Hub airport aircraft operation collision risk quantification and evaluation method

Abstract

The invention discloses a hub airport aircraft operation collision risk quantification and evaluation method comprising the following steps: obtaining airport flight operation information in a certain time, carrying out integrated analysis on data, obtaining an airport apron operation network diagram, and establishing an airport operation Petri network for the airport apron operation network; predicting the probability that the aircraft arrives at different positions for the aircraft which is sliding on the airport scene, and converting the probability into the probability of different places in the Petri network; calculating collision risks of different aircrafts in different areas by using the arrival probabilities of the places corresponding to the different aircrafts; and an XGBoost algorithm is utilized to classify the collision risk, so that evaluation on the airport operation collision risk is generated. According to the method, the problems that in the traditional airport apron sliding process, aircraft collision risk quantification is not accurate, collision area definition is not accurate, and risk classification evaluation is not accurate are solved; the collision risk can be accurately quantified when the airport undertakes most flight operation tasks, the risk area is highlighted, and a reference is provided for daily management of the airport apron.

Description

Technical Field

[0001] The present invention belongs to the field of civil aviation airport operation safety, and specifically relates to a method for quantifying and evaluating collision risks of aircraft operations at hub airports. Background Art

[0002] The airport apron is the core area of ​​airport operations and transportation, where aircraft take off, land, taxi and other operations. With the increasing demand in the civil aviation market, the number of flights undertaken by airports every day has also gradually increased. Hub airports bear greater flight pressure than feeder airports. In the case of large-scale flight transportation, there will be multiple aircraft taxiing on the airport apron at the same time, and the risk of collision between multiple aircraft will increase significantly. Since the collision risk is an abstract indicator, there will be a large deviation in the degree of danger of the collision risk judged by the apron controller alone. At the same time, controllers with different work experience also have different criteria for judging the collision risk of aircraft. Therefore, it is particularly important to accurately quantify the collision risk between different aircraft and classify and evaluate the different levels of collision risk, which can also provide relevant references for airport operation management.

[0003] At present, there are two main methods for quantifying aircraft collision risks. One method is to establish a collision risk index system, which mainly includes: safety influencing factor ranking, hierarchical analysis method, etc.; the other is to conduct physical motion modeling for aircraft in operation, which mainly includes: lateral and longitudinal collision models of aircraft in the air, and car-following collision models. The former can classify and evaluate the collision risk indicators, but lacks the corresponding accurate quantification process. Although the latter can quantify the collision risk from a physical perspective, its model lacks consideration of the possible collision area and lacks research on the classification and evaluation of collision risks. It is obviously not suitable for the current hub airport's requirements for quantitative evaluation of aircraft collision risks. Summary of the invention

[0004] Purpose of the invention: The present invention proposes a method for quantifying and evaluating the collision risk of aircraft operations at hub airports to solve the problems of inaccurate quantification of aircraft collision risks during traditional apron taxiing, inaccurate definition of collision areas, and inaccurate risk classification evaluation.

[0005] Technical solution: A method for quantifying and evaluating the collision risk of aircraft operations at a hub airport according to the present invention comprises the following steps:

[0006] (1) Obtain airport flight operation information within a certain period of time, integrate and analyze the data, and select flight operation information during peak hours on peak days;

[0007] (2) Obtain the airport apron operation network diagram and establish an airport operation Petri net for the airport apron operation network;

[0008] (3) Predict the probability of an aircraft taxiing on the airport surface arriving at different locations and convert it into the probability of different locations in the Petri net;

[0009] (4) Calculate the collision risk of different aircraft in different areas using the arrival probabilities of different aircraft at corresponding locations;

[0010] (5) The XGBoost algorithm is used to classify collision risks, thereby generating an evaluation of airport operation collision risks.

[0011] Furthermore, the airport flight operation information in step (1) includes flight operation take-off and landing times, flight entry and exit types, corresponding parking positions and aircraft taxiing speeds.

[0012] Furthermore, the airport apron operation network diagram in step (2) includes the specific location distribution of the airport taxiways, the operation status of the airport taxiway areas, and the length of the airport taxiway areas.

