Airport operation guarantee capability evaluation and analysis method and system

Abstract

The invention relates to an airport operation guarantee capability evaluation and analysis method, which belongs to the field of airport operation and maintenance, and comprises the following steps: intelligently predicting the number of entering airplanes and the number of entering and exiting passenger flows of a target airport in a future time interval by using an airport operation and maintenance analysis model; sending a runway increase request when the number of entering aircrafts exceeds the aircraft capacity threshold value of the target airport in the future time interval, and sending a passenger flow overrun signal when the number of entering and exiting passenger flows is larger than the upper limit of the number of entering and exiting passenger flows of the target airport in the set interval duration. The invention also relates to an airport operation guarantee capability evaluation and analysis system. According to the invention, in order to solve the technical problem that it is difficult to consider time-sharing passenger transport demand meeting and airport operation and maintenance resource saving in the prior art, the airport operation and maintenance analysis model is introduced to predict the number of entering airplanes and the number of entering and exiting passenger flows of the target airport in the future time interval; and executing airport operation guarantee capability evaluation analysis and airport operation and maintenance resource dynamic adjustment, thereby solving the technical problems.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of airport operation and maintenance, and in particular to an airport operation and maintenance capacity evaluation and analysis method and system. BACKGROUND

[0002] Airports come in different sizes, in addition to runways and terminals, airports usually have facilities such as parking aprons, air passenger stations, maintenance plants, and provide services such as airport control services, air traffic control, and other services. As an important place for traffic tools to enter and exit, the operation and maintenance capacity of the airport is the focus of the airport management and the traffic management department, for example, it is hoped that the existing operation and maintenance configuration of the airport can meet the demand for transport capacity while occupying as little runway resources and temporary terminal resources as possible, so that the operation and maintenance efficiency of the airport can be guaranteed while the operation and maintenance cost of the airport is reduced as much as possible.

[0003] For example, Chinese invention patent publication CN116056295A proposes an airport ground intelligent command and dispatch system based on cloud edge collaborative computing, which includes a mobile terminal for viewing lighting plans and business attribute information of lighting fixtures through a wireless network; a desktop terminal for monitoring the running state of the fixtures, auditing and adjusting the fixture use plan, and performing overall inspection and information maintenance; an edge computing module for connecting front-end sensors, performing artificial intelligence operations and fusion, and communicating with the back-end network, and receiving lighting plans issued by the lighting center through the Internet of Things. The advantages of the present application are: the cloud edge collaborative computing is configured, a unified automatic lighting control system is constructed, the Internet access convenience and the centralized control ability of the local network are fully utilized, and at the same time, the dynamic lighting processing of the full automation is realized for the flight support tasks in the daily business, the intelligent access capability of the front end is matched to realize the overall automation of the airport lighting and control and the field access to reduce energy consumption.

[0004] For example, Chinese invention patent publication CN115204425A proposes a BIM-based visual operation and maintenance method and system, relating to the field of artificial intelligence, which includes: obtaining airport historical operation and maintenance data based on big data, and constructing an operation and maintenance decision model; collecting and constructing a basic database and an extended database of a target airport; constructing a BIM model; using the BIM model to perform visual monitoring on the target airport to obtain real-time monitoring data; using a data processing model to obtain data processing results; using the operation and maintenance decision model to obtain operation and maintenance decisions; generating real-time operation and maintenance tasks, and using a task allocation model to allocate the real-time operation and maintenance tasks to target operation and maintenance personnel. The technical problems of high operation and maintenance cost, low efficiency, uncontrollable operation and maintenance quality, affecting the overall operation and maintenance management quality of the airport and the overall safety of the airport in the prior art are solved. The technical effect of reducing the operation and maintenance cost of the airport, improving the operation and maintenance management efficiency and effect of the airport, thereby providing protection for the stable operation of the airport is achieved.

[0005] However, the above technical solutions only involve dynamic lighting processing in airport operation and maintenance or allocation of airport operation and maintenance tasks, and since stable and reliable prediction processing cannot be performed on the number of incoming aircraft and the number of incoming and outgoing passenger flows of the target airport in the future time interval in an intelligent manner, the airport management and the traffic management department can only set the number of working runways in the future time interval and decide whether to use a temporary terminal in advance according to artificial experience or historical experience when formulating an operation and maintenance plan for the future time interval, which is likely to result in insufficient or wasted airport operation and maintenance resources, and cannot achieve dynamic balance between meeting the time-sharing passenger transport demand and saving operation and maintenance resources as much as possible, thereby seriously affecting the ability and efficiency of airport management. SUMMARY

[0006] To solve the technical problems in the prior art, the present application provides an airport operation and maintenance capacity evaluation and analysis method and system, which intelligently predicts the number of incoming aircraft and the number of incoming and outgoing passenger flows of the target airport in the future time interval according to the historical operation and maintenance data and airport configuration information of the target airport by introducing an airport operation and maintenance analysis model designed with customized structure, and when the number of incoming aircraft of the target airport in the future time interval predicted intelligently exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of incoming and outgoing passenger flows of the target airport in the future time interval predicted intelligently is greater than the upper limit of the number of incoming and outgoing passenger flows of the target airport in the set interval, a passenger flow over-limit signal is sent, and then the number of airport operation and maintenance resources in the future time interval is dynamically adjusted according to the number difference between the pre-allocated airport operation and maintenance resources and the actual needed airport operation and maintenance resources, so as to complete the evaluation and analysis of the operation and maintenance capacity of the target airport in the future time interval, and dynamically increase the corresponding airport operation and maintenance resources when the operation and maintenance capacity is determined to be insufficient, so as to achieve dynamic balance between meeting the time-sharing passenger transport demand and saving operation and maintenance resources as much as possible, and improve the ability and efficiency of airport management.

[0007] According to a first aspect of the present application, an airport operation and maintenance capacity evaluation and analysis method is provided, which comprises:

[0008] Collecting the average runway length, the average runway width, the number of permanent residents in the city, the number of recent permanent residents in the city, the total number of terminals, and the average capacity of the terminals of the target airport as the airport configuration information of the target airport;

[0009] Analyzing each part of the historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport, and the historical operation and maintenance data corresponding to each time interval is the number of working runways, the number of incoming aircraft, and the number of incoming and outgoing passenger flows of the target airport in the time interval;

[0010] performing multiple training operations on the deep neural network to obtain a deep neural network after the multiple training operations are completed and as an airport operation analysis model;

[0011] using the airport operation analysis model to intelligently predict the number of incoming aircraft and the number of passenger flows of the target airport in the future time interval according to the total number of runways of the target airport, the set interval duration, the various airport configuration information of the target airport, and each part of historical operation data corresponding to each historical time interval before the future time interval of the target airport;

[0012] when the intelligently predicted number of incoming aircraft of the target airport in the future time interval exceeds the aircraft capacity threshold of the target airport in the future time interval, issuing a runway increase request, and when the intelligently predicted number of passenger flows of the target airport in the future time interval is greater than the upper limit of the number of passenger flows of the target airport in the set interval duration, issuing a passenger flow over-limit signal;

[0013] wherein the number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

[0014] According to a second aspect of the present application, an airport operation guarantee capability evaluation and analysis system is provided, which comprises a memory and a plurality of processors, the memory storing a computer program configured to be executed by the plurality of processors to complete the following steps:

[0015] collecting the average runway length, the average runway width, the number of permanent residents in the city where the target airport is located, the number of permanent residents in the city recently, the total number of terminals, and the average capacity of the terminals of the target airport as the various airport configuration information of the target airport;

[0016] analyzing each part of historical operation data corresponding to each historical time interval before the future time interval of the target airport, and the historical operation data corresponding to each time interval being the number of working runways, the number of incoming aircraft, and the number of passenger flows of the target airport in the time interval;

[0017] performing multiple training operations on the deep neural network to obtain a deep neural network after the multiple training operations are completed and as an airport operation analysis model;

[0018] using the airport operation analysis model to intelligently predict the number of incoming aircraft and the number of passenger flows of the target airport in the future time interval according to the total number of runways of the target airport, the set interval duration, the various airport configuration information of the target airport, and each part of historical operation data corresponding to each historical time interval before the future time interval of the target airport;

[0019] When the number of incoming aircraft of the target airport in the future time interval predicted by the intelligent prediction exceeds the threshold of the number of aircrafts that the target airport can accommodate in the future time interval, a runway increase request is sent out, and when the number of passenger flows in and out of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows in and out of the target airport in the set interval, an over-limit signal of passenger flow is sent out.

