CN114999117B - Airport pavement ice and snow condition monitoring and early warning method, system, terminal and medium - Google Patents
Airport pavement ice and snow condition monitoring and early warning method, system, terminal and medium Download PDFInfo
- Publication number
- CN114999117B CN114999117B CN202210745767.1A CN202210745767A CN114999117B CN 114999117 B CN114999117 B CN 114999117B CN 202210745767 A CN202210745767 A CN 202210745767A CN 114999117 B CN114999117 B CN 114999117B
- Authority
- CN
- China
- Prior art keywords
- pollutant
- data
- condition
- simulated
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 268
- 231100000719 pollutant Toxicity 0.000 claims abstract description 268
- 238000004088 simulation Methods 0.000 claims abstract description 78
- 238000012360 testing method Methods 0.000 claims abstract description 44
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000009825 accumulation Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 21
- 239000000356 contaminant Substances 0.000 claims description 20
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000010276 construction Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 230000005855 radiation Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000004566 building material Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Environmental & Geological Engineering (AREA)
- Primary Health Care (AREA)
- Geology (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method, a system, a terminal and a medium for monitoring and early warning ice and snow conditions on an airport pavement, wherein the method comprises the following steps: based on a preset simulation test piece and metering equipment arranged on the simulation test piece, obtaining simulation training data of an airport pavement under the condition of simulating ice and snow, wherein the simulation training data comprise simulation meteorological data, simulation pavement temperature data and simulation pollutant condition data; constructing a pollutant condition prediction model based on XGBoost algorithm and simulated training data; acquiring predicted input data of the airport pavement in real time based on metering equipment, wherein the predicted input data comprises real-time meteorological data and real-time pavement temperature data; predicting the ice and snow condition of the road surface based on the pollutant condition prediction model and the predicted input data, and outputting pollutant prediction data; and sending out an early warning signal based on the pollutant prediction data and a preset early warning grade standard. The method has the effects of improving the accuracy of prediction of the ice and snow condition of the airport pavement and timely sending out ice and snow condition early warning signals.
Description
Technical Field
The application relates to the technical field of airport pavement ice and snow condition research, in particular to an airport pavement ice and snow condition monitoring and early warning method, an airport pavement ice and snow condition monitoring and early warning system, an airport pavement ice and snow condition monitoring and early warning terminal and an airport pavement ice and snow condition monitoring and early warning medium.
Background
The airport pavement refers to one or more layers of artificial structures paved on the top surfaces of natural soil bases and base layers by road building materials, and is a runway for taking off, landing, sliding, maintaining and parking airplanes, such as runways, taxiways, passenger plane floors, maintenance floors, cargo plane floors, parking floors and the like.
In the field of aviation, ensuring the safety of air transportation is a primary task, and ensuring the smoothness and safety of airport pavement is an important one. If snow or ice occurs on the airport pavement, the airplane can land or take off at extremely high risk, so that the ice and snow conditions of the airport pavement are predicted, and early warning is necessary.
At present, most of the early warning of the airport pavement is performed through the weather angle, the icing or snow situation of the airport pavement is predicted according to the weather situation, and an early warning signal is sent out. However, since building materials or building structures of various airfield pavement are different, heat transfer effects of different airfield pavement are different, and ice and snow conditions occurring in the same weather conditions may be different, prediction is performed only by means of weather forecast or from a weather perspective, and accuracy is not sufficient.
Disclosure of Invention
In order to improve the accuracy of ice and snow condition prediction of an airport pavement and timely send ice and snow condition early warning signals, the application provides an airport pavement ice and snow condition monitoring and early warning method, an airport pavement ice and snow condition monitoring and early warning system, a terminal and a medium.
In a first aspect, the application provides a method for monitoring and early warning ice and snow conditions on an airport pavement, which adopts the following technical scheme: a monitoring and early warning method for ice and snow conditions of an airport pavement comprises the following steps:
based on a preset simulation test piece and metering equipment arranged on the simulation test piece, obtaining simulation training data of the airport pavement under the condition of simulating ice and snow, wherein the simulation training data comprise simulation meteorological data, simulation pavement temperature data and simulation pollutant condition data of the airport pavement;
constructing a pollutant condition prediction model based on an XGBoost algorithm and the simulated training data;
acquiring predicted input data of the airport pavement in real time based on the metering equipment, wherein the predicted input data comprises real-time meteorological data and real-time pavement temperature data;
predicting the ice and snow condition of the runway surface based on the pollutant condition prediction model and the prediction input data, and outputting pollutant prediction data of the airport runway surface;
And sending out an early warning signal based on the pollutant prediction data and a preset early warning grade standard.
By adopting the technical scheme, the pollutant condition prediction model is constructed according to the simulated meteorological data, the simulated pavement temperature data and the simulated pollutant condition data, and the model can be trained according to the actual airfield pavement temperature change, so that the constructed pollutant condition model is more attached to the actual airfield pavement situation, and the prediction accuracy of the pollutant condition prediction model is improved; the method has the advantages that the prediction input data are input into the pollutant condition prediction model, the pollutant prediction data are obtained, the early warning grade of the ice and snow condition of the road surface is determined according to the pollutant prediction data, and the early warning is sent out according to the early warning grade, so that the accuracy of the prediction of the ice and snow condition of the road surface of the airport is improved, meanwhile, the airport flight scheduling system or the service department can respond timely, and a processing decision is made.
Optionally, the constructing the pollutant condition prediction model based on the XGBoost algorithm and the simulated training data includes the following steps:
determining an input variable according to the simulated meteorological data and the simulated road surface temperature data;
determining an output result according to the simulated contaminant condition data;
And constructing a pollutant condition prediction model based on the input variable, the output result and an XGBoost algorithm.
By adopting the technical scheme, the simulated meteorological data and the simulated road surface temperature data are used as the simulated input variables, the simulation is carried out, the model is trained and corrected according to the simulated pollutant condition data, and the accuracy of the pollutant condition prediction model prediction is improved.
Optionally, the simulated pollutant condition data includes simulated pollutant type data and simulated pollutant thickness data, the simulated pollutant type data is used as a first simulated output result, the simulated pollutant thickness data is used as a second simulated output result, and the constructing the pollutant condition prediction model based on the simulated input variable, the simulated output result and the XGBoost algorithm includes the following steps:
constructing a pollutant type prediction model based on the analog input variable, the first analog output result and an XGBoost algorithm, wherein the pollutant type prediction model is used for predicting the pollutant type on an airport pavement;
constructing a pollutant thickness prediction model based on the analog input variable, the second analog output result and an XGBoost algorithm, wherein the pollutant thickness prediction model is used for predicting the pollutant thickness on an airport pavement;
And taking the pollutant type prediction model and the pollutant thickness prediction model as pollutant condition prediction models.
