A method and system for intelligent operation and maintenance of civil airport flight area facilities and equipment

Abstract

A method and system for intelligent operation and maintenance of facilities and equipment in a civil airport flight zone, which relates to the field of airport operation and maintenance, includes: obtaining comprehensive status data of key facilities in the current flight zone, calculating the current loss data of the key facilities based on the usage intensity data and the environmental impact data; calculating the predicted loss data of the key facilities within a preset maintenance time period, and calculating the remaining use time of the key facilities; obtaining equipment usage specification files, parsing the equipment usage specification files, obtaining the preset use time threshold corresponding to the key facilities, and determining the maintenance frequency and preventive maintenance plan corresponding to the key facilities according to the remaining use time, and performing preventive maintenance on the key facilities at the preset maintenance frequency based on the preventive maintenance plan. The implementation of this method can improve the safety early warning capability of facility and equipment loss, and timely remind equipment users to repair or replace the equipment.

Description

Technical Field

[0001] The present application relates to the field of airport operation and maintenance, and in particular to a method and system for intelligent operation and maintenance of facilities and equipment in the airfield of a civil airport. Background Art

[0002] With the rapid development of the civil aviation industry, the number of airports is increasing, and the types and number of facilities in the airfield are also growing. In order to ensure the safety of flight operations and the quality of passenger travel services, key facilities in the airfield such as runways, taxiways, aprons, etc. must be in good working condition at all times.

[0003] In related technologies, the operation and maintenance management of airfield facilities mainly relies on regular manual inspections and passive repair reporting. Operation and maintenance personnel conduct routine inspections of various facilities in the airfield at fixed time intervals, record the status data of the facilities, and submit maintenance applications when problems are found.

[0004] However, this approach has certain flaws. The periodic inspection cycle is relatively random, and it is easy to miss the best time to detect facility wear and tear, resulting in untimely maintenance and possible problems in airport management. Summary of the invention

[0005] The present application provides a method and system for intelligent operation and maintenance of facilities and equipment in the airfield of a civil airport, which is used to improve the safety early warning capability of facility and equipment loss and promptly remind equipment users to repair or replace the equipment.

[0006] In the first aspect, the present application provides a smart operation and maintenance method for facilities and equipment in the airfield of a civil airport, which is applied to a smart operation and maintenance system, and the method includes: obtaining comprehensive status data of key facilities in the current airfield, the comprehensive status data including facility usage intensity data, environmental impact data and facility performance data; calculating the current loss data of the key facility based on the usage intensity data and the environmental impact data; inputting the current loss data into a performance prediction model to obtain predicted loss data of the key facility within a preset maintenance time period; calculating the remaining usage time of the key facility based on the predicted loss data and a performance curve corresponding to the key facility; obtaining an equipment usage specification file, and parsing the equipment usage specification file to obtain a preset usage time threshold corresponding to the key facility; when the remaining usage time is less than the preset usage time threshold, determining the corresponding maintenance frequency and preventive maintenance plan for the key facility according to the remaining usage time, and performing preventive maintenance on the key facility at the preset maintenance frequency based on the preventive maintenance plan.

[0007] By adopting the above technical solution, the comprehensive status data of key facilities in the current flight zone is obtained, including facility usage intensity data, environmental impact data and facility performance data, so as to fully understand the status of the facilities. The current loss data is calculated based on the usage intensity and environmental impact data, and then it is input into the performance prediction model to obtain the predicted loss data, and the remaining use time is calculated in combination with the performance curve corresponding to the key facilities. The equipment usage specification document is obtained and parsed to obtain the preset usage time threshold. When the remaining usage time is less than the threshold, the maintenance frequency and preventive maintenance plan are determined according to the remaining usage time, and preventive maintenance is performed at the preset maintenance frequency. It can accurately grasp the loss of key facilities, carry out preventive maintenance in a timely manner, and avoid the problem of untimely maintenance caused by facility loss.

[0008] In combination with some embodiments of the first aspect, in some embodiments, when the remaining usage time is less than the preset usage time threshold, after the step of determining the corresponding maintenance frequency and preventive maintenance plan for the key facility based on the remaining usage time, the method further includes: obtaining historical traffic volume, current temperature data and current precipitation data in the current pavement, and calculating current pavement wear data in the current pavement based on the historical traffic volume, the current temperature data and the current precipitation data; dividing the current pavement into multiple units based on the flight zone surface, each unit corresponding to the current pavement wear data within a preset range; The wear data is input into the pavement prediction model to obtain the predicted wear data of each unit within the preset maintenance time period; the remaining use time of each unit is calculated based on the pavement material performance curve and the predicted wear data; the pavement use specification file is obtained, and the pavement use specification file is parsed to obtain the preset use time threshold corresponding to the current pavement; when the remaining use time is less than the preset use time threshold, a preventive maintenance plan is determined according to the remaining use time, and a corresponding preset maintenance frequency is determined for each unit, and preventive maintenance is performed on each unit at the preset maintenance frequency based on the preventive maintenance plan.

[0009] By adopting the above technical solution, when the remaining use time is less than the preset use time threshold, the historical traffic volume, current temperature data and current precipitation data in the current pavement are obtained, and the current pavement wear data is calculated. The current pavement is divided into multiple units based on the flight zone surface, and the current pavement wear data is input into the pavement prediction model to obtain the predicted wear data of each unit within the preset maintenance time period. The remaining use time of each unit is calculated based on the pavement material performance curve and the predicted wear data, and the pavement use specification file is obtained and parsed to obtain the preset use time threshold. When the remaining use time is less than the threshold, a preventive maintenance plan is determined based on the remaining use time and a preset maintenance frequency is determined for each unit. Preventive maintenance can be performed to accurately predict the pavement wear, perform targeted maintenance, and extend the pavement service life.

[0010] In combination with some embodiments of the first aspect, in some embodiments, when the remaining usage time is less than the preset usage time threshold, the step of determining a preventive maintenance plan based on the remaining usage time specifically includes: when the remaining usage time is less than the preset usage time threshold, acquiring the pavement area image and position information of the unit based on the acquisition device; identifying the pavement area image to obtain the pavement type and damage information, the damage information includes the damage type, degree of damage and size of damage, and calculating the repair size based on the damage type, degree of damage and size of damage; inputting the pavement type into a preset repair model to obtain the repair material type; generating a preventive maintenance plan based on the position information, the repair size, the repair material type and the remaining usage time, and the maintenance intensity of the preventive maintenance plan is adjusted based on the remaining usage time.

[0011] By adopting the above technical solution, when the remaining use time is less than the preset use time threshold, the image and position information of the pavement area acquired by the acquisition device are used to identify the pavement type and damage information, and the repair size is calculated according to the damage type, degree and size. The pavement type is input into the preset repair model to obtain the type of repair material, and a preventive maintenance plan is generated based on the position information, repair size, repair material type and remaining use time, and the maintenance intensity is adjusted based on the remaining use time. This makes the maintenance plan more scientific and reasonable, and can select appropriate repair materials and maintenance intensity according to the specific conditions of the pavement, accurately repair the damaged area, and restore the pavement performance to the greatest extent.

[0012] In combination with some embodiments of the first aspect, in some embodiments, when the remaining usage time is less than the preset usage time threshold, a preventive maintenance plan is determined according to the remaining usage time, and a corresponding preset maintenance frequency is determined for each unit, and after the step of performing preventive maintenance on each unit at the preset maintenance frequency based on the preventive maintenance plan, the method also includes: obtaining GIS data, pavement area data, pavement hierarchical structure data and real photos of the current pavement, the GIS data including pavement boundary data, centerline data and marking line data; constructing a pavement basic plane model based on the GIS data, and creating a vertical section for each pavement area based on the pavement hierarchical structure data, and generating a multi-layer stereoscopic structure model based on the pavement basic plane model and the vertical section of each pavement area; mapping the real photos to the multi-layer stereoscopic structure model to obtain a three-dimensional model of the current pavement; marking the predicted wear data and the remaining usage time on the three-dimensional model, and marking the pavement area where the remaining usage time is less than the preset usage time threshold as a diseased area, and each remaining usage time corresponds to a different color on the three-dimensional model.

[0013] By adopting the above technical solution, the GIS data, road surface area data, road surface hierarchical structure data and real photos of the current road surface are obtained, and the basic plane model of the road surface is constructed based on the GIS data. A vertical section is created for each road surface area according to the road surface hierarchical structure data, and then a multi-layer three-dimensional structure model is generated. The real photos are mapped onto the model to obtain a three-dimensional model of the current road surface, and the predicted wear data and remaining use time are marked on the three-dimensional model. The road surface area with a remaining use time less than the preset use time threshold is marked as a diseased area, and each remaining use time corresponds to a different color on the three-dimensional model, which can intuitively display the condition of the road surface.

