of the road surface. The internal response acquisition unit constructs an inversion model based on the one-dimensional heat conduction equation:

[0081] ;

[0082] In the formula, For material density, For specific heat capacity, Thermal conductivity, For depth coordinates, Represents the partial differential symbol. Represents temperature variable. Represents a time variable. This represents the rate of change of temperature over time.

[0083] The internal response acquisition unit uses the measured road surface temperature as the upper boundary condition and solves the above equation using the finite difference method to calculate the temperature time series at the depth of the base layer. .

[0084] Regarding the internal dielectric constant of the substrate The internal response acquisition unit uses high-frequency GPR technology to acquire the reflected signals of electromagnetic waves in the pavement structure. The internal response acquisition unit identifies the two-way travel time difference of the reflected signals of electromagnetic waves on the top and bottom surfaces of the base course. Based on the known base layer design thickness The dielectric constant can be calculated using the following formula.

[0085] ;

[0086] In the formula, Indicates the dielectric constant inside the substrate. This represents the speed of light in a vacuum. Indicates the difference or increment sign. Represents a time variable. This represents the two-way travel time difference of the electromagnetic wave reflected signals from the top and bottom surfaces of the substrate. This indicates the known base layer design thickness.

[0087] After performing geometric correction and filtering on the acquired data, the internal response acquisition unit outputs the inverted result. Data sequence.

[0088] See attached document Figure 4 , Figure 4 This is a schematic diagram of the logic structure of a damping inversion module according to one embodiment of the present invention.

[0089] The damping inversion module 300 is configured to process multi-source heterogeneous data and invert the microstructural state of the pavement base layer through a physical model. The damping inversion module includes a theoretical reference value calculation unit, a dynamic parameter identification unit, a functional attenuation assessment unit, and a comprehensive health evaluation unit.

[0090] The theoretical reference value calculation unit is configured to construct an ideal heat and moisture transfer damping model based on the initial physicochemical properties of the material. The theoretical reference value calculation unit receives the initial performance state vector from the material modeling module 100. It contains dense performance factors. Water retention efficiency factor Under ideal conditions where the material's microstructure is intact and its chemical components are not degraded, the road base layer exhibits inherent thermal inertia in its response to changes in external environmental temperature. This thermal inertia is expressed by the theoretical environmental response hysteresis time constant. Quantification is performed. The theoretical reference value calculation unit establishes a mapping relationship through a multiple linear regression model, and the calculation formula is as follows;

[0091] ;

[0092] In the formula, This represents the theoretical environmental response lag time constant. This represents the density influence coefficient. Indicates the density efficiency factor. Indicates the influence coefficient of water retention. Indicates water retention efficiency factor, This represents the reference constant.

[0093] coefficient , and The preset values ​​were obtained by conducting thermal cycling tests on specimens with different dosage ratios in a laboratory environmental chamber and performing regression analysis on the measured thermal response data. The physical meaning of this is to characterize the effect of a step change in external temperature. The higher the temperature, the denser the material and the greater the heat capacity. The higher the temperature, the more stable the bound water inside; the combined effect of these two factors enhances the damping effect of heat transfer. Increase.

[0094] The dynamic parameter identification unit is connected to the multi-source sensing module 200 and the theoretical reference value calculation unit, respectively, and is configured to identify the current actual thermal response characteristics of the road surface based on measured data. As the system input stimulus, the internal temperature sequence of the base layer is obtained. As the system output response, the dynamic parameter identification unit treats the road base layer as a first-order linear heat conduction system, whose governing equations satisfy the discretized form of Newton's law of cooling;

[0095] ;

[0096] In the formula, Indicates the current time The internal temperature of the base layer, This indicates the internal temperature of the substrate at the previous sampling time. Indicates the sampling time interval. This represents the actual time lag constant to be identified. Represents the external atmospheric temperature sequence. Indicates the current time The internal temperature of the base layer.