By adopting the technical scheme, the pollutant type prediction model and the pollutant thickness prediction model are respectively constructed, the type and the thickness of the pollutant can be respectively predicted, and the prediction result is relatively accurate.
Optionally, the predicting the ice and snow condition of the runway based on the contaminant condition prediction model and the predicted input data, and outputting the contaminant prediction data of the airport runway includes the following steps:
determining a predicted input variable based on the real-time weather data and the real-time road surface temperature data;
inputting the predicted input variable into the pollutant type prediction model to obtain a pollutant type prediction result;
inputting the predicted input variable into the pollutant thickness prediction model based on the pollutant type prediction result to obtain a pollutant thickness prediction result;
and obtaining pollutant prediction data based on the pollutant type prediction result and the pollutant thickness prediction result.
By adopting the technical scheme, the real-time meteorological data and the real-time pavement temperature data are input into the model, so that the model can predict the ice and snow condition of the airport pavement according to actual conditions, and the model is relatively attached to the actual situation.
Optionally, the early warning level standard includes contaminant condition information of the airport pavement and an early warning level corresponding to the contaminant condition information, and the early warning signal sent based on the contaminant prediction data and a preset early warning level standard includes the following steps:
presetting an early warning grade standard;
comparing the pollutant forecast data with the pollutant condition information, and judging whether the pollutant forecast data is matched with the pollutant condition information or not;
if so, acquiring an early warning grade corresponding to the pollutant condition information;
and sending out an early warning signal based on the early warning grade.
By adopting the technical scheme, the early warning level is determined according to the pollutant prediction data, so that the danger degree of freezing or snow on the airport pavement can be intuitively known.
Optionally, the preset early warning level standard includes the following steps:
the method comprises the steps of obtaining pollutant condition information when ice and snow conditions occur on an airport pavement, wherein the pollutant condition information comprises pollutant types and pollutant thicknesses, and the pollutant types comprise snow and ice;
analyzing the pollutant type and the pollutant thickness to obtain an early warning grade corresponding to the pollutant type: if the snow accumulation phenomenon exists on the airport pavement and the snow accumulation thickness does not exceed a preset snow accumulation thickness threshold value, setting the early warning grade as a first grade;
If the snow accumulation phenomenon exists on the airport pavement and the snow accumulation thickness exceeds a preset snow accumulation thickness threshold value, setting the early warning grade as a second grade;
and if the airport pavement has the icing phenomenon, setting the early warning grade to be a third grade.
By adopting the technical scheme, the early warning grade is determined according to different degrees of snow accumulation and icing, so that an airport flight scheduling system or an airport service department can conveniently formulate different treatment strategies according to the early warning grade.
In a second aspect, the application also provides an airport pavement ice and snow condition monitoring and early warning system, which adopts the following technical scheme:
an airport pavement ice and snow condition monitoring and early warning system, comprising:
the first acquisition module is used for acquiring simulation training data of the airport pavement under the condition of simulating ice and snow based on a preset simulation test piece and metering equipment arranged on the simulation test piece, wherein the simulation training data comprise simulation meteorological data, simulation pavement temperature data and simulation pollutant condition data of the airport pavement;
the model construction module is used for constructing a pollutant condition prediction model based on the XGBoost algorithm and the simulation training data;
the second acquisition module is used for acquiring predicted input data of the airport pavement in real time based on the metering equipment, wherein the predicted input data comprises real-time meteorological data and real-time pavement temperature data;
The prediction output module is used for predicting the ice and snow conditions of the runway surface based on the pollutant condition prediction model and the prediction input data and outputting the pollutant prediction data of the airport runway surface;
and the early warning prompt module is used for sending out early warning signals based on the pollutant prediction data and a preset early warning grade standard.
By adopting the technical scheme, the pollutant condition prediction model is constructed according to the simulated meteorological data, the simulated pavement temperature data and the simulated pollutant condition data, and the model can be trained according to the actual airfield pavement temperature change, so that the constructed pollutant condition model is more attached to the actual airfield pavement situation, and the prediction accuracy of the pollutant condition prediction model is improved; the method has the advantages that the pollutant prediction data are obtained by inputting the prediction input data into the pollutant condition prediction model, the early warning grade of the ice and snow condition of the runway surface is determined according to the pollutant prediction data, the early warning is sent out according to the early warning grade, the accuracy of the prediction of the ice and snow condition of the runway surface is improved, meanwhile, the airport flight scheduling system or the service department can respond timely, and a processing decision is made.
Optionally, the model building module further includes:
A first determining unit that determines an analog input variable based on the analog weather data and the analog road surface temperature data;
a second determination unit that determines a simulation output result based on the simulation contaminant status data;
and the model construction unit is used for constructing a pollutant condition prediction model based on the analog input variable, the analog output result and the XGBoost algorithm.
In a third aspect, the present application provides a terminal device, which adopts the following technical scheme:
the terminal equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the computer program is loaded and executed by the processor, and the airport pavement ice and snow condition monitoring and early warning method is adopted.
By adopting the technical scheme, the computer program is generated by the airport pavement ice and snow condition monitoring and early warning method and is stored in the memory to be loaded and executed by the processor, so that the terminal equipment is manufactured according to the memory and the processor, and the use is convenient.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is loaded and executed by a processor, the method for monitoring and early warning the ice and snow condition of an airport pavement is adopted.
By adopting the technical scheme, the computer program is generated by the airport pavement ice and snow condition monitoring and early warning method and is stored in the computer readable storage medium to be loaded and executed by the processor, and the computer program is convenient to read and store by the computer readable storage medium.
Drawings
Fig. 1 is a schematic overall flow chart of an ice and snow condition monitoring and early warning method for an airport pavement according to an embodiment of the application.
Fig. 2 is a schematic flow chart of step S201 to step S203 in the method for monitoring and early warning the ice and snow condition of the airport pavement according to the embodiment of the application.