[0014] In combination with some embodiments of the first aspect, in some embodiments, when the remaining usage time is less than the preset usage time threshold, the corresponding maintenance frequency and preventive maintenance plan for the key facility are determined according to the remaining usage time, and after the step of performing preventive maintenance on the key facility at the preset maintenance frequency based on the preventive maintenance plan, the method also includes: obtaining the building type of all pre-modeled buildings in the current flight zone, and determining the corresponding geometric expression accuracy and attribute information depth in a preset parameter table according to the building type, the geometric expression accuracy includes multiple geometric information degree levels, and the attribute information depth includes multiple attribute information depth requirements; based on the geometric expression accuracy and the attribute information depth, obtaining modeling information corresponding to all the pre-modeled buildings, the modeling information includes real-shot images of buildings, equipment 3D models, equipment information, and real-shot texture materials of equipment; performing three-dimensional modeling on all the pre-modeled buildings based on the modeling information to obtain a three-dimensional model of the current flight zone; searching for all the pre-modeled buildings and corresponding building business parameters in the complete business data, and displaying the building business data and the pre-modeled buildings in a one-to-one correspondence on the three-dimensional model.

[0015] By adopting the above technical solution, the building types of all pre-modeled buildings in the current airfield are obtained, and the corresponding geometric expression accuracy and attribute information depth are determined in the preset parameter table according to the building type. Based on this, modeling information is obtained, including real-shot images of buildings, 3D models of equipment, equipment information, and real-shot texture materials of equipment. Three-dimensional modeling is performed on all pre-modeled buildings to obtain a three-dimensional model of the current airfield. All pre-modeled buildings and corresponding building business parameters are searched in the complete business data, and the building business data and the pre-modeled buildings are fused and displayed on the three-dimensional model in a one-to-one correspondence. This can realize three-dimensional visual management of airfield buildings, make the relevant information of the buildings more intuitive, and facilitate managers to understand the status of airfield buildings.

[0016] In combination with some embodiments of the first aspect, in some embodiments, when the remaining usage time is less than the preset usage time threshold, the corresponding maintenance frequency and preventive maintenance plan for the key facility are determined according to the remaining usage time, and after the step of performing preventive maintenance on the key facility at the preset maintenance frequency based on the preventive maintenance plan, the method also includes: acquiring real-time vehicle driving data in the current flight area, the real-time vehicle driving data including vehicle position, speed, acceleration and steering angle; analyzing the real-time vehicle driving data based on a preset behavior recognition algorithm to identify abnormal behavior data of the real-time vehicle, the abnormal behavior data including acceleration changes, speed changes and steering angle changes exceeding a preset threshold; calculating the risk coefficient around each of the key facilities according to the location information of the key facilities and the spatial distribution and temporal frequency of the abnormal behavior data; generating an abnormal behavior heat map based on the location information and abnormal behavior data of the key facilities greater than the preset risk threshold; and visually displaying the abnormal behavior heat map in the three-dimensional model.

[0017] By adopting the above technical solution, real-time vehicle driving data in the current flight zone is obtained, and these data are analyzed based on the preset behavior recognition algorithm to identify abnormal behavior data of real-time vehicles. The risk coefficient around each key facility is calculated based on the location information of the key facilities and the spatial distribution and time frequency of the abnormal behavior data. The correlation between abnormal behavior and key facilities is taken into account, making the assessment of risk coefficient more accurate. Based on the location information and abnormal behavior data of key facilities greater than the preset risk threshold, an abnormal behavior heat map is generated. The heat map can intuitively display the distribution and risk level of abnormal behavior in the flight zone.

[0018] In combination with some embodiments of the first aspect, in some embodiments, when the remaining usage time is less than the preset usage time threshold, the corresponding maintenance frequency and preventive maintenance plan of the key facility are determined according to the remaining usage time, and after the step of performing preventive maintenance on the key facility at the preset maintenance frequency based on the preventive maintenance plan, the method also includes: acquiring all collected data in the current flight area based on the collection equipment; dividing all collected data into business data based on the business part type, and dividing the business data into business module data based on the location information in the collected data; determining the business data exchange platform corresponding to the business data, and acquiring business docking data from the business data exchange platform; merging the business module data with the data of the same type in the business docking data according to the preset data type, and complementing the business module data with the data of different types in the business docking data to obtain complete business data; and displaying the complete business data.

[0019] By adopting the above technical solution, all collected data in the current flight zone are obtained based on the collection equipment. These data cover various information of the flight zone, such as pavement conditions, weather information, equipment operating status, etc. All collected data are divided into business data based on the business part type, so that the data can be classified and managed according to different business needs. At the same time, based on the location information in the collected data, the business data is divided into business module data, the business data exchange platform corresponding to the business data is determined, and the business docking data is obtained from the platform, realizing the expansion and supplement of data. According to the preset data type, the business module data and the data of the same type in the business docking data are merged, and the data of different types are complemented to obtain complete business data, and the complete business data is displayed, so that relevant personnel can intuitively understand the operating status of the flight zone.

[0020] In the second aspect, an embodiment of the present application provides an intelligent operation and maintenance system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent operation and maintenance system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the above-mentioned computer program product runs on an intelligent operation and maintenance system, the above-mentioned intelligent operation and maintenance system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on an intelligent operation and maintenance system, the intelligent operation and maintenance system executes the method described in the first aspect and any possible implementation method in the first aspect.

[0023] It is understandable that the intelligent operation and maintenance system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. This application calculates the current pavement wear data by obtaining the historical traffic volume, current temperature data and current precipitation data in the current pavement when the remaining use time is less than the preset use time threshold. The current pavement is divided into multiple units based on the flight zone surface, and the current pavement wear data is input into the pavement prediction model to obtain the predicted wear data of each unit within the preset maintenance time period. The remaining use time of each unit is calculated based on the pavement material performance curve and the predicted wear data, and the pavement use specification file is obtained and parsed to obtain the preset use time threshold. When the remaining use time is less than the threshold, a preventive maintenance plan is determined based on the remaining use time and a preset maintenance frequency is determined for each unit. Preventive maintenance can be performed to accurately predict the pavement wear, perform targeted maintenance, and extend the service life of the pavement.

[0026] 2. This application calculates the current pavement wear data by obtaining the historical traffic volume, current temperature data and current precipitation data in the current pavement when the remaining use time is less than the preset use time threshold. The current pavement is divided into multiple units based on the airfield surface, and the current pavement wear data is input into the pavement prediction model to obtain the predicted wear data of each unit within the preset maintenance time period. The remaining use time of each unit is calculated based on the pavement material performance curve and the predicted wear data, and the pavement use specification file is obtained and parsed to obtain the preset use time threshold. When the remaining use time is less than the threshold, a preventive maintenance plan is determined based on the remaining use time and a preset maintenance frequency is determined for each unit. Preventive maintenance can be performed to accurately predict the pavement wear, perform targeted maintenance, and extend the service life of the pavement.

[0027] 3. The present application obtains real-time vehicle driving data in the current flight zone, analyzes these data based on a preset behavior recognition algorithm, and can identify abnormal behavior data of real-time vehicles. According to the location information of key facilities and the spatial distribution and temporal frequency of abnormal behavior data, the risk coefficient around each key facility is calculated, and the correlation between abnormal behavior and key facilities is taken into account, making the assessment of risk coefficient more accurate. Based on the location information and abnormal behavior data of key facilities greater than the preset risk threshold, an abnormal behavior heat map is generated. The heat map can intuitively display the distribution and risk level of abnormal behavior in the flight zone. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of the intelligent operation and maintenance method of the civil airport flight area facilities and equipment in the embodiment of the present application;

[0029] Figure 2 It is another flowchart of the intelligent operation and maintenance method of the civil airport flight area facilities and equipment in the embodiment of the present application;

[0030] Figure 3It is another flow chart of the intelligent operation and maintenance method of the civil airport flight area facilities and equipment in the embodiment of the present application;

[0031] Figure 4 It is a schematic diagram of the structure of a physical device of the intelligent operation and maintenance system in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0033] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0034] The following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of the intelligent operation and maintenance method of civil airport airfield facilities and equipment in an embodiment of the present application.

[0035] S101. Obtain comprehensive status data of key facilities in the current flight zone, where the comprehensive status data includes facility usage intensity data, environmental impact data, and facility performance data.

[0036] Among them, the airfield refers to the area in the airport for aircraft takeoff, landing and taxiing, including runways, taxiways, aprons, etc. Key facilities refer to infrastructure that is crucial to flight safety and airport operations, such as runways, machinery and equipment, vehicles, navigation equipment, lighting systems, etc. Comprehensive status data refers to a multi-dimensional data set that comprehensively reflects the current operating status of the facilities. Facility usage intensity data refers to the frequency and load of facility usage, such as the average daily number of take-offs and landings. Environmental impact data refers to data on external factors that affect facility performance, such as temperature, precipitation, etc. Facility performance data refers to technical parameters that reflect the functional status of the facilities, such as the runway friction coefficient.

[0037] Specifically, the system collects and summarizes multi-dimensional data such as the usage of key facilities, surrounding environmental conditions, and performance parameters in real time through various channels such as various sensors, monitoring equipment, and management system interfaces.