[0020] The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

[0021] According to a third aspect of the present application, an airport operation guarantee capacity evaluation and analysis system is provided, and the system comprises:

[0022] An airport collection mechanism is configured to collect the average runway length, the average runway width, the number of permanent residents in the city where the target airport is located, the number of permanent residents in the nearest city, the total number of terminal buildings, and the average capacity of the terminal buildings of the target airport as the airport configuration information of the target airport.

[0023] A historical analysis mechanism is configured to analyze each piece of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport, and the historical operation and maintenance data corresponding to each time interval is the number of working runways, the number of incoming aircrafts, and the number of passenger flows in and out of the target airport in the time interval.

[0024] A model establishing mechanism is configured to perform multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations and use the deep neural network as the airport operation and maintenance analysis model.

[0025] A data prediction mechanism is connected with the airport collection mechanism, the historical analysis mechanism, and the model establishing mechanism, and is configured to use the airport operation and maintenance analysis model to intelligently predict the number of incoming aircrafts and the number of passenger flows in and out of the target airport in the future time interval according to the total number of runways of the target airport, the set interval, the airport configuration information of the target airport, and each piece of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport.

[0026] A capacity evaluation mechanism is connected with the data prediction mechanism, and is configured to send out a runway increase request when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the threshold of the number of aircrafts that the target airport can accommodate in the future time interval, and send out an over-limit signal of passenger flow when the number of passenger flows in and out of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows in and out of the target airport in the set interval.

[0027] The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

[0028] Compared with the prior art, the present application has at least the following four key points:

[0029] Invention point one: different structures of airport operation analysis models are designed for target airports with different population sizes to complete intelligent prediction of the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport, specifically, the airport operation analysis model is a deep neural network after multiple training operations, the number of training operations of the deep neural network is positively correlated with the permanent population of the city where the target airport is located, thereby ensuring the stability and reliability of the intelligent prediction data;

[0030] Invention point two: for intelligent prediction of the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport, multiple basic information are selected, specifically, the total number of runways of the target airport, the set interval time, the various airport configuration information of the target airport, and each part of the historical operation data corresponding to each historical time interval before the future time interval of the target airport, the various airport configuration information of the target airport is the average runway length, the average runway width, the permanent population of the city, the recent permanent population of the city, the total number of terminals, and the average capacity of the terminal, and the historical operation data corresponding to each time interval is the number of working runways, the number of incoming aircraft and the number of passenger flows in the target airport in the time interval. The targeted selection of the above comprehensive and sufficient multiple basic information further ensures the stability and reliability of the intelligent prediction data;

[0031] Invention point three: when the number of incoming aircraft of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and according to the absolute value of the difference between the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction and the upper limit of the number of passenger flows of the target airport in the set interval time, the number of temporary terminals to be added in the future time interval of the target airport is determined in a positive correlation with the absolute value, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval time, a passenger flow overrun signal is sent, and according to the absolute value of the difference between the number of incoming aircraft of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval, the number of runways to be added in the future time interval of the target airport is determined in a positive correlation with the absolute value, thereby completing the dynamic balance between meeting the time-sharing passenger flow demand and saving operation resources as much as possible based on the intelligent prediction result, and improving the ability and efficiency of airport management;

[0032] The fourth invention point is that in each training operation performed on the deep neural network, the known target airport incoming aircraft quantity and the incoming and outgoing passenger flow quantity in a historical time interval are taken as the output content of the deep neural network, and the runway total number of the target airport, the set interval time length, the various airport configuration information of the target airport and each historical operation and maintenance data corresponding to each historical time interval before the certain historical time interval of the target airport are taken as the input content of the deep neural network, the training operation is completed, and the training effect of each training operation of the deep neural network is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0033] The embodiments of the present application will be described below in conjunction with the accompanying drawings, in which:

[0034] Figure 1 The working scene schematic diagram of the airport operation guarantee capacity evaluation and analysis method and system according to the present application is shown.

[0035] Figure 2 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to the embodiment 1 of the present application is shown.

[0036] Figure 3 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to the embodiment 2 of the present application is shown.

[0037] Figure 4 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to the embodiment 3 of the present application is shown.

[0038] Figure 5 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to the embodiment 4 of the present application is shown.

[0039] Figure 6 The structural schematic diagram of the airport operation guarantee capacity evaluation and analysis system according to the embodiment 5 of the present application is shown.

[0040] Figure 7 The structural schematic diagram of the airport operation guarantee capacity evaluation and analysis system according to the embodiment 6 of the present application is shown. DETAILED DESCRIPTION

[0041] As shown in the drawings, the working scene schematic diagram of the airport operation guarantee capacity evaluation and analysis method and system according to the present application is shown. Figure 1

[0042] The specific technical process of the present application is as follows:

[0043] Technical process A: in order to complete the intelligent prediction of the incoming aircraft quantity and the incoming and outgoing passenger flow quantity of the target airport in a future time interval, the airport operation and maintenance analysis model with a corresponding structure is customized for the target airport;​

[0044] Specifically, the following several items embody the customized structure design of the airport operation analysis model:

[0045] (1) The airport operation analysis model is a deep neural network after completing multiple training operations;

[0046] (2) The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located;

[0047] (3) In each training operation performed on the deep neural network, the known number of incoming aircraft and the number of passenger flows of the target airport in a certain historical time interval are taken as the output content of the deep neural network, and the total number of runways of the target airport, the set interval duration, the various airport configuration information of the target airport, and each historical operation data corresponding to each historical time interval before the certain historical time interval of the target airport are taken as the input content of the deep neural network, to complete this training operation, thereby ensuring the training effect of each training operation of the deep neural network;

[0048] In this way, the multiple model customization structure designs of the above-mentioned airport operation analysis model ensure the stability and reliability of the intelligent prediction data;

[0049] Technical process B: For the intelligent prediction of the number of incoming aircraft and the number of passenger flows of the target airport in the future time interval, multiple basic information is selected;

[0050] Specifically, as shown in Figure 1 The multiple basic information includes: each part of the auxiliary content, each item of the airport configuration information of the target airport, and each part of the historical operation data corresponding to each historical time interval before the future time interval, the auxiliary content includes the total number of runways of the target airport and the set interval duration;

[0051] Further specifically, the future time interval takes the current time as the starting time, the historical time interval closest to the future time interval among the historical time intervals before the future time interval takes the current time as the ending time, and each historical time interval before the future time interval and the future time interval form a complete time segment on the time axis, and the duration of each time interval is equal to the set interval duration;

