A method for dividing aircraft taxiing situation

Abstract

The present invention provides a method for classifying aircraft surface taxiing situations, the method comprising: constructing an aircraft surface taxiing situation index system; determining a measurement standard for aircraft surface taxiing situations; based on the measurement standard for aircraft surface taxiing situations, performing data grouping on various indicators in the aircraft surface taxiing situation index system; based on the data grouping, converting various indicators into numerical variables, and establishing a logistic regression model, and calculating an aircraft surface taxiing situation score based on the logistic regression model. The present invention establishes a unified aircraft surface taxiing situation index system, and determines a measurement standard for aircraft surface taxiing situations, and calculates an aircraft surface taxiing situation score based on various indicators in the aircraft surface taxiing situation index system, so as to provide real-time decision support for controllers to issue taxiing instructions.

Description

Technical Field

[0001] The invention belongs to the technical field of civil aviation operation characteristic analysis, and in particular relates to a method for dividing aircraft taxiing situation on a surface. Background Art

[0002] Airports are important carriers for the development of the civil aviation industry. In the process of the development of the civil aviation industry, airport congestion is the main operational bottleneck. At present, many large domestic airports have built Airport Collaborative Decision Making (A-CDM) systems. The system provides certain operational decision support for aircraft surface operations through accurate prediction and comprehensive sharing of data from various stakeholders in the airport operation process. In the actual operation of the airport, it is crucial to accurately grasp the taxiing time nodes of the aircraft surface. This requires airport control personnel to accurately identify the taxiing situation of the current airport surface within a limited time range, so as to determine the push-out taxiing time of the aircraft.

[0003] There are few studies on the classification of airport surface operation situation at home and abroad. At present, most of the research on surface taxiing situation remains at the theoretical level. The establishment of a relevant airport surface operation situation identification index system, based on the airport surface operation space-time network, airport operation and aircraft attributes, deeply cultivates the characteristic indicators that affect the aircraft surface operation, and uses data mining methods to extract highly important indicators. The number of taxiing aircraft on the surface, the cumulative number of aircraft arriving, the cumulative number of aircraft departing, and the number of aircraft queuing at the runway head are used as important indicators of surface operation situation perception. Fruitful research results have been achieved in aircraft taxiing time prediction and push-out time control. However, there is no unified system for the classification of aircraft surface taxiing situation, and the situation recognition model has high requirements for data quality. The relevant operation situation index system does not rely on the existing airport on-site monitoring facilities, and does not consider relying on the data quality of the existing surface monitoring equipment from the application level. Consider the classification of aircraft surface taxiing situation, and provide real-time decision support for controllers to issue push-out taxiing instructions. Therefore, providing an aircraft surface taxiing situation classification method has become a problem that needs to be solved urgently. Summary of the invention

[0004] In view of the defects existing in the above-mentioned prior art, the present invention provides an aircraft surface taxiing situation classification method based on an aircraft surface taxiing situation index system.

[0005] The technical solution proposed by the present invention is as follows:

[0006] In a first aspect, the present invention discloses a method for dividing the taxiing situation of an aircraft, comprising the following steps:

[0007] Construct an aircraft taxiing situation indicator system;

[0008] Determine the criteria for determining aircraft surface taxiing posture;

[0009] Based on the measurement standard of the aircraft surface taxiing situation, data grouping is performed on various indicators in the aircraft surface taxiing situation index system;

[0010] Based on the data grouping, each indicator is converted into a numerical variable, and a logistic regression model is established. Based on the logistic regression model, the aircraft surface taxiing situation score is calculated.

[0011] Furthermore, the aircraft taxiing situation index system at least includes: time index, space index, operation index, and aircraft attribute index.

[0012] Further, including:

[0013] The time index at least includes: the current month and the current hour;

[0014] The spatial indicators include at least: whether a runway crossing is carried out, the runway number used by the aircraft, and the number of path conflict hotspots;

[0015] The operation indicators include at least: instantaneous departure flow, instantaneous arrival flow, cumulative departure flow, cumulative arrival flow, and the number of aircraft queuing for departure;

[0016] The aircraft attribute index includes at least: aircraft type.

[0017] Furthermore, the measurement standard of the aircraft surface taxiing situation is the surface delay time of the departing aircraft.

[0018] Furthermore, an aircraft with a surface delay time of ≥8 minutes for the departing aircraft is a delayed aircraft, and an aircraft with a surface delay time of <8 minutes for the departing aircraft is a non-delayed aircraft.

[0019] Furthermore, based on the data grouping, each indicator is converted into a numerical variable and calculated according to the following formula:

[0020] woe i =goodrate i / badrate i

[0021] Among them, goodrate i = Number of non-delayed aircraft in group i / number of delayed aircraft in each group, indicating a positive indicator; badrate i = Number of delayed aircraft in the i-th group / Number of non-delayed aircraft in each group, which represents the reverse indicator.

