Multi-agent collaborative airport scene intelligent scheduling system and method

Abstract

The invention discloses a multi-subject collaborative airport scene intelligent scheduling system and method, and relates to the technical field of scene intelligent scheduling, and the method comprises the following steps: carrying out the comparative analysis of the arrival and departure time and the preset time, calculating the delay time of a flight, and calculating the extra fuel consumption according to the delay time of the flight and the fuel consumption; the method comprises the following steps: acquiring a total entering and leaving taxiing distance and taxiing time of an aircraft, calculating a taxiing speed, and constructing a taxiing consumption model according to the taxiing speed and the taxiing time to obtain taxiing consumption data; the fuel consumption condition of the aircraft is judged based on fuzzy reasoning, and the fuel consumption of the aircraft is reduced by shortening the taxiing distance and reducing the delay time; the passenger walking distance and the aircraft fuel consumption are optimized based on an NSGA-II algorithm, and an optimization scheme is selected according to actual requirements. The problems of resource waste and scheduling conflicts are solved, so that the overall operation efficiency of an airport is improved, flight delay is reduced, and resource utilization is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scene dispatching, and more specifically, to a multi-agent collaborative intelligent airport scene dispatching system and method. Background Art

[0002] With the continuous growth of global air transport demand, the passenger flow and the number of flights at airports are increasing, and the management of airport surface (i.e. the airport ground and surrounding areas) is facing more complex scheduling tasks.

[0003] Deficiencies of existing technologies:

[0004] Traditional airport scene dispatch methods mostly rely on manual dispatch or make decisions based on a single system. This method is inefficient when dealing with complex dynamic scenes and is easily affected by human factors, resulting in resource waste and dispatch conflicts, which may eventually cause flight delays or airport operation bottlenecks. Therefore, there is an urgent need for a multi-agent collaborative airport scene intelligent dispatch system to improve the operation efficiency of the airport and reduce human intervention.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a multi-agent collaborative airport scene intelligent dispatching system and method, which solves the problems raised in the above-mentioned background technology by optimizing the multi-agent collaborative airport scene intelligent dispatching system.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The multi-agent collaborative airport scene intelligent dispatching system includes an acquisition module, a construction module, a reasoning module, and an optimization module, and there are connections between the modules: the acquisition module is used to obtain the aircraft's approach and departure time, flight distance, and fuel consumption during the flight, and compare and analyze the approach and departure time with the scheduled time, calculate the flight delay time, and calculate the additional fuel consumption based on the flight delay time and fuel consumption; the construction module is used to obtain the aircraft's approach and departure total taxiing distance and taxiing time, and calculate the taxiing speed, and build a taxiing consumption model based on the taxiing speed and taxiing time to obtain taxiing consumption data; the reasoning module is used to judge the aircraft's fuel consumption based on fuzzy reasoning according to the additional fuel consumption and taxiing consumption data, and reduce the aircraft's fuel consumption by shortening the taxiing distance and reducing the delay time;

[0009] The optimization module is used to obtain the passenger walking distance based on the Dijkstra algorithm, optimize the passenger walking distance and aircraft fuel consumption based on the NSGA-II algorithm, output the Pareto solution set, and select the optimization plan according to actual needs.

[0010] In a preferred embodiment, the specific calculation process of the flight delay time is as follows: the actual departure time and the scheduled departure time of the aircraft are obtained, and the actual departure time is subtracted from the scheduled departure time to obtain the take-off delay time; the actual arrival time and the scheduled arrival time of the aircraft are obtained, and the actual arrival time is subtracted from the scheduled arrival time to obtain the arrival delay time; the take-off delay time and the arrival delay time are added to obtain the flight delay time.