[0052] For example, the future time interval is a time interval starting at 6:00 pm and lasting for 30 minutes, the previous historical time intervals of the future time interval are 5:30 pm to 6:00 pm, 5:00 pm to 5:30 pm, 4:30 pm to 5:00 pm, 4:00 pm to 4:30 pm, 3:30 pm to 4:00 pm, 3:00 pm to 3:30 pm, 2:30 pm to 3:00 pm, and 2:00 pm to 2:30 pm, a total of 8 historical time intervals;

[0053] Further specifically, the airport configuration information of the target airport includes the average runway length, the average runway width, the number of permanent residents in the city, the number of permanent residents in the nearest city, the total number of terminal buildings, and the average capacity of the terminal buildings;

[0054] Further specifically, the historical operation data corresponding to each time interval includes the number of working runways, the number of incoming aircraft, and the number of passenger flows in the target airport in the time interval;

[0055] In this way, the targeted selection of the comprehensive and sufficient multiple basic information further ensures the stability and reliability of the intelligent prediction data;

[0056] Technical process C: using the airport operation analysis model designed according to technical process A to intelligently predict the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport based on the comprehensive and sufficient multiple basic information selected according to technical process B;

[0057] Technical process D: based on the intelligent prediction data of technical process C, performing evaluation and analysis on the operation support capacity of the target airport in the future time interval, and dynamically increasing the corresponding airport operation resources when the operation support capacity is insufficient;

[0058] For example, when the number of incoming aircraft of the target airport in the future time interval predicted intelligently exceeds the capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted intelligently is greater than the upper limit of the number of passenger flows of the target airport in the set interval, a passenger flow overrun signal is sent, and then the number of airport operation resources in the future time interval is dynamically adjusted according to the number difference between the pre-allocated airport operation resources and the actually needed airport operation resources;

[0059] Further exemplarily, when issuing a runway increase request, the absolute value of the difference between the number of passenger flows in and out of the target airport in the future time interval according to the intelligent prediction and the upper limit of the number of passenger flows in and out of the target airport in the set interval length is determined, and the number of temporary terminal buildings to be added in the future time interval of the target airport is determined in positive correlation with the absolute value; and when issuing a passenger flow over-limit signal, the absolute value of the difference between the number of incoming aircrafts in the future time interval of the target airport according to the intelligent prediction and the aircraft capacity threshold in the future time interval of the target airport is determined, and the number of runways to be added in the future time interval of the target airport is determined in positive correlation with the absolute value.

[0060] In this way, the dynamic balance between meeting the time-sharing passenger transport demand and saving operation and maintenance resources as much as possible based on the intelligent prediction result is achieved, and the ability and efficiency of airport management are improved.

[0061] The key points of the present application are: the customized structure design of different airport operation and maintenance analysis models of target airports of different city sizes, the comprehensive and sufficient selection of multiple basic information for intelligent prediction of the number of incoming aircrafts and the number of passenger flows in the future time interval of the target airport, the evaluation and analysis of the operation guarantee capacity of the target airport in the future time interval based on the intelligent prediction result, and the time-sharing dynamic allocation of airport operation and maintenance resources based on the evaluation and analysis result.

[0062] Hereinafter, the airport operation guarantee capacity evaluation and analysis method and system of the present application will be specifically described in the form of embodiments.

[0063] Embodiment 1

[0064] Figure 2 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to Embodiment 1 of the present application is shown.

[0065] As shown in Figure 2 , the airport operation guarantee capacity evaluation and analysis method includes the following specific steps:

[0066] Step 21: Collect the average runway length, the average runway width, the number of permanent residents in the city, the number of recent permanent residents in the city, the total number of terminals, and the average capacity of the terminals of the target airport as the various airport configuration information of the target airport;

[0067] Exemplarily, collecting the average runway length, the average runway width, the number of permanent residents in the city, the number of recent permanent residents in the city, the total number of terminals, and the average capacity of the terminals of the target airport as the various airport configuration information of the target airport includes: a plurality of different information collection devices can be selected to collect the average runway length, the average runway width, the number of permanent residents in the city, the number of recent permanent residents in the city, the total number of terminals, and the average capacity of the terminals of the target airport, respectively;

[0068] Step 22: parsing each part of historical operation and maintenance data respectively corresponding to each historical time interval before the future time interval of the target airport, the historical operation and maintenance data corresponding to each time interval being the number of working runways, the number of incoming aircraft and the number of passenger flow in and out of the target airport in the time interval;

[0069] For example, the future time interval is a time interval with 6:00 pm as the starting time and a duration of 30 minutes, and the historical time intervals before the future time interval are 5:30 pm to 6:00 pm, 5:00 pm to 5:30 pm, 4:30 pm to 5:00 pm, 4:00 pm to 4:30 pm, 3:30 pm to 4:00 pm, 3:00 pm to 3:30 pm, 2:30 pm to 3:00 pm, and 2:00 pm to 2:30 pm, a total of 8 historical time intervals;

[0070] Step 23: performing multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations and as an airport operation and maintenance analysis model;

[0071] Specifically, the test and simulation of the model establishment process of performing multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations and as an airport operation and maintenance analysis model can be completed by selecting a numerical simulation mechanism;

[0072] Step 24: using the airport operation and maintenance analysis model to intelligently predict the number of incoming aircraft and the number of passenger flow in and out of the target airport in the future time interval according to the total number of runways of the target airport, the set interval duration, the airport configuration information of the target airport, and each part of historical operation and maintenance data respectively corresponding to each historical time interval before the future time interval of the target airport;

[0073] In this way, on the basis of the artificial intelligence model of customized structural design, according to the configuration information of the target airport itself, multiple historical operation and maintenance data of the target airport, and each part of auxiliary content including the total number of runways of the target airport and the set interval duration, intelligent prediction of the operation and maintenance demand data of the target airport in the future time interval is realized;

[0074] Correspondingly, through the above stable and reliable intelligent prediction, a solid data foundation is provided for subsequent evaluation and analysis of the airport operation support capability of the target airport in the future time interval, and dynamic allocation of airport operation and maintenance resources in the future time interval according to the evaluation and analysis results;

[0075] Step 25: when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval, a passenger flow over-limit signal is sent;

[0076] For example, when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval, a passenger flow over-limit signal is sent, including: when the sum of the number of incoming aircrafts and the number of outgoing aircrafts accommodated by a single runway of the target airport in 30 minutes is 15, and the number of working runways configured by the target airport for the future time interval from 5:30 pm to 6:00 pm on the same day is 6, the aircraft capacity threshold of the target airport in the future time interval from 5:30 pm to 6:00 pm on the same day is 90, and the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction is 102, a runway increase request needs to be sent;

[0077] Conversely, when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction does not exceed the aircraft capacity threshold of the target airport in the future time interval, a runway matching signal is sent.

[0078] For example, when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval, a passenger flow over-limit signal is sent, which further includes: when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is 5,000, and the upper limit of the number of passenger flows of the target airport in 30 minutes is 3,000, a passenger flow over-limit signal needs to be sent.

[0079] Conversely, when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is less than or equal to the upper limit of the number of passenger flows of the target airport in the set interval, a passenger flow low-limit signal is sent.

[0080] The number of times of the training operation of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

[0081] For example, the number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located, including: when the number of permanent residents in the city where the target airport is located is 500,000, the number of training operations of the deep neural network is 3000, when the number of permanent residents in the city where the target airport is located is 1,000,000, the number of training operations of the deep neural network is 4000, when the number of permanent residents in the city where the target airport is located is 2,000,000, the number of training operations of the deep neural network is 5000, when the number of permanent residents in the city where the target airport is located is 3,000,000, the number of training operations of the deep neural network is 6000, and so on.