Fig. 3 is a schematic flow chart of step S301 to step S303 in the method for monitoring and early warning the ice and snow condition of the airfield pavement according to the embodiment of the application.
Fig. 4 is a schematic diagram of a relationship among simulated training data, simulated input variables, simulated output data, training set and test set in an embodiment of the application for monitoring and early warning of ice and snow conditions on an airport pavement.
Fig. 5 is a schematic diagram of a decision tree of a pollutant condition prediction model in an airport pavement ice and snow condition monitoring and early warning method according to an embodiment of the application.
Fig. 6 is a schematic diagram of a model for predicting the thickness of pollutants in an embodiment of a method for monitoring and early warning the ice and snow condition of an airport pavement.
Fig. 7 is a schematic flow chart of step S401 to step S404 in the method for monitoring and early warning the ice and snow condition of the airport pavement according to the embodiment of the application.
Fig. 8 is a schematic flow chart of steps S501 to S504 in the method for monitoring and early warning the ice and snow condition of the airfield pavement according to the embodiment of the application.
Fig. 9 is a schematic flow chart of step S601 to step S605 in the method for monitoring and early warning the ice and snow condition of the airport pavement according to the embodiment of the application.
Fig. 10 is a schematic diagram of module connection of an ice and snow condition monitoring and early warning system for an airport pavement according to an embodiment of the present application.
Reference numerals illustrate:
1. a first acquisition module; 2. a model building module; 3. a second acquisition module; 4. a prediction output module; 5. and the early warning prompt module.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
The embodiment of the application discloses a method for monitoring and early warning ice and snow conditions on an airport pavement, which comprises the following steps with reference to fig. 1:
s101, acquiring simulation training data of an airport pavement under the condition of simulating ice and snow based on a preset simulation test piece and metering equipment arranged on the simulation test piece, wherein the simulation training data comprise simulation meteorological data, simulation pavement temperature data and simulation pollutant condition data of the airport pavement;
S102, constructing a pollutant condition prediction model based on an XGBoost algorithm and simulated training data;
s103, acquiring predicted input data of the airport pavement in real time based on metering equipment, wherein the predicted input data comprises real-time meteorological data and real-time pavement temperature data;
s104, predicting the ice and snow condition of the runway surface based on the pollutant condition prediction model and the predicted input data, and outputting the pollutant prediction data of the airport runway surface;
s105, sending out an early warning signal based on the pollutant prediction data and a preset early warning grade standard.
In order to facilitate the test without damaging the airport pavement, a simulation test piece which is the same as the current airport pavement building material is preset in the airport environment to simulate the airport pavement to acquire various parameters, in this embodiment, the test piece is set to be long in width in height=300 in 300 in 380mm, and is used for simulating the actual icing and snow accumulation conditions of the 38cm thick cement concrete pavement of the airport runway.
The method comprises the steps of obtaining simulation training data and prediction input data through metering equipment preset on a simulation test piece, wherein the simulation training data comprise simulation meteorological data, simulation pavement temperature data and simulation pollutant condition data of an airport pavement, and the prediction input data comprise real-time meteorological data and real-time pavement temperature data. The simulation meteorological data and the real-time meteorological data comprise atmospheric temperature, humidity, solar radiation intensity, rainfall and snowfall, and the corresponding metering equipment comprises an air temperature sensor, a humidity sensor, a wind speed sensor, a rainfall cylinder and a solar radiation sensor which are all arranged above the simulation test piece;
The simulated pavement temperature data and the real-time pavement temperature data refer to temperatures of different depths of the simulated test piece, the adopted metering equipment is pavement temperature sensors, and the pavement temperature sensors are respectively positioned at different depths, such as 5cm, 10cm, 20cm and 30cm, of the surface of the simulated test piece and are used for acquiring the temperatures of the simulated test piece at the different depths as pavement temperature data of the airport pavement; the simulated pollutant condition data refer to the pollutant condition of an airport pavement, including pollutant types and pollutant thicknesses, such as snow, 3mm or icing, 2mm, and the metering equipment for acquiring the simulated pollutant condition is a pavement surface condition sensor, namely a common pavement condition sensor in the market, which is arranged on the surface of a simulated test piece, and the sensor surface is flush with the surface of the simulated test piece.
All the metering devices are connected with the computer system and realize communication, and the specific communication mode can be realized through an RS-485 serial communication interface or other communication modes, and the metering device is used for reading the simulation test data and the forecast input data acquired by the metering devices by the computer system.
Specifically, simulated weather data and simulated pavement temperature data of an airport pavement are simulated through a simulated test piece, so that icing or snow situation occurs on the simulated test piece after preset time, and the icing or snow situation is used as simulated pollutant situation data. For example, the simulated test piece is under certain meteorological data and road surface temperature data, and icing 2mm occurs after 20 minutes; under certain meteorological data and road surface temperature data, snow accumulation phenomenon of 3mm and the like can occur after 20 minutes, the meteorological data and the road surface temperature data are recorded to serve as simulated meteorological data and simulated road surface temperature data, and meanwhile 'icing, 2 mm' and 'snow accumulation, 3 mm' are taken as simulated pollutant condition data.
After the simulated training data are obtained, a pollutant condition prediction model is built on the basis of an XGBoost algorithm according to the simulated training data, so that predicted input data are input into the pollutant condition prediction model, and the pollutant thickness on the airport pavement can be predicted.
In this embodiment, according to the metering device, the predicted input data, that is, the real-time meteorological data and the real-time pavement temperature data, are obtained in real time, the predicted input data is input into the pollutant condition prediction model, the pollutant condition prediction model outputs the pollutant prediction data of the airfield pavement after the preset time, the preset time is set to 20min, that is, the current predicted data is obtained, and the specific situation of the airfield pavement after 20min is predicted. Specific contaminant forecast data includes contaminant type and contaminant thickness.
After the pollutant prediction data are obtained, the computer system determines the early warning grade according to the pollutant prediction data and a preset early warning grade standard, and sends an early warning signal according to the early warning grade so as to prompt an airport service department to conduct pavement processing decisions in advance.
Specifically, referring to fig. 2, step S102: constructing a pollutant condition prediction model based on an XGBoost algorithm and simulated training data comprises the following steps of:
S201, determining an analog input variable based on analog meteorological data and analog pavement temperature data;
s202, determining a simulation output result based on the simulation pollutant condition data;
s203, constructing a pollutant condition prediction model based on the input variable, the output result and the XGBoost algorithm.