[0013] Furthermore, the implementation process of establishing the airport operation Petri net for the airport apron operation network in step (2) is as follows:

[0014] The surface activity area is discretely divided into multiple taxiway sub-areas as the library p i The length of the area is sufficient to allow only one aircraft to operate in it. The operating state of the surface flight corresponds to the state mark m, and the transition t i For flights from taxiway sub-area p i Enter the next taxiway sub-area p i+1 Events; establish a Petri net of the following form:

[0015] N={P,T,Pre,Post,m,K}

[0016] Among them, the library set P represents the sub-area where the aircraft operates, the transition set T represents the boundary between the aircraft operating sub-area and the next one; Pre and Post represent the forward and backward association matrices of P and T; m is the surface state identifier; and the mapping K controls the aircraft that cannot enter the activity area.

[0017] Furthermore, the implementation process of step (3) is as follows:

[0018] According to the operation status of the aircraft, the potential motion space of the taxiing aircraft at different times is calculated. The taxiing motion of the aircraft from the starting point to the end point is regarded as Brownian motion to calculate the probability of the aircraft arriving at different locations. To ensure that the aircraft arrives on time, the reachable range of the aircraft is calculated:

[0019]

[0020] Among them, L x (t) is the lower bound of the aircraft’s operating position at time t, U x (t) is the upper limit of the aircraft’s operating position at time t, t i is the time when the aircraft starts to taxi from the starting point, t j D is the estimated time when the aircraft arrives at the end of taxiing. ij is the distance from the aircraft's origin to its destination, is the average operating speed of the aircraft, V m is the maximum taxiing speed of the aircraft;

[0021] By calculating the upper and lower bounds of the aircraft's position at different times, we can get the probability that the aircraft may reach different positions in the taxi route. The calculation formula is:

[0022]

[0023] Among them, h(x) is the modified probability density function, f(x) is the standard unbounded Brownian motion probability density function, F(x) is the cumulative distribution function, σ′ 2 is the corrected variance; hence the probability of an aircraft within the interval arriving at any location;

[0024] Assume that a library place p k The designated length is m meters, and the probability of the aircraft arriving at the depot at the current moment is obtained by summing the corresponding arrival probabilities at different positions in the depot:

[0025]

[0026] Among them, h(x h ) is the library place p k Medium h The probability of aircraft arrival at position.

[0027] Furthermore, step (4) is implemented by the following formula:

[0028]

[0029] Where n represents the number of aircraft on the scene whose arrival probability at place k is not zero.

[0030] Furthermore, the implementation process of classifying collision risks using the XGBoost algorithm in step (5) is as follows:

[0031]

[0032] Among them, (x j ,y j ) is the observed value; l is the loss function; is the estimated value calculated at the k-1th iteration; Ω(f k (x)) is the penalty term, which penalizes the complexity of the tree; The results of each tree are summed up; different regions are taken as x vectors, regional collision risk values ​​are taken as corresponding values, and comprehensive classification levels are taken as y vectors, and the XGBoost algorithm is used for training and classification.

[0033] Furthermore, the collision risk in step (5) is divided into six levels; if the risk value is 0, the risk level is 0, and no alarm is required; if the risk value is 0-0.01, the risk level is 1, and a mild alarm is issued; if the risk value is 0.01-0.1, the risk level is 2, and a moderate alarm is issued; if the risk value is 0.1-0.3, the risk level is 3, and a high alarm is issued; if the risk value is 0.3-0.5, the risk level is 4, and a serious alarm is issued; if the risk value is above 0.5, the risk level is 5, and an emergency alarm is issued.

[0034] Beneficial effects: Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention calculates the potential motion space of the aircraft on the taxiing path, models the aircraft activity as Brownian motion under constraints, calculates the arrival probability of the aircraft at different positions at different times, maps it to the established apron Petri net to calculate the collision risks in different areas, and uses the XGBoost algorithm to classify and evaluate the collision risks to obtain the final evaluation results; solves the problems of inaccurate quantification of aircraft collision risks during traditional apron taxiing, inaccurate definition of collision areas, and inaccurate risk classification and evaluation; is beneficial for airports to accurately quantify collision risks when undertaking most flight operation tasks, highlight risk areas, and provide a reference for daily apron management. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0036] Figure 2 It is a schematic diagram of collision risk quantification of an instance;

[0037] Figure 3 It is a simplified schematic diagram of the Petri net collision risk classification evaluation of the instance. DETAILED DESCRIPTION

[0038] The present invention is further described in detail below with reference to the accompanying drawings.