[0082] In each training operation performed on the deep neural network, the number of incoming aircraft and the number of passenger flows of the known target airport in a certain historical time interval are taken as the output content of the deep neural network, and the total number of runways of the target airport, the set interval time, each item of airport configuration information of the target airport, and each historical operation and maintenance data corresponding to each historical time interval before the certain historical time interval of the target airport are taken as the input content of the deep neural network, to complete the training operation.

[0083] The number of historical time intervals before the future time interval of the target airport is positively correlated with the total number of terminals of the target airport.

[0084] For example, the number of historical time intervals before the future time interval of the target airport is positively correlated with the total number of terminals of the target airport, including: when the total number of terminals of the target airport is 3, the number of historical time intervals before the future time interval of the target airport is 8, when the total number of terminals of the target airport is 5, the number of historical time intervals before the future time interval of the target airport is 16, when the total number of terminals of the target airport is 7, the number of historical time intervals before the future time interval of the target airport is 24, and so on.

[0085] The product of the number of runways of the target airport planned for the future time interval and the upper limit of the number of aircraft accommodated by a single runway in the set interval time is taken as the aircraft accommodation threshold of the target airport in the future time interval.

[0086] Specifically, when the sum of the number of aircraft arriving and the number of aircraft departing accommodated by a single runway of the target airport within 30 minutes is 15, and the number of working runways configured by the target airport for the future time interval from 5:30 pm to 6:00 pm is 6, the aircraft accommodation threshold of the target airport in the future time interval from 5:30 pm to 6:00 pm is 90.

[0087] Specifically, the analysis involves resolving the historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport. The historical operation and maintenance data corresponding to each time interval includes the number of working runways, the number of arriving aircraft, and the number of arriving and departing passengers of the target airport within the time interval. The number of arriving and departing passengers of the target airport within the time interval is the sum of the number of arriving passengers and the number of departing passengers of the target airport within the time interval.

[0088] The future time interval starts at the current time, the most recent historical time interval before the future time interval ends at the current time, and all the historical time intervals before the future time interval and the future time interval together form a complete time segment on the time axis, and the duration of each time interval is equal to the set interval duration.

[0089] For example, the future time interval starts at the current time, the most recent historical time interval before the future time interval ends at the current time, and the previous historical time intervals and the future time interval together form a complete time segment on the time axis, with each time interval having the same duration, which is equal to the set interval duration, including: the set interval duration can be selected as 30 minutes.

[0090] Example 2

[0091] Figure 3 The following is a flowchart illustrating the steps of an airport operation support capability assessment and analysis method according to Embodiment 2 of the present invention.

[0092] like Figure 3 As shown, with Figure 2 Unlike the previous implementation, after issuing a runway expansion request when the number of arriving aircraft at the target airport in a future time interval, as predicted by the intelligent system, exceeds the airport's capacity threshold for that time interval, and after issuing a passenger flow overload signal when the number of arriving and departing passengers at the target airport in a future time interval exceeds the upper limit of the passenger flow at the target airport for a set interval, i.e., after step S25, the method further includes:

[0093] Step S26: Upon receiving a passenger flow over-limit signal, determine the number of temporary terminals to be added to the target airport in the future time interval based on the absolute value of the difference between the intelligently predicted number of passengers entering and leaving the target airport in the future time interval and the upper limit of the number of passengers entering and leaving the target airport at the set interval.

[0094] Among them, the absolute value of the difference between the number of temporary terminals to be added at the target airport in the future time interval and the number of passengers entering and leaving the target airport in the future time interval predicted by the intelligent system and the upper limit of the number of passengers entering and leaving the target airport at the set interval is positively correlated.

[0095] For example, when the absolute value of the difference between the number of incoming and outgoing passengers of the target airport in the future time interval and the upper limit of the number of incoming and outgoing passengers of the target airport in the set interval is 2000, the determined number of temporary terminal buildings to be added in the future time interval of the target airport is 1; when the absolute value of the difference between the number of incoming and outgoing passengers of the target airport in the future time interval and the upper limit of the number of incoming and outgoing passengers of the target airport in the set interval is 4000, the determined number of temporary terminal buildings to be added in the future time interval of the target airport is 2; and so on.

[0096] Embodiment 3

[0097] Figure 4 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to Embodiment 3 of the present application is shown.

[0098] As Figure 4 shown, unlike the embodiment in the Figure 2 , when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and after the signal of passenger flow exceeding the limit is sent when the number of incoming and outgoing passengers of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of incoming and outgoing passengers of the target airport in the set interval, that is, after step S25, the method further comprises:

[0099] Step S27: When the runway increase request is received, the number of runways to be added in the future time interval of the target airport is determined according to the absolute value of the difference between the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval;

[0100] Wherein, the number of runways to be added in the future time interval of the target airport is positively correlated with the absolute value of the difference between the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval;

[0101] For example, when the absolute value of the difference between the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval is 12, the determined number of runways to be added in the future time interval of the target airport is 1; when the absolute value of the difference between the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval is 24, the determined number of runways to be added in the future time interval of the target airport is 2; and so on.

[0102] Embodiment 4

[0103] Figure 5 The step flow chart of the airport operation guarantee capacity evaluation and analysis method according to Embodiment 4 of the present application is shown.

[0104] As Figure 5 shown, unlike the embodiment in Figure 2 , after performing multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations are completed and as the airport operation and maintenance analysis model, that is, after step S23, the method further comprises:

[0105] Step S28: completing model storage of the airport operation and maintenance analysis model by storing the model parameters of the airport operation and maintenance analysis model;

[0106] Specifically, completing the model storage of the airport operation and maintenance analysis model by storing the model parameters of the airport operation and maintenance analysis model includes that a TF storage chip, an MMC storage chip or a FLASH storage chip can be selected to complete the model storage of the airport operation and maintenance analysis model by storing the model parameters of the airport operation and maintenance analysis model.

[0107] Next, the various method embodiments of the application will be described in detail.

[0108] In the airport operation guarantee capacity evaluation and analysis method according to the various method embodiments of the application:

[0109] Collecting the average runway length, the average runway width, the number of permanent residents in the city, the number of permanent residents in the nearest city, the total number of terminal buildings and the average capacity of terminal buildings of the target airport as the airport configuration information of the target airport includes: obtaining the upper limit of the number of passengers accommodated by each terminal building of the target airport, and taking the average value of the upper limit of the number of passengers accommodated by each terminal building as the average capacity of the terminal buildings of the target airport;

[0110] For example, obtaining the upper limit of the number of passengers accommodated by each terminal building of the target airport, and taking the average value of the upper limit of the number of passengers accommodated by each terminal building as the average capacity of the terminal buildings of the target airport includes: when there are three terminal buildings in the target airport, and the upper limit of the number of passengers accommodated by each terminal building is two thousand, one thousand and three thousand respectively, the average capacity of the terminal buildings of the target airport is two thousand;

[0111] Among them, collecting the average runway length, the average runway width, the number of permanent residents in the city, the number of permanent residents in the nearest city, the total number of terminal buildings and the average capacity of terminal buildings of the target airport as the airport configuration information of the target airport further includes: obtaining the runway length corresponding to each runway of the target airport, and taking the average value of the runway length as the average runway length of the target airport;

[0112] and wherein the collecting the average runway length, the average runway width, the number of permanent residents in the city where the target airport is located, the number of permanent residents in the nearest city, the total number of terminals, and the average capacity of the terminals of the target airport as the airport configuration information of the target airport comprises: obtaining each runway width corresponding to each runway of the target airport, and taking the average of each runway width as the average runway width of the target airport.