[0097] To eliminate environmental noise interference and improve recognition accuracy, the dynamic parameter recognition unit employs the least squares method within a sliding time window. Optimal estimation is performed. The dynamic parameter identification unit constructs the objective function. The aim is to minimize the sum of squared residuals between the observed temperature and the model-predicted temperature:

[0098] ;

[0099] In the formula, The length of the sliding window. These are measured values. For hypothesis-based Calculated predicted value, Describe the objective function. This represents the actual thermal response hysteresis time constant to be identified. This represents the loop variable used in the summation operation. Indicates the current moment.

[0100] The dynamic parameter identification unit achieves this through iterative solution. Take the minimum value This value represents the actual thermal response hysteresis time constant of the road base layer at the current moment. When microcracks appear inside the road surface, leading to increased air convection, or when the water-repellent groups fail, causing moisture infiltration and altering the thermal conductivity, Significant drift will occur.

[0101] The function degradation assessment unit is connected to the dynamic parameter identification unit and configured to quantify the degree of degradation of the material's microscopic functions. The function degradation assessment unit calculates the function degradation index. This index reflects the degree to which actual thermal damping characteristics deviate from the theoretical ideal state. The calculation formula is as follows:

[0102] ;

[0103] In the formula, Represented as time The functional decline index, This represents the theoretical environmental response lag time constant. Indicates time The actual thermal response hysteresis time constant, Represents a time variable.

[0104] when When the value approaches 0, it indicates that the actual thermal response characteristics of the road surface are highly consistent with the theoretical characteristics calculated based on the material genes, the microstructure is intact, and the water repellency and densification functions are normal.

[0105] when When the value gradually increases and exceeds the preset monitoring threshold, it indicates a decline in the heat and moisture transfer damping capacity of the pavement material. This decline can be detected before macroscopic physical cracks form, and its physical essence corresponds to the change in thermal conductivity caused by the chemical degradation of the organosilicon water-repellent film, or the formation of internal thermal convection channels due to the accumulation of microscopic damage.

[0106] The functional degradation assessment unit will also simultaneously incorporate the rate of change of dielectric constant. Make corrections. If the multi-source sensing module 200 detects a dielectric constant... If an abnormal rise occurs that is not caused by rainfall, the functional decline assessment unit will introduce a correction factor. ,Will Revised to To improve sensitivity to water-damaged diseases.

[0107] The comprehensive health assessment unit is configured based on grey relational analysis theory, which couples the single-dimensional functional degradation index with the multi-dimensional mechanical structural state to generate a comprehensive health index characterizing the overall service status of the pavement. .

[0108] The comprehensive health assessment unit first constructs a multidimensional feature sequence for evaluation. This sequence includes indicators characterizing chemical microscopic function, indicators characterizing mechanical fatigue accumulation, and indicators characterizing the risk of drying shrinkage cracking. The comprehensive health assessment unit also establishes a reference sequence. This reference sequence represents the feature vectors of the road surface under ideal, undamaged conditions. (Setting...) ,

[0109] in, The ideal functional attenuation value is 0; The ideal level of fatigue accumulation is 0. The ideal shrinkage risk level is 0.

[0110] Establish a comparison sequence for the comprehensive health assessment unit. The comparison sequence is based on the current time. The composition of the normalized index obtained from actual measurement or inversion calculation:

[0111] ;

[0112] In the formula;

[0113] The function degradation index output by the function degradation assessment unit ;

[0114] Structural fatigue accumulation The comprehensive health assessment unit obtains the cumulative number of axle loads monitored by the multi-source sensing module 200. In conjunction with the cumulative standard axle loads within the design service life specified in the pavement design documents. ,calculate .

[0115] Risk level of drying shrinkage cracks The comprehensive health assessment unit utilizes the internal temperature of the grassroots level. and dielectric constant Calculate the humidity gradient inside the base layer and compared it with the material's limit allowable humidity gradient. Compare and calculate

[0116] Comprehensive health assessment unit calculation comparison sequence Chinese indicators and reference sequences Correlation coefficient of corresponding indicators The correlation coefficient characterizes the degree to which the current actual state and the ideal state are closely related in terms of geometric curve shape. The calculation formula is as follows;

[0117] ;

[0118] In the formula: Represents the correlation coefficient. This represents the minimum difference operator between two levels. Indicates the first Each indicator in The sequence of absolute differences at time points, Reference sequence The corresponding indicator value, For comparing sequences The corresponding indicators in China The measured or inverted value at time, Represents the resolution coefficient. This represents the maximum difference operator between two levels.