[0039] The present invention provides a method for quantitatively evaluating the collision risk of aircraft operations at hub airports, including establishing an apron operation Petri net, calculating the collision risk of different locations of taxiing aircraft on the apron at different times, and using the XGBoost algorithm to classify and evaluate the collision risk. The present invention is suitable for hub airports to accurately quantify and classify the collision risk generated by operating aircraft, and can highlight the possible collision risk areas, which has good practicality and provides a reference for daily apron management. Figure 1 As shown, the specific steps include:

[0040] Step 1: Obtain airport-related flight information, which mainly includes flight take-off and landing times, flight entry and exit types, and corresponding parking positions and other detailed operation information to provide a basis for subsequent simulation.

[0041] Through field surveys and online inquiries, we obtain information about passenger flights operating at the airport within a week, including flight take-off and landing times, flight entry and exit types, corresponding parking positions, aircraft taxiing speeds and other aircraft surface operation information. We integrate and analyze the flight data obtained, and select flight operation information during peak hours on peak days as simulation data support.

[0042] Step 2: Obtain relevant information such as the airport taxiway distribution, and establish the corresponding apron operation Petri net based on its distribution.

[0043] The detailed information obtained mainly includes the specific location distribution of the airport taxiways, the operation status of the airport taxiway area (whether there are any abnormal situations such as maintenance), and the length of the airport taxiway area.

[0044] The airport operation Petri net is established for the airport apron operation network. The principle is to divide the surface activity area into multiple taxiway sub-areas as the library p i The length of the area is sufficient to allow only one aircraft to operate in it. The operating state of the surface flight corresponds to the state mark m, and the transition t i For flights from taxiway sub-area p i Enter the next taxiway sub-area p i+1 Events. Thus, the following Petri net is established:

[0045] N={P,T,Pre,Post,m,K}

[0046] Among them, the library set P represents the sub-area where the aircraft operates; the transition set T represents the boundary between the aircraft operating sub-area and the next one; Pre and Post represent the forward (backward) association matrix of P and T; m is the surface state identifier; and the mapping K controls the aircraft that cannot enter the activity area.

[0047] Step 3: Establish an aircraft trajectory prediction model for the aircraft currently in operation on the scene, so as to obtain the probability of the aircraft arriving at different locations at different times, and calculate the probabilities of different locations in the Petri net.

[0048] During the taxiing process of an aircraft, it is restricted by many factors such as time, speed, and position. It cannot taxi smoothly at a stable speed, which causes a deviation between its actual position and the expected position (the expected position is the position to be reached at each moment when running at the average speed). However, in order to ensure that it arrives on time, the aircraft will always ensure that this deviation is within a range. This deviation range is called the aircraft's reachable range.

[0049] First, we need to calculate the potential motion space of the taxiing aircraft. In a uniform motion state, the position space that an object can reach at any time is represented by a circle. The radius of the circle is the product of its maximum running speed and the corresponding time. Therefore, under the condition that the starting and ending points are determined, there are two corresponding reachable areas, one is the reachable area at the starting point, and the other is the reachable area at the end point. The two areas will change with time, and the intersection of the areas determines the calculation of the upper and lower bounds of the aircraft at that time:

[0050]

[0051] Among them, t i is the time when the aircraft starts to taxi from the starting point, t j D is the estimated time when the aircraft arrives at the end of taxiing. ij is the distance from the aircraft's origin to its destination, is the average operating speed (expected speed) of the aircraft, V m is the maximum taxiing speed of the aircraft. x (t) is the upper limit of the aircraft's operating position at time t, L x (t) is the lower bound of the aircraft's operating position at time t. Therefore, the aircraft's motion during taxiing can be regarded as a bounded Brownian motion. The standard Brownian motion formula without boundaries is:

[0052]