Because the ice and snow on the surface of an airport pavement is related to the temperature, the humidity, the wind speed and the characteristics of the surface of the airport and has nonlinear coupling relation with the temperature, the humidity and the wind speed (input and output are not in direct proportion and are called nonlinear systems, and the relationship of mutual entanglement between two factors is called coupling), which is a time-varying nonlinear link, the input and the output are difficult to express by specific mathematical functions. Considering this, the present embodiment adopts a mathematical model, and realizes prediction of the ice and snow condition on the surface of the airport pavement by training the mathematical model.
Specifically, the model is constructed by inputting variables, outputting results and a training algorithm, in this embodiment, the simulated weather data and the simulated road surface temperature data in the simulated training data are subjected to numerical processing, and characteristic numerical value information in the simulated weather data and the simulated road surface temperature data is extracted as the simulated input variables; and extracting characteristic numerical value information of the simulated pollutant condition data as a simulation output result.
For example, in simulated meteorological data: the atmospheric temperature is 1 ℃, the humidity is 60%, the solar radiation intensity is 200W/square meter, the snowfall is 1mm, the simulated pavement temperatures measured by the four pavement temperature sensors are 2 ℃, 1 ℃ and 0 ℃, the characteristic numerical information extracted sequentially is 1, 60, 200, 1, 2, 1 and 0 respectively, and the characteristic numerical information of the simulated meteorological data and the simulated pavement temperature data is used as a simulated input variable. The simulated pollutant condition data comprise simulated pollutant type data and simulated pollutant thickness data, wherein the simulated pollutant type data represent pollutant type information on an airport pavement, and comprise three conditions of 'dry/snow/ice', wherein the three conditions are respectively represented by characteristic numerical value information '0/1/2', and the characteristic numerical value information of the simulated pollutant type data is used as a first simulation output result; the simulated pollutant thickness data represents the thickness of the pollutant on the airport pavement, such as 1mm/2mm, and the characteristic numerical information of the pollutant thickness is extracted from the simulated pollutant thickness data, for example, the simulated pollutant thickness data is 2mm, the characteristic numerical information is 2, the characteristic numerical information of the simulated pollutant condition data is taken as a second simulation output result, and the first simulation output result and the second simulation output result are collectively called as a simulation output result.
And constructing a pollutant condition prediction model based on the XGBoost algorithm according to the analog input variable and the analog output result. Specifically, referring to fig. 3, step S203 includes the steps of:
s301, constructing a pollutant type prediction model based on an analog input variable, a first analog output result and an XGBoost algorithm, wherein the pollutant type prediction model is used for predicting the pollutant type on an airport pavement;
s302, constructing a pollutant thickness prediction model based on the analog input variable, the second analog output result and the XGBoost algorithm, wherein the pollutant thickness prediction model is used for predicting the pollutant thickness on the airport pavement;
s303, using the pollutant type prediction model and the pollutant thickness prediction model as pollutant condition prediction models.
Referring to fig. 4, in order to ensure the prediction accuracy of the model, the analog input variables and the analog output results in the analog training data are divided to obtain a training set and a test set, the training set includes the corresponding analog input variables and analog output results, the test set also includes the corresponding analog input variables and analog output results, the pollutant type prediction model and the pollutant thickness prediction model are trained through the training set, and the pollutant type prediction model and the pollutant thickness prediction model are tested through the test set.
In one implementation of this embodiment, a ten fold cross-validation method is used to ensure the reliability of the model calculation results by randomly partitioning the training set into 10 different subsets, each subset being one fold, then training and evaluating the model 10 times—one fold is selected for evaluation at a time, another 9 folds are used for training, and the result is an array containing 10 evaluation scores.
The construction principle of the pollutant type prediction model and the pollutant thickness prediction model is as follows: referring to fig. 5, assuming that the model has K trees, wherein the first tree represents a constructed first model, each tree node represents different judging conditions, inputting a simulation input variable in a training set into the first tree, obtaining a first simulation prediction result through judging the judging conditions of different nodes of the first tree, comparing the first simulation prediction result with a first simulation output result in a test set to obtain error information, and taking the error information as a target output result of a second tree; the second tree is used for carrying out error fitting on the first simulation output result of the first tree to obtain a more accurate prediction result.
The specific model construction process is as follows:
with a function f for each tree k (x i ) Expressed, the model may be expressed as the sum of K trees:
the XGBoost algorithm generates a new tree for each iteration, which is used for fitting the residual error of the previous tree, so the predicted value at the t-th iteration is assumed to beThen
The objective function has two purposes:
1. the difference between the predicted value and the actual value, i.e. the loss value, is optimized.
2. And adding a regularization penalty term to reduce the possibility of model overfitting.
The resulting objective function is thus composed of loss values, regularization terms and constant term 3 parts.
The regular term:
wherein gamma and lambda are model parameters; t is the total number of leaf nodes of the tree, w j Is the weight of the j-th leaf node in the book.
Expanding the loss function taylor to second order and removing the constant term, the objective function becomes:
when a new tree is generatedBeing a fixed value may be considered a constant ignore and integrate the traversal of the samples by the function into the traversal of the leaf nodes. The objective function can be further reduced to:
wherein the method comprises the steps ofI j Is the set of samples on the j-th leaf node.
Let partial derivative
ThenThe surrogate primitive objective function is
And when the objective function value is minimum, the whole tree structure is optimal.
And the optimal parameters in the XGBoost model are searched by using a grid search method, so that the prediction performance of the model is improved. The tuning parameters comprise decision tree number, learning rate, maximum depth of tree, minimum leaf node weight sum, gamma penalty term coefficient and lambda regularization coefficient. After parameter adjustment, the model parameters reach the optimum. The method is a trained airport pavement pollutant condition prediction model.
The prediction effect of the model is evaluated using the Mean Square Error (MSE) of the predicted icing thickness. The calculation formula of the mean square error is:
wherein: y is i Is true, f (x i ) For the predicted value, m is the number of test samples, and i is the sample number.
The decision tree node segmentation point dividing method specifically comprises the following steps:
starting from the depth of the tree being 0, feature enumeration is carried out on each leaf node, training samples of the node are arranged according to the ascending order of feature values corresponding to each feature, the optimal splitting point of the feature is determined in a linear scanning mode, and splitting benefits of the feature are recorded.