[0119] The comprehensive health assessment unit calculates the comprehensive health index using a weighted summation method based on the differences in the impact of each indicator on the overall lifespan of the road surface. .

[0120] ;

[0121] In the formula, This represents the overall health index. This represents the initial value of the loop variable, calculated starting from the first evaluation indicator. Indicates the first Each evaluation indicator is in Correlation coefficient at time, Represents a time variable. For the first The weight coefficients of each evaluation indicator, and satisfying .

[0122] In this embodiment, the weighting coefficient allocation strategy follows the principle of prioritizing function while taking into account structure, in order to highlight the early warning capability for early functional diseases.

[0123] when When the value is close to 1, it indicates that the comparison sequence is highly correlated with the reference sequence, meaning that the actual condition of the road surface is close to the ideal undamaged state and the health condition is excellent.

[0124] when A significant decrease indicates that the pavement has suffered damage at the microscopic functional or macroscopic structural levels, deviating from its ideal state. The comprehensive health assessment unit will calculate and generate... The sequence is transmitted in real time to the maintenance decision module 400 as a basis for determining whether the pavement has entered the structural fatigue period.

[0125] See attached document Figure 5 , Figure 5This is a schematic diagram of the hierarchical early warning logic of the maintenance decision module according to one embodiment of the present invention.

[0126] The maintenance decision module 400 includes a state determination unit, a scheme generation unit, and a benefit evaluation unit. The maintenance decision module 400 is configured to receive quantitative indicators calculated by the front end, decouple the evolution stages of pavement distress at the physical level through a dual-threshold logic tree, and output corresponding engineering intervention instructions.

[0127] The state determination unit receives the function degradation index output by the function degradation evaluation unit. and the comprehensive health index output by the comprehensive health evaluation unit The status determination unit has a built-in functional failure threshold. and structural damage threshold The threshold is based on accelerated aging test data of high-toughness crack-resistant materials and and The evolution curve fitting results determine this. When the material microstructure test results show that the cumulative functional failure rate reaches 25% before the appearance of macroscopic cracks, it will... Set to 0.25; when the road surface fatigue life is reduced to 40% of the design life, the corresponding... The value was calibrated to 0.60 as the structural failure threshold. .

[0128] The status determination unit compares the real-time indicators with the above thresholds to divide the road surface service status into three specific physical stages:

[0129] when and At this point, the material is considered to be in stable service. During this stage, the material's microscopic functions remain intact, and its macroscopic structure is undamaged, requiring no intervention.

[0130] when and At this time, it is determined to be in the functional defect period. The characteristics of this stage are: although the macroscopic mechanical properties of the road surface... While no obvious structural degradation has been observed, the damping inversion results show that the heat and moisture transfer characteristics inside the material have shifted, indicating that the hydrophobic film at the microscopic level has failed or the micropores are interconnected.

[0131] when At this point, it is determined to be the structural fatigue period. During this stage, regardless of... Regardless of the numerical values, it indicates that the road surface has developed macroscopic cracks, loosening, or significant strength loss, and structural repair is necessary.

[0132] The scheme generation unit is connected to the state determination unit and configured to generate differentiated technical instructions based on the determination results. For the functional hazard period, the scheme generation unit generates a chemical function restoration scheme. This scheme instruction system calls preventative maintenance equipment to spray a penetrating water-repellent agent onto the road surface. In this embodiment, the specific chemical component of the penetrating water-repellent agent is isobutyltriethoxysilane emulsion, with an effective ingredient content of not less than 90%. This instruction aims to utilize the permeability of silane small molecules to rebuild the surface tension of capillary walls without damaging the road surface structure, thereby repairing the water-repellent performance factor. This blocks the evolutionary path of water damage.