[0038] In some embodiments, the acquisition of comprehensive status data can be achieved in a variety of ways: Optionally, the system can collect data in real time through the Internet of Things sensor network deployed on key facilities. Optionally, the flight area facility operation and maintenance management system exchanges data with other external application systems through data interfaces, and can obtain the map service interface of the airport geographic information system, the location service of the high-precision integrated positioning system, and the video service of the security management system, so as to obtain the field data collected by the mobile terminal device, thereby obtaining the comprehensive status data. It is understandable that other methods can also be used, which are not limited here.

[0039] S102. Calculate current loss data of the key facility based on the usage intensity data and the environmental impact data.

[0040] Among them, current loss data indicates the degree of wear or performance degradation of key facilities at the current point in time. Usage intensity data reflects the frequency and load of facility use, which directly affects the rate of facility loss. Environmental impact data includes factors such as temperature, humidity, and precipitation, which can accelerate or change the facility loss process.

[0041] Specifically, the system uses a pre-established loss model, using usage intensity data and environmental impact data as input variables. The loss model is built based on historical data and expert experience, and can simulate the loss process of facilities under different usage intensities and environmental conditions. By running this model, the system converts qualitative usage and environmental data into quantitative loss indicators, such as material wear depth, structural fatigue degree, etc.

[0042] In some embodiments, a cumulative damage model can be used for calculation. First, the system converts the usage intensity data (such as take-off and landing times) into the number of load cycles. Then, the fatigue limit of the material is adjusted according to the environmental impact data (such as temperature and humidity). Next, based on the linear cumulative damage theory, the system calculates the amount of damage caused by each load cycle and accumulates the damage of all cycles. Finally, the system compares the cumulative damage amount with the critical damage value of the material to derive the current degree of loss, where the calculation process includes the dynamic influence of usage intensity and environmental factors. Optionally, a machine learning method can be used for calculation. The system first uses historical data to train a loss prediction model, such as a random forest or a neural network model, and the training data includes historical usage intensity data, environmental impact data, and corresponding actual loss data.

[0043] S103: Input the current loss data into a performance prediction model to obtain predicted loss data of the key facility within a preset maintenance time period.

[0044] Among them, usage intensity data indicates the degree of load that key facilities bear during use, which may include factors such as traffic flow and vehicle weight. Environmental impact data refers to external environmental conditions that affect the status of facilities, such as temperature, precipitation, etc. Predicted loss data is used to indicate the degree of loss that may occur in facilities in the future, usually expressed in indicators such as the pavement condition index (PCI). The PCI value range is usually 0-100, where 100 represents the best state and 0 represents the worst state. Influencing factors refer to the specific degree of influence of various environmental and usage conditions on facility loss, such as temperature, precipitation, and traffic volume.

[0045] When the system needs to evaluate the future status of key facilities or formulate maintenance plans, it will perform the steps of calculating the predicted loss data of key facilities based on the usage intensity data and environmental impact data. Specifically, the system first obtains relevant data from the database or real-time monitoring equipment, including historical PCI values, temperature, precipitation, and traffic flow. Then, the system calculates each influencing factor according to the preset formula, which includes temperature impact, precipitation impact, and traffic volume impact. Then, the system calculates these influencing factors comprehensively to obtain variable C. Subsequently, the system substitutes variable C into the loss prediction formula containing adjustable parameters a, b, and c for calculation. The system optimizes the prediction results by fine-tuning these parameters (step size is 0.001). Finally, the system generates two curves of predicted values ​​and actual values, which are intuitively displayed in the coordinate system, with the x-axis representing the service life (maximum 30 years) and the y-axis representing the PCI value (maximum 100). The system adds a color legend in the upper left corner of the chart to clearly distinguish the PCI decay curve from the PCI measured curve. To ensure the accuracy and timeliness of the prediction, the system updates the data and recalculates the prediction results every year.

[0046] In some embodiments, the predicted loss data of key facilities can be calculated based on the usage intensity data and environmental impact data in a variety of ways: Optionally, the system can use machine learning methods to achieve prediction. First, the system collects a large amount of historical data, including usage intensity data, environmental impact data, and corresponding actual PCI value changes in the past few years, and then uses these data to train a machine learning model, such as a support vector machine (SVM) or a random forest algorithm. After the training is completed, the system inputs the current usage intensity data and environmental impact data, and the model can output the predicted PCI value changes. The system regularly updates the model with new data to improve the accuracy of the prediction. Finally, the system visualizes the prediction results and generates a comparison chart of the prediction curve and the actual value curve. Optionally, the system can use a method based on a mathematical model to achieve prediction. First, the system establishes a mathematical model containing multiple variables, which represent factors such as temperature, precipitation, and traffic load. The model contains equations that describe the effect of temperature on pavement materials, functions that represent the effect of precipitation on pavement erosion, and mathematical expressions that characterize the effect of traffic load on pavement structure. Then, the system substitutes the collected usage intensity data and environmental impact data into the corresponding variables in the model, and obtains the PCI value changes in the future through numerical calculations. The system can also perform parameter sensitivity analysis to evaluate the impact of different factors on the prediction results. Finally, the system generates a prediction curve based on the calculation results and compares and analyzes it with the actual value curve. It is understandable that other methods can also be used, which are not limited here.

[0047] S104. Calculate the remaining usage time of the key facility based on the predicted loss data and the performance curve corresponding to the key facility.

[0048] Among them, the predicted loss data indicates the future loss degree of key facilities predicted based on historical data and environmental factors, usually expressed in indicators such as the pavement condition index (PCI). The performance curve refers to a chart that describes the performance of key facilities over time, usually with time on the horizontal axis and performance indicators on the vertical axis. The remaining service life is used to indicate the length of time that the key facilities can continue to be used in the current state, usually in years or months.

[0049] Specifically, the system first compares the predicted loss data with the performance curve. The system uses a pre-set minimum acceptable level of performance indicators, which comes from industry standards or regulations of management departments. Then, the system finds the time point on the performance curve when the performance indicator first reaches this minimum acceptable level. Finally, the system calculates the difference between this time point and the current time to obtain the remaining usage time.

[0050] In some embodiments, the calculation of the remaining use time based on the predicted loss data and the performance curve can be achieved in a variety of ways: Optionally, the system uses an interpolation method. First, the system marks the performance values ​​of several future time points on the performance curve based on the predicted loss data. Then, the system uses linear interpolation or cubic spline interpolation to interpolate between known performance points to find the exact time point when the performance indicator first reaches the minimum acceptable level. Finally, the system uses the difference between this time point and the current time as the remaining use time. Optionally, the system collects historical data, including performance curves of different facilities, actual service life and other information. Then, the system uses this data to train a regression model, such as a random forest or a gradient boosting tree. After the training is completed, the system inputs the predicted loss data and part of the performance curve data of the current facility, and the model directly outputs the predicted remaining use time. It is understandable that other methods can also be used, which are not limited here.

[0051] S105: Acquire a device usage specification file, and parse the device usage specification file to obtain a preset usage time threshold corresponding to the key facility.

[0052] Among them, the equipment use specification document is a technical document containing information such as normal use conditions, maintenance requirements and expected service life of the equipment. The preset use time threshold represents the normal service life of the equipment set in advance by the equipment manufacturer or management department, and is an important reference indicator for judging whether the equipment needs to be replaced or overhauled.

[0053] Specifically, the system first obtains the corresponding equipment usage specification file from the database or external interface, and then uses the corresponding parsing technology, such as natural language processing or predefined parsing rules, to analyze the file. The system extracts information related to the usage time, especially the preset usage time threshold, which varies depending on factors such as device type and usage environment.

[0054] In some embodiments, the acquisition and parsing of the equipment usage specification file can be achieved in a variety of ways: Optionally, the system uses OCR technology combined with natural language processing. First, the system uses OCR technology to convert the specification file in paper or image format into electronic text. Then, the system uses natural language processing technology, such as keyword extraction and semantic analysis, to locate the paragraph containing the usage time information. Finally, the system extracts specific values ​​through regular expressions or other text processing technologies to obtain the preset usage time threshold. Optionally, the system establishes and uses a structured database. First, the system establishes a database containing the standard usage time of various facilities, including fields such as facility type, model, and preset usage time. Then, the system retrieves matching records in the database based on the type, model, and other information of the facility. If no completely matching record is found, the system uses a similarity algorithm to find the closest few records, and adjusts them according to the specific situation, and finally obtains an applicable preset usage time threshold. It is understandable that other methods can also be used, which are not limited here.

[0055] S106. When the remaining usage time is less than the preset usage time threshold, determine the corresponding maintenance frequency and preventive maintenance plan for the key facility according to the remaining usage time, and perform preventive maintenance on the key facility at the preset maintenance frequency based on the preventive maintenance plan.