[0022] Furthermore, the chi-square binning supervised discretization method is used to group the data of various indicators in the aircraft taxiing situation index system.

[0023] Furthermore, before constructing the aircraft taxiing situation index system, the following steps are also included:

[0024] Determine whether the numerical variables of various indicators in the aircraft surface taxiing situation indicator system meet the preset conditions.

[0025] In a second aspect, the present invention discloses a device for dividing aircraft taxiing situations, comprising the following units:

[0026] A construction unit is used to construct an aircraft taxiing situation indicator system;

[0027] A storage unit for storing the measurement standard of the aircraft surface taxiing situation;

[0028] A processing unit, configured to group data of various indicators in the aircraft surface taxiing situation index system based on the aircraft surface taxiing situation measurement standard;

[0029] The scoring unit is used to convert various indicators into numerical variables based on the data grouping, establish a logistic regression model, and calculate the aircraft surface taxiing situation score based on the logistic regression model.

[0030] In a third aspect, the present invention discloses a computer-readable storage medium for storing computer-executable instructions. When the computer-executable instructions are executed, any possible method for dividing the aircraft surface taxiing situation described in the first aspect is implemented.

[0031] The prior art generally does not form a unified system for the classification of aircraft surface taxiing situations, and the situation recognition model has high requirements for data quality. The relevant operation situation index system does not rely on the existing airport on-site monitoring facilities, and does not consider relying on the data quality of the existing surface monitoring equipment from the application level to consider the classification of aircraft surface taxiing situations. The aircraft surface taxiing situation classification method proposed in the present invention establishes a unified aircraft surface taxiing situation index system, and determines the measurement standard of aircraft surface taxiing situation. Based on the measurement standard of aircraft surface taxiing situation, data grouping is performed on various indicators in the aircraft surface taxiing situation index system, thereby improving the accuracy of aircraft surface taxiing situation scoring. Based on the data grouping, various indicators are converted into numerical variables, and a logistic regression model is established. Based on the logistic regression model, the aircraft surface taxiing situation score is calculated, thereby providing real-time decision support for controllers to issue taxiing instructions.

[0032] Furthermore, the surface delay time of departing aircraft is used as the measurement standard for aircraft surface taxiing status. Since the airport surface operation efficiency is directly related to the delay level, the surface delay time of departing aircraft is used as the standard for measuring the entire airport surface operation status, making the entire aircraft surface taxiing status indicator system both objective and accurate.

[0033] Further, it is determined whether the numerical variables of the various indicators in the aircraft surface taxiing situation index system meet the preset conditions. If the numerical variables of the indicators do not meet the preset conditions, the indicators are deleted from the aircraft surface taxiing situation index system to ensure the objectivity and accuracy of the aircraft surface taxiing situation index system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the technical solutions. Obviously, the schematic embodiments of the present invention and their descriptions are only used to explain the present invention and do not constitute improper limitations on the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without creative work. In the drawings:

[0035] Figure 1 is a schematic flow chart of the method of Example 1 of the present invention;

[0036] Figure 2 is a schematic diagram of the aircraft surface taxiing situation indicator system structure in the method of embodiment 1 of the present invention;

[0037] Figure 3 Schematic diagram of the distribution results of the training set and the test set of the method of Example 2 of the present invention;

[0038] Figure 4 It is a schematic diagram of the structure of the device of Example 3 of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Example 1

[0041] Reference Figure 1 This embodiment provides a method for dividing the taxiing situation of an aircraft, and the method comprises the following steps:

[0042] S1: Construct an aircraft taxiing situation indicator system;

[0043] Specifically, based on the existing aircraft surface operation related indicators, from the airport surface operation space-time network level, combined with the practical needs of the present invention, an aircraft surface taxiing situation indicator system is improved and proposed.

[0044] Furthermore, the existing aircraft taxiing related indicators are centered around the aircraft surface operation situation. Based on extensive reading of relevant literature, based on the airport surface operation space-time network, airport operation and aircraft attributes, Figure 2 The 11 indicators shown are used as indicators in the aircraft taxiing situation indicator system, where the time indicators include: the current month and the current hour; the space indicators include: whether to cross the runway, the runway number used by the aircraft, and the number of conflict hotspots; the operation indicators include: instantaneous departure flow, instantaneous arrival flow, cumulative departure flow, cumulative arrival flow, and the number of aircraft queuing for departure; the aircraft attribute indicators include: aircraft type; the aircraft taxiing situation indicator system constructed in this embodiment is as follows: Figure 2 shown.