[0113] and in the airport operation guarantee capacity evaluation and analysis method according to the various method embodiments of the present application:

[0114] the intelligent prediction of the number of incoming aircraft and the number of incoming and outgoing passenger flows of the target airport in the future time interval using the airport operation analysis model according to the total number of runways of the target airport, the set interval length, the airport configuration information of the target airport, and each historical operation data corresponding to each historical time interval before the future time interval of the target airport comprises: performing octal value conversion processing on the total number of runways of the target airport, the set interval length, the airport configuration information of the target airport, and each historical operation data corresponding to each historical time interval before the future time interval of the target airport, and then inputting them into the airport operation analysis model in parallel;

[0115] For example, the MATLAB toolbox can be used to complete the test and simulation of the data processing process of performing octal value conversion processing on the total number of runways of the target airport, the set interval length, the airport configuration information of the target airport, and each historical operation data corresponding to each historical time interval before the future time interval of the target airport, and then inputting them into the airport operation analysis model in parallel;

[0116] The intelligent prediction of the number of incoming aircraft and the number of incoming and outgoing passenger flows of the target airport in the future time interval using the airport operation analysis model according to the total number of runways of the target airport, the set interval length, the airport configuration information of the target airport, and each historical operation data corresponding to each historical time interval before the future time interval of the target airport further comprises: running the airport operation analysis model to obtain the number of incoming aircraft and the number of incoming and outgoing passenger flows of the target airport in the future time interval represented by the octal value output by the airport operation analysis model;

[0117] The positive correlation between the number of training operations of the deep neural network and the number of permanent residents in the city where the target airport is located comprises: using a numerical conversion function to represent the numerical conversion relationship between the number of training operations of the deep neural network and the number of permanent residents in the city where the target airport is located.

[0118] The numerical conversion function is used to represent the positive correlation between the number of training operations of the deep neural network and the number of permanent residents in the city where the target airport is located.

[0119] The numerical conversion function is used to represent the positive correlation between the number of training operations of the deep neural network and the number of permanent residents in the city where the target airport is located.

[0120] When the number of incoming aircraft of the target airport in the future time interval exceeds the capacity threshold of the target airport in the future time interval, the runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval exceeds the upper limit of the number of passenger flows of the target airport in the set interval, the passenger flow overflow signal is sent. The runway increase request is sent, and the airport number corresponding to the target airport, the runway increase request and the number of incoming aircraft of the target airport in the future time interval are packed into a network data packet and then sent to the remote airport operation support server through a wireless communication link.

[0121] For example, when the runway increase request is sent, the airport number corresponding to the target airport, the runway increase request and the number of incoming aircraft of the target airport in the future time interval are packed into a network data packet and then sent to the remote airport operation support server through a wireless communication link. The network data packet is an IP data packet.

[0122] For example, when the runway increase request is sent, the airport number corresponding to the target airport, the runway increase request and the number of incoming aircraft of the target airport in the future time interval are packed into a network data packet and then sent to the remote airport operation support server through a wireless communication link. The network data packet is an IP data packet.

[0123] When the number of incoming aircraft of the target airport in the future time interval exceeds the capacity threshold of the target airport in the future time interval, the runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval exceeds the upper limit of the number of passenger flows of the target airport in the set interval, the passenger flow overflow signal is sent. The runway increase request is sent, and the airport number corresponding to the target airport, the runway increase request and the number of incoming aircraft of the target airport in the future time interval are packed into a network data packet and then sent to the remote airport operation support server through a wireless communication link.

[0124] Embodiment 5

[0125] Figure 6 A structural schematic diagram of an airport operation guarantee capacity evaluation and analysis system according to Embodiment 5 of the present application is shown.

[0126] As shown in Figure 6 the airport operation guarantee capacity evaluation and analysis system includes a memory and a plurality of processors, the memory storing a computer program configured to be executed by the plurality of processors to complete the following steps:

[0127] Step 21: Collecting average runway length, average runway width, resident population of the city where the target airport is located, recent resident population of the city, total number of terminal buildings and average capacity of terminal buildings of the target airport as various airport configuration information of the target airport;

[0128] For example, collecting average runway length, average runway width, resident population of the city where the target airport is located, recent resident population of the city, total number of terminal buildings and average capacity of terminal buildings of the target airport as various airport configuration information of the target airport includes: a plurality of different information collection devices can be selected to collect average runway length, average runway width, resident population of the city where the target airport is located, recent resident population of the city, total number of terminal buildings and average capacity of terminal buildings of the target airport, respectively;

[0129] Step 22: Analyzing each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport, the historical operation and maintenance data corresponding to each time interval being the number of working runways, the number of incoming aircraft and the number of passenger flows in the target airport in the time interval;

[0130] For example, the future time interval is a time interval with 6:00 pm as the starting time and a duration of 30 minutes, and the historical time intervals before the future time interval are 5:30 pm to 6:00 pm, 5:00 pm to 5:30 pm, 4:30 pm to 5:00 pm, 4:00 pm to 4:30 pm, 3:30 pm to 4:00 pm, 3:00 pm to 3:30 pm, 2:30 pm to 3:00 pm, and 2:00 pm to 2:30 pm, a total of 8 historical time intervals;

[0131] Step 23: performing a plurality of training operations on the deep neural network to obtain the deep neural network after completing the plurality of training operations and as an airport operation and maintenance analysis model;

[0132] Specifically, the numerical simulation mechanism can be selected to perform multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations and serve as a test and simulation of the model establishment process of the airport operation analysis model.

[0133] Step 24: Using the airport operation analysis model, intelligently predicting the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport according to the total number of runways of the target airport, the set interval duration, the airport configuration information of the target airport, and each historical operation data corresponding to each historical time interval before the future time interval of the target airport;

[0134] In this way, on the basis of the artificial intelligence model for customizing the structural design, according to the configuration information of the target airport itself, multiple historical operation data of the target airport, and each auxiliary content including the total number of runways of the target airport and the set interval duration, the intelligent prediction of the operation demand data of the target airport in the future time interval is realized;

[0135] Correspondingly, through the above stable and reliable intelligent prediction, a solid data foundation is provided for the subsequent evaluation and analysis of the airport operation support capability of the target airport in the future time interval, and the dynamic allocation of airport operation resources in the future time interval according to the evaluation and analysis results;

[0136] Step 25: When the number of incoming aircraft of the target airport in the future time interval predicted intelligently exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows in the future time interval of the target airport predicted intelligently is greater than the upper limit of the number of passenger flows of the target airport in the set interval duration, a passenger flow overrun signal is sent;

[0137] For example, when the number of incoming aircraft of the target airport in the future time interval predicted intelligently exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows in the future time interval of the target airport predicted intelligently is greater than the upper limit of the number of passenger flows of the target airport in the set interval duration, a passenger flow overrun signal is sent, including: when the sum of the number of incoming aircraft and the number of outgoing aircraft accommodated by a single runway of the target airport in 30 minutes is 15, and the number of working runways configured by the target airport for the future time interval from 5:30 pm to 6:00 pm on the same day is 6, the aircraft capacity threshold of the target airport in the future time interval from 5:30 pm to 6:00 pm on the same day is 90, and the number of incoming aircraft of the target airport in the future time interval predicted intelligently is 102, a runway increase request needs to be sent;

[0138] On the contrary, when the number of incoming aircraft of the target airport in the future time interval predicted intelligently does not exceed the aircraft capacity threshold of the target airport in the future time interval, a runway matching signal is sent.