[0133] For the structural fatigue phase, the solution generation unit generates physical structural repair solutions. These solutions include milling and repaving or high-pressure grouting of the affected areas. When selecting the grouting solution, a low-viscosity modified epoxy resin material is specified to restore the pavement's density performance factor. and overall strength.

[0134] The benefit assessment unit is configured to calculate the return on investment (ROI) of maintenance decisions and dynamically adjusts the ROI by incorporating the disease evolution rate to determine the optimal implementation timing. The benefit assessment unit considers not only static repair costs but also adjusts decision weights based on the urgency of disease development. The adjusted dynamic ROI is shown below. The calculation formula is as follows:

[0135] ;

[0136] In the formula, This represents the adjusted dynamic input-output ratio. This represents the present value of the economic benefits resulting from the expected extension of the road surface's service life after maintenance. It is preset by the system database based on the road surface grade and historical maintenance data. Represents the evolution sensitivity coefficient. This indicates the direct economic cost of implementing the current maintenance plan. This represents the average annual rainfall. It is used to determine... The environmental parameters that take the values The rate of disease evolution is defined as the derivative of the functional decay exponent with respect to time, i.e. ;

[0137] In the formula, Indicates the functional decline index, Representing differential operations, the benefit evaluation unit evaluates the results within the most recent monitoring period. The slope is obtained by performing linear regression on the data.

[0138] The value of is related to the environmental factors of the monitored road section and is determined through a preset lookup table or piecewise function. When When mm / a, set ;when When mm / a, set .

[0139] The benefit evaluation unit will calculate the results. Compare with the preset economic threshold.

[0140] like If the value exceeds the threshold, the maintenance decision module will immediately output the execution command and a detailed engineering parameter table.

[0141] If the value is below the threshold, the road segment will be added to the continuous observation queue and await evaluation in the next monitoring cycle.

Claims

1. A smart identification and preventive maintenance analysis system for asphalt pavement defects, characterized in that, include: The materials modeling module is used to construct a heat and moisture transfer characteristic model of the pavement structure based on the material mix data and laboratory mechanical performance indicators of asphalt pavement, and output the initial performance state vector. The multi-source sensing module is deployed at the road service site to collect real-time data on external environmental excitation, internal structural response, and traffic load. The damping inversion module is connected to the material modeling module and the multi-source sensing module respectively, and is used to receive the initial performance state vector and the dynamic data collected on site; The damping inversion module calculates the functional attenuation index, which characterizes the changes in the micropore characteristics of the road surface, by comparing the differences between the theoretical heat and moisture transfer model and the actual response data, and calculates the comprehensive health index, which characterizes the macroscopic mechanical performance of the road surface, in conjunction with traffic load data. The maintenance decision module, connected to the damping inversion module, is used to make a dual threshold judgment based on the functional decay index and the comprehensive health index, identify the current stage of pavement disease evolution, and generate corresponding preventive maintenance plan instructions.

2. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 1, characterized in that, The material modeling module includes a component performance calibration unit, which performs the following calculation logic to generate the initial performance state vector: Calculate the water-repellent efficiency factor based on the water absorption rate inhibition ratio of the mixture; Calculate the compaction performance factor based on the mapping relationship between water-binder ratio and dynamic modulus; Water retention efficiency factor calculated based on extreme shrinkage strain; The water-repellent efficiency factor, the density efficiency factor, and the water-retention efficiency factor are encapsulated into the initial performance state vector.

3. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 1, characterized in that, The multi-source sensing module includes: An environmental sensing unit is used to collect the external environmental stimulus data, including atmospheric temperature, atmospheric humidity, and rainfall. An internal response acquisition unit is used to acquire the base temperature and dielectric constant inside the road structure as the internal structure response data; The load monitoring unit is used to collect the cumulative number of axle loads acting on the road surface, which is used as the traffic load data.

4. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 1, characterized in that, The damping inversion module includes a theoretical reference value calculation unit and a dynamic parameter identification unit: The theoretical reference value calculation unit is used to input the initial performance state vector into the heat and moisture transfer differential equation and solve it to obtain the theoretical environmental response hysteresis time constant of the pavement structure to the external environmental excitation data under the ideal undamaged state. The dynamic parameter identification unit is used to perform cross-correlation analysis on the synchronously collected atmospheric temperature time series and base layer temperature time series to identify the actual lag time constant under the actual service state of the road surface.

5. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 4, characterized in that, The damping inversion module also includes a functional degradation assessment unit: The functional degradation assessment unit calculates the deviation between the theoretical environmental response hysteresis time constant and the actual hysteresis time constant, and corrects the deviation using the measured dielectric constant to obtain the functional degradation index. The functional degradation index is calculated according to the following formula: ； In the formula, Represented as time Functional decline index This represents the theoretical environmental response lag time constant. Indicates time The actual thermal response hysteresis time constant, Represents a time variable; The functional decay index is used to quantitatively characterize the changes in the connectivity of the micropore structure inside the pavement material caused by water erosion.

6. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 1, characterized in that, The damping inversion module also includes a comprehensive health assessment unit: The comprehensive health evaluation unit uses grey relational analysis to select the cumulative number of axle loads, dielectric constant, and functional decay index to construct a comparison sequence. Taking the ultimate state of the pavement design life as a reference sequence, the grey relational coefficients of each parameter are calculated and weighted summed to obtain the comprehensive health index. The comprehensive health index is calculated according to the following formula: ； In the formula, This represents the overall health index. This represents the initial value of the loop variable, calculated starting from the first evaluation indicator. Indicates the first Each evaluation indicator is in Correlation coefficient at time, Represents a time variable. For the first The weight coefficients of each evaluation indicator, and satisfying .

7. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 1, characterized in that, The maintenance decision module is preset with functional early warning thresholds and structural safety thresholds, and executes the following judgment logic: If the functional degradation index is less than the functional warning threshold and the comprehensive health index is greater than the structural safety threshold, the road surface is determined to be in a stable service period. If the functional degradation index is greater than or equal to the functional warning threshold, and the comprehensive health index is greater than the structural safety threshold, the road surface is determined to be in a period of functional hazard. If the comprehensive health index is less than or equal to the structural safety threshold, the road surface is determined to be in a period of structural fatigue.

8. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 7, characterized in that, The maintenance decision module includes a scheme generation unit, used to generate instructions based on the judgment results: When the road surface is determined to be in the aforementioned functional hazard period, a chemical functional restoration plan instruction is generated, which includes construction parameters for spraying a penetrating water-repellent agent. When the road surface is determined to be in the structural fatigue period, a physical structure repair plan instruction is generated, which includes construction parameters for road surface milling and repaving or high-pressure grouting.

9. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 1, characterized in that, The maintenance decision-making module also includes a benefit evaluation unit: The benefit evaluation unit is used to calculate the dynamic input-output ratio of the maintenance plan in conjunction with the disease evolution rate; The dynamic input-output ratio is calculated according to the following formula: ； In the formula, This represents the adjusted dynamic input-output ratio. This represents the present value of the economic benefits resulting from the expected extension of the road surface's service life after maintenance. Represents the evolution sensitivity coefficient. This indicates the direct economic cost of implementing the current maintenance plan. This represents the average annual rainfall. The preventive maintenance plan instruction is output only when the dynamic input-output ratio is greater than the preset benefit threshold; otherwise, the road surface is added to the continuous observation queue.

10. The intelligent identification and preventive maintenance analysis system for asphalt pavement defects according to claim 4, characterized in that, When constructing the differential equation for heat and moisture transfer, the theoretical reference value calculation unit maps the water-repellent efficiency factor in the initial performance state vector to the moisture diffusion coefficient parameter of the equation, maps the density efficiency factor to the thermal conductivity parameter of the equation, and introduces atmospheric humidity and rainfall data collected by the environmental sensing unit as dynamic boundary conditions of the equation to construct a theoretical heat transfer model that reflects the specific material properties of the road surface and the real-time environmental humidity.

Images