[0011] In a preferred embodiment, the specific process of obtaining the flight delay time is as follows: the flight time is obtained according to the aircraft's arrival and departure time, that is, the actual arrival time is subtracted from the actual departure time to obtain the flight time; the aircraft's detour distance is obtained according to the flight distance and the predetermined flight distance, and the flight speed is calculated according to the flight distance and the flight time; the unit trip fuel consumption rate is calculated according to the fuel consumption during the flight and the flight distance; the additional fuel consumption is calculated according to the flight delay time, the flight time and the unit trip fuel consumption rate.

[0012] In a preferred embodiment, the specific process of obtaining the taxiing consumption data is as follows: obtaining the aircraft's approach and departure taxiing distance and taxiing time, adding the approach and departure taxiing distance and taxiing time to obtain the total taxiing distance and taxiing time; dividing the aircraft's total taxiing distance by the taxiing time to calculate the aircraft's taxiing speed; constructing a taxiing consumption model based on the taxiing speed and taxiing time to obtain the taxiing consumption data.

[0013] In a preferred embodiment, the specific steps of judging the aircraft fuel consumption based on the additional fuel consumption and taxiing consumption data based on fuzzy reasoning are as follows: defining the additional fuel consumption and taxiing consumption data as input variables, and dividing them into different fuzzy sets respectively; defining the aircraft fuel consumption situation as an output variable, and dividing it into fuzzy sets; formulating fuzzy rules to describe the influence of the additional fuel consumption and taxiing consumption data on the aircraft fuel consumption situation; and performing fuzzy reasoning according to the fuzzy rules to determine the aircraft fuel consumption situation.

[0014] In a preferred embodiment, the specific process of obtaining the passenger walking distance based on the Dijkstra algorithm is as follows: a directed graph G = (V, E) is used to represent the passenger walking network in the airport; in the graph, V is a set of nodes, each node represents an intersection, E is a set of edges, each edge represents a passenger road connection between two nodes, and the weight of the edge represents the passenger's walking distance on the road; d(u, v) is the distance from node u to node v, and the goal of path planning is to find a shortest path from the starting node s to the target node t so that the sum of d(u, v) is minimized.

[0015] In a preferred embodiment, the steps of optimizing the passenger walking distance and aircraft fuel consumption based on the NSGA-II algorithm are as follows: randomly generate an initial solution set, each solution represents a scheduling scheme; including a passenger walking path, an aircraft taxiing path, and an aircraft path; for each solution, calculate the corresponding passenger walking distance and aircraft fuel consumption; perform non-dominated sorting on the solution set according to the target value, divide the solution set into different levels, and calculate the congestion degree for the solutions in each level to ensure the diversity of the solution set; use selection, crossover, and mutation operations to generate a new population, select the optimal solution to continue to evolve to the next generation; continuously optimize the solution set and tend to the Pareto frontier; after the maximum number of iterations is set, the algorithm terminates and outputs the Pareto frontier solution set; after several generations of evolution, the NSGA-II algorithm will output a set of Pareto optimal solutions, which represent the optimal trade-off between passenger walking distance and aircraft fuel consumption under given target constraints; each solution has different passenger walking distances and fuel consumption, and the most suitable solution is selected according to actual needs.

[0016] The multi-agent collaborative airport scene intelligent scheduling method includes the following steps: obtaining the aircraft's arrival and departure time, flight distance, and fuel consumption during the flight, comparing and analyzing the arrival and departure time with the scheduled time, calculating the flight delay time, and calculating the additional fuel consumption based on the flight delay time and fuel consumption; obtaining the aircraft's total arrival and departure taxiing distance and taxiing time, calculating the taxiing speed, building a taxiing consumption model based on the taxiing speed and taxiing time, and obtaining taxiing consumption data; judging the aircraft's fuel consumption based on fuzzy reasoning based on the additional fuel consumption and taxiing consumption data, and reducing the aircraft's fuel consumption by shortening the taxiing distance and reducing the delay time; obtaining the passenger's walking distance based on the Dijkstra algorithm, optimizing the passenger's walking distance and the aircraft's fuel consumption based on the NSGA-II algorithm, and outputting the Pareto solution set, and selecting the optimization plan according to actual needs.