[0056] The remaining service life indicates the length of time that the critical facility is expected to continue to be used, in months or years. The preset service life threshold refers to the standard value of the normal service life of the equipment. The maintenance frequency indicates the time interval for maintenance of the facility. The preventive maintenance plan is a collection of maintenance measures formulated to extend the life of the equipment. Preventive maintenance refers to regular maintenance work performed before serious problems occur in the equipment.

[0057] The system executes this step when it finds that the remaining usage time is less than the preset usage time threshold. Specifically, the system first determines the maintenance frequency based on the remaining usage time. The shorter the time, the higher the frequency. Then, the system analyzes the facility conditions and formulates a preventive maintenance plan with specific maintenance measures. Finally, the system executes the maintenance plan at the determined frequency and records the maintenance status for subsequent evaluation and adjustment.

[0058] In some embodiments, this step can be implemented in a variety of ways: Optionally, the system adopts a rule-based approach. First, the maintenance frequency is determined according to preset rules. Then, appropriate measures are selected from the maintenance measures library to form a plan. Finally, a maintenance plan is generated, tasks are assigned to relevant personnel to execute, and the equipment status is updated based on the execution results. Optionally, the system first uses historical data to train the model to determine the optimal maintenance frequency. Then, a personalized maintenance plan is generated based on the equipment status. Finally, the equipment status is monitored through the Internet of Things device, the maintenance process is automatically triggered, and the plan is dynamically adjusted based on feedback. It is understandable that other methods can also be used to implement this step, which is not limited here.

[0059] In some embodiments, after step S106, the following steps may be performed: Figure 2 Steps S201~S215 are shown.

[0060] The following is a further description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the intelligent operation and maintenance method of civil airport airfield facilities and equipment in an embodiment of the present application.

[0061] S201. Acquire real-time vehicle driving data in the current flight zone, where the real-time vehicle driving data includes vehicle position, speed, acceleration and steering angle.

[0062] By installing GPS positioning equipment and motion sensors on vehicles in the flight zone, the vehicle's position, speed, acceleration and steering angle data are collected and transmitted in real time. The data collection frequency can be set to once per second to ensure the real-time nature of the data, and the collected data is transmitted to the central data processing system via a wireless network. The system can set a data buffer to store the vehicle's driving data for the last 5 minutes.

[0063] S202: Analyze the real-time vehicle driving data based on a preset behavior recognition algorithm to identify abnormal behavior data of the real-time vehicle, where the abnormal behavior data includes acceleration changes, speed changes, and steering angle changes that exceed preset thresholds.

[0064] Preset behavior recognition algorithms refer to pre-set calculation methods for analyzing vehicle behavior patterns, usually based on machine learning or statistical analysis techniques. Abnormal behavior data refers to vehicle movement data that deviates from normal driving patterns. Preset thresholds refer to critical values ​​of various parameters set according to safety standards and normal operating specifications. Acceleration changes refer to the magnitude of vehicle acceleration or deceleration, speed changes refer to sudden increases or decreases in vehicle speed, and steering angle changes refer to the magnitude and frequency of vehicle steering.

[0065] First, the vehicle driving data is segmented using a sliding time window (such as 5 seconds). For the data in each time window, the rate of change of acceleration, speed and steering angle is calculated. Then, these change rates are compared with the preset thresholds, for example, the acceleration change threshold is set to 2m / s², the speed change threshold is set to 20km / h / s, and the steering angle change threshold is set to 30° / s. If the rate of change of any parameter exceeds the corresponding threshold, the data in the time window is marked as abnormal behavior data. At the same time, the system can also dynamically adjust the threshold based on the specific location of the vehicle (such as straight roads, curves, intersections, etc.) to improve the accuracy of recognition.

[0066] S203. Calculate the risk factor around each key facility based on the location information of the key facility and the spatial distribution and temporal frequency of the abnormal behavior data.

[0067] Time frequency refers to the ratio of the number of abnormal behaviors in a specific area to the time, usually in units of times / hour. The risk factor is a quantitative indicator used to indicate the degree of potential threats to critical facilities, usually expressed as a value between 0 and 1, with a larger value indicating a higher risk.

[0068] First, the flight area is divided into several grids, each of which is 20 meters by 20 meters in size. An impact range is defined for each key facility, such as 100 meters for a runway and 50 meters for a taxiway. The abnormal behavior data in each grid is counted to extract the following features: the number of abnormal behaviors, the distribution of abnormal behavior types (such as the proportion of speeding, sharp turns, etc.), and the average severity of abnormal behaviors (based on the degree of exceeding the threshold).

[0069] Perform time series analysis on abnormal behaviors of each grid: calculate the frequency of abnormal behaviors per hour, identify peak and trough periods, detect whether there are periodic patterns (such as an increase in abnormal behaviors during a specific period of time each day), and calculate the correlation coefficient of abnormal behaviors between each grid and adjacent grids, identify the spatial aggregation area of ​​abnormal behaviors, and conduct risk assessment on key facilities: conduct a comprehensive assessment of the grids within the influence range of each key facility, calculate the weighted average of abnormal behaviors within the influence range, and the weight decays with distance. Consider the importance factor of the facility type (such as the importance of runways is higher than taxiways), combine the time pattern, and give higher weights to abnormal behaviors during peak periods. Finally, calculate the final risk coefficient: risk coefficient = w1*weighted average of abnormal behaviors + w2*time pattern risk + w3*spatial aggregation + w4*facility importance, where w1, w2, w3, and w4 are the weights of each factor, which can be determined through historical data analysis or expert experience. Set a sliding time window (such as 24 hours) and regularly update the risk coefficient calculation: retain the impact of historical data, but give higher weights to recent data.

[0070] S204: Generate an abnormal behavior heat map based on the location information and abnormal behavior data of key facilities that are greater than a preset risk threshold.

[0071] The preset risk threshold refers to the critical value of the risk factor determined in advance, which is used to screen high-risk areas. Critical facilities refer to the infrastructure in the airfield that is critical to the operation of the airport, such as runways, taxiways, etc. Location information refers to the geographic coordinates of these facilities, usually expressed in longitude and latitude. Abnormal behavior data refers to the abnormal vehicle movement status information identified in the previous step, including speeding, sharp turns, etc. The abnormal behavior heat map is a visualization tool that uses color depth to intuitively indicate the density and risk level of abnormal behaviors in different areas.

[0072] According to the preset risk threshold (for example, the risk coefficient is greater than 0.7), high-risk critical facilities and their related abnormal behavior data are screened out, and the entire flight area is divided into uniform grids. The grid size can be set to 10 meters × 10 meters. Each grid is used as a data point of the heat map. The abnormal behavior data in each grid is aggregated, and the weighted frequency of abnormal behavior is calculated. The grid data is smoothed using the kernel density estimation method to generate a continuous density distribution. The kernel function can select the Gaussian kernel, and the bandwidth parameter can be determined by cross-validation. The density value is normalized to the range of 0-1, and the normalized density value is mapped to the color spectrum. A gradient color band from green (low risk) to red (high risk) can be used. For example, 0-0.2 can be mapped to green, 0.2-0.4 can be mapped to yellow, 0.4-0.6 can be mapped to orange, and 0.6-1 can be mapped to red. Based on the color mapping results, a heat map image is generated.

[0073] S205: Visually display the abnormal behavior heat map in the three-dimensional model.

[0074] Align the geographic coordinate system of the heat map with the coordinate system of the 3D model, perform coordinate conversion and projection transformation, convert the 2D heat map data into a format suitable for 3D display, discretize the heat map data into a series of 3D points or polygons, each of which contains location information and a corresponding risk value, map the risk value to height, and create an undulating surface with peaks representing high-risk areas. Generate a 3D texture based on the heat map data, create a semi-transparent color gradient texture where the colors represent different risk levels and the transparency allows visibility of the underlying model, and map the generated texture onto the surface of the 3D model. For planar heat map representations, project the texture directly onto the ground; for height representations, apply the texture to the generated undulating surface.

[0075] S206. Obtain the building types of all pre-modeled buildings in the current flight zone, and determine the corresponding geometric expression accuracy and attribute information depth in the preset parameter table according to the building type. The geometric expression accuracy includes multiple geometric information levels, and the attribute information depth includes multiple attribute information depth requirements.

[0076] Pre-modeled buildings refer to buildings in the flight zone that have been 3D models built in the system. Building type refers to the functional classification of buildings, such as terminal, hangar, control tower, etc. The preset parameter table is a pre-defined data structure that contains modeling parameters corresponding to different building types. Geometric expression accuracy refers to the degree of geometric detail of the 3D model, including multiple levels, such as low, medium, and high accuracy. Attribute information depth refers to the level of detail of non-geometric information related to the building, also including multiple levels, such as basic information, detailed information, complete information, etc.

