An airport pavement sudden damage intelligent early warning and operation and maintenance decision method and system and medium

Abstract

This invention discloses an intelligent early warning and maintenance decision-making method, system, and medium for sudden pavement damage at airports, belonging to the field of airport pavement maintenance technology. Addressing the problems of delayed early warning, inefficient management, and non-standard decision-making in existing pavement maintenance systems, this solution first divides pavement management grids into differentiated sizes based on pavement functional zoning and structural boundaries, and constructs a dynamic basic library by binding multi-source data throughout the entire lifecycle. It then uses scenario-adaptive weighting to calculate a pavement health index, combining the static index value and short-term decline rate to determine risk and generate sudden damage early warnings. Finally, it matches tiered maintenance strategies and executes closed-loop management throughout the entire process. This invention can identify sudden pavement damage risks in advance, improve early warning accuracy and maintenance resource utilization, and is applicable to the full lifecycle maintenance management of civil airport pavements.

Description

Technical Field

[0001] This invention relates to the field of airport pavement operation and maintenance technology, specifically to an intelligent early warning and operation and maintenance decision-making method, system and medium for sudden damage to airport pavement. Background Technology

[0002] Civil airport pavements are core infrastructure ensuring the safe takeoff, landing, and taxiing of aircraft, and their health directly affects flight operation safety and efficiency. Currently, the industry generally conducts pavement operation and maintenance management based on MH / T 5024-2019 "Civil Airport Pavement Evaluation Specification". The conventional model involves quarterly / annual manual or vehicle inspections to calculate static indicators such as the Pavement Condition Index (PCI) and the Airworthiness Index (IRI). Maintenance plans are then developed based on the inspection results and the experience of maintenance personnel, which is a reactive approach.

[0003] The aforementioned existing technologies have the following significant drawbacks in practical applications: First, the timeliness of early warning is insufficient: the routine detection cycle is too long and cannot capture the sudden deterioration process of the pavement under the coupled effect of extreme weather (freeze-thaw cycle, extreme temperature difference) and short-term heavy flight surge. Sudden damage such as corner fracture and slab breakage is often only discovered after it occurs, which poses a safety hazard that interferes with flight operations and cannot achieve proactive risk prevention.

[0004] Secondly, the management granularity is coarse: the existing pavement management generally takes the runway, taxiway and apron as the smallest management unit, without going down to the pavement block level micro unit, and cannot accurately link flight load and meteorological effects to specific pavement locations. The accuracy of risk positioning is difficult to match the refined operation and maintenance needs of high-level airports.

[0005] Third, fragmented multi-source data: pavement structure parameters, meteorological monitoring data, flight operation data, FOD (foreign object) inspection data, and historical damage data are scattered across different business systems, lacking a unified framework for integration and correlation. This makes it impossible to achieve linkage analysis between damage and its causes, and in particular, it is impossible to identify the potential safety risks of hidden pavement damage inducing FOD.

[0006] Fourth, there is a lack of standardization in operation and maintenance decisions: existing disease treatment relies heavily on the experience of operation and maintenance personnel. There are no unified rules for the treatment strategies and process selection for the same type of disease in different protection levels and areas. This can easily lead to problems such as untimely treatment in core areas and excessive maintenance in non-core areas. The operation and maintenance solutions are not easily replicable and scalable.

[0007] The aforementioned issues make it difficult for the existing pavement operation and maintenance model to meet the high safety and high efficiency operation and maintenance needs of airports with tens of millions of passengers, and it is impossible to achieve refined management and control of the entire life cycle of the pavement. Summary of the Invention

[0008] To address the problems existing in the above background art, the present invention provides an intelligent early warning and operation and maintenance decision-making method, system and medium for sudden damage of airport pavement, so as to solve the problems of untimely pavement damage detection, low risk positioning accuracy, mismatched operation and maintenance resources, and difficult identification of pavement-derived FOD risks caused by lagging early warning of sudden deterioration, extensive management granularity, disconnected multi-source data incapable of linkage analysis, and non-standardized operation and maintenance decision in the existing airport pavement operation and maintenance mode, and realize dynamic and accurate assessment of pavement health status, early warning of sudden damage, automatic matching of hierarchical operation and maintenance strategies and whole-process closed-loop control, which provides reliable technical support for fine operation and maintenance of the whole life cycle of civil airport pavement, flight area safety guarantee and optimal allocation of operation and maintenance resources.

[0009] To achieve the above purpose, the present invention adopts the following technical solutions: An intelligent early warning and operation and maintenance decision-making method for sudden damage of airport pavement, comprising the following steps: S1, dividing pavement management grids with differentiated sizes based on functional divisions and structural physical boundaries of airport pavement, binding full-life-cycle multi-source pavement attribute data to each pavement management grid, and constructing a dynamically updated grid data basic database; S2, matching weight distribution rules adapted to the current operation scenario, and calculating the pavement health index of each pavement management grid by combining the multi-source pavement attribute data of the corresponding grid; S3, performing two-dimensional risk determination by combining the static value of the pavement health index and the fluctuation amplitude of the health index within a preset period, and generating sudden damage early warning information of a corresponding level; S4, matching a standardized operation and maintenance disposal strategy of a corresponding level by combining the sudden damage early warning information, the functional guarantee level of the pavement, and on-site disease characteristics, generating an operation and maintenance task and implementing whole-process closed-loop control.