[0139] For example, when the number of incoming aircrafts of the target airport in the future time interval exceeds the threshold of the number of aircrafts of the target airport in the future time interval, the runway increase request is sent out, and when the number of passenger flows of the target airport in the future time interval is greater than the upper limit of the number of passenger flows of the target airport in the set interval, the passenger flow over-limit signal is sent out. Further, when the number of passenger flows of the target airport in the future time interval is 5,000 and the upper limit of the number of passenger flows of the target airport in 30 minutes is 3,000, the passenger flow over-limit signal needs to be sent out.

[0140] Conversely, when the number of passenger flows of the target airport in the future time interval is less than or equal to the upper limit of the number of passenger flows of the target airport in the set interval, the passenger flow lower-limit signal is sent out.

[0141] The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

[0142] For example, the number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located, including: when the number of permanent residents in the city where the target airport is located is 0.5 million, the number of training operations of the deep neural network is 3,000; when the number of permanent residents in the city where the target airport is located is 1 million, the number of training operations of the deep neural network is 4,000; when the number of permanent residents in the city where the target airport is located is 2 million, the number of training operations of the deep neural network is 5,000; when the number of permanent residents in the city where the target airport is located is 3 million, the number of training operations of the deep neural network is 6,000, and so on.

[0143] In each training operation of the deep neural network, the known number of incoming aircrafts and the number of passenger flows of the target airport in a certain historical time interval are taken as the output content of the deep neural network, and the total number of runways of the target airport, the set interval, the airport configuration information of the target airport, and each historical operation and maintenance data corresponding to each historical time interval before the certain historical time interval are taken as the input content of the deep neural network, so as to complete the training operation.

[0144] The number of historical time intervals before the future time interval of the target airport is proportional to the total number of terminals of the target airport.

[0145] For example, the number of historical time intervals before the future time interval for the target airport is proportional to the total number of terminals of the target airport, including: when the total number of terminals of the target airport is 3, the number of historical time intervals before the future time interval for the target airport is 8; when the total number of terminals of the target airport is 5, the number of historical time intervals before the future time interval for the target airport is 16; when the total number of terminals of the target airport is 7, the number of historical time intervals before the future time interval for the target airport is 24; and so on.

[0146] wherein the product of the number of runways pre-planned by the target airport for the future time interval and the upper limit of the number of aircrafts accommodated by a single runway in the set interval duration is taken as the aircraft accommodation threshold of the target airport in the future time interval.

[0147] Specifically, when the sum of the number of aircrafts accommodated by a single runway and the number of aircrafts taking off from a single runway within 30 minutes is 15, and the number of working runways configured by the target airport in advance for the future time interval from 5:30 pm to 6:00 pm is 6, the aircraft accommodation threshold of the target airport in the future time interval from 5:30 pm to 6:00 pm is 90.

[0148] wherein the historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport is analyzed, and the historical operation and maintenance data corresponding to each time interval includes the number of working runways, the number of incoming aircrafts and the number of passenger flows of the target airport in the time interval, including: the number of passenger flows of the target airport in the time interval is the sum of the number of incoming passengers and the number of outgoing passengers of the target airport in the time interval.

[0149] wherein the future time interval takes the current time as the start time, the nearest historical time interval before the future time interval takes the current time as the end time, each historical time interval before the future time interval and the future time interval form a complete time segment on the time axis, and the duration of each time interval is equal, all equal to the set interval duration.

[0150] For example, the future time interval takes the current time as the start time, the nearest historical time interval before the future time interval takes the current time as the end time, each historical time interval before the future time interval and the future time interval form a complete time segment on the time axis, and the duration of each time interval is equal, all equal to the set interval duration, including: the set interval duration can be selected as 30 minutes.

[0151] As shown in FIG. 1, Figure 6 As shown in FIG. 1,

[0152] Embodiment 6

[0153] Figure 7 A structural schematic diagram of an airport operation support capability evaluation and analysis system according to Embodiment 6 of the present application is shown.

[0154] As shown in Figure 7 , the airport operation support capability evaluation and analysis system comprises the following components:

[0155] An airport collection mechanism for collecting average runway length, average runway width, resident population of the city where the target airport is located, recent resident population of the city, total number of terminal buildings, and average capacity of terminal buildings of the target airport as various airport configuration information of the target airport;

[0156] For example, collecting average runway length, average runway width, resident population of the city where the target airport is located, recent resident population of the city, total number of terminal buildings, and average capacity of terminal buildings of the target airport as various airport configuration information of the target airport includes: a plurality of different information collection devices can be selected to be used to collect average runway length, average runway width, resident population of the city where the target airport is located, recent resident population of the city, total number of terminal buildings, and average capacity of terminal buildings of the target airport, respectively;

[0157] A history analysis mechanism for analyzing each historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport, the historical operation and maintenance data corresponding to each time interval being the number of working runways, the number of incoming aircraft, and the number of passenger flows of the target airport in the time interval;

[0158] For example, the future time interval is a time interval with 6:00 pm as the starting time and a duration of 30 minutes, and the historical time intervals before the future time interval are 5:30 pm to 6:00 pm, 5:00 pm to 5:30 pm, 4:30 pm to 5:00 pm, 4:00 pm to 4:30 pm, 3:30 pm to 4:00 pm, 3:00 pm to 3:30 pm, 2:30 pm to 3:00 pm, and 2:00 pm to 2:30 pm, a total of 8 historical time intervals;

[0159] A model establishment mechanism for performing a plurality of training operations on a deep neural network to obtain a deep neural network after the plurality of training operations and as an airport operation and maintenance analysis model;

[0160] Specifically, a numerical simulation mechanism can be selected to complete the test and simulation of the model establishment process of performing a plurality of training operations on a deep neural network to obtain a deep neural network after the plurality of training operations and as an airport operation and maintenance analysis model.

[0161] The data prediction mechanism is connected with the airport collection mechanism, the historical analysis mechanism and the model establishment mechanism respectively, and is configured to use the airport operation and maintenance analysis model to intelligently predict the number of incoming aircraft and the number of passenger flows of the target airport in the future time interval according to the total number of runways of the target airport, the set interval length, the various airport configuration information of the target airport and each part of the historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport.

[0162] In this way, on the basis of the artificial intelligence model for customizing the structural design, the intelligent prediction of the operation and maintenance demand data of the target airport in the future time interval is realized according to the configuration information of the target airport itself, the multiple historical operation and maintenance data of the target airport and each part of the auxiliary content including the total number of runways of the target airport and the set interval length.

[0163] Correspondingly, through the above stable and reliable intelligent prediction, a solid data foundation is provided for the subsequent evaluation and analysis of the airport operation support capability of the target airport in the future time interval and the dynamic supplement of the airport operation and maintenance resources in the future time interval according to the evaluation and analysis results.

[0164] The capability evaluation mechanism is connected with the data prediction mechanism, and is configured to send a runway increase request when the number of incoming aircraft of the target airport in the future time interval predicted intelligently exceeds the aircraft capacity threshold of the target airport in the future time interval, and send a passenger flow overrun signal when the number of passenger flows of the target airport in the future time interval predicted intelligently is greater than the upper limit of the number of passenger flows of the target airport in the set interval length.