Assuming feature splitting is done at a node, the objective function before splitting can be written as:
the post-splitting objective function is:
then for the objective function, the post-splitting yield is:
and selecting the feature with the biggest post-splitting yield, taking the optimal splitting point of the feature as a splitting position, splitting out two new leaf nodes, and associating a sample set corresponding to each new node.
Because the newly introduced leaf node has a corresponding penalty term, when the introduced split yields less than the penalty, the split can be cut.
Repeating the above operation until the decision tree is constructed, and forming a pollutant type prediction model and a pollutant thickness prediction model. For example, referring to FIG. 6, a model of contaminant thickness prediction after training is shown.
Referring to fig. 7, in step S104, the road surface ice and snow condition prediction is performed based on the pollutant condition prediction model and the predicted input data, and the pollutant prediction data of the output airport road surface specifically includes the steps of:
s401, determining a predicted input variable based on real-time meteorological data and real-time road surface temperature data;
s402, inputting a predicted input variable into a pollutant type prediction model to obtain a pollutant type prediction result;
s403, inputting a predicted input variable into a pollutant thickness prediction model based on a pollutant type prediction result to obtain a pollutant thickness prediction result;
s404, obtaining pollutant prediction data based on the pollutant type prediction result and the pollutant thickness prediction result.
The method for determining the predicted input variable is the same as the method for determining the analog input variable, and the predicted input variable is determined by extracting characteristic numerical value information in the real-time weather data and the real-time road surface temperature data. Inputting a predicted input variable into a pollutant type prediction model, wherein the trained pollutant type prediction model can output an accurate pollutant type prediction result; and similarly, inputting the predicted input variable into a pollutant thickness prediction model to obtain a pollutant thickness prediction result. And analyzing the pollutant type prediction result and the pollutant thickness prediction result to obtain pollutant prediction data. For example, the predicted output results output by the pollutant type prediction model and the pollutant thickness prediction model are respectively 1 and 2, and analysis of the model predicted output results shows that the pollutant type is snow and the thickness is 2mm according to the current predicted input data, namely the predicted result is that snow will appear on the airport pavement after 20min, and the thickness of the snow is 2mm.
Referring to fig. 8, in step S105, sending an early warning signal based on the pollutant prediction data and the preset early warning level criteria specifically includes the following steps:
s501, presetting an early warning grade standard;
s502, comparing the pollutant forecast data with the pollutant condition information, and judging whether the pollutant forecast data is matched with the pollutant condition information;
s503, if the two types of the pollutants are matched, acquiring an early warning grade corresponding to the pollutant condition information;
s504, sending out an early warning signal based on the early warning level.
Firstly, pre-setting early warning grade standards according to the actual ice and snow conditions of the runway surface, storing the pre-warning grade standards in a computer system, prescribing airport runway surface pollutant condition information and early warning grades corresponding to the pollutant condition information in the early warning grade standards, and enabling the pollutant condition information with different degrees to correspond to different early warning grades. After the pollutant prediction data is obtained, comparing the pollutant prediction data with the pollutant condition information through an early warning grade standard, and selecting the pollutant condition information matched with the pollutant prediction data, so that an early warning grade corresponding to the pollutant condition information is obtained, and the computer system sends an early warning signal based on the early warning grade.
Specifically, referring to fig. 9, the preset early warning level criteria includes the following steps in the present embodiment:
S601, obtaining pollutant condition information when ice and snow conditions occur on an airport pavement, wherein the pollutant condition information comprises pollutant types and pollutant thickness, and the pollutant types comprise snow and ice;
s602, analyzing the type of the pollutant and the thickness of the pollutant, and acquiring an early warning grade corresponding to the type of the pollutant:
s603, if snow is accumulated on the airport pavement, and the thickness of the snow does not exceed a preset snow thickness threshold, setting the early warning grade as a first grade;
s604, if the airport pavement has snow accumulation phenomenon and the snow accumulation thickness exceeds a preset snow accumulation thickness threshold value, setting the early warning grade as a second grade;
s605, if the airport pavement has icing, setting the early warning grade to be a third grade.
When ice and snow occur on the airport pavement, the early warning level is set according to the snow or ice condition, and in this embodiment, the early warning level is embodied according to color, for example, yellow, orange, red, and the like. If the snow accumulation phenomenon occurs, comparing the predicted snow accumulation thickness in the pollutant prediction data with a preset snow accumulation thickness threshold value, and judging whether the snow accumulation thickness threshold value is exceeded or not to determine the early warning grade. For example, if the preset snow thickness threshold is 3mm and the pollutant prediction data obtained by the pollutant condition prediction model is "snow and 2mm", determining that the snow thickness does not exceed the snow thickness threshold, and giving a yellow early warning grade at the moment; if the pollutant prediction data is "snow cover, 5mm", then confirm that snow cover thickness exceeds snow cover thickness threshold value, give orange early warning grade this moment. If the situation that the airport pavement is frozen is predicted, the red early warning grade is directly given to the airport pavement, so that the danger degree of the airport pavement is indicated.
One matching relationship of the pre-warning level criteria is as follows:
| ice and snow condition of airport pavement | Early warning level |
| Snow is accumulated on the road surface, and the depth of the snow is not more than 3mm (containing) | Yellow colour |
| Snow is accumulated on the surface of the road surface, and the depth of the snow exceeds 3mm | Orange with a color of white |
| Ice formation on the road surface | Red colour |
Specifically, the computer system is connected with the airport flight scheduling system through a remote network or other connection modes, and after the early warning level of the airport pavement is determined, the computer system transmits the early warning level and relevant data to the airport flight scheduling system in the middle of transmission, so that the airport flight scheduling system can timely react to make pavement processing decisions in advance.
The implementation principle of the method for monitoring and early warning the ice and snow condition of the airport pavement provided by the embodiment of the application is as follows: constructing a pollutant condition prediction model according to the simulated meteorological data, the simulated pavement temperature data and the simulated pollutant condition data, and training the model according to the actual airfield pavement temperature change, so that the constructed pollutant condition model is more attached to the actual airfield pavement, and the accuracy of the pollutant condition prediction model is improved; the method has the advantages that the prediction input data are input into the pollutant condition prediction model, the pollutant prediction data are obtained, the early warning grade of the ice and snow condition of the road surface is determined according to the pollutant prediction data, and the early warning is sent out according to the early warning grade, so that the accuracy of the prediction of the ice and snow condition of the road surface of the airport is improved, meanwhile, the airport flight scheduling system or the service department can respond timely, and a processing decision is made.