[0010] Specifically, the rule for dividing pavement management grids in step S1 is: the higher the functional guarantee level and the more concentrated the aircraft wheel track effect, the smaller the grid division size; Each pavement management grid is configured with a unique spatial association code, the spatial association code includes a partition type field, a region level field and a plane coordinate field, and the functional attribute and GIS spatial position of each pavement management grid are directly matched and corresponding through the spatial association code.

[0011] Specifically, the multi-source pavement attribute data bound to each pavement management grid in step S1 includes four categories: The first category is structural static attributes, including pavement structural layer parameters, construction years, and historical large and medium maintenance records; The second category is meteorological environmental attributes, including temperature and humidity, freeze-thaw cycle records, extreme weather records, and corrosive medium spreading records; The third category is load-related attributes, including aircraft takeoff and landing records, wheel track coverage ratio, and proportion of heavy-load aircraft in the corresponding grid. The fourth category is historical damage attributes, including historical pavement inspection indicators, damage records, repair records, and post-repair durability data; The four types of attribute data are dynamically synchronized to the gridded data base according to their respective collection and update frequencies.

[0012] Specifically, the weight allocation rule in step S2 is as follows: The operation scenarios are pre-divided into four categories: routine operation scenarios, extreme weather scenarios, peak flight scenarios, and scenarios with high incidence of malfunctions. Each type of operation scenario corresponds to a set of weight allocation coefficients, which respectively correspond to four types of pavement influencing factors: structural safety factor, environmental degradation factor, load fatigue factor, and historical damage factor. The weighting coefficients for different operating scenarios are adjusted according to the core deterioration causes of the scenario. The environmental deterioration factor has the highest weight in extreme weather scenarios, the load fatigue factor has the highest weight in peak flight scenarios, and the historical damage factor has the highest weight in scenarios with high incidence of defects.

[0013] Specifically, the pavement health index in step S2 is calculated using the following formula: ; in, For pavement health index, , , , The following are the scenario adaptation weight allocation coefficients corresponding to the structural safety factor, environmental degradation factor, load fatigue factor, and historical damage factor, in that order. For structural safety factor, As a factor of environmental degradation, The load fatigue factor, Historical damage factors; The structural safety factor The calculation formula is: ; In the formula, The structural correction coefficient is determined based on the historical major and minor repair records of the structural static attributes in the gridded data base database. To accommodate the deflection allowance of the corresponding grid pavement design, The measured representative deflection corresponds to the grid pavement. The environmental degradation factors The calculation formula is: ; In the formula, , , This is a seasonal correction factor, with a value determined based on the current season. The cumulative deduction value for freeze-thaw cycles, Accumulated deductions for extreme temperatures The cumulative deduction value for corrosive media; The load fatigue factor The calculation formula is: ; In the formula, This is the wheel track coverage correction coefficient, which is determined based on the wheel track coverage ratio of the corresponding grid. For the first time in the statistical period The actual number of takeoffs and landings of this aircraft type in the corresponding grid. For the first time within the design life of the pavement The number of permitted takeoffs and landings for this aircraft type; The historical damage factor The calculation formula is: ; In the formula, , , Preset the weighting coefficient for the impact of diseases; This represents the weight value for the disease type. The size of the disease is the weighted value. To repair the remaining lifetime weight value.

[0014] Specifically, the two-dimensional risk assessment rule in step S3 is as follows: (1) Based on the static value of the pavement health index, the pavement health index is divided into four basic risk levels in descending order. The higher the pavement health index, the lower the basic risk level. Each basic risk level corresponds to a preset basic inspection frequency. (2) Calculate the decline of the pavement health index of a single pavement management grid within the preset statistical period. If the decline is greater than the preset abnormality threshold, the basic risk level of the grid is increased by one level to obtain the corrected risk level. (3) Based on the pavement health index of the pavement management grid and the decline rate of the pavement health index within a preset statistical period, the probability of sudden damage to the grid in a preset future period is calculated using a logistic regression model. The formula for calculating the probability of sudden damage is as follows: ; in, , , These are the preset model coefficients obtained by fitting historical pavement defect data. To determine the expected decline in pavement health index within a pre-defined statistical period, The pavement health index for the pavement management grid; Then, according to the preset threshold range of the probability of sudden damage, the corresponding level of sudden damage early warning information is generated. The sudden damage early warning information includes the spatial association code of the corresponding grid, the corrected risk level, the probability of sudden damage and inspection and handling suggestions.