[0077] In this step, the type information of all pre-modeled buildings is first obtained from the airfield building database. Then, the system queries the preset parameter table, which defines the modeling parameters corresponding to different building types. For each building type, the system determines the corresponding geometric expression accuracy and attribute information depth requirements. The geometric expression accuracy is divided into four levels: G1, G2, G3, and G4, corresponding to different accuracy requirements, from two-dimensional or symbolic identification (G1) to high-precision rendering display and manufacturing processing preparation (G4). The attribute information depth is also divided into four levels: N1, N2, N3, and N4, ranging from basic identity description (N1) to detailed asset and maintenance information (N4). The system assigns appropriate levels of geometric expression accuracy and attribute information depth to each building based on the importance and purpose of the building.

[0078] It can be understood that steps S206 to S209 can be executed after step S205 or after step S107.

[0079] S207. Based on the geometric expression accuracy and the depth of the attribute information, the modeling information corresponding to all the pre-modeled buildings is obtained, where the modeling information includes real-shot images of the buildings, 3D models of equipment, equipment information, and real-shot texture materials of the equipment.

[0080] Modeling information refers to a comprehensive data set used to construct and describe a building's 3D model. Architectural real-shot images refer to real photos of buildings, which are used for texture mapping and reference. Equipment 3D models refer to 3D geometric models of important equipment inside a building. Equipment information includes attribute data such as the equipment's technical parameters and maintenance records. Equipment real-shot texture materials refer to real-object photo textures used to enhance the realism of equipment 3D models.

[0081] The system retrieves detailed modeling information of each pre-modeled building from the building information database according to the geometric expression accuracy and attribute information depth determined in step S207.

[0082] For example, for entities such as terminal buildings (G3, N2), the system first collects and organizes existing design drawings to build a preliminary 3D model. It then conducts on-site surveys and mapping to obtain real-life mapping materials to improve model details; for pavements (G3, N2), the system exports 2D data such as GIS and grids from the pavement system, and builds a 3D hierarchical model in combination with hierarchical attribute data. At the same time, the real-life photos and texture materials are obtained on site to improve the realism of the model. The treatment of the soil surface area (G4, N2) is similar to that of the road surface, but with higher accuracy requirements, requiring more detailed layered models and high-quality textures. For road surface facilities, fences, clearance management, etc. (G4, N2), the system refers to relevant technical standards to establish accurate 3D models, conducts on-site physical measurements to ensure the accuracy of the model, and collects high-quality real-life photos and texture materials. For navigation lights, lighting fixtures, etc. (G4, N2), the system not only establishes accurate 3D models, but also collects equipment manufacturer design information, including light power and color data, for subsequent lighting effect simulation. The modeling of underground pipe networks (G4, N2) involves collecting existing pipe network data and on-site detection information, and establishing accurate underground pipe network models of different types including cables, optical cables, communications, sewage, water supply, rainwater, etc. For machinery and equipment, vehicles and non-powered equipment (G4, N2), the system collects detailed equipment information, including materials, specifications, production dates, etc., and obtains high-precision 3D models and real-life photos and textures.

[0083] S208: Perform three-dimensional modeling on all pre-modeled buildings based on the modeling information to obtain a three-dimensional model of the current flight zone.

[0084] The airfield 3D model refers to the digital 3D representation of all buildings, facilities and terrain in the airport airfield.

[0085] The system first parses the modeling information obtained in step S208, including high-precision measurement data, real-shot images of buildings, 3D models of equipment, and material information. For each pre-modeled building, the system performs a parametric modeling process based on its geometric expression accuracy (G1-G4) and attribute information depth (N1-N4) requirements. The system uses a modeling method based on boundary representation, combined with non-uniform rational B-spline technology, to describe complex surface geometry. For special airport structures, such as control towers, the system applies subdivision surface modeling technology to ensure the fidelity of the model. The system uses real-time global illumination algorithms and physically based rendering technology to apply material information extracted from real-shot images to the model surface to achieve realistic visual effects. For complex equipment, the system imports pre-prepared CAD models and optimizes the number of polygons through a mesh simplification algorithm to improve rendering efficiency while maintaining geometric accuracy. The system creates a high-precision terrain model, including accurate pavement slopes and drainage systems, by integrating procedural terrain generation technology and using the airport's digital elevation model data and orthophotos. Finally, the system uses spatial indexing technology to organize all monomer models and uses level-of-detail technology to optimize the rendering performance of large-scale scenes.

[0086] S209, searching the complete business data for all the pre-modeled buildings and corresponding building business parameters, and displaying the building business data and the pre-modeled buildings in a one-to-one correspondence on the three-dimensional model.

[0087] Complete business data refers to a structured database containing information related to operations, management and maintenance in the airport's integrated information management system, covering business data of various departments and systems of the airport, such as flight information, passenger flow, security records, etc. Pre-modeled buildings refer to standardized building models created in advance during the 3D modeling process, which contain basic geometric structure and attribute information. Building business parameters are operational indicators, performance parameters and maintenance data related to specific buildings or facilities, such as energy consumption, equipment status, utilization rate, etc. Building business data are the specific values ​​of these parameters and related metadata.

[0088] The system first connects to the airport's enterprise resource planning system and facility management system through a secure database connection protocol to obtain complete business data, retrieve corresponding business parameters based on the unique identifier of the pre-modeled building, and query results include asset utilization, energy consumption data, maintenance records, safety inspection logs, etc. These business data are encapsulated as data structures associated with three-dimensional model objects. The system uses spatial database technology to establish a three-dimensional spatial index to achieve efficient spatial query and data association. The system uses WebGL technology combined with 3D rendering libraries such as Three.js to achieve three-dimensional visualization on the browser side, and uses a data binding framework to dynamically bind business data to the properties of 3D objects, thereby realizing data aggregation and visualization technology based on spatial analysis, such as heat maps, contour maps, etc., integrating real-time data stream processing technology, and using message middleware to achieve real-time update and push of business data.

[0089] S210, acquiring all collected data in the current flight area based on the collection device.

[0090] Collection equipment is hardware equipment used to obtain various data of the flight zone, such as sensors, cameras, drones, etc. Collection data refers to various types of data obtained through these devices, including but not limited to pavement conditions, weather information, equipment operating status, etc. For example, pavement condition data includes information such as cracks, potholes, and water accumulation; weather information includes temperature, humidity, wind speed, etc.; equipment operating status includes the working condition of the lighting system, the operating efficiency of the drainage system, etc.

[0091] Specifically, various types of collection equipment are initialized first, including fixed sensor networks, mobile data collection vehicles, inspection drones, etc. For mobile collection equipment, real-time positioning technology is used to determine its precise position, and the collected data is associated with the location information. The drone adopts a pre-programmed flight path and uses high-resolution cameras and multi-spectral sensors to collect ground conditions. The system receives and processes data streams from various collection devices in real time, and implements data verification algorithms to detect and mark outliers or incomplete data records. For large-scale image data, the system uses edge computing technology to perform preliminary processing and feature extraction on the collection device side, and only transmits key information.

[0092] S211. Divide all the collected data into business data based on the business part type, and divide the business data into business module data based on the location information in the collected data.

[0093] In this step, the business department type refers to the division of departments responsible for different functions within the airport, such as the ground management division, lighting division, and clearance management division. Business data refers to the data set related to a specific business department. Business module data refers to a subset of data that is further subdivided according to function or geographical location within a specific business department. Location information refers to the geographic coordinates or relative location identifier of the data collection point. For example, the business data of the ground management division includes pavement, soil surface area, drainage facilities, etc.; and the data of the pavement business module is further subdivided into data of different locations such as runways, taxiways, and aprons.

[0094] Specifically, we first establish a business department classification tree to define the scope of responsibility and data type of each department. We use data classification algorithms, such as decision trees or support vector machines (SVMs), to assign the collected data to the corresponding business department categories based on the characteristics and attributes of the data. We further divide the data into business module data based on spatial clustering algorithms and location information. For data collected by mobile devices, we use trajectory analysis algorithms to map continuous location data to corresponding business modules.

[0095] S212: Determine a business data exchange platform corresponding to the business data, and obtain business connection data from the business data exchange platform.

[0096] The business data exchange platform is a system that centrally manages and distributes various types of business data. It provides a unified interface and standard for data interaction between different business systems. Business docking data refers to supplementary or extended data related to current business data obtained from the business data exchange platform.

[0097] Specifically, first establish a business data exchange platform registry to record the data exchange platform information corresponding to each business field, use a mapping algorithm to determine the corresponding business data exchange platform based on the attributes and metadata of the current business data, and after determining the platform, send a data request to the selected data exchange platform. The request parameters include key identifiers of the business data, time range, data type and other screening conditions.

[0098] S213: According to a preset data type, the business module data is merged with data of the same type in the business docking data, and the business module data is complemented with data of different types in the business docking data to obtain complete business data.

[0099] Preset data types refer to data classification standards pre-defined by the system, which are used to identify and distinguish different types of data. Complete business data refers to a comprehensive and detailed set of business data formed after fusion and complementation. For example, for pavement management, preset data types include pavement conditions, maintenance records, frequency of use, etc. The fusion process involves merging pavement condition data from on-site inspections and historical records, while the complementary process includes combining weather data with pavement usage data to analyze the impact of environmental factors on pavement conditions.