[0017] The technical effects and advantages of the multi-agent coordinated airport scene intelligent dispatching system and method of the present invention are as follows:

[0018] 1. The present invention reduces waiting time and unnecessary idle operations through intelligent collaborative scheduling, ensures efficient use of resources, and automatically calculates the optimal resource allocation plan through real-time data and intelligent algorithm analysis, avoids delays or errors in manual decision-making, and improves the efficiency of scheduling decisions. The system adjusts and optimizes the allocation of airport resources in real time according to multi-dimensional data such as flights, equipment, personnel and weather, so that resources can be flexibly scheduled between different entities to avoid bottlenecks and waste of resources; according to real-time changes in the airport scene, such as flight delays, equipment failures, weather changes, etc., the system can dynamically adjust the scheduling plan and respond to emergencies in a timely manner. It automatically completes scheduling decisions, task allocation and instruction issuance through intelligent algorithms, reduces manual intervention, and reduces efficiency losses and safety risks caused by human operational errors. The system can monitor the status of all entities in real time, automatically issue warnings when potential problems are found, and take corresponding measures to avoid scheduling conflicts or safety accidents caused by human misjudgment.

[0019] 2. Through real-time data sharing and intelligent decision-making, the system of the present invention can ensure the dispatching distance and time safety between different entities, avoid collisions or conflicts between aircraft, vehicles, personnel, etc. If the system detects an abnormality (such as equipment failure, flight delays, weather changes, etc.), it can give a warning in time and take corresponding emergency measures to ensure the safe operation of the airport scene; through intelligent scheduling and precise resource allocation, the system can avoid congestion at the airport scene, improve the smoothness of boarding, transfer, baggage collection and other links, and enhance the overall experience of passengers; through real-time analysis of passenger data and flight information, the system can provide passengers with personalized services, such as timely flight change notifications, boarding gate guidance, etc., optimize ground equipment, flight scheduling, vehicles The system can collect and analyze a large amount of airport operation data, including flight information, ground equipment status, personnel arrangements, etc., and make predictions, optimizations and decision-making support based on these data. Through historical data analysis and machine learning, the system can continuously optimize scheduling strategies and improve the efficiency and safety of future airport operations. The airport scene is a dynamic, complex and changeable environment. The intelligent scheduling system can flexibly adapt to complex scene changes, including dense flights, weather changes, emergencies, etc., to ensure the efficient operation of the airport. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the structure of the airport scene intelligent dispatching system with multi-agent collaboration of the present invention.

[0021] Figure 2 It is a structural schematic diagram of the multi-agent collaborative airport scene intelligent scheduling method of the present invention. DETAILED DESCRIPTION

[0022] 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.

[0023] Embodiment 1, Figure 1 The invention provides a multi-agent coordinated airport scene intelligent dispatching system.

[0024] S10, obtaining the aircraft's arrival and departure time, flight distance, and fuel consumption during the flight, performing comparative analysis based on the arrival and departure time and the scheduled time, calculating the flight delay time, and calculating the additional fuel consumption based on the flight delay time and fuel consumption;

[0025] Obtaining the arrival and departure times of aircraft, fuel consumption during flight, calculating flight delay time and analyzing additional fuel consumption is a very important part of aviation operations, especially in flight scheduling, flight delay management and fuel cost control.