[0053] Among them, x i and x j are the coordinates of the relative positions of the starting and ending points, respectively. When the upper and lower bounds are taken into account, the probability distribution of the aircraft position within the upper and lower bounds still satisfies the corresponding formula, but the probability distribution of the position outside the bounds is uniformly regarded as 0. In the Petri network, the path of the aircraft and the library it passes through are calculated. By calculating the upper and lower bounds of the aircraft position at different times, the probability that the aircraft may reach different positions in the taxi route can be obtained. The calculation formula is:

[0054]

[0055]

[0056] Among them, h(x) is the modified probability density function, f(x) is the standard unbounded Brownian motion probability density function, F(x) is the cumulative distribution function, σ′ 2 is the corrected variance. From this, we can get the probability of an aircraft within the interval arriving at any location.

[0057] In the Petri net, suppose a place (p i ) is defined as k meters, and the arrival probabilities corresponding to different positions in the depot are summed (accumulated by meter) as the probability of the aircraft arriving at the depot at the current moment:

[0058]

[0059] Among them, h(x h ) is the library place p k Medium h The probability of aircraft arrival at position.

[0060] Step 4: Calculate the collision risk of the corresponding warehouse based on the probability of the aircraft arriving at the warehouse at different times.

[0061] Arrange the arrival probability of each aircraft at different locations in different time periods in order vertically and horizontally in time order to obtain the arrival probability matrix of different aircraft. Assume that there are aircraft, and all aircraft corresponding to the location p k The arrival probability (non-zero) is multiplied to obtain the collision risk of the place at the current moment:

[0062]

[0063] Where n represents the number of aircraft whose arrival probability at place k is not 0. Based on the above formula, the collision risk of different places in the Petri net at different times can be calculated, as follows: Figure 2 shown.

[0064] Afterwards, the risk can be classified according to the numerical value of the collision risk, and the risk can be divided into 6 levels: if the risk value is 0, the risk level is 0, and no alarm is required; if the risk value is 0-0.01, the risk level is 1, and a mild alarm is issued; if the risk value is 0.01-0.1, the risk level is 2, and a moderate alarm is issued; if the risk value is 0.1-0.3, the risk level is 3, and a high alarm is issued; if the risk value is 0.3-0.5, the risk level is 4, and a serious alarm is issued; if the risk value is above 0.5, the risk level is 5, and an emergency alarm is issued.

[0065] Step 5: Classify and evaluate the collision risks in different areas, and use the XGBoost algorithm to verify the classification.

[0066] The XGBoost algorithm is based on the accumulation of multiple decision trees. In each iterative training, the decision tree is obtained by minimizing an objective function:

[0067]

[0068] Among them, (x j ,y j ) is the observed value; l is the loss function; is the estimated value calculated at the k-1th iteration; Ω(f k (x)) is the penalty term, which penalizes the complexity of the tree; The results of each tree are summed up to obtain the regional collision risk and the corresponding classification level at different times. Different regions are taken as x vectors, regional collision risk values ​​are taken as corresponding values, and comprehensive classification levels are taken as y vectors. The XGBoost algorithm is used for training and classification, and the classification accuracy is taken as the accuracy of the classification method.

[0069] After classifying and evaluating the collision risks of different areas, the color mapping method can be used to grade and map the levels of different areas to highlight the differences in risk levels between apron areas, such as Figure 3 This processing effect enables better visualization and makes risk areas more prominent.

[0070] The above disclosure is only the preferred embodiment of the present invention, which cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for quantifying and evaluating collision risk of aircraft operations at hub airports, characterized in that: The following steps are involved: (1) Obtain airport flight operation information within a certain period of time, integrate and analyze the data, and select flight operation information during peak hours on peak days; (2) Obtain the airport apron operation network diagram and establish an airport operation Petri net for the airport apron operation network; (3) Predict the probability of an aircraft taxiing on the airport surface arriving at different locations and convert it into the probability of different locations in the Petri net; (4) Calculate the collision risk of different aircraft in different areas using the arrival probabilities of different aircraft at corresponding depots; (5) The XGBoost algorithm is used to classify collision risks, thereby generating an evaluation of airport operation collision risks.