[0015] Specifically, step S4 includes: Combining four dimensions—early warning information of sudden damage, the functional protection level of the pavement, and the type and size of the on-site defects—the defects to be dealt with are divided into three levels of operation and maintenance treatment. Each level of operation and maintenance treatment corresponds to the preset applicable defects, standardized treatment process, and treatment time limit, and generates corresponding operation and maintenance tasks. Simultaneously count the frequency of FOD occurrence in each pavement management grid. If the frequency of FOD occurrence in a single grid is greater than a preset frequency multiple threshold and the pavement health index of that grid is lower than a preset health index threshold, mark that grid as a FOD risk zone induced by disease, and correspondingly increase the inspection frequency and cleaning operation level of that grid. After the operation and maintenance task is completed, upload the verification materials that match the operation and maintenance handling level to complete the system verification. After the verification is passed, the handling record will be synchronously updated to the multi-source pavement attribute data of the corresponding grid.

[0016] Specifically, the closed-loop management of the entire process in step S4 also includes the following steps: (1) For the pavement management grid that has been repaired, match the preset re-inspection cycle corresponding to the treatment process adopted in this grid. Before the preset re-inspection cycle expires, the re-inspection work order is automatically generated. If secondary defects are found during the re-inspection, the operation and maintenance treatment level of the secondary defects is upgraded by one level on the basis of the original treatment level and the operation and maintenance task is reassigned. The re-inspection results are synchronously updated to the multi-source pavement attribute data of the corresponding grid. (2) For pavement ancillary facilities that require periodic maintenance, establish corresponding grid periodic maintenance electronic files, automatically trigger the dispatch of operation and maintenance tasks before the preset maintenance cycle node, and store the full cycle maintenance records in the grid-based data base database.

[0017] An intelligent early warning and maintenance decision-making system for sudden airport pavement damage, applying the intelligent early warning and maintenance decision-making method for sudden airport pavement damage as described above, includes the following functional modules: The gridded data management module is used to divide pavement management grids with different sizes based on the functional zoning and structural physical boundaries of the airport pavement. It binds multi-source pavement attribute data with the entire life cycle to each pavement management grid and builds a dynamically updated gridded data base library. The pavement health index calculation module is used to match the weight allocation rules adapted to the current operating scenario and calculate the pavement health index of each pavement management grid by combining the multi-source pavement attribute data of the corresponding grid. The dual-dimensional risk warning module is used to combine the static value of the pavement health index and the decline of the pavement health index within a preset abnormality statistical period to make a dual-dimensional risk judgment and generate corresponding level of sudden damage warning information. The hierarchical operation and maintenance closed-loop management module is used to combine sudden damage early warning information, the functional protection level of the pavement, and the on-site defect characteristics to match the corresponding level of standardized operation and maintenance handling strategies, generate operation and maintenance tasks, and carry out closed-loop management of the entire process.

[0018] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-described intelligent early warning and maintenance decision-making method for sudden damage to airport pavement.

[0019] In summary, the beneficial technical effects of the present invention are as follows: 1. Enhanced early warning capability for sudden pavement damage: This invention adopts a two-dimensional risk assessment logic of "static risk level + short-term anomaly adjustment". It combines the objective calculation results of the pavement health index with the short-term deterioration range to identify the risk of sudden damage. Compared with the traditional quarterly / annual inspection post-event handling mode, it can provide early warning of sudden damage such as pavement corner fractures and broken panels, changing the traditional passive repair operation and maintenance logic and effectively reducing the impact of sudden pavement damage on flight operation safety.

[0020] 2. Improved accuracy of pavement operation and maintenance management: This invention adopts differentiated grid division rules adapted to the pavement functional level and load concentration, and sinks the smallest management unit of the pavement from the traditional macro level of "runway-taxiway-apex" to the micro unit of the pavement. This improves the accuracy of risk positioning and enables precise binding of multi-source data such as meteorology, load, and defects to specific pavement locations, matching the refined operation and maintenance needs of airports with tens of millions of passengers per day.

[0021] 3. Significantly optimized efficiency of operation and maintenance resource allocation: This invention adopts a scenario-adaptive pavement health index calculation model and a standardized operation and maintenance decision-making system that matches multiple dimensions of "early warning level - protection level - disease characteristics". This effectively improves the accuracy of pavement health status assessment and operation and maintenance resource utilization, avoids resource misallocation problems such as untimely handling in core areas and excessive maintenance in non-core areas. The standardized decision-making system can be directly replicated and promoted to civil airports of different sizes.

[0022] 4. Enhanced safety and control capabilities in the flight area: This invention enables the linkage analysis of pavement health status and FOD inspection data, which can proactively identify high-risk areas where pavement defects induce FOD and reduce pavement-borne FOD; at the same time, the closed-loop management mechanism throughout the entire process enables traceability and verification of defect treatment, further improving the safety redundancy of flight area operations.