[0026] Obtain the actual departure time and scheduled departure time of the aircraft, and subtract the actual departure time from the scheduled departure time to obtain the takeoff delay time;

[0027] Obtain the actual arrival time and scheduled arrival time of the aircraft, and subtract the actual arrival time from the scheduled arrival time to obtain the arrival delay time;

[0028] The flight delay time is calculated by adding the departure delay time and the arrival delay time. The specific calculation formula is as follows: y =(t s1 -t d1 )+(t s2 -t d2 );where t y is the flight delay time, t s1 is the actual departure time, t d1 is the scheduled departure time, t s2 is the actual arrival time, t d2 is the scheduled arrival time;

[0029] The flight time is obtained based on the aircraft's arrival and departure times, that is, the actual arrival time is subtracted from the actual departure time to obtain the flight time;

[0030] Obtain the aircraft's detour distance according to the flight distance and the scheduled flight distance, and calculate the flight speed according to the flight distance and flight time;

[0031] Calculate the fuel consumption rate per unit distance based on the fuel consumption during the flight and the flight distance;

[0032] The additional fuel consumption is calculated based on the flight delay time, flight time and fuel consumption per unit distance. The specific calculation formula is as follows: Where W is the extra fuel consumption, Q is the fuel consumption during the flight, d is the flight distance, Δd is the detour distance, and t y is the flight delay time, t s2 is the actual arrival time, t s1 is the actual departure time, is the fuel consumption per unit distance traveled, It is the flight speed.

[0033] S20, obtaining the total taxiing distance and taxiing time of the aircraft during arrival and departure, and calculating the taxiing speed, building a taxiing consumption model according to the taxiing speed and taxiing time, and obtaining taxiing consumption data;

[0034] Obtain the taxiing distance and taxiing time of the aircraft, add the taxiing distance and taxiing time of the aircraft to get the total taxiing distance and taxiing time, divide the total taxiing distance of the aircraft by the taxiing time to calculate the taxiing speed of the aircraft, build a taxiing consumption model based on the taxiing speed and taxiing time, and obtain the taxiing consumption data. The specific formula is as follows: F = a*t h +b*V h 2 ; In the formula, F is the taxiing consumption data, t h is the glide time, a is the glide time weight factor, V h is the glide speed, and b is the glide speed weighting factor.

[0035] S30, judging the fuel consumption of the aircraft based on fuzzy reasoning according to the additional fuel consumption and taxiing consumption data, and reducing the fuel consumption of the aircraft by shortening the taxiing distance and reducing the delay time;

[0036] The specific steps of judging the aircraft fuel consumption based on fuzzy reasoning according to the additional fuel consumption and taxiing consumption data are as follows:

[0037] In step C1, the extra fuel consumption and taxiing consumption data are defined as input variables, and they are divided into different fuzzy sets.

[0038] For example, "Low", "Medium", "High" for additional fuel consumption, "Low", "Medium", "High" for taxiing consumption data.

[0039] In step C2, the aircraft fuel consumption is defined as the output variable and divided into fuzzy sets, for example, "Low", "High", for the aircraft fuel consumption.

[0040] Step C3, formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0041] The additional fuel consumption is marked as L, the taxiing consumption data is marked as , and the aircraft fuel consumption is marked as P, then it can be defined

[0042] Rule 1: If (W is High) and (F is High) then (P is High)

[0043] Rule 2: If (W is Low) and (F is Low) then (P is Low) ...

[0045] Step C4, performing fuzzy reasoning according to fuzzy rules to determine the fuel consumption of the aircraft.

[0046] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although the present embodiment takes three fuzzy sets as examples, in fact, the additional fuel consumption, taxiing consumption data, and aircraft fuel consumption can be divided into more than three sets to facilitate better and more accurate identification.

[0047] Furthermore, for the judgment of the extra fuel consumption and the coasting consumption data, a threshold value can be set according to the actual situation; when the extra fuel consumption is higher than 100L / km, it is marked as "High", and when the coasting consumption data is higher than 100L / km, it is marked as "High", and so on. I will not go into details here.

[0048] If P is High, the aircraft consumes more fuel, so the aircraft fuel consumption can be reduced by shortening the taxi distance and reducing the delay time.

[0049] S40, obtains the passenger walking distance based on the Dijkstra algorithm, optimizes the passenger walking distance and aircraft fuel consumption based on the NSGA-II algorithm, and outputs the Pareto frontier solution set, and selects the optimization scheme according to actual needs.