[0045] S2: The aircraft surface operation efficiency is classified into two categories, and the index segmentation results are optimized by combining professional knowledge in the civil aviation field with the chi-square binning supervised discrete method;

[0046] Specifically, combined with the relevant statistical standards of the Civil Aviation Administration, the aircraft surface delay time is used as the standard to measure the entire airport surface operation situation, and the aircraft surface delay time is divided into two categories. Based on the binary classification results, the professional knowledge in the civil aviation field and the chi-square binning method are combined to discretize each continuous indicator and determine the optimal grouping of each indicator.

[0047] S2.1: In combination with the relevant statistical standards of the Civil Aviation Administration of China, namely the "Civil Aviation Flight Normal Statistics Method", since the airport surface operation efficiency is directly related to the delay level, the surface delay time of departing aircraft is used as the standard to measure the entire airport surface operation situation, and the aircraft surface delay time is divided into two categories. Considering that the average delay of departing aircraft is less than 4 minutes or less, the airport is in the category of efficient operation; the average delay of departing aircraft is 6 minutes, the airport is at an acceptable delay level; the average delay of departing aircraft reaches 9 minutes, and the airport is operating at full capacity. In combination with the relevant regulations of the Civil Aviation Administration of China and the relevant standards of the International Civil Aviation Organization, aircraft with a surface delay time of 8 minutes or more are considered delayed aircraft, and aircraft with a surface delay time of less than 8 minutes are considered non-delayed aircraft.

[0048] S2.2: Based on the real aircraft operation data, the discrete attributes of the aircraft taxiing situation related indicators established in step S1 are sorted in ascending order from small to large, and the chi-square value of each pair of adjacent intervals is calculated. The pair of intervals with the smallest chi-square value are merged to obtain the optimal data segmentation.

[0049] S3: Perform evidence weight conversion according to the data segmentation results, that is, based on the segmented data, convert each segment of data into a new numerical variable, build a bridge between the aircraft surface taxiing situation segmentation index established in S1 and the judgment of whether it is a delayed aircraft; then establish a logistic regression model, calculate the aircraft surface taxiing situation score, and divide the aircraft surface taxiing situation.

[0050] S3.1: For a specific indicator, calculate the weight of evidence woe corresponding to data segment i i , the calculation formula is as follows:

[0051] woe i =goodrate i / badrate i (1)

[0052] Among them, goodrate i = Number of non-delayed aircraft in group i / number of delayed aircraft in each group, which is a positive indicator; badrate i = Number of delayed aircraft in group i / Number of non-delayed aircraft in each group, which is a negative indicator. The larger the positive indicator, the higher the woe i The smaller the value, the larger the reverse indicator. i The larger the value. The greater the negative slope of the positive indicator, the greater the positive slope of the reverse indicator, which means that the indicator has good discrimination ability. i If the value is close to a straight line, it means that the indicator's judgment ability is weak. i Positive correlation trend, reverse indicator is the same as woe i If a negative correlation trend appears, it means that this indicator does not meet economic significance and should be removed.

[0053] S3.2: According to the above calculation method, based on the optimal segmentation results, randomly select 70% of the aircraft data as the training set and 30% of the data as the test set, and convert the training set and the test set into woe values. Perform Logisic regression on the training set and make a scorecard.

[0054] S4: Use the airport’s real historical operation data to verify the model solution results.

[0055] Example 2

[0056] This embodiment uses the aircraft taxiing data of Shenzhen Airport in 2019, and selects relevant indicators that affect the aircraft operation status based on existing research, such as aircraft type, take-off / arrival runway, time period, take-off queue length, number of aircraft taxiing at the same time, etc. For the aircraft flow statistics method of taxiing on the ground, this method adopts a method of calculating the flow based on the macro network topology map, which is divided into instantaneous departure flow, cumulative departure flow, instantaneous arrival flow and cumulative arrival flow. Combined with the analysis and extraction of specific influencing factors, all aircraft such as Figure 2 It should be noted that this embodiment is based on the method described in the first embodiment.

[0057] Furthermore, in this embodiment, 0 is taken as the basic score, PDO is the branch for doubling the ratio, and PDO is set to 50, that is, the good-bad ratio doubles for every 50 points increase in the total score of the score card.

[0058] Furthermore, the distribution results of the training set and the test set in this embodiment are as follows: Figure 3 shown.