[0100] Specifically, first establish a data type mapping table to define the correspondence between each field in the business module data and the business docking data, and use the semantic analysis algorithm to identify fields with similar semantics in data from different sources. Then, use the pattern matching algorithm for structured data to automatically identify and align similar data structures, and use the weighted fusion algorithm to reasonably allocate the weights of data from different sources. Use natural language processing and computer vision technology to extract key information from unstructured data and associate it with structured data. Generate synthetic data based on existing data to supplement the data set, and finally obtain complete business data.

[0101] S214: Display the complete business data.

[0102] Specifically, data preprocessing is first performed, including data cleaning, normalization, and aggregation. Then, appropriate visualization methods are selected based on data characteristics, such as using a chart library to generate statistical charts, using a GIS library to display geospatial data, or using a 3D rendering engine to create three-dimensional visualization effects, and based on an adaptive layout algorithm, the view layout is automatically adjusted according to the characteristics of the display device.

[0103] It can be understood that steps S210 to S214 can be executed after step S209 or after step S107.

[0104] In some embodiments, step S107 may be followed by the following steps: acquiring historical event data in the current flight zone, the historical event data including the location coordinates of the event, the event type and the event occurrence time, predicting the event occurrence probability of each flight area in the current flight zone based on a preset event prediction model, and obtaining the event occurrence probability of each flight area in a preset future time period, the preset event prediction model uses the location coordinates, the event type and the event occurrence time as training data, determines the flight area where the event occurrence probability is greater than a preset probability threshold as a risk area, and marks the risk area on the flight zone map, and acquires the location information and driving trajectory data of all vehicles in the current flight zone in real time based on video monitoring equipment and vehicle positioning equipment, the location information includes the real-time geographic coordinates of all vehicles, and the driving trajectory data includes the historical driving paths of all vehicles in the current flight zone, inputs the location information into the preset vehicle path prediction model, and determines whether there is a target vehicle entering the risk area in the preset future time period, and if the target vehicle enters the risk area in the preset future time period, issues a warning message.

[0105] The following is a more detailed description of the process of the method provided by this implementation. Figure 3 , which is another flow chart of the intelligent operation and maintenance method of civil airport airfield facilities and equipment in the embodiment of the present application.

[0106] S301. Obtain comprehensive status data of key facilities in the current flight zone, where the comprehensive status data includes facility usage intensity data, environmental impact data, and facility performance data.

[0107] S302. Calculate current loss data of the key facility based on the usage intensity data and the environmental impact data.

[0108] S303: Input the current loss data into a performance prediction model to obtain predicted loss data of the key facility within a preset maintenance time period.

[0109] S304: Calculate the remaining usage time of the key facility based on the predicted loss data and the performance curve corresponding to the key facility.

[0110] S305: Obtain a device usage specification file, and parse the device usage specification file to obtain a preset usage time threshold corresponding to the key facility.

[0111] S306. When the remaining usage time is less than the preset usage time threshold, determine the corresponding maintenance frequency and preventive maintenance plan for the key facility according to the remaining usage time, and perform preventive maintenance on the key facility at the preset maintenance frequency based on the preventive maintenance plan.

[0112] It can be understood that steps S301 to S306 are similar to steps S101 to S106 and will not be described in detail here.

[0113] S307, obtaining historical traffic volume, current temperature data and current precipitation data on the current road surface, and calculating current road surface wear data on the current road surface based on the historical traffic volume, the current temperature data and the current precipitation data.

[0114] Pavement refers to the ground surface layer such as airport runways and taxiways for aircraft to travel on. Historical traffic volume refers to the number of aircraft passing on the pavement and the load conditions in the past period of time. Current temperature data refers to the temperature information of the area where the pavement is located at the current moment. Current precipitation data refers to the precipitation information of the area where the pavement is located at the current moment. Current pavement wear data refers to the current wear degree data of the pavement calculated based on the above factors.

[0115] When calculating the current pavement wear data, it is assumed that a section of runway has experienced many take-offs and landings in the past year. First, the data collected through the sensor network shows that this section of runway is subject to an average of 50 aircraft take-offs and landings per day, including different types of aircraft models and loads. These data are input into the cumulative damage model and converted into actual stress effects on the pavement through equivalent load conversion. At the same time, meteorological sensors provide the temperature fluctuation range and annual precipitation in the area. These data are then used to adjust the fatigue limit of the material, because temperature changes may cause thermal expansion and contraction of pavement materials, while precipitation affects the wetness and friction coefficient of the pavement. Then, all these processed data are input into the linear cumulative damage formula of the mine to calculate the cumulative damage value. The formula combines the effects of traffic load, temperature change and precipitation on pavement wear to obtain an estimated wear depth, such as 2 mm. This value is simulated by the model based on the pavement material properties and usage conditions, reflecting the actual wear of the current pavement.

[0116] S308, dividing the current pavement into a plurality of units based on the flight zone surface, each unit corresponding to the current pavement wear data within a preset range.

[0117] The airfield surface refers to the ground area within the airport for aircraft activities, including runways, taxiways, etc. A unit refers to a smaller area unit after the entire pavement is divided. A preset range refers to a wear data interval determined in advance.

[0118] The system divides the entire pavement into multiple units of appropriate sizes based on the actual layout and characteristics of the airfield. The division can be a uniform grid or an uneven division based on the usage characteristics of the pavement, such as dividing smaller units at turns or joints. For each divided unit, the system will match its corresponding current pavement wear data with a preset wear data range. This preset range can be multiple levels determined based on the pavement material properties and usage requirements, such as slight wear (0-5%), moderate wear (5-15%), severe wear (more than 15%), etc. Through this division, the system can more accurately locate and evaluate the wear condition of various parts of the pavement.

[0119] S309: Input the current pavement wear data into a pavement prediction model to obtain predicted wear data for each unit within a preset maintenance time period.

[0120] The pavement prediction model is a mathematical model used to predict the future wear of the pavement. The preset maintenance period refers to a predetermined period of time, usually the time period before the next scheduled maintenance. The predicted wear data refers to the degree of pavement wear at a certain point in the future predicted by the model.

[0121] The system uses the current pavement wear data obtained in the previous step as input and passes it into the pre-trained pavement prediction model. The model will predict the pavement wear within a preset maintenance period (such as the next 6 months or 1 year). The prediction results will give the expected wear data of each divided unit at the end of the period. These prediction data include multiple indicators such as wear depth, crack degree, and flatness index.

[0122] The construction process of the pavement prediction model includes: the training data includes historical traffic data collected over many years, such as the number of aircraft takeoffs and landings, aircraft models and loads, as well as meteorological data, including temperature, precipitation and humidity. The input data is the processed traffic volume, meteorological data, and current wear status. The output data is the predicted future wear degree, such as wear depth or crack propagation rate. The specific training process includes dividing the data into training set, validation set and test set, training the model on the training set, optimizing parameters using batch gradient descent, selecting the best hyperparameters through cross-validation, evaluating the model performance on the validation set, and using indicators such as mean square error (MSE) to adjust the model structure or parameters.

[0123] S310: Calculate the remaining use time of each unit according to the pavement material performance curve and the predicted wear data.

[0124] The pavement material performance curve is a function graph that describes the performance changes of pavement materials under different use conditions. It usually takes time or use intensity as the horizontal axis and performance indicators as the vertical axis. Predicted wear data refers to the degree of wear that may occur on the pavement in the future, obtained through model prediction. Unit refers to the smaller area unit after the entire pavement is divided. The remaining service life refers to the time that the pavement can continue to be used safely without large-scale maintenance.

[0125] The system first obtains the performance curve of each pavement material, which is usually provided by the material manufacturer or obtained by fitting a large amount of experimental data. For each divided pavement unit, the system compares its predicted wear data with the performance curve of the corresponding material. Through mathematical methods such as interpolation or extrapolation, the system can find the time point on the performance curve that corresponds to the predicted wear data. The difference between this time point and the current time is the remaining service life of the unit.

[0126] S311, obtaining a road surface usage specification file, and parsing the road surface usage specification file to obtain a preset usage time threshold corresponding to the current road surface.

[0127] The pavement usage specification document refers to an official document formulated by the relevant management department that stipulates the pavement usage standards and maintenance requirements. The preset usage time threshold refers to the maximum allowable usage time of the pavement before large-scale repairs or replacements are required, as stipulated in the specification document.

[0128] The system obtains the latest version of the pavement usage specification file from a database or file server. These files are usually in a structured text format, such as XML or JSON. The system uses natural language processing (NLP) technology to parse the file and extract information related to the current pavement type, material, and usage conditions. During the parsing process, the system identifies keywords and values, including "service life", "maintenance cycle", "performance indicators", etc. By analyzing and correlating this information, the system determines the preset usage time threshold applicable to the current pavement, and the system selects the corresponding threshold based on the specific parameters of the current pavement.