[0165] For example, when the number of incoming aircraft of the target airport in the future time interval predicted intelligently exceeds the aircraft capacity threshold of the target airport in the future time interval, the runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted intelligently is greater than the upper limit of the number of passenger flows of the target airport in the set interval length, the passenger flow overrun signal is sent, which includes that when the sum of the number of incoming aircraft and the number of outgoing aircraft accommodated by a single runway of the target airport in 30 minutes is 15 and the number of working runways configured by the target airport for the future time interval from 5:30 pm to 6:00 pm on the same day is 6, the aircraft capacity threshold of the target airport in the future time interval from 5:30 pm to 6:00 pm on the same day is 90, and the number of incoming aircraft of the target airport in the future time interval predicted intelligently is 102, the runway increase request needs to be sent.

[0166] On the contrary, when the number of incoming aircraft of the target airport in the future time interval predicted intelligently does not exceed the aircraft capacity threshold of the target airport in the future time interval, a runway matching signal is sent.

[0167] For example, when the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the threshold of the number of aircrafts of the target airport in the future time interval, the runway increase request is sent out, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval, the passenger flow over-limit signal is sent out. For example, when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is 5,000, and the upper limit of the number of passenger flows of the target airport in 30 minutes is 3,000, the passenger flow over-limit signal needs to be sent out.

[0168] Conversely, when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is less than or equal to the upper limit of the number of passenger flows of the target airport in the set interval, the passenger flow lower limit signal is sent out.

[0169] The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

[0170] For example, the number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located. For example, when the number of permanent residents in the city where the target airport is located is 0.5 million, the number of training operations of the deep neural network is 3,000, when the number of permanent residents in the city where the target airport is located is 1 million, the number of training operations of the deep neural network is 4,000, when the number of permanent residents in the city where the target airport is located is 2 million, the number of training operations of the deep neural network is 5,000, when the number of permanent residents in the city where the target airport is located is 3 million, the number of training operations of the deep neural network is 6,000, and so on.

[0171] In each training operation performed on the deep neural network, the known number of incoming aircrafts and the number of passenger flows of the target airport in a certain historical time interval are taken as the output content of the deep neural network, and the total number of runways of the target airport, the set interval, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the certain historical time interval of the target airport are taken as the input content of the deep neural network, to complete the training operation.

[0172] The number of historical time intervals before the future time interval of the target airport is proportional to the total number of terminals of the target airport.

[0173] For example, the number of each historical time interval before the future time interval of the target airport is proportional to the total number of terminals of the target airport, including: when the total number of terminals of the target airport is 3, the number of each historical time interval before the future time interval of the target airport is 8; when the total number of terminals of the target airport is 5, the number of each historical time interval before the future time interval of the target airport is 16; when the total number of terminals of the target airport is 7, the number of each historical time interval before the future time interval of the target airport is 24; and the like.

[0174] Wherein, the product of the number of runways of the target airport pre-planned for the future time interval and the upper limit of the number of aircrafts accommodated by a single runway in the set interval length is taken as the aircraft accommodation threshold of the target airport in the future time interval.

[0175] Specifically, when the sum of the number of aircrafts approaching and the number of aircrafts departing accommodated by a single runway of the target airport within 30 minutes is 15, and the number of working runways of the target airport configured in advance for the future time interval from 5:30 pm to 6:00 pm of the current day is 6, the aircraft accommodation threshold of the target airport in the future time interval from 5:30 pm to 6:00 pm of the current day is 90.

[0176] Wherein, each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport is analyzed, and the historical operation and maintenance data corresponding to each time interval includes the number of working runways, the number of approaching aircrafts and the number of passenger flows of the target airport in the time interval, including: the number of passenger flows of the target airport in the time interval is the sum of the number of approaching passengers and the number of departing passengers of the target airport in the time interval.

[0177] Wherein, the future time interval takes the current time as the start time, the nearest historical time interval before the future time interval takes the current time as the end time, each historical time interval before the future time interval and the future time interval form a complete time segment on the time axis and the duration of each time interval is equal, all equal to the set interval length.

[0178] For example, the future time interval takes the current time as the start time, the nearest historical time interval before the future time interval takes the current time as the end time, each historical time interval before the future time interval and the future time interval form a complete time segment on the time axis and the duration of each time interval is equal, all equal to the set interval length, including: the set interval length can be selected as 30 minutes.

[0179] In addition, the present application can also refer to the following technical contents to further show the outstanding substantial progress of the present application:

[0180] The runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport are respectively executed by an octal number conversion device to obtain the runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport represented by an octal number.

[0181] For example, the runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport are respectively executed by an octal number conversion device to obtain the runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport represented by an octal number, which includes that the octal number conversion device is implemented by a CPLD chip designed by VHDL language.

[0182] The runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport are respectively executed by an octal number conversion device to obtain the runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport represented by an octal number, which includes that the octal number conversion device is implemented by a CPLD chip designed by VHDL language.

[0183] For example, the runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport are respectively executed by an octal number conversion device to obtain the runway total number of the target airport, the set interval duration, each item of airport configuration information of the target airport, and each part of historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport represented by an octal number, which includes that the octal number conversion device is implemented by a CPLD chip designed by VHDL language.

[0184] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, and are not intended to limit the present disclosure; although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present disclosure, and they should be covered in the scope of the claims and the specification of the present disclosure.

Claims

1. An airport operation support capacity evaluation analysis method, characterized in that, The method comprises: collecting average runway length, average runway width, number of permanent residents in the city, number of permanent residents in the nearest city, total number of terminals, and average capacity of terminals of the target airport as various airport configuration information of the target airport; analyzing various historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport, and the historical operation and maintenance data corresponding to each time interval being the number of working runways, the number of incoming aircraft, and the number of passenger flows of the target airport in the time interval; performing multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations and as an airport operation and maintenance analysis model; using the airport operation and maintenance analysis model to intelligently predict the number of incoming aircraft and the number of passenger flows of the target airport in the future time interval according to the total number of runways of the target airport, the set interval duration, the various airport configuration information of the target airport, and the various historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport; when the intelligently predicted number of incoming aircraft of the target airport in the future time interval exceeds the aircraft capacity threshold of the target airport in the future time interval, issuing a runway increase request, and when the intelligently predicted number of passenger flows of the target airport in the future time interval is greater than the upper limit of the number of passenger flows of the target airport in the set interval duration, issuing a passenger flow over-limit signal; wherein the number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

2. The airport operation and maintenance capacity evaluation and analysis method of claim 1, wherein: in each training operation performed on the deep neural network, the known number of incoming aircraft and the number of passenger flows of the target airport in a certain historical time interval are taken as the output content of the deep neural network, and the total number of runways of the target airport, the set interval duration, the various airport configuration information of the target airport, and the various historical operation and maintenance data corresponding to each historical time interval before the certain historical time interval of the target airport are taken as the input content of the deep neural network, to complete the training operation; wherein the number of historical time intervals before the future time interval of the target airport is proportional to the total number of terminals of the target airport; wherein the product of the number of runways of the target airport planned for the future time interval and the upper limit of the number of aircraft that a single runway can accommodate in the set interval duration is taken as the aircraft capacity threshold of the target airport in the future time interval.

3. The airport operation and maintenance capacity evaluation and analysis method of claim 2, wherein: analyzing various historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport, and the historical operation and maintenance data corresponding to each time interval being the number of working runways, the number of incoming aircraft, and the number of passenger flows of the target airport in the time interval, including: the number of passenger flows of the target airport in the time interval being the sum of the number of incoming passengers and the number of outgoing passengers of the target airport in the time interval; The future time interval has a starting time point of the current time, the nearest historical time interval before the future time interval has an ending time point of the current time, each historical time interval before the future time interval and the future time interval form a complete time segment on a time axis, and the duration of each time interval is equal, which is equal to the set interval duration.