[0059] Furthermore, the 11 index scoring criteria obtained by solving this embodiment are shown in Table 1:

[0060] Table 1 Indicator scoring criteria

[0061]

[0062]

[0063] Furthermore, according to the calculated total score, the aircraft taxiing situation is divided into 15 levels. The specific results are shown in Table 2:

[0064] Table 2 Classification standards for aircraft taxiing situations

[0065]

[0066]

[0067] like Figure 3 As shown in Figure 2, the proportion of delayed aircraft in each taxiing situation in the training set and the test set is almost the same, which proves that the model has good performance in aircraft taxiing situation classification; Figure 3It can be seen that the higher the taxiing situation score, the smaller the proportion of aircraft taxiing delays, and the lower the taxiing situation score, the greater the proportion of aircraft taxiing delays. The characteristic scoring criteria are shown in Table 1. The cumulative departure flow, the cumulative arrival flow, and the number of aircraft queuing for departure are the main factors affecting the aircraft taxiing situation. The more the cumulative departure flow, the cumulative arrival flow, and the number of aircraft queuing for departure, the lower the score, and the greater the proportion of aircraft taxiing delays; conversely, the higher the score, the smaller the proportion of aircraft taxiing delays.

[0068] Example 3

[0069] The present invention also provides an aircraft taxiing situation division device, referring to Figure 4 , the device comprises the following units:

[0070] A construction unit 101 is used to construct an aircraft taxiing situation index system;

[0071] A storage unit 102, used to store a measure of the aircraft surface taxiing situation;

[0072] The processing unit 103 is used to group the indicators in the aircraft surface taxiing situation index system based on the aircraft surface taxiing situation measurement standard;

[0073] The scoring unit 104 is used to convert various indicators into numerical variables based on the data grouping, establish a logistic regression model, and calculate the aircraft surface taxiing situation score based on the logistic regression model.

[0074] In addition, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium may store a program, and when the program is executed, the program includes part or all of the steps of any aircraft surface taxiing situation division method recorded in the above method embodiment.

[0075] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0076] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0077] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0078] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation methods of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the present application should be included in the scope of protection of the present application.

Claims

1. A method for dividing the taxiing situation of an aircraft, characterized in that: The method comprises the following steps: Construct an aircraft taxiing situation indicator system; Determine the criteria for determining aircraft surface taxiing posture; Based on the measurement standard of the aircraft surface taxiing situation, data grouping is performed on various indicators in the aircraft surface taxiing situation index system; Based on the data grouping, each indicator is converted into a numerical variable, and a logistic regression model is established, and based on the logistic regression model, an aircraft surface taxiing situation score is calculated; The aircraft taxiing situation index system at least includes: time index, space index, operation index, and aircraft attribute index; The time index at least includes: the current month and the current hour; The spatial indicators include at least: whether a runway crossing is carried out, the runway number used by the aircraft, and the number of path conflict hotspots; The operation indicators include at least: instantaneous departure flow, instantaneous arrival flow, cumulative departure flow, cumulative arrival flow, and the number of aircraft queuing for departure; The aircraft attribute index includes at least: aircraft type; The measurement standard of the aircraft surface taxiing situation is the surface delay time of the departing aircraft; The chi-square binning supervised discrete method is used to group the data of various indicators in the aircraft taxiing situation index system; Relying on the real aircraft operation data, the discrete attributes of the established aircraft taxiing situation related indicators are sorted in ascending order from small to large, the chi-square value of each pair of adjacent intervals is calculated, and the pair of intervals with the smallest chi-square value are merged to obtain the optimal data segmentation.

2. The method for dividing the aircraft taxiing situation according to claim 1, characterized in that: An aircraft with a surface delay time of ≥8 minutes is a delayed aircraft, and an aircraft with a surface delay time of <8 minutes is a non-delayed aircraft.

3. The method for dividing the aircraft taxiing situation according to claim 2, characterized in that: Based on the data grouping, each indicator is converted into a numerical variable and calculated according to the following formula: oh my i =goodrate i / badrate i Among them, goodrate i = Number of non-delayed aircraft in group i / number of delayed aircraft in each group, indicating a positive indicator; badrate i = Number of delayed aircraft in the i-th group / Number of non-delayed aircraft in each group, which represents the reverse indicator.

4. The method for dividing the aircraft taxiing situation according to claim 3, characterized in that: Before constructing the aircraft taxiing situation index system, the following steps are also included: Determine whether the numerical variables of various indicators in the aircraft surface taxiing situation indicator system meet the preset conditions.

5. An aircraft taxiing situation division device implemented by the method according to any one of claims 1 to 4, characterized in that: include: A construction unit is used to construct an aircraft taxiing situation indicator system; A storage unit for storing the measurement standard of the aircraft surface taxiing situation; A processing unit, configured to group data of various indicators in the aircraft surface taxiing situation index system based on the aircraft surface taxiing situation measurement standard; The scoring unit is used to convert various indicators into numerical variables based on the data grouping, establish a logistic regression model, and calculate the aircraft surface taxiing situation score based on the logistic regression model.

6. A computer-readable storage medium, characterized in that: The storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, the aircraft surface taxiing situation division method as described in any one of claims 1 to 4 is implemented.

Images