The embodiment of the application also provides an ice and snow condition monitoring and early warning system of the airport pavement, which is applied to the ice and snow condition monitoring and early warning method of the airport pavement, and referring to fig. 10, the system comprises: the system comprises a first acquisition module 1, a model construction module 2, a second acquisition module 3, a prediction output module 4 and an early warning prompt module 5, wherein the first acquisition module 1 is used for acquiring simulation training data of an airport pavement under the condition of simulating ice and snow based on a preset simulation test piece and metering equipment arranged on the simulation test piece; the model construction module 2 is used for constructing a pollutant condition prediction model based on the XGBoost algorithm and the simulation training data; the second acquisition module 3 is used for acquiring predicted input data of the airport pavement in real time based on the metering equipment; the prediction output module 4 is used for predicting the ice and snow condition of the runway surface based on the pollutant condition prediction model and the predicted input data and outputting the pollutant prediction data of the airport runway surface; the early warning prompt module 5 is used for sending out early warning signals based on the pollutant prediction data and the preset early warning grade standard.
Specifically, the simulated training data includes simulated weather data, simulated pavement temperature data, and simulated contaminant condition data for the airport pavement, and the predicted input data includes real-time weather data and real-time pavement temperature data. The simulation meteorological data and the real-time meteorological data comprise atmospheric temperature, humidity, solar radiation intensity, rainfall and snowfall, and the corresponding metering equipment comprises an air temperature sensor, a humidity sensor, a wind speed sensor, a rainfall cylinder and a solar radiation sensor which are all arranged above the simulation test piece;
The simulated pavement temperature data and the real-time pavement temperature data refer to temperatures of different depths of the simulated test piece, the adopted metering equipment is pavement temperature sensors, and the pavement temperature sensors are respectively positioned at different depths, such as 5cm, 10cm, 20cm and 30cm, of the surface of the simulated test piece and are used for acquiring the temperatures of the simulated test piece at the different depths as pavement temperature data of the airport pavement; the simulated pollutant condition data refer to the pollutant condition of an airport pavement, including pollutant types and pollutant thicknesses, such as snow, 3mm or icing, 2mm, and the metering equipment for acquiring the simulated pollutant condition is a pavement surface condition sensor, namely a common pavement condition sensor in the market, which is arranged on the surface of a simulated test piece, and the sensor surface is flush with the surface of the simulated test piece.
All the metering devices are connected with the computer system and realize communication, and the specific communication mode can be realized through an RS-485 serial communication interface or other communication modes, and the metering device is used for reading the simulation test data and the forecast input data acquired by the metering devices by the computer system.
Specifically, the first acquisition module 1 simulates simulated weather data and simulated road surface temperature data of an airport road surface through a simulated test piece, so that icing or snow situation occurs on the simulated test piece after a preset time, and the icing or snow situation is used as simulated pollutant situation data. For example, the simulated test piece is under certain meteorological data and road surface temperature data, and icing 2mm occurs after 20 minutes; under certain meteorological data and road surface temperature data, snow accumulation phenomenon of 3mm and the like can occur after 20 minutes, the meteorological data and the road surface temperature data are recorded to serve as simulated meteorological data and simulated road surface temperature data, and meanwhile 'icing, 2 mm' and 'snow accumulation, 3 mm' are taken as simulated pollutant condition data.
After the first acquisition module 1 acquires the simulated training data, the model construction module 2 constructs a pollutant condition prediction model based on an XGBoost algorithm according to the simulated training data, so that predicted input data is input into the pollutant condition prediction model, and the pollutant thickness on the airport pavement can be predicted.
The model building module further comprises a first determining unit, a second determining unit and a model building unit, wherein the first determining unit is used for determining a simulation input variable based on simulation meteorological data and simulation road surface temperature data; the second determining unit is used for determining a simulation output result based on the simulation pollutant condition data; the model building unit is used for building a pollutant condition prediction model based on the analog input variable, the analog output result and the XGBoost algorithm. The concrete construction process is the same as the monitoring and early warning method for the ice and snow condition of the airport pavement.
In this embodiment, the second obtaining module 3 obtains prediction input data, that is, real-time meteorological data and real-time pavement temperature data, in real time according to the metering device, inputs the prediction input data into the pollutant condition prediction model, and the prediction output module 4 outputs the pollutant prediction data of the airfield pavement after a preset time through the pollutant condition prediction model, and sets the preset time to 20min, that is, obtains current prediction data, and predicts the specific situation of the airfield pavement after 20 min. Specific contaminant forecast data includes contaminant type and contaminant thickness.
After the pollutant prediction data are obtained, an early warning prompt module 5 in the computer system determines an early warning grade according to the pollutant prediction data and a preset early warning grade standard, and sends an early warning signal according to the early warning grade so as to prompt an airport service department to make a pavement processing decision in advance.
Other specific implementations of the system for monitoring and early warning the ice and snow condition of the airport pavement in the embodiment of the application are the same as the method for monitoring and early warning the ice and snow condition of the airport pavement, so that the detailed description is omitted here.
The embodiment of the application also discloses a terminal device which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the computer program is executed by the processor, and the airport pavement ice and snow condition monitoring and early warning method in the embodiment is adopted.
The terminal device may be a computer device such as a desktop computer, a notebook computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory, for example, the terminal device may further include an input/output device, a network access device, a bus, and the like.
The processor may be a Central Processing Unit (CPU), or of course, according to actual use, other general purpose processors, digital Signal Processors (DSP), application Specific Integrated Circuits (ASIC), ready-made programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., and the general purpose processor may be a microprocessor or any conventional processor, etc., which is not limited in this respect.
The memory may be an internal storage unit of the terminal device, for example, a hard disk or a memory of the terminal device, or an external storage device of the terminal device, for example, a plug-in hard disk, a Smart Memory Card (SMC), a secure digital card (SD), or a flash memory card (FC) provided on the terminal device, or the like, and may be a combination of the internal storage unit of the terminal device and the external storage device, where the memory is used to store a computer program and other programs and data required by the terminal device, and the memory may be used to temporarily store data that has been output or is to be output, which is not limited by the present application.