[0023] 5. Data value is fully released: The gridded multi-source data base constructed by this invention can realize unified management of pavement data throughout its entire life cycle. Data such as the treatment of defects and the effect of repair generated during operation and maintenance can feed back into the iterative optimization of the health assessment model, forming a virtuous management closed loop of "data collection-assessment and early warning-decision handling-data feedback", providing data support for pavement structure design optimization and the formulation of major and medium-sized repair plans. Attached Figure Description

[0024] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a system framework diagram of the present invention. Detailed Implementation

[0025] To make the technical means, creative features, objectives and effects of this invention clearer and easier to understand, the invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0026] Example like Figure 1 As shown, the intelligent early warning and maintenance decision-making method for sudden damage to airport pavement provided by the present invention specifically includes the following steps: S1. Pavement management grid division and gridded data base construction; S11. This embodiment first connects to the existing 3D GIS base map of the airport's flight area, and divides the flight area into four support level zones according to functional importance, load concentration, and usage frequency: (1) Special attention area: Important flight support routes; (2) Core Concern Area: High-speed aircraft operating areas on runways and taxiways; (3) Key Area of ​​Concern: Apron Area; (4) General Concern Area: Service lane area.

[0027] Furthermore, the grid was divided according to the rule that "the higher the functional protection level and the more concentrated the aircraft wheel tracks, the smaller the grid size." All grid boundaries were fully aligned with the physical joints and expansion joints of the pavement to avoid monitoring errors caused by cross-segment grids. Special attention area (important flight support route): Divided into 1m×1m micro-grids, this area is the fixed taxiing path of important flights, with the highest priority, high concentration of aircraft wheel tracks and fixed path, the micro-grid can accurately capture local deterioration risks and match the concentrated effect range of aircraft wheel tracks; Core concern area (runway and taxiway high-speed aircraft operating area): Divided into 5m×5m standard grids, aligned with the size of a single precast concrete pavement panel, to meet the pavement deterioration monitoring needs of high-speed operating areas. Key monitoring area (apron area): Divided into a standard grid of 5m×5m, which can take into account both the accuracy of risk monitoring and management efficiency of aircraft parking and taxiing in the apron area; General Concern Area (Service Lane Area): Divided into a simplified grid of 10m×10m. This area is only for ground support vehicles and has no aircraft load. The simplified grid can reduce management costs while meeting monitoring needs.

[0028] Each grid is assigned a unique 16-bit spatial association code, with the coding rule being [2-bit partition type][2-bit area level][6-bit X coordinate][6-bit Y coordinate]. This code is embedded in the grid attribute fields of the GIS system, allowing direct access to the grid's core attributes without the need for an additional mapping table. The partition type values ​​are 01=runway, 02=taxiway, 03=apron, 04=service lane; the area level values ​​are 01=special concern area, 02=core concern area, 03=key concern area, 04=general concern area; and the X / Y coordinates correspond to the spatial coordinates of the 3D GIS base map. For example, the grid code for an important flight support route located on a taxiway is 0201012345067890. The first two digits, 02, represent the partition as a taxiway; the 3rd and 4th digits, 01, represent a special concern area; the 5th to 10th digits correspond to the X coordinate; and the 11th to 16th digits correspond to the Y coordinate.

[0029] S12. Bind four types of multi-source attribute data to each grid, specifically including: Structural static properties: The pavement structural layer parameters, construction year, and historical major and medium repair records are obtained from the airport construction archive system, pavement inspection reports over the years, and major and medium repair completion data. The parameters are updated once a year after the pavement inspection is completed. The structural layer parameters include the structural layer type, the thickness of each layer, and the material type. Meteorological and environmental attributes: Based on daily monitoring data from airport meteorological stations and de-icing / snow removal operation records in the flight area, daily temperature and humidity, freeze-thaw cycle count, extreme weather records, and de-icing agent / de-icing fluid application volume are obtained and updated daily. Load effect attributes: By connecting to the airport flight operation management system, the system calculates the aircraft take-off and landing records, wheel track coverage ratio, and heavy-load aircraft ratio for each grid by matching flight take-off and landing times, aircraft type parameters, taxi paths, and grid GIS coordinates. The system is automatically updated after the end of each day's flight operation. Historical Defect Attributes: Based on the airport flight area inspection system and historical repair work orders, historical pavement inspection indicators, defect types / sizes, repair processes, and post-repair durability data are obtained. Inspection personnel enter defects on-site, and work orders are updated in real time after closure.