[0050] □The passenger walking network in the airport can be represented by a directed graph. Each node in the graph represents an intersection, and each edge represents the passenger walking road connection between two nodes. The weight of the edge can represent the distance a passenger needs to walk on the road.

[0051] □G=(V,E) is the passenger walking network diagram in the airport, where V is a set of nodes representing intersections, E is an edge set representing pedestrian road connections, d(u,v) is the distance from node u to node v, and the goal of path planning is to find the shortest path from the starting node s to the target node t so that the walking distance is minimized.

[0052] □First, initialize the population, and then perform a fast non-dominated sort on the individuals in the population. The individuals in the first layer are completely independent and are not dominated by any individual in the population. The individuals in the second layer are only dominated by the individuals in the first layer, and so on. Each layer is a completely non-dominated solution starting from this layer. After the non-dominated sort is completed, the next step is to sort the individuals in each layer with respect to crowding, which is used to describe the distance between an individual and its neighboring individuals. Next, the selection operation is performed based on the results of the non-dominated sort and crowding sort previously performed. At the same time, crossover and mutation operations are performed on the individuals in the population to generate a new population. This completes an iteration. Next, just repeat the iterative process until the convergence condition is met.

[0053] □It is important to note here that the solution set generated by each iteration of the NSGA-II algorithm is only a non-dominated solution set, not an optimal solution.

[0054] □The steps to optimize passenger walking distance and aircraft fuel consumption based on NSGA-II algorithm are as follows:

[0055] □ Initialize the population: Randomly generate a certain number of initial solution sets, each of which represents a scheduling scheme. Each solution includes information such as passenger walking paths and aircraft taxiing paths.

[0056] □ Target evaluation: For each individual (solution), calculate the corresponding passenger walking distance and aircraft fuel consumption.

[0057] □ Non-dominated sorting: Perform non-dominated sorting on the solution set according to the target value and divide the solution set into different levels. For the solutions in each level, calculate the congestion degree to ensure the diversity of the solution set.

[0058] □Genetic operation: Use selection, crossover, and mutation operations to generate a new population, select the best solution to continue evolving to the next generation. This process continuously optimizes the solution set and tends to the Pareto frontier.

[0059] □Termination condition: When the maximum number of iterations is reached, the algorithm terminates and the Pareto frontier solution set is output.

[0060] □After several generations of evolution, the NSGA-II algorithm will output a set of Pareto optimal solutions, which represent the optimal trade-off between passenger walking distance and aircraft fuel consumption under given target constraints. Each solution has different passenger walking distance and fuel consumption, and decision makers can choose the most suitable solution according to actual needs.

[0061] □The optimized dispatching system can reduce passengers’ walking distance, improve their travel comfort, and reduce passenger dissatisfaction and delays caused by long walking distances.

[0062] □ Reduced fuel consumption: By optimizing the taxiing path and standby strategy of the aircraft, fuel consumption is reduced. Especially during peak hours, reasonable taxiing paths and optimized scheduling strategies can significantly reduce the operating costs of airlines.

[0063] □ System flexibility and adaptability: The NSGA-II algorithm can adjust the scheduling plan according to dynamic factors such as different airport layouts and flight schedules. Therefore, it has strong flexibility and adaptability and can cope with complex scheduling scenarios.

[0064] □Multi-objective balance: Since the NSGA-II algorithm can optimize multiple objectives at the same time, airport managers can choose the best solution to balance passenger experience and fuel consumption according to specific needs. For example, during peak hours, more attention may be paid to passenger walking distance; while during idle hours, more attention may be paid to reducing fuel consumption. By comparing with traditional scheduling methods, the NSGA-II scheduling system based on multi-objective optimization can achieve more efficient airport field scheduling while ensuring safety, especially in large airports and complex flight networks, which can significantly improve the airport's operational efficiency.