The airport pavement ice and snow condition monitoring and early warning method in the embodiment is stored in the memory of the terminal equipment through the terminal equipment, and is loaded and executed on the processor of the terminal equipment, so that the airport pavement ice and snow condition monitoring and early warning method is convenient to use.
The embodiment of the application also discloses a computer readable storage medium, and the computer readable storage medium stores a computer program, wherein the computer program adopts the method for monitoring and early warning the ice and snow condition of the airport pavement in the embodiment when being executed by a processor.
The computer program may be stored in a computer readable medium, where the computer program includes computer program code, where the computer program code may be in a source code form, an object code form, an executable file form, or some middleware form, etc., and the computer readable medium includes any entity or device capable of carrying the computer program code, a recording medium, a usb disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, etc., where the computer readable medium includes, but is not limited to, the above components.
The method for monitoring and early warning the ice and snow condition of the airport pavement in the embodiment is stored in the computer readable storage medium through the computer readable storage medium, and is loaded and executed on a processor so as to facilitate the storage and application of the method.
The above embodiments are not intended to limit the scope of the present application, so: all equivalent changes in structure, shape and principle of the application should be covered in the scope of protection of the application.
Claims (7)
1. The method for monitoring and early warning the ice and snow condition of the airport pavement is characterized by comprising the following steps of:
based on a preset simulation test piece and metering equipment arranged on the simulation test piece, obtaining simulation training data of the airport pavement under the condition of simulating ice and snow, wherein the simulation training data comprise simulation meteorological data, simulation pavement temperature data and simulation pollutant condition data of the airport pavement;
determining an analog input variable based on the analog weather data and the analog ballast temperature data;
determining a simulated output result based on the simulated contaminant condition data;
the simulated pollutant condition data comprise simulated pollutant type data and simulated pollutant thickness data, the simulated pollutant type data are used as a first simulation output result, and the simulated pollutant thickness data are used as a second simulation output result;
constructing a pollutant type prediction model based on the analog input variable, the first analog output result and an XGBoost algorithm, wherein the pollutant type prediction model is used for predicting the pollutant type on an airport pavement;
constructing a pollutant thickness prediction model based on the analog input variable, the second analog output result and an XGBoost algorithm, wherein the pollutant thickness prediction model is used for predicting the pollutant thickness on an airport pavement;
Taking the pollutant type prediction model and the pollutant thickness prediction model as pollutant condition prediction models;
acquiring predicted input data of the airport pavement in real time based on the metering equipment, wherein the predicted input data comprises real-time meteorological data and real-time pavement temperature data;
predicting the ice and snow condition of the runway surface based on the pollutant condition prediction model and the prediction input data, and outputting pollutant prediction data of the airport runway surface;
and sending out an early warning signal based on the pollutant prediction data and a preset early warning grade standard.
2. The method for monitoring and pre-warning ice and snow conditions on an airport pavement according to claim 1, wherein the predicting ice and snow conditions on the pavement based on the pollutant condition prediction model and the predicted input data, and outputting the pollutant prediction data on the airport pavement comprises the following steps:
determining a predicted input variable based on the real-time weather data and the real-time road surface temperature data;
inputting the predicted input variable into the pollutant type prediction model to obtain a pollutant type prediction result;
inputting the predicted input variable into the pollutant thickness prediction model based on the pollutant type prediction result to obtain a pollutant thickness prediction result;
And obtaining pollutant prediction data based on the pollutant type prediction result and the pollutant thickness prediction result.
3. The method for monitoring and pre-warning ice and snow conditions on an airport pavement according to claim 2, wherein the pre-warning level standard comprises contaminant condition information of the airport pavement and a pre-warning level corresponding to the contaminant condition information, and the step of sending a pre-warning signal based on the contaminant prediction data and a preset pre-warning level standard comprises the following steps:
presetting an early warning grade standard;
comparing the pollutant forecast data with the pollutant condition information, and judging whether the pollutant forecast data is matched with the pollutant condition information or not;
if so, acquiring an early warning grade corresponding to the pollutant condition information;
and sending out an early warning signal based on the early warning grade.
4. A method for monitoring and pre-warning ice and snow conditions on an airport pavement according to claim 3, wherein the preset pre-warning level criteria comprises the steps of:
the method comprises the steps of obtaining pollutant condition information when ice and snow conditions occur on an airport pavement, wherein the pollutant condition information comprises pollutant types and pollutant thicknesses, and the pollutant types comprise snow and ice;
Analyzing the pollutant type and the pollutant thickness to obtain an early warning grade corresponding to the pollutant type:
if the snow accumulation phenomenon exists on the airport pavement and the snow accumulation thickness does not exceed a preset snow accumulation thickness threshold value, setting the early warning grade as a first grade;
if the snow accumulation phenomenon exists on the airport pavement and the snow accumulation thickness exceeds a preset snow accumulation thickness threshold value, setting the early warning grade as a second grade;
and if the airport pavement has the icing phenomenon, setting the early warning grade to be a third grade.
5. An airport pavement ice and snow condition monitoring and early warning system, which is characterized by comprising:
the first acquisition module (1) is used for acquiring simulated training data of the airport pavement under the condition of simulating ice and snow based on a preset simulated test piece and metering equipment arranged on the simulated test piece, wherein the simulated training data comprises simulated meteorological data, simulated pavement temperature data and simulated pollutant condition data of the airport pavement;
a model building module (2) for determining a simulated input variable based on the simulated meteorological data and the simulated road surface temperature data; determining a simulated output result based on the simulated contaminant condition data; the simulated pollutant condition data comprise simulated pollutant type data and simulated pollutant thickness data, the simulated pollutant type data are used as a first simulation output result, and the simulated pollutant thickness data are used as a second simulation output result; constructing a pollutant type prediction model based on the analog input variable, the first analog output result and an XGBoost algorithm, wherein the pollutant type prediction model is used for predicting the pollutant type on an airport pavement; constructing a pollutant thickness prediction model based on the analog input variable, the second analog output result and an XGBoost algorithm, wherein the pollutant thickness prediction model is used for predicting the pollutant thickness on an airport pavement; taking the pollutant type prediction model and the pollutant thickness prediction model as pollutant condition prediction models;
A second acquisition module (3) for acquiring predicted input data of the airport pavement in real time based on the metering equipment, wherein the predicted input data comprises real-time meteorological data and real-time pavement temperature data;
a prediction output module (4) for predicting the ice and snow condition of the runway surface based on the pollutant condition prediction model and the predicted input data, and outputting the pollutant prediction data of the airport runway surface;
and the early warning prompt module (5) is used for sending out early warning signals based on the pollutant prediction data and a preset early warning grade standard.