2. A hub airport aircraft operation collision risk quantification and evaluation method according to claim 1, characterized in that: The airport flight operation information in step (1) includes flight operation take-off and landing times, flight entry and exit types, corresponding parking positions and aircraft taxiing speeds.

3. The method for quantifying and evaluating the collision risk of aircraft operations at a hub airport according to claim 1, characterized in that: The airport apron operation network diagram in step (2) includes the specific location distribution of the airport taxiways, the operation status of the airport taxiway area, and the length of the airport taxiway area.

4. A hub airport aircraft operation collision risk quantification and evaluation method according to claim 1, characterized in that: The implementation process of establishing the airport operation Petri net for the airport apron operation network in step (2) is as follows: The surface activity area is discretely divided into multiple taxiway sub-areas as the library p i The length of the area is sufficient to allow only one aircraft to operate in it. The operating state of the surface flight corresponds to the state mark m, and the transition t i For flights from taxiway sub-area p i Enter the next taxiway sub-area p i+1 Events; establish a Petri net of the following form: N={P,T,Pre,Post,m,K} Among them, the library set P represents the sub-area where the aircraft operates, the transition set T represents the boundary between the aircraft operating sub-area and the next one; Pre and Post represent the forward and backward association matrices of P and T; m is the surface state identifier; and the mapping K controls the aircraft that cannot enter the activity area.

5. The method for quantifying and evaluating collision risk of aircraft operations at a hub airport according to claim 1, characterized in that: The implementation process of step (3) is as follows: According to the operation status of the aircraft, the potential motion space of the taxiing aircraft at different times is calculated. The taxiing motion of the aircraft from the starting point to the end point is regarded as Brownian motion to calculate the probability of the aircraft arriving at different locations. To ensure that the aircraft arrives on time, the reachable range of the aircraft is calculated: Among them, L x (t) is the lower bound of the aircraft’s operating position at time t, U x (t) is the upper limit of the aircraft’s operating position at time t, t i is the time when the aircraft starts to taxi from the starting point, t j D is the estimated time when the aircraft arrives at the end of taxiing. ij is the distance from the aircraft's origin to its destination, is the average operating speed of the aircraft, V m is the maximum taxiing speed of the aircraft; By calculating the upper and lower bounds of the aircraft's position at different times, we can get the probability that the aircraft may reach different positions in the taxi route. The calculation formula is: Among them, h(x) is the modified probability density function, f(x) is the standard unbounded Brownian motion probability density function, F(x) is the cumulative distribution function, σ′ 2 is the corrected variance; hence the probability of an aircraft within the interval arriving at any location; Assume that a library place p k The designated length is m meters, and the probability of the aircraft arriving at the depot at the current moment is obtained by summing the corresponding arrival probabilities at different positions in the depot: Among them, h(x h ) is the library place p k Medium h The probability of aircraft arrival at position.

6. A hub airport aircraft operation collision risk quantification and evaluation method according to claim 1, characterized in that: The step (4) is implemented by the following formula: Where n represents the number of aircraft on the scene whose arrival probability at place k is not zero.

7. A hub airport aircraft operation collision risk quantification and evaluation method according to claim 1, characterized in that: The implementation process of classifying collision risks using the XGBoost algorithm in step (5) is as follows: Among them, (x j ,y j ) is the observed value; l is the loss function; is the estimated value calculated at the k-1th iteration; Ω(f k (x)) is the penalty term, which penalizes the complexity of the tree; The results of each tree are summed up; different regions are taken as x vectors, regional collision risk values ​​are taken as corresponding values, and comprehensive classification levels are taken as y vectors, and the XGBoost algorithm is used for training and classification.

8. The method for quantifying and evaluating collision risk of aircraft operations at a hub airport according to claim 1, characterized in that: The collision risk in step (5) is divided into six levels; If the risk value is 0, the risk level is 0, and no alarm is required; if the risk value is 0-0.01, the risk level is 1, and a slight alarm is issued; If the risk value is 0.01-0.1, the risk level is 2, which means a moderate warning. If the risk value is 0.1-0.3, the risk level is 3, which means a high warning. If the risk value is 0.3-0.5, the risk level is 4, which means a serious warning. If the risk value is above 0.5, the risk level is 5, which means an emergency warning.

Images