[0129] S312: When the remaining usage time is less than the preset usage time threshold, the road surface area image and position information of the unit are acquired based on the acquisition device.

[0130] Acquisition equipment refers to various sensors and cameras used to obtain pavement information. Pavement area images refer to high-resolution pictures of specific pavement units, which are used to analyze pavement conditions in detail. Location information refers to the precise geographic coordinates of pavement units in the entire flight area.

[0131] When the system determines that the remaining usage time of a pavement unit is less than the preset usage time threshold, a more detailed inspection process will be triggered. The system first activates the image acquisition equipment installed in the flight area, including a high-definition camera fixed at a specific location, or a multi-angle camera system installed on a moving vehicle. These devices are programmed to automatically shoot the target unit at multiple angles and multiple lighting conditions to capture the overall situation of the pavement. At the same time, the system calls positioning equipment, such as differential GPS or real-time dynamic positioning (RTK) systems, to obtain the precise geographic coordinates of the pavement unit. The coordinate information is associated with the image data to form a geo-tagged image data set. For example, for a 5-meter-by-5-meter pavement unit, the system collects 20 high-resolution images, each of which is accompanied by location information accurate to the centimeter level.

[0132] S313, identifying the road surface area image to obtain the road surface type and damage information, wherein the damage information includes the damage type, damage degree and damage size, and calculating the repair size according to the damage type, damage degree and damage size.

[0133] The repair size is the size of the area that needs to be repaired, including specific values ​​of length, width and depth. The type of repair material is the specific material used for the repair determined in the previous step, such as a specific type of asphalt mixture or cement concrete. The remaining service life is the estimated safe service life of the pavement without large-scale repairs calculated by the prediction model, in months or years. The preventive maintenance plan is a series of specific maintenance measures and operational procedures formulated to extend the service life of the pavement. The maintenance intensity refers to the scale and depth of the maintenance measures, including quantitative indicators such as material usage, construction depth and scope. The preset maintenance frequency is the time interval for performing maintenance measures, in days, weeks or months.

[0134] First, the collected images of the pavement area are preprocessed, including image enhancement, denoising and standardization. Subsequently, the system uses deep learning models, such as convolutional neural networks (CNNs), to analyze the images. This CNN model has been trained with a large amount of annotated data and can accurately identify different pavement types and various damage conditions. The identification of pavement types is based on surface texture, color and structural features. For the extraction of damage information, the system uses instance segmentation algorithms, such as Mask R-CNN, to accurately locate and classify each damage instance. The degree of damage is automatically evaluated using predefined scoring criteria, such as cracks with a width greater than 10mm being classified as severe damage. The damage size is obtained through pixel-level measurement, and the system uses calibration objects in the image (such as markers of known size) to convert the actual size. After obtaining this information, the system calculates the repair size according to the preset repair rules.

[0135] S314: Input the pavement type into a preset repair model to obtain a repair material type.

[0136] The system passes the pavement type identified in the previous step as an input parameter to the preset repair model, which is a decision tree or random forest algorithm built based on a large amount of historical repair data and expert knowledge. The model divides the pavement into major categories, such as asphalt or concrete. Then, based on factors such as damage type, damage degree, climate conditions, and traffic load, the model uses these factors as different nodes of the decision tree, and finally reaches the leaf node of the recommended repair material through conditional judgment. For example, for minor surface cracks on asphalt pavement, the model recommends the use of emulsified asphalt seal; for severe concrete pavement fractures, the model recommends the use of fast-hardening cement concrete. The model also contains a material performance database, which can select the most suitable material formula based on local environmental factors such as temperature and humidity.

[0137] S315. Generate a preventive maintenance plan based on the location information, the repair size, the type of repair material and the remaining use time, adjust the maintenance intensity of the preventive maintenance plan based on the remaining use time, and determine a corresponding preset maintenance frequency for each unit, and perform preventive maintenance on each unit based on the preventive maintenance plan and the preset maintenance frequency.

[0138] First, a maintenance measure database is established. The maintenance measure database contains all the maintenance measures that have been implemented. Each measure has detailed attributes, such as applicable pavement type, damage type, construction method, required equipment, material specifications, expected effect and cost, etc. According to the input pavement type, damage information and repair material type, the applicable measures are screened from the maintenance measure database. Then, the system uses a decision tree algorithm to select the most suitable maintenance measure according to the degree of damage, repair size and remaining use time. The system dynamically adjusts the maintenance intensity according to the remaining use time. The system uses a predefined intensity adjustment matrix to map the remaining use time to different intensity levels. The system determines the preset maintenance frequency for each pavement unit. This process uses time series analysis methods, such as the autoregressive integrated moving average model (ARIMA), to analyze the trend of pavement conditions over time. Based on the pavement usage intensity, climate conditions and historical degradation rate, the system predicts the future degradation curve and sets the maintenance trigger threshold. When the predicted pavement condition reaches this threshold, a maintenance activity is scheduled.

[0139] In some embodiments, the following steps may be further included after step S315:

[0140] The GIS data, road surface area data, road surface hierarchical structure data and real photos of the current road surface are obtained. The GIS data includes road surface boundary data, center line data and marking line data.

[0141] In this step, GIS data is a data set used in geographic information systems to describe geographic spatial features. In pavement management, GIS data includes pavement boundary data, centerline data, and marking line data. The centerline data describes the central axis of the pavement. The marking line data includes various marking lines on the pavement, such as runway markings, taxiway centerlines, etc. The pavement area data divides the entire pavement into different functional areas, such as runways, taxiways, aprons, etc. The pavement hierarchical structure data describes the vertical composition of the pavement, including the material type and thickness of each layer such as the surface layer, base layer, and subbase layer.

[0142] In this step, the GIS data of the current pavement is first obtained through the interface with the airport GIS database, and the vector data of the pavement boundary, center line and marking line are extracted from the GIS database, the pavement area data is obtained from the airport asset management database, and the pavement hierarchical structure data, including the material specifications, thickness and construction date of each layer, are extracted from the pavement design documents or the most recent engineering records.

[0143] A road surface basic plane model is constructed based on the GIS data, a vertical section is created for each road surface area based on the road surface hierarchical structure data, and a multi-layer three-dimensional structure model is generated based on the road surface basic plane model and the vertical sections of each road surface area.

[0144] In this step, the basic plane model of the pavement is a two-dimensional representation of the geometric features of the pavement plane, the vertical section shows the structural composition of the pavement in the vertical direction, and the multi-layer three-dimensional structure model combines the plane and vertical information to form a complete three-dimensional pavement representation.

[0145] In this step, the model building process is as follows: the system first uses computational geometry algorithms to process GIS data to build a basic plane model of the road surface. The polygon processing algorithm converts the road surface boundary data into closed polygons to form the outer contour of the road surface. The spline interpolation algorithm processes the centerline data and generates a smooth centerline curve. The vector graphics processing algorithm accurately draws the marker line data on the plane model. For vertical section creation, the system generates detailed vertical section diagrams for each area based on the road surface layered structure data. The CAD modeling algorithm creates the thickness and material property representation of each layer. The interpolation algorithm generates a continuous layer interface between known points to ensure the integrity of the section model. The generation of multi-layer stereoscopic structure models uses a three-dimensional modeling algorithm, such as scanning or stretching, to extend the two-dimensional plane contour in the vertical direction to form a three-dimensional body. For each layer, a corresponding three-dimensional geometric body is generated according to its position and thickness in the vertical section. Digital elevation model (DEM) data is used to adjust the elevation of each layer to reflect the actual terrain characteristics.

[0146] The real-life photo is mapped onto the multi-layer stereoscopic structure model to obtain a three-dimensional model of the current road surface.

[0147] In this step, the image processing algorithm first preprocesses the real photos. The geometric correction algorithm eliminates the deformation caused by lens distortion and shooting angle. The color correction and brightness equalization algorithms ensure that the photos taken under different conditions have consistent visual effects. The photogrammetry algorithm determines the exact shooting position and direction of each photo. For aerial photos, the algorithm uses the GPS and IMU data recorded by the drone; for photos taken on the ground, the feature point-based image registration algorithm associates the photos with known geographic reference points. The projection transformation algorithm projects each photo to the corresponding position of the multi-layer stereo structure model. The coordinate conversion algorithm maps the two-dimensional image coordinates to the three-dimensional model coordinates. For each point on the model surface, the interpolation algorithm calculates its corresponding position in the photo and extracts the corresponding color and texture information. In the overlapping area, the image fusion algorithm uses weighted averaging or multi-band blending to mix the information from different photos. Block processing and multi-resolution techniques are used to process large-scale image data to improve processing efficiency while maintaining details. The texture compression algorithm reduces the amount of data, and the detail enhancement algorithm highlights key features.

[0148] The predicted wear data and the remaining usage time are marked on the three-dimensional model, and the road surface area where the remaining usage time is less than the preset usage time threshold is marked as a damaged area, and each remaining usage time corresponds to a different color on the three-dimensional model.