[0030] S2, Calculation of Pavement Health Index (PHI); All preset parameter values ​​involved in this step can be flexibly adjusted according to the pavement structure characteristics and operation and maintenance requirements of different airports. The specific parameter value rules in this embodiment are as follows: (1) Scene adaptation weight The pre-classification includes four types of operating scenarios: routine operating scenarios, extreme weather scenarios, peak flight scenarios, and scenarios with a high incidence of malfunctions. Among them, structural security in conventional operating scenarios is the core influencing factor, with a weight configuration of [missing information]. , , , ; In extreme weather scenarios, freeze-thaw cycles and corrosion are the core causes of degradation, with the following weighting: , , , ; Peak flight scenarios with load fatigue as the core degradation factor, with the following weighting: , , , ; Historical damage is the core influencing factor during periods of high disease incidence, with the following weighting: , , , ; (2) Structural correction factor Based on the variation law of bearing capacity after major and medium repairs of pavement, the following values ​​are set: 1.0 for original pavement that has not undergone any major or medium repairs; 1.1 for pavement that has undergone overall overlay and major repairs due to the increase in structural bearing capacity; and 0.95 for pavement with local medium repairs due to the presence of weak layers at the repair interface.

[0031] (3) Seasonal correction factor , , Settings based on core degradation factors in different seasons: Winter (November to February): Freeze-thaw cycles and corrosion from de-icing fluids are the main deterioration factors. , , ; Summer (June-August each year): Freeze-thaw cycles and high-temperature deformation are the main deterioration factors. , , ; Spring and autumn (March-May and September-October each year): Take 2. , .

[0032] (4) Wheel track coverage correction factor Based on the acceleration effect of wheel track concentration on fatigue damage, the following settings are applied: 1.0 for wheel track coverage < 50%; 0.95 for wheel track coverage < 80% for 50% ≤ wheel track coverage; and 0.9 for wheel track coverage ≥ 80%.

[0033] (5) Disease impact weighting coefficient , , Based on the statistical conclusion that the impact of disease type, size, and remaining repair life on pavement health is relatively equal, this embodiment uses 1.0 for all values, which can be adjusted according to the disease characteristics of different airports.

[0034] S21. First, determine the scene type based on the current running characteristics and match the corresponding scene adaptation weight allocation coefficient.

[0035] S22. Calculate the impact factors of four types of pavement; Among them, structural safety factor The calculation formula is: ; In the formula, For structural correction factors; To accommodate the deflection allowance of the corresponding grid pavement design, The measured representative deflection corresponds to the grid pavement. Environmental degradation factors The calculation formula is: ; In the formula, , , This is a seasonal correction factor; The cumulative deduction value for freeze-thaw cycles, Accumulated deductions for extreme temperatures The cumulative deduction value for corrosive media; Load fatigue factor The calculation formula is: ; In the formula, This is the wheel track coverage correction factor; For the first time in the statistical period The actual number of takeoffs and landings of this aircraft type in the corresponding grid. For the first time within the design life of the pavement The number of permitted takeoffs and landings for this aircraft type; Historical damage factors The calculation formula is: ; In the formula, , , Preset the weighting coefficient for the impact of diseases; This represents the weight value for the disease type. The size of the disease is the weighted value. To repair the remaining lifetime weight value.

[0036] S23. Substitute the scores of the four factors and the scene adaptation weights into the weighted formula to calculate the pavement health index of the grid: ; in, For pavement health index, , , , The following are the scenario adaptation weight allocation coefficients corresponding to the structural safety factor, environmental degradation factor, load fatigue factor, and historical damage factor, in that order. For structural safety factor, As a factor of environmental degradation, The load fatigue factor, Historical damage factors; S3. A two-dimensional risk assessment is conducted by combining the static value of the pavement health index with the fluctuation range of the health index within a preset period. The two-dimensional risk assessment is as follows: (1) Based on the static value of the pavement health index, four basic risk levels are divided in descending order of the pavement health index. The higher the pavement health index, the lower the basic risk level. Each basic risk level corresponds to a preset basic inspection frequency, which specifically includes: Level 1: Healthy Zone (PHI≥85), routine patrols; Level 2: Sub-health zone (70≤PHI<85), key focus; Level 3: High-risk area (50≤PHI<70), routine maintenance; Level 4: Failure zone (PHI < 50), emergency repair; (2) Calculate the decline of the pavement health index of a single pavement management grid within the preset period. If the decline is greater than the preset anomaly threshold, the basic risk level of the grid is increased by one level to obtain the corrected risk level, and the inspection frequency is increased accordingly. (3) Based on the pavement health index of the pavement management grid and the decline rate of the pavement health index within a preset statistical period, the probability of sudden damage to the grid in a preset future period is calculated using a logistic regression model. The formula for calculating the probability of sudden damage is as follows: ; in, , , These are the preset model coefficients obtained by fitting historical pavement defect data. To determine the expected decline in pavement health index within a pre-defined statistical period, The pavement health index for the pavement management grid; Then, based on the preset threshold range of the probability of sudden damage, corresponding levels of sudden damage early warning information are generated, including the spatial correlation code of the corresponding grid, the corrected risk level, the probability of sudden damage, and inspection and handling suggestions.