4. The method for evaluating and analyzing airport operation support capability according to claim 3, wherein, When the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval duration, a passenger flow overrun signal is sent, the method further comprises: When the passenger flow overrun signal is received, the number of temporary terminal buildings to be added to the target airport in the future time interval is determined according to the absolute value of the difference between the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction and the upper limit of the number of passenger flows of the target airport in the set interval duration; The number of temporary terminal buildings to be added to the target airport in the future time interval is positively correlated with the absolute value of the difference between the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction and the upper limit of the number of passenger flows of the target airport in the set interval duration.

5. The method for evaluating and analyzing airport operation support capability according to claim 3, wherein, When the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction exceeds the aircraft capacity threshold of the target airport in the future time interval, a runway increase request is sent, and when the number of passenger flows of the target airport in the future time interval predicted by the intelligent prediction is greater than the upper limit of the number of passenger flows of the target airport in the set interval duration, a passenger flow overrun signal is sent, the method further comprises: When the runway increase request is received, the number of runways to be added to the target airport in the future time interval is determined according to the absolute value of the difference between the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval; The number of runways to be added to the target airport in the future time interval is positively correlated with the absolute value of the difference between the number of incoming aircrafts of the target airport in the future time interval predicted by the intelligent prediction and the aircraft capacity threshold of the target airport in the future time interval.

6. The method for evaluating and analyzing airport operation support capability according to claim 3, wherein, After performing multiple training operations on the deep neural network to obtain a deep neural network after completing the multiple training operations and as an airport operation and maintenance analysis model, the method further comprises: Model storage of the airport operation and maintenance analysis model is completed by storing each model parameter of the airport operation and maintenance analysis model.

7. The airport operation guarantee capacity evaluation and analysis method according to any one of claims 3-6, characterized in that: The average runway length, the average runway width, the number of permanent residents in the city, the number of permanent residents in the nearest city, the total number of terminal buildings, and the average capacity of the terminal buildings of the target airport are collected as the airport configuration information of the target airport, and the average value of the upper limit of the number of passengers accommodated by each terminal building of the target airport is obtained as the average capacity of the terminal buildings of the target airport. The average runway length, the average runway width, the number of permanent residents in the city where the target airport is located, the number of permanent residents in the nearest city, the total number of terminals, and the average capacity of the terminals of the target airport are collected as the airport configuration information of the target airport, and the average runway length is obtained by averaging the runway lengths of the runways of the target airport. The average runway length, the average runway width, the number of permanent residents in the city where the target airport is located, the number of permanent residents in the nearest city, the total number of terminals, and the average capacity of the terminals of the target airport are collected as the airport configuration information of the target airport, and the average runway width is obtained by averaging the runway widths of the runways of the target airport.

8. The airport operation guarantee capacity evaluation and analysis method according to any one of claims 3-6, characterized in that: The airport operation analysis model is used to intelligently predict the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport according to the total number of runways of the target airport, the set interval time length, the airport configuration information of the target airport, and the historical operation data corresponding to each historical time interval before the future time interval of the target airport, and the total number of runways of the target airport, the set interval time length, the airport configuration information of the target airport, and the historical operation data corresponding to each historical time interval before the future time interval of the target airport are respectively subjected to octal number conversion processing and then input in parallel to the airport operation analysis model. The airport operation analysis model is used to intelligently predict the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport according to the total number of runways of the target airport, the set interval time length, the airport configuration information of the target airport, and the historical operation data corresponding to each historical time interval before the future time interval of the target airport, and the airport operation analysis model is run to obtain the number of incoming aircraft and the number of passenger flows in the future time interval of the target airport output by the airport operation analysis model in octal number representation. The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located, and the number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located. In the numerical conversion function, the number of permanent residents in the city where the target airport is located is used as the input content of the numerical conversion function. In the numerical conversion function, the number of training operations of the deep neural network corresponding to the number of permanent residents in the city where the target airport is located is used as the output content of the numerical conversion function. The runway increase request is sent when the number of incoming aircrafts of the target airport in the future time interval exceeds a threshold of the number of aircrafts that the target airport can accommodate in the future time interval, and the passenger flow overrun signal is sent when the number of passenger flows of the target airport in the future time interval exceeds an upper limit of the number of passenger flows of the target airport in a set interval. The runway increase request is sent when the number of incoming aircrafts of the target airport in the future time interval exceeds a threshold of the number of aircrafts that the target airport can accommodate in the future time interval, and the passenger flow overrun signal is sent when the number of passenger flows of the target airport in the future time interval exceeds an upper limit of the number of passenger flows of the target airport in a set interval.

9. An airport operation support capability evaluation and analysis system, characterized by, The system comprises a memory and a plurality of processors, the memory storing a computer program configured to be executed by the plurality of processors to complete the following steps: The average runway length, the average runway width, the number of permanent residents in the city where the target airport is located, the number of permanent residents in the nearest city, the total number of terminal buildings, and the average capacity of the terminal buildings of the target airport are collected as the airport configuration information of the target airport; The historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport are analyzed, and the historical operation and maintenance data corresponding to each time interval are the number of working runways, the number of incoming aircrafts, and the number of passenger flows of the target airport in the time interval; The deep neural network is trained multiple times to obtain the deep neural network after the multiple training operations and as the airport operation and maintenance analysis model; The airport operation and maintenance analysis model is used to intelligently predict the number of incoming aircrafts and the number of passenger flows of the target airport in the future time interval according to the total number of runways of the target airport, the set interval, the airport configuration information of the target airport, and the historical operation and maintenance data corresponding to each historical time interval before the future time interval of the target airport; The runway increase request is sent when the number of incoming aircrafts of the target airport in the future time interval exceeds a threshold of the number of aircrafts that the target airport can accommodate in the future time interval, and the passenger flow overrun signal is sent when the number of passenger flows of the target airport in the future time interval exceeds an upper limit of the number of passenger flows of the target airport in a set interval. The number of training operations of the deep neural network is positively correlated with the number of permanent residents in the city where the target airport is located.

10. An airport operation support capability evaluation and analysis system, characterized by, The system comprises: An airport collection mechanism is configured to collect average runway length, average runway width, resident population of a city where the target airport is located, resident population of a nearest city, total number of terminals, and average capacity of the terminals of the target airport as airport configuration information of the target airport; A history analysis mechanism is configured to analyze historical operation and maintenance data of the target airport corresponding to each historical time interval before the future time interval, and the historical operation and maintenance data corresponding to each time interval is the number of active runways, the number of incoming aircraft, and the number of passenger flows of the target airport in the time interval; A model establishing mechanism is configured to perform multiple training operations on the deep neural network to obtain the deep neural network after the multiple training operations and use the deep neural network as an airport operation and maintenance analysis model; A data prediction mechanism is connected with the airport collection mechanism, the history analysis mechanism, and the model establishing mechanism, and is configured to use the airport operation and maintenance analysis model to intelligently predict the number of incoming aircraft and the number of passenger flows of the target airport in the future time interval according to the total number of runways of the target airport, the set interval length, the airport configuration information of the target airport, and the historical operation and maintenance data of the target airport corresponding to each historical time interval before the future time interval; An ability evaluation mechanism is connected with the data prediction mechanism, and is configured to send a runway increase request when the intelligently predicted number of incoming aircraft of the target airport in the future time interval exceeds the capacity threshold of the target airport in the future time interval, and send a passenger flow over-limit signal when the intelligently predicted number of passenger flows of the target airport in the future time interval is greater than the upper limit of the number of passenger flows of the target airport in the set interval length. The number of training operations of the deep neural network is positively correlated with the resident population of the city where the target airport is located.

Images