[0149] In this step, a spatial data processing algorithm is used to associate the predicted wear data with each part of the three-dimensional model, and the two-dimensional wear prediction data is mapped to the corresponding position in the three-dimensional space. An interpolation algorithm, such as Kriging or inverse distance weighted method, is used to ensure that the wear data is smoothly distributed over the entire pavement. A numerical analysis algorithm is used for the remaining use time to calculate the remaining use time of each area based on the predicted wear data and the current condition of the pavement. A threshold comparison algorithm is used to compare the remaining use time of each area with a preset threshold. For areas where the remaining use time is less than the preset threshold, the system uses a geometric marking algorithm to make special annotations on the three-dimensional model, such as highlighting or adding specific patterns. During the color coding process, the system first discretizes the remaining use time range into multiple intervals. The system uses a color mapping algorithm to assign a specific color to each interval. For example, red can be used to represent the area with the shortest remaining use time, green can be used to represent the area with the longest remaining use time, and transition colors such as yellow and orange can be used in between. The system uses a texture mapping algorithm to apply these colors to the corresponding areas of the three-dimensional model. In order to enhance the visualization effect, the system also implements dynamic rendering technology, allowing users to switch between different remaining use time thresholds and update the color representation of the model in real time. In addition, the system integrates a label generation algorithm that can add digital labels to the 3D model to display specific predicted wear values ​​and remaining usage time. In order to handle large-scale data, the layered detail (LOD) technology is used to adjust the displayed information density at different zoom levels, and finally an interactive query function is implemented, allowing users to click on any part of the 3D model to obtain detailed predicted wear data and remaining usage time information for that area.

[0150] The following describes the intelligent operation and maintenance system in the embodiment of the present invention from the perspective of hardware processing. Figure 4 , which is a schematic diagram of a physical device structure of the intelligent operation and maintenance system in an embodiment of the present application.

[0151] It should be noted that Figure 4 The structure of the intelligent operation and maintenance system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0152] like Figure 4As shown, the intelligent operation and maintenance system includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in RAM403. CPU401, ROM402 and RAM403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0153] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0154] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0155] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0157] Specifically, the intelligent operation and maintenance system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the intelligent operation and maintenance method for civil airport airfield facilities and equipment provided in the above embodiment is implemented.

[0158] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the intelligent operation and maintenance system described in the above embodiment; or it may exist independently without being assembled into the intelligent operation and maintenance system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the intelligent operation and maintenance system, the intelligent operation and maintenance system implements the intelligent operation and maintenance method for civil airport flight area facilities and equipment provided in the above embodiment.

[0159] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0160] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0161] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for intelligent operation and maintenance of facilities and equipment in a civil airport flight area, characterized in that: Applied to the intelligent operation and maintenance system, the method includes: Obtaining comprehensive status data of key facilities in the current flight zone, the comprehensive status data including facility usage intensity data, environmental impact data and facility performance data, the key facilities are the infrastructure in the current flight zone, including runways, machinery and equipment, vehicles, navigation equipment and lighting systems, the usage intensity data are the usage frequency and load of the facilities, including the average daily take-offs and landings, and the environmental impact data are the external factors data that affect the performance of the facilities, including temperature and precipitation; Calculating current loss data of the key facility based on the usage intensity data and the environmental impact data; Inputting the current loss data into a performance prediction model to obtain predicted loss data of the key facilities within a preset maintenance time period; Calculating the remaining usage time of the key facility based on the predicted loss data and the performance curve corresponding to the key facility; Obtaining a device usage specification file, and parsing the device usage specification file to obtain a preset usage time threshold corresponding to the key facility; In the case where the remaining usage time is less than the preset usage time threshold, determining a preventive maintenance plan corresponding to the key facility according to the remaining usage time, and performing preventive maintenance on the key facility at a preset maintenance frequency based on the preventive maintenance plan, wherein the preventive maintenance plan includes a maintenance frequency; Acquire historical traffic volume, current temperature data and current precipitation data on the current road surface, and calculate current road surface wear data on the current road surface based on the historical traffic volume, the current temperature data and the current precipitation data; Dividing the current pavement into a plurality of units based on the flight zone surface, each of the units corresponding to the current pavement wear data within a preset range; Inputting the current pavement wear data into a pavement prediction model to obtain predicted wear data for each unit within a preset maintenance time period; Calculating the remaining service life of each of the units according to the pavement material performance curve and the predicted wear data; Obtaining a road surface usage specification file, and parsing the road surface usage specification file to obtain a preset usage time threshold corresponding to the current road surface; When the remaining usage time is less than the preset usage time threshold, a preventive maintenance plan is determined according to the remaining usage time, and a corresponding preset maintenance frequency is determined for each of the units, and preventive maintenance is performed on each of the units at the preset maintenance frequency based on the preventive maintenance plan; Obtain the building types of all pre-modeled buildings in the current flight zone, and determine the corresponding geometric expression accuracy and attribute information depth in a preset parameter table according to the building type, wherein the geometric expression accuracy includes multiple geometric information degree levels, and the attribute information depth includes multiple attribute information depth requirements; Based on the geometric expression accuracy and the attribute information depth, the modeling information corresponding to all the pre-modeled buildings is obtained, wherein the modeling information includes real-shot images of buildings, 3D models of equipment, equipment information, and real-shot texture materials of equipment; Performing three-dimensional modeling on all the pre-modeled buildings based on the modeling information to obtain a three-dimensional model of the current flight zone; Searching for all the pre-modeled buildings and corresponding building business parameters in the complete business data, and integrating the building business data corresponding to the building business parameters with the pre-modeled buildings in a one-to-one correspondence and displaying them on the three-dimensional model; Acquiring real-time vehicle driving data within the current flight zone, the real-time vehicle driving data including vehicle position, speed, acceleration and steering angle; Analyzing the real-time vehicle driving data based on a preset behavior recognition algorithm to identify abnormal behavior data of the real-time vehicle, wherein the abnormal behavior data includes acceleration changes, speed changes, and steering angle changes exceeding a preset threshold; Calculate the risk factor around each of the key facilities according to the location information of the key facilities and the spatial distribution and temporal frequency of the abnormal behavior data; Generate abnormal behavior heat map based on location information and abnormal behavior data of key facilities with risk thresholds greater than preset thresholds; Visually displaying the abnormal behavior heat map in the three-dimensional model; Acquire all collected data in the current flight area based on the collection equipment; Dividing all the collected data into business data based on business part types, and dividing the business data into business module data based on location information within the collected data; Determine a business data exchange platform corresponding to the business data, and obtain business connection data from the business data exchange platform; According to the preset data type, the business module data is merged with the data of the same type in the business docking data, and the business module data is complemented with the data of different types in the business docking data to obtain complete business data; The complete business data is displayed.

2. The method according to claim 1, characterized in that The step of determining a preventive maintenance plan according to the remaining usage time when the remaining usage time is less than the preset usage time threshold specifically includes: When the remaining usage time is less than the preset usage time threshold, acquiring the road surface area image and position information of the unit based on the acquisition device; Identify the road surface area image to obtain road surface type and damage information, wherein the damage information includes damage type, damage degree and damage size, and calculate the repair size according to the damage type, damage degree and damage size; Inputting the pavement type into a preset repair model to obtain a repair material type; A preventive maintenance plan is generated based on the location information, the repair size, the type of repair material and the remaining use time, and the maintenance intensity of the preventive maintenance plan is adjusted based on the remaining use time.

3. The method according to claim 1, characterized in that In the case where the remaining usage time is less than the preset usage time threshold, determining a preventive maintenance plan according to the remaining usage time, determining a corresponding preset maintenance frequency for each of the units, and performing preventive maintenance on each of the units at the preset maintenance frequency based on the preventive maintenance plan, the method further includes: Acquire GIS data, road surface area data, road surface hierarchical structure data and real photos of the current road surface, wherein the GIS data includes road surface boundary data, center line data and marking line data; Constructing a road surface basic plane model based on the GIS data, creating a vertical section for each road surface area based on the road surface hierarchical structure data, and generating a multi-layer three-dimensional structure model based on the road surface basic plane model and the vertical section of each road surface area; Mapping the real-life photos onto the multi-layer three-dimensional structure model to obtain a three-dimensional model of the current road surface; The predicted wear data and the remaining usage time are marked on the three-dimensional model, and the road surface area where the remaining usage time is less than the preset usage time threshold is marked as a damaged area, and each remaining usage time corresponds to a different color on the three-dimensional model.

4. A smart operation and maintenance system, characterized in that: The intelligent operation and maintenance system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent operation and maintenance system to execute the method as described in any one of claims 1-3.

5. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the intelligent operation and maintenance system, the intelligent operation and maintenance system executes the method as described in any one of claims 1-3.

6. A computer program product, characterized in that When the computer program product runs on the intelligent operation and maintenance system, the intelligent operation and maintenance system executes the method as described in any one of claims 1-3.

Images