[0037] S4, hierarchical operation and maintenance decision-making and full-process closed-loop management; S41. Combining four dimensions—sudden damage early warning information, pavement functional protection level, type and size of on-site defects—defects to be addressed are classified into three levels of maintenance and handling: red, orange, and yellow. Each level corresponds to standardized handling procedures, compliant materials, and handling time limits, and matching maintenance tasks are automatically generated, as detailed below: 1. Red (Emergency Repair Level): Applicable defects: ① Cement pavement meets the emergency repair scenario: runway pavement fracture or misalignment ≥5mm, long side of missing block ≥120mm or depth ≥70mm; ② Asphalt pavement meets the sudden defect scenario: potholes, bumps, ruts, large area of ​​loose particles that affect aircraft operation.

[0038] Solution: Prioritize repairs during flight intervals. Temporary repairs will use early-strength cement mortar, epoxy resin mortar, and cold-mix asphalt mixture. Permanent repairs will use hot-mix asphalt mixture and fast-hardening early-strength cement concrete.

[0039] Time requirements: Response time ≤ 10 minutes, temporary repairs ≤ 30 minutes to complete, permanent repairs to be completed within the next 12-hour downtime window.

[0040] 2. Orange (Routine Maintenance Level): Applicable defects: Corner cracks, large-area joint breakage, pitting and other defects in cement pavement that do not affect operation.

[0041] Solution: Repair using modified silicate early-strength cement / phosphate cement repair mortar, silicone sealant, pressure-sensitive asphalt, and other materials.

[0042] Time limit: Treatment time ≤ 30 minutes, durability repair to be completed within 24 hours.

[0043] 3. Yellow (Preventative Repair Grade): Applicable defects: ① Preventive maintenance scenarios: minor cracks, aging, and insufficient friction coefficient of asphalt pavement; surface wear, aging of joint materials, and high-risk areas of cement pavement affected by de-icing agents / de-icing fluid corrosion; ② Structural defects: large-area network cracking and granulation of asphalt pavement; single broken slabs and structural cracks of cement pavement.

[0044] Treatment options: Preventive maintenance includes sand fog sealing, thin-layer overlay, in-situ hot recycling, or replacement of joint materials, silane impregnation, and thin-layer repair; structural defects are treated with milling and repaving or replacement of entire slabs with fast-hardening cement concrete.

[0045] Time limit requirement: It should be implemented during the planned suspension window or in a season with suitable weather, and the processing time should be ≤7 hours.

[0046] S42. Synchronously count the frequency of FOD occurrence in each pavement management grid. If the frequency of FOD occurrence in a single grid is greater than the preset frequency multiple threshold and the pavement health index of that grid is lower than the preset health index threshold, mark that grid as a FOD risk zone induced by disease, and correspondingly increase the inspection frequency and cleaning operation level of that grid. After the operation and maintenance task is completed, upload the verification materials that match the operation and maintenance handling level to complete the system verification. After the verification is passed, the handling record will be synchronously updated to the multi-source pavement attribute data of the corresponding grid.

[0047] S43. For pavement management grids that have been repaired, match the preset re-inspection cycle corresponding to the treatment process adopted for this grid. In this embodiment, the preset re-inspection cycle is bound to the treatment level: red-level emergency repair process corresponds to 1 month, orange-level daily maintenance process corresponds to 6 months, and yellow-level preventive repair process corresponds to 1 year. A re-inspection work order is automatically generated 7 days before the preset re-inspection cycle expires. If secondary defects are found during the re-inspection, the operation and maintenance treatment level of the secondary defects is upgraded by one level based on the original treatment level and the operation and maintenance task is reassigned. The re-inspection results are synchronously updated to the multi-source pavement attribute data of the corresponding grid. S44. For pavement ancillary facilities that require periodic maintenance, establish corresponding grid-based electronic maintenance files. Before the preset maintenance cycle node is reached, the operation and maintenance task assignment will be automatically triggered, and the full cycle maintenance record will be synchronously stored in the grid-based data base database.

[0048] like Figure 2As shown, the present invention further provides an intelligent early warning and operation and maintenance decision-making system for sudden damage of airport pavement, which is deployed on an airport flight area operation and maintenance management platform and includes the following functional modules: A gridded data management module, configured to divide pavement management grids with differentiated sizes based on the functional partitions and structural physical boundaries of the airport pavement, bind full-life-cycle multi-source pavement attribute data to each pavement management grid, and construct a dynamically updated gridded basic data library; A pavement health index calculation module, configured to match weight distribution rules adapted to the current operation scenario, and calculate the pavement health index of each pavement management grid by combining the multi-source pavement attribute data of the corresponding grid; A two-dimensional risk early warning module, configured to perform two-dimensional risk determination by combining the static value of the pavement health index and the decline range of the pavement health index within a preset abnormal change statistical period, and generate sudden damage early warning information of corresponding levels; A hierarchical closed-loop operation and maintenance control module, configured to match a standardized operation and maintenance disposal strategy of a corresponding level by combining the sudden damage early warning information, the function guarantee level of the pavement and the on-site disease characteristics, generate operation and maintenance tasks and perform closed-loop control of the whole process.

[0049] The present invention also discloses a computer-readable storage medium, which stores an executable computer program. When the program is executed by a server processor, all the method steps of S1 to S4 described above are implemented. The program is deployed in a cloud server of an airport operation and maintenance platform, and supports multi-device access and invocation including PC, mobile PAD and inspection terminals.

[0050] Therefore, the method, system and medium for intelligent early warning and operation and maintenance decision-making of sudden damage of airport pavement provided by the present invention, by adopting the core processes of dividing pavement grids with differentiated sizes and binding full-life-cycle multi-source attribute data, dynamically calculating pavement health index with scene-adaptive weights, two-dimensional sudden damage risk determination combining static values and short-term abnormal changes, multi-factor matching standardized hierarchical operation and maintenance and whole-process closed-loop control, realizes the whole chain of full-life-cycle fine management of pavement of "micro-unit precise control - multi-source data deep fusion - active risk early warning - intelligent decision optimization", solves the core pain points of the traditional pavement operation and maintenance mode that only relies on periodic static detection, insufficient early warning timeliness, extensive management granularity, separated multi-source data that cannot be linked for analysis, and operation and maintenance decision-making highly relying on personnel experience, which lead to delayed discovery of sudden damage, inaccurate risk positioning, mismatched resource allocation, and difficult identification of pavement-derived FOD risks, effectively improves the accuracy of early warning of sudden pavement damage and the allocation efficiency of operation and maintenance resources, and provides an efficient and reliable technical solution for airport pavement safety guarantee, full-life-cycle control and optimal allocation of operation and maintenance resources under the background of smart civil aviation.

[0051] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent early warning and maintenance decision-making for sudden damage to airport pavement, characterized in that, Includes the following steps: S1. Based on the functional zoning and structural physical boundaries of the airport pavement, a pavement management grid with differentiated dimensions is divided. Multi-source pavement attribute data with the entire life cycle is bound to each pavement management grid to build a dynamically updated gridded data base library. S2. Match the weight allocation rules that are compatible with the current operating scenario, and calculate the pavement health index of each pavement management grid by combining the multi-source pavement attribute data of the corresponding grid. S3. Combine the static value of the pavement health index with the fluctuation range of the health index within a preset period to make a two-dimensional risk judgment and generate a corresponding level of sudden damage warning information. S4. Combine sudden damage early warning information, the functional protection level of the pavement, and the on-site defect characteristics to match the corresponding level of standardized operation and maintenance handling strategy, generate operation and maintenance tasks and execute closed-loop management of the whole process.

2. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 1, characterized in that, The specific rules for pavement management grid division in step S1 are as follows: the higher the functional support level and the more concentrated the aircraft wheel track effect, the smaller the grid size. Each pavement management grid is configured with a unique spatial association code, which includes a partition type field, a region level field, and a planar coordinate field. The functional attributes of each pavement management grid are directly matched with its GIS spatial location through the spatial association code.

3. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 2, characterized in that, The multi-source pavement attribute data bound to each pavement management grid in step S1 includes four categories: The first category is structural static attributes, including pavement structural layer parameters, construction date, and historical major and minor repair records; The second category is meteorological and environmental attributes, including temperature and humidity, freeze-thaw cycle records, extreme weather records, and corrosive medium spread records; The third category is load-related attributes, including aircraft takeoff and landing records, wheel track coverage ratio, and proportion of heavy-load aircraft in the corresponding grid. The fourth category is historical damage attributes, including historical pavement inspection indicators, damage records, repair records, and post-repair durability data; The four types of attribute data are dynamically synchronized to the gridded data base according to their respective collection and update frequencies.

4. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 1, characterized in that, The weight allocation rules in step S2 are as follows: The operation scenarios are pre-divided into four categories: routine operation scenarios, extreme weather scenarios, peak flight scenarios, and scenarios with high incidence of malfunctions. Each type of operation scenario corresponds to a set of weight allocation coefficients, which respectively correspond to four types of pavement influencing factors: structural safety factor, environmental degradation factor, load fatigue factor, and historical damage factor. The weighting coefficients for different operating scenarios are adjusted according to the core deterioration causes of the scenario. The environmental deterioration factor has the highest weight in extreme weather scenarios, the load fatigue factor has the highest weight in peak flight scenarios, and the historical damage factor has the highest weight in scenarios with high incidence of defects.

5. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 4, characterized in that, The pavement health index in step S2 is calculated using the following formula: ； in, For pavement health index, , , , The following are the scenario adaptation weight allocation coefficients corresponding to the structural safety factor, environmental degradation factor, load fatigue factor, and historical damage factor, in that order. For structural safety factor, As a factor of environmental degradation, The load fatigue factor, Historical damage factors; The structural safety factor The calculation formula is: ； In the formula, The structural correction coefficient is determined based on the historical major and minor repair records of the structural static attributes in the gridded data base database. To accommodate the deflection allowance of the corresponding grid pavement design, The measured representative deflection corresponds to the grid pavement. The environmental degradation factors The calculation formula is: ； In the formula, , , This is a seasonal correction factor, with a value determined based on the current season. The cumulative deduction value for freeze-thaw cycles, Accumulated deductions for extreme temperatures The cumulative deduction value for corrosive media; The load fatigue factor The calculation formula is: ； In the formula, This is the wheel track coverage correction coefficient, which is determined based on the wheel track coverage ratio of the corresponding grid. For the first time in the statistical period The actual number of takeoffs and landings of this aircraft type in the corresponding grid. For the first time within the design life of the pavement The number of permitted takeoffs and landings for this aircraft type; The historical damage factor The calculation formula is: ； In the formula, , , Preset the weighting coefficient for the impact of diseases; This represents the weight value for the disease type. The size of the disease is the weighted value. To repair the remaining lifetime weight value.

6. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 1, characterized in that, The two-dimensional risk assessment in step S3 specifically involves: (1) Based on the static value of the pavement health index, the pavement health index is divided into four basic risk levels in descending order. The higher the pavement health index, the lower the basic risk level. Each basic risk level corresponds to a preset basic inspection frequency. (2) Calculate the decline of the pavement health index of a single pavement management grid within the preset statistical period. If the decline is greater than the preset abnormality threshold, the basic risk level of the grid is increased by one level to obtain the corrected risk level. (3) Based on the pavement health index of the pavement management grid and the decline rate of the pavement health index within a preset statistical period, the probability of sudden damage to the grid in a preset future period is calculated using a logistic regression model. The formula for calculating the probability of sudden damage is as follows: ； in, , , These are the preset model coefficients obtained by fitting historical pavement defect data. To determine the expected decline in pavement health index within a pre-defined statistical period, The pavement health index for the pavement management grid; Then, according to the preset threshold range of the probability of sudden damage, the corresponding level of sudden damage early warning information is generated. The sudden damage early warning information includes the spatial association code of the corresponding grid, the corrected risk level, the probability of sudden damage and inspection and handling suggestions.

7. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 1, characterized in that, Step S4 specifically includes: Combining four dimensions—early warning information of sudden damage, the functional protection level of the pavement, and the type and size of the on-site defects—the defects to be dealt with are divided into three levels of operation and maintenance treatment. Each level of operation and maintenance treatment corresponds to the preset applicable defects, standardized treatment process, and treatment time limit, and generates corresponding operation and maintenance tasks. Simultaneously count the frequency of FOD occurrence in each pavement management grid. If the frequency of FOD occurrence in a single grid is greater than a preset frequency multiple threshold and the pavement health index of that grid is lower than a preset health index threshold, mark that grid as a FOD risk zone induced by disease, and correspondingly increase the inspection frequency and cleaning operation level of that grid. After the operation and maintenance task is completed, upload the verification materials that match the operation and maintenance handling level to complete the system verification. After the verification is passed, the handling record will be synchronously updated to the multi-source pavement attribute data of the corresponding grid.

8. The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement according to claim 7, characterized in that, The closed-loop management of the entire process in step S4 also includes the following steps: (1) For the pavement management grid that has been repaired, match the preset re-inspection cycle corresponding to the treatment process adopted in this grid. Before the preset re-inspection cycle expires, the re-inspection work order is automatically generated. If secondary defects are found during the re-inspection, the operation and maintenance treatment level of the secondary defects is upgraded by one level on the basis of the original treatment level and the operation and maintenance task is reassigned. The re-inspection results are synchronously updated to the multi-source pavement attribute data of the corresponding grid. (2) For pavement ancillary facilities that require periodic maintenance, establish corresponding grid periodic maintenance electronic files, automatically trigger the dispatch of operation and maintenance tasks before the preset maintenance cycle node, and store the full cycle maintenance records in the grid-based data base database.

9. An intelligent early warning and maintenance decision-making system for sudden damage to airport pavement, characterized in that, The intelligent early warning and maintenance decision-making method for sudden damage to airport pavement as described in any one of claims 1-8, the system comprising the following functional modules: The gridded data management module is used to divide pavement management grids with different sizes based on the functional zoning and structural physical boundaries of the airport pavement. It binds multi-source pavement attribute data with the entire life cycle to each pavement management grid and builds a dynamically updated gridded data base library. The pavement health index calculation module is used to match the weight allocation rules adapted to the current operating scenario and calculate the pavement health index of each pavement management grid by combining the multi-source pavement attribute data of the corresponding grid. The dual-dimensional risk warning module is used to combine the static value of the pavement health index and the decline of the pavement health index within a preset abnormality statistical period to make a dual-dimensional risk judgment and generate corresponding level of sudden damage warning information. The hierarchical operation and maintenance closed-loop management module is used to combine sudden damage early warning information, the functional protection level of the pavement, and the on-site defect characteristics to match the corresponding level of standardized operation and maintenance handling strategies, generate operation and maintenance tasks, and carry out closed-loop management of the entire process.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method steps of any one of claims 1-8.

Images