[0065] □Example 2, Figure 2 It is a structural schematic diagram of the multi-agent collaborative airport scene intelligent scheduling method of the present invention.

[0066] The multi-agent collaborative airport scene intelligent scheduling method includes the following steps: obtaining the aircraft's arrival and departure time, flight distance, and fuel consumption during the flight, comparing and analyzing the arrival and departure time with the scheduled time, calculating the flight delay time, and calculating the additional fuel consumption based on the flight delay time and fuel consumption; obtaining the aircraft's total arrival and departure taxiing distance and taxiing time, calculating the taxiing speed, building a taxiing consumption model based on the taxiing speed and taxiing time, and obtaining taxiing consumption data; judging the aircraft's fuel consumption based on fuzzy reasoning based on the additional fuel consumption and taxiing consumption data, and reducing the aircraft's fuel consumption by shortening the taxiing distance and reducing the delay time; obtaining the passenger's walking distance based on the Dijkstra algorithm, optimizing the passenger's walking distance and the aircraft's fuel consumption based on the NSGA-II algorithm, and outputting the Pareto solution set, and selecting the optimization plan according to actual needs.

[0067] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0068] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0069] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0070] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0071] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0072] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-agent collaborative airport scene intelligent dispatching system and method, characterized in that: Including acquisition module, construction module, reasoning module, optimization module, there are connections between modules: The acquisition module is used to obtain the aircraft's arrival and departure time, flight distance, and fuel consumption during the flight, compare and analyze the arrival and departure time with the scheduled time, calculate the flight delay time, and calculate the additional fuel consumption based on the flight delay time and fuel consumption; A construction module is used to obtain the total taxiing distance and taxiing time of the aircraft entering and leaving the airport, calculate the taxiing speed, build a taxiing consumption model according to the taxiing speed and taxiing time, and obtain taxiing consumption data; A reasoning module, used to judge the aircraft fuel consumption based on fuzzy reasoning according to the additional fuel consumption and taxiing consumption data, and reduce the aircraft fuel consumption by shortening the taxiing distance and reducing the delay time; The optimization module is used to obtain the passenger walking distance based on the Dijkstra algorithm, optimize the passenger walking distance and aircraft fuel consumption based on the NSGA-II algorithm, output the Pareto solution set, and select the optimization plan according to actual needs.

2. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 1 is characterized in that: The specific calculation process of the flight delay time is as follows: Obtain the actual departure time and scheduled departure time of the aircraft, and subtract the actual departure time from the scheduled departure time to obtain the takeoff delay time; Obtain the actual arrival time and scheduled arrival time of the aircraft, and subtract the actual arrival time from the scheduled arrival time to obtain the arrival delay time; The flight delay time is calculated by adding the departure delay time and the arrival delay time. The specific calculation formula is as follows: y =(t s1 -t d1 )+(t s2 -t d2 );where t y is the flight delay time, t s1 is the actual departure time, t d1 is the scheduled departure time, t s2 is the actual arrival time, t d2 is the scheduled arrival time.

3. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 2 is characterized in that: The specific process of obtaining the flight delay time is as follows: The flight time is obtained based on the aircraft's arrival and departure times, that is, the actual arrival time is subtracted from the actual departure time to obtain the flight time; Obtain the aircraft's detour distance according to the flight distance and the scheduled flight distance, and calculate the flight speed according to the flight distance and flight time; Calculate the fuel consumption rate per unit distance based on the fuel consumption during the flight and the flight distance; The additional fuel consumption is calculated based on the flight delay time, flight time and fuel consumption per unit distance.

4. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 3 is characterized in that: The specific process of obtaining the taxiing consumption data is as follows: Get the taxiing distance and taxiing time of the aircraft, and add the taxiing distance and taxiing time of the aircraft to get the total taxiing distance and taxiing time; The aircraft's taxiing speed is calculated by dividing the aircraft's total taxiing distance by the taxiing time; A taxiing consumption model is constructed according to the taxiing speed and taxiing time to obtain taxiing consumption data.

5. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 4 is characterized in that: The specific steps of judging the aircraft fuel consumption based on fuzzy reasoning according to the additional fuel consumption and taxiing consumption data are as follows: The extra fuel consumption and taxiing consumption data are defined as input variables and divided into different fuzzy sets respectively; The aircraft fuel consumption is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of additional fuel consumption and taxiing consumption data on aircraft fuel consumption; Fuzzy reasoning is performed based on fuzzy rules to determine the aircraft fuel consumption.

6. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 5 is characterized in that: The specific process of obtaining the passenger walking distance based on the Dijkstra algorithm is as follows: The passenger walking network in the airport is represented by a directed graph G = (V, E); in the graph, V is a set of nodes, each node represents an intersection, E is a set of edges, each edge represents a passenger road connection between two nodes, and the weight of the edge represents the walking distance of the passenger on the road; d(u, v) is the distance from node u to node v, and the goal of path planning is to find a shortest path from the starting node s to the target node t so that the sum of d(u, v) is minimized.

7. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 6 is characterized in that: The steps of optimizing the passenger walking distance and aircraft fuel consumption based on the NSGA-II algorithm are as follows: Randomly generate an initial solution set, each solution represents a scheduling scheme; including passenger walking paths, aircraft taxi paths, and aircraft paths; For each solution, calculate the corresponding passenger walking distance and aircraft fuel consumption; According to the target value, the solution set is non-dominated and sorted, and the solution set is divided into different levels. For the solutions in each level, the congestion degree is calculated to ensure the diversity of the solution set. Use selection, crossover, and mutation operations to generate new populations, select the best solution to continue evolving to the next generation; continuously optimize the solution set and move toward the Pareto frontier; After the maximum number of iterations is reached, the algorithm terminates and outputs the Pareto frontier solution set; After several generations of evolution, the NSGA-II algorithm will output a set of Pareto optimal solutions, which represent the optimal trade-off between passenger walking distance and aircraft fuel consumption under given objective constraints; Each solution has different passenger walking distance and fuel consumption. Choose the most suitable solution according to actual needs.

8. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 7 is characterized in that: The specific calculation formula for the additional fuel consumption is as follows: ;W is the additional fuel consumption, Q is the fuel consumption during the flight, d is the flight distance, Δd is the detour distance, t y is the flight delay time, t s2 is the actual arrival time, t s1 is the actual departure time, is the fuel consumption per unit distance traveled, It is the flight speed.

9. The multi-agent coordinated airport scene intelligent dispatching system and method according to claim 7 is characterized in that: The specific calculation formula of the sliding consumption data is as follows: F = a*t h +b*V h 2 ; In the formula, F is the taxiing consumption data, t h is the glide time, a is the glide time weight factor, V h is the glide speed, and b is the glide speed weighting factor.

10. The multi-agent coordinated airport scene intelligent dispatching method is characterized by: The following steps are involved: Obtain the aircraft's arrival and departure times, flight distance, and fuel consumption during the flight, compare and analyze the arrival and departure times with the scheduled times, calculate the flight delay time, and calculate the additional fuel consumption based on the flight delay time and fuel consumption; Obtain the total taxiing distance and taxiing time of the aircraft's arrival and departure, calculate the taxiing speed, build a taxiing consumption model based on the taxiing speed and taxiing time, and obtain taxiing consumption data; According to the extra fuel consumption and taxiing consumption data, the aircraft fuel consumption is judged based on fuzzy reasoning, and the aircraft fuel consumption is reduced by shortening the taxiing distance and reducing the delay time; The passenger walking distance is obtained based on the Dijkstra algorithm, and the passenger walking distance and aircraft fuel consumption are optimized based on the NSGA-II algorithm. The Pareto solution set is output and the optimization scheme is selected according to actual needs.

Images