6. A terminal device comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, characterized in that the method according to any of claims 1-4 is used when the computer program is loaded and executed by the processor.
7. A computer readable storage medium having a computer program stored therein, characterized in that the method according to any of claims 1-4 is employed when the computer program is loaded and executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210745767.1A CN114999117B (en) | 2022-06-29 | 2022-06-29 | Airport pavement ice and snow condition monitoring and early warning method, system, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210745767.1A CN114999117B (en) | 2022-06-29 | 2022-06-29 | Airport pavement ice and snow condition monitoring and early warning method, system, terminal and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114999117A CN114999117A (en) | 2022-09-02 |
| CN114999117B true CN114999117B (en) | 2023-09-01 |
Family
ID=83037852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210745767.1A Active CN114999117B (en) | 2022-06-29 | 2022-06-29 | Airport pavement ice and snow condition monitoring and early warning method, system, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114999117B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485046A (en) * | 2023-06-21 | 2023-07-25 | 华北电力科学研究院有限责任公司 | Photovoltaic output prediction method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866525A (en) * | 2010-05-28 | 2010-10-20 | 中国民航大学 | Device and method for forecasting freezing on surface of ground plane based on multisensor |
| CN106408857A (en) * | 2016-08-31 | 2017-02-15 | 江苏中路工程技术研究院有限公司 | Highway road surface icing monitoring device and monitoring method |
| CN107016819A (en) * | 2017-06-05 | 2017-08-04 | 中国民航大学 | A kind of airfield pavement accumulated ice early warning system and its method for early warning |
| CN108513674A (en) * | 2018-03-26 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN108701396A (en) * | 2018-03-26 | 2018-10-23 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN111047844A (en) * | 2019-12-26 | 2020-04-21 | 西安靖轩航空科技有限公司 | Snow and ice removing early warning system and method for military airport pavement |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109958588B (en) * | 2017-12-14 | 2020-08-07 | 北京金风科创风电设备有限公司 | Icing prediction method, icing prediction device, storage medium, model generation method and model generation device |
-
2022
- 2022-06-29 CN CN202210745767.1A patent/CN114999117B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866525A (en) * | 2010-05-28 | 2010-10-20 | 中国民航大学 | Device and method for forecasting freezing on surface of ground plane based on multisensor |
| CN106408857A (en) * | 2016-08-31 | 2017-02-15 | 江苏中路工程技术研究院有限公司 | Highway road surface icing monitoring device and monitoring method |
| CN107016819A (en) * | 2017-06-05 | 2017-08-04 | 中国民航大学 | A kind of airfield pavement accumulated ice early warning system and its method for early warning |
| CN108513674A (en) * | 2018-03-26 | 2018-09-07 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN108701396A (en) * | 2018-03-26 | 2018-10-23 | 深圳市锐明技术股份有限公司 | A kind of detection alarm method, storage medium and the server of Chinese herbaceous peony accumulated snow and icing |
| CN111047844A (en) * | 2019-12-26 | 2020-04-21 | 西安靖轩航空科技有限公司 | Snow and ice removing early warning system and method for military airport pavement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114999117A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lafaysse et al. | A multiphysical ensemble system of numerical snow modelling | |
| CN106650825B (en) | Motor vehicle exhaust emission data fusion system | |
| Astsatryan et al. | Air temperature forecasting using artificial neural network for Ararat valley | |
| Dumedah et al. | Root-zone soil moisture estimation from assimilation of downscaled Soil Moisture and Ocean Salinity data | |
| CN110826788A (en) | Airport scene variable slide-out time prediction method based on big data deep learning | |
| Sekertekin et al. | Modeling diurnal Land Surface Temperature on a local scale of an arid environment using artificial Neural Network (ANN) and time series of Landsat-8 derived spectral indexes | |
| CN114999117B (en) | Airport pavement ice and snow condition monitoring and early warning method, system, terminal and medium | |
| Kent et al. | Aerodynamic roughness variation with vegetation: analysis in a suburban neighbourhood and a city park | |
| CN110738354A (en) | Method and device for predicting particulate matter concentration, storage medium and electronic equipment | |
| Shaghlil et al. | Automating highway infrastructure maintenance using unmanned aerial vehicles | |
| CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
| Carvalho et al. | Maintenance of airport pavements: the use of visual inspection and IRI in the definition of degradation trends | |
| Rostam et al. | Towards the determination of driving factors of varying LST-LCZ relationships–a case study over 25 cities | |
| CN112215416A (en) | Intelligent routing inspection planning system and method | |
| Soleimani et al. | Satellite aerosol optical depth prediction using data mining of climate parameters | |
| Bottyán et al. | Measuring and modeling of hazardous weather phenomena to aviation using the Hungarian Unmanned Meteorological Aircraft System (HUMAS) | |
| Darghiasi et al. | Enhancing Winter Maintenance Decision Making through Deep Learning-Based Road Surface Temperature Estimation | |
| CN110968926A (en) | Method for predicting atmospheric parameters based on improved background error covariance matrix | |
| CN117574493A (en) | Highway frozen soil range deformation identification method and system in permafrost region | |
| Hammond et al. | Verification of route-based road weather forecasts | |
| da Silveira et al. | Observational Investigation of the Statistical Properties of Surface-Layer Turbulence in a Suburban Area of São Paulo, Brazil: Objective Analysis of Scaling-Parameter Accuracy and Uncertainties | |
| Zingerle et al. | Monitoring and verifying cloud forecasts originating from operational numerical models | |
| Franceschi et al. | Identifying treetops from aerial laser scanning data with particle swarming optimization | |
| Qi et al. | Evaluating multivariable statistical methods for downscaling nighttime land surface temperature in urban areas | |
| Reiweger et al. | Measuring acoustic emissions in an avalanche starting zone to monitor snow stability |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 471000 room 210, building 11, phase I standardized workshop, Yiluo Industrial Park, Luoyang City, Henan Province Applicant after: Luoyang Tengfei Construction Engineering Group Co.,Ltd. Address before: 471000 room 210, building 11, phase I standardized workshop, Yiluo Industrial Park, Luoyang City, Henan Province Applicant before: Luoyang Tengfei Municipal Engineering Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |