Airport special vehicle dispatching method and system based on multi-vehicle collaboration

By building a special vehicle collaborative scheduling model and virtual model, combining genetic algorithms and digital twin technology, the global coordination and dynamic problems in special vehicle scheduling in airports are solved, and efficient vehicle scheduling and delay reduction are achieved.

CN118863689BActive Publication Date: 2024-12-03THE SECOND RES INST OF CIVIL AVIATION ADMINISTRATION OF CHINA +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411337313.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-12-03
Estimated Expiration
2044-09-25

AI Technical Summary

Technical Problem

The prior art lacks global coordinated scheduling in special vehicle scheduling in airports, resulting in flight delays, and traditional methods ignore the dynamic nature of the ground service process and the response ability of abnormal events.

Method used

Using a multi-vehicle collaboration scheduling method, by building a special vehicle collaborative scheduling model and virtual model, combining genetic algorithms and digital twin technology, the vehicle scheduling plan is adjusted in real time to optimize the total mileage and waiting time, monitor abnormal events and respond quickly.

Benefits of technology

It realizes efficient coordinated dispatch of multiple types of vehicles at the airport, reduces the total mileage and waiting time of special vehicles, reduces the spread of delays caused by emergencies, and can dynamically adjust the scheduling plan to cope with complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118863689B_ABST
    Figure CN118863689B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of digital models for airport scheduling, and more specifically, to a method and system for scheduling special vehicles at airports based on multi-vehicle collaboration. The present invention establishes a collaborative scheduling model for multiple types of special vehicles at airports, takes the total mileage and total waiting time of vehicles as optimization targets, and simultaneously considers resource utilization. In a digital twin real-time scheduling system, the optimal solution for fleet service plans in complex environments is calculated by combining improved genetic algorithms and simulation models. With the support of digital twin technology, dynamic adjustment of plans and rescheduling under uncertain events are achieved, solving the problem of collaborative scheduling optimization of multiple types of vehicles in complex environments, reducing the total mileage and waiting time of special vehicles, and reducing the delay propagation caused by emergencies. This method can not only achieve efficient scheduling of special vehicles, but also make real-time adjustments to plans.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of airport dispatching digital models, and in particular to an airport special vehicle dispatching method and system based on multi-vehicle collaboration. Background Art

[0002] With the rapid development of the global civil aviation industry and the substantial increase in passenger demand, many international airports are facing the dual challenges of rising air traffic volume and inefficient service. In airport operations, flight ground support plays a vital role, involving aircraft guidance, baggage and cargo loading and unloading, refueling, water supply, aircraft cleaning, passenger services and many other tasks. According to statistics, in addition to weather factors, low utilization of airport ground handling fleets, poor coordination capabilities and inefficient scheduling are considered to be the main causes of flight delays. Especially for major airports in hub cities, efficient scheduling of special vehicles during peak flight periods is crucial. However, with the increase in the number of flights, traditional special vehicle scheduling strategies can no longer meet the airport's high-quality service requirements.

[0003] In the existing technology, most studies focus on optimizing the scheduling of single-type vehicles. Although some mainline support services are taken into account, there is no coordination of cabin services, energy supply and baggage loading from a global perspective. There is a lack of in-depth exploration and modeling of the flight ground support process. The delay of a single service may cause delays in other services, which in turn leads to flight delays. In addition, the above methods usually assume that the ground service process is a deterministic process, assuming that the flight schedule does not fluctuate, the service time is fixed, the vehicle travel time is the same, etc., ignoring that the ground service process is a dynamic system. At the same time, due to the lack of real-time interaction with the actual airport, it is impossible to monitor abnormal events during the airport operation process, and it is impossible to respond quickly to random interference that causes flight delays. Summary of the invention

[0004] The purpose of the present invention is to provide an airport special vehicle dispatching method and system based on multi-vehicle collaboration to solve the above-mentioned problems in the prior art.

[0005] The embodiments of the present invention are implemented by the following technical solutions:

[0006] First, the airport special vehicle dispatching method based on multi-vehicle collaboration includes:

[0007] Constructing a special vehicle collaborative dispatching model, which includes setting an objective function and several constraints, and constructing a virtual model based on the basic data and three-dimensional model of the airport and special vehicles, and the virtual model is used to collect data in real time and provide data support for the vehicle collaborative dispatching model;

[0008] Solve the objective function through genetic algorithm and obtain the optimal solution of genetic algorithm based on the fitness value;

[0009] The optimal solution is input into the special vehicle collaborative scheduling model to obtain the special vehicle scheduling plan, and the data generated by the implementation of the special vehicle according to the special vehicle scheduling plan is fed back to the virtual model;

[0010] The virtual model is updated synchronously and the special vehicle dispatch plan is adjusted according to real-time dynamic data.

[0011] Preferably, the objective of the objective function is to minimize the total mileage and waiting time of special vehicles, including:

[0012]

[0013]

[0014] In the formula, To minimize the total mileage function of special vehicles, To minimize the waiting time function of special vehicles, A collection of special vehicle types. For flight collection, For flights Is it necessary Type Special Vehicle Services, For service flights of Type Special Vehicle Whether it comes from other seats, is the distance from the parking space to the aircraft space, For service seats of Type Special Vehicle Do you need to return to the parking space? The distance from the aircraft to the parking space, To complete the current flight Next flights served , For flights Parking to flight The distance to the parking space, is the penalty coefficient for waiting service time for incoming flights, Waiting time for special vehicles for incoming flights, is the penalty coefficient for waiting service time of departing flights, Waiting time for special vehicles to depart from Hong Kong. is the flight number, It is a special vehicle type.

[0015] Preferably, the several constraints include service constraints, parking constraints, time window constraints and resource capacity constraints.

[0016] Preferably, the service constraints include:

[0017]

[0018]

[0019]

[0020]

[0021]

[0022] In the formula, in the formula, For flights quilt Type Special Vehicle Serve, for Number of special vehicles of type, Assemble for departing and arriving flights, For flights Several special vehicles are needed. is the maximum capacity, Gather for the shuttle bus, Assemble for luggage carts, Assemble for the fuel truck.

[0023] Preferably, the parking restrictions include:

[0024]

[0025]

[0026] In the formula, It is a sign for counting vehicles going to the parking space. Counting mark for the vehicle returning to the parking position. Number for special vehicles.

[0027] Preferably, the time window constraint includes:

[0028] ;

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] ;

[0034] ;

[0035] In the formula, in the formula, The shuttle bus for flights departing from remote parking positions can only start service after the catering truck, cleaning truck, fuel truck and other vehicles have completed their services. is the actual arrival time at the aircraft stand. Waiting time for special vehicles. is the average service time, is the actual arrival time of the shuttle bus at the aircraft stand. The waiting time for the inbound shuttle bus. For non-shuttle vehicle numbers, The shuttle bus vehicle number, Gather for the shuttle bus, The time when the inbound shuttle bus arrives at the aircraft stand. Waiting time for the outbound shuttle bus. For service time, The time when the cleaning vehicle arrives at the aircraft stand. Waiting time for cleaning car, Assemble for the cleaning car, The latest service completion time for vehicles other than the tractor, The time when the non-tractor vehicle arrives at the parking space. is the time when the tractor arrives at the parking position, The waiting time for the tractor. Assemble for the tractor, To allow the vehicle to arrive at the gate at the earliest possible time, To allow the vehicle to arrive at the gate at the latest time, for Type Special Vehicle The time when the service flight arrives at the gate, Waiting time for special vehicles. For flights The distance from the parking space to the parking space, is the driving speed, To fix the time, is the distance from the parking space to the aircraft space, To allow for the earliest possible start time of service, The arrival time of vehicles serving inbound flights. The flight is scheduled to arrive at the gate time. is the completion time of the preceding service, The time when the vehicle arrives at the gate to serve the departing flight.

[0036] Preferably, the resource capacity constraint includes:

[0037]

[0038]

[0039]

[0040] In the formula, For service flights of Type Special Vehicle Do you need to return to your parking space? is the current available resources of the vehicle, is the flight number, For flights Is it necessary Type Special Vehicle Services, For flights resource requirements, For service flights of Type Special Vehicle Is it from another seat? To complete the current flight Next flights served .

[0041] Preferably, solving the objective function by genetic algorithm comprises:

[0042] The flight number, service sequence and service phase are represented by a three-layer chromosome structure;

[0043] Calculate the objective function value, convert the objective value into a fitness value, sort according to the fitness value, and set the ranking threshold;

[0044] A crossover operation is performed on chromosomes ranked after the ranking threshold. Two chromosomes are selected as parent chromosomes, and the two chromosome fragments are crossed to form two new daughter chromosomes. The fitness values ​​of the daughter chromosomes are compared with those of the parent chromosomes to determine whether to retain them.

[0045] Preferably, the crossover operation further includes:

[0046] Establish local evaluation factors:

[0047]

[0048] In the formula, and Represent the paternal chromosome and the maternal chromosome, respectively. is the special vehicle driving distance of the parent chromosome, is the special vehicle travel distance of the parent chromosome, The waiting time for the special vehicle of the parent chromosome, Waiting time for special vehicles of parent chromosomes, is the local evaluation factor, is the weight, is the total travel distance of the chromosome fragment, is the total waiting time of chromosome fragments.

[0049] In a second aspect, the present invention further provides an airport special vehicle dispatching system based on multi-vehicle collaboration, comprising:

[0050] A model building module is configured to build a special vehicle collaborative scheduling model, wherein the special vehicle collaborative scheduling model includes setting an objective function and a number of constraints, and building a virtual model based on basic data and a three-dimensional model of the airport and the special vehicle, wherein the virtual model is used to collect data in real time and provide data support for the vehicle collaborative scheduling model;

[0051] The solution module is configured to solve the objective function through a genetic algorithm and obtain an optimal solution of the genetic algorithm based on the fitness value; input the optimal solution into the special vehicle collaborative scheduling model to obtain a special vehicle scheduling plan, and feed back data generated by the special vehicle in the implementation of the special vehicle scheduling plan to the virtual model;

[0052] The synchronization module is configured to synchronize the virtual model and adjust the special vehicle dispatch plan according to the real-time dynamic data;

[0053] A main control module, which is connected to the model building module, the solving module and the synchronization module, is used to execute the above-mentioned airport special vehicle scheduling method based on multi-vehicle collaboration.

[0054] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0055] The present invention establishes a collaborative scheduling model for multiple types of special vehicles at an airport, takes the total mileage and total waiting time of the vehicles as optimization targets, and considers resource utilization at the same time. In the digital twin real-time scheduling system, the optimal solution of the fleet service plan under a complex environment is calculated by combining an improved genetic algorithm with a simulation model. With the support of digital twin technology, dynamic adjustment of the plan and rescheduling under uncertain events are realized, solving the problem of collaborative scheduling optimization of multiple types of vehicles under a complex environment, reducing the total mileage and waiting time of special vehicles, and reducing the delay propagation caused by emergencies. This method can not only achieve efficient scheduling of special vehicles, but also adjust the plan in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0059] The modules or submodules described independently may be physically separated or not: they may be implemented by software or hardware, and some modules or submodules may be implemented by software, and the processor may call the software to implement the functions of these modules or submodules, and other modules or submodules may be implemented by hardware, such as by hardware circuits. In addition, some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0060] Please refer to Figure 1 The present invention provides an airport special vehicle dispatching method based on multi-vehicle collaboration, comprising:

[0061] S101: constructing a special vehicle collaborative dispatching model, wherein the special vehicle collaborative dispatching model includes setting an objective function and a number of constraints, and constructing a virtual model based on basic data and a three-dimensional model of the airport and special vehicles, wherein the virtual model is used to collect data in real time and provide data support for the vehicle collaborative dispatching model;

[0062] Specifically, with the support of digital twin technology, three-dimensional models, data models, behavioral models and simulation models are integrated to construct a virtual model of flight ground support services.

[0063] In addition, to build a virtual model of flight ground support services, a high-precision three-dimensional model can be used to establish business scenarios. By building sub-models such as data models, behavior models and simulation models, a virtual model synchronized with the actual business scenarios can be finally formed. With the support of digital twin technology, the virtual model can obtain operation data in real time, process and clean it, realize the integration of real-time data and historical data, and provide data support for the dispatch center. At the same time, the business operation status in the virtual model can be observed, the existing problems in the operation can be monitored, and the feasibility of the scheme can be verified by the simulation model to provide a reference for the dispatch center. Digital twin technology realizes real-time communication between the physical airport, the virtual airport and the dispatch center, keeps the information of the physical airport and the virtual airport updated synchronously, and the dispatch center calculates a set of feasible solutions based on the dispatch task and real-time equipment status information, verifies them in the simulation model, and then sends the optimal solution to the physical airport to perform the support task. The virtual model synchronously updates the task progress, monitors the execution deviation of the dispatch plan in real time, and provides early warning information for the dispatch center.

[0064] S102: solving the objective function by using a genetic algorithm, and obtaining the optimal solution of the genetic algorithm based on the fitness value;

[0065] S103: inputting the optimal solution into the special vehicle collaborative scheduling model to obtain a special vehicle scheduling plan, and feeding back the data generated by the special vehicle in the implementation of the special vehicle scheduling plan to the virtual model;

[0066] S104: The virtual model is synchronously updated, and the special vehicle dispatch plan is adjusted according to the real-time dynamic data.

[0067] An exemplary implementation of the present invention can be expressed as a vehicle routing problem with a time window, the goal of which is to minimize the total mileage of the vehicle and the waiting time of the vehicle.

[0068] Every flight The protection needs of flights are different. right Resource requirements for special vehicles For task allocation, the first departure position of all special vehicles is from the parking lot , and all parking locations are known, and you need to return to the parking lot when all tasks are completed. Type Special Vehicle Service flights Time to arrive at the seat The flight vehicle arrival time window must be met ,in Indicates the flight is arriving or departing. The parking space is far or near. , the distance between the aircraft positions and driving speed , the departure time of each vehicle mission can be calculated. Once completed, you can start the support service for this mission and calculate the waiting time of the vehicle at the parking space. , when the service duration meets the specified average service time After that, determine the vehicle's existing resources Is it greater than the resource requirement for the next support mission? Otherwise, return to the parking space to replenish resources to maximum capacity and rest at the prescribed time.

[0069] Therefore, the objective function is to minimize the total mileage and waiting time of special vehicles, including:

[0070]

[0071]

[0072] In the formula, To minimize the total mileage function of special vehicles, To minimize the waiting time function of special vehicles, A collection of special vehicle types. For flight collection, For flights Is it necessary Type Special Vehicle Services, For service flights of Type Special Vehicle Whether it comes from other seats, is the distance from the parking space to the aircraft space, For service seats of Type Special Vehicle Do you need to return to the parking space? The distance from the aircraft to the parking space, To complete the current flight Next flights served , For flights Parking to flight The distance to the parking space, is the penalty coefficient for waiting service time for incoming flights, Waiting time for special vehicles for incoming flights, is the penalty coefficient for waiting service time of departing flights, Waiting time for special vehicles to depart from Hong Kong. is the flight number, It is a special vehicle type.

[0073] In an exemplary embodiment of the present invention, the plurality of constraints include service constraints, parking constraints, time window constraints and resource capacity constraints.

[0074] In an exemplary embodiment of the present invention, the service constraints include:

[0075]

[0076]

[0077]

[0078]

[0079]

[0080] In the formula, For flights quilt Type Special Vehicle Serve, for Number of special vehicles of type, Assemble for departing and arriving flights, For flights Several special vehicles are needed. is the maximum capacity, Gather for the shuttle bus, Assemble for luggage carts, Assemble for the fuel truck.

[0081] Among them, constraints Ensure that the same type of service is provided by only one special vehicle at any one time to avoid service duplication. Limit the number of special vehicles served on each flight to no more than the set upper limit , to optimize resource utilization. Constraints This means that the total number of services received by all flights is equal to the total number of times special vehicles are used, ensuring that all service needs are fully covered. and It is stipulated that shuttle buses, luggage trucks and refueling trucks must return to the parking spaces to replenish resources after each mission, while other special vehicles can continue to serve until the resources are exhausted.

[0082] In an exemplary embodiment of the present invention, the parking restriction comprises:

[0083]

[0084]

[0085] In the formula, It is a sign for counting vehicles going to the parking space. Counting mark for the vehicle returning to the parking position. Number for special vehicles.

[0086] Among them, the constraints This means that each vehicle must have a clearly assigned task before departure to ensure efficient use of resources. This means that the vehicle will return to the parking space when its capacity is exhausted or all tasks are completed, and will not remain in the parking space or other places.

[0087] In an exemplary embodiment of the present invention, the time window constraint includes:

[0088] ;

[0089] ;

[0090]

[0091] ;

[0092] ;

[0093] ;

[0094] ;

[0095] ;

[0096] In the formula, The shuttle bus for flights departing from remote parking positions can only start service after the catering truck, cleaning truck, fuel truck and other vehicles have completed their services. is the actual arrival time at the aircraft stand. Waiting time for special vehicles. is the average service time, is the actual arrival time of the shuttle bus at the aircraft stand. The waiting time for the inbound shuttle bus. For non-shuttle vehicle numbers, The shuttle bus vehicle number, Gather for the shuttle bus, The time when the inbound shuttle bus arrives at the aircraft stand. Waiting time for the outbound shuttle bus. For service time, The time when the cleaning vehicle arrives at the aircraft stand. Waiting time for cleaning car, Assemble for the cleaning car, The latest service completion time for vehicles other than the tractor, The time when the non-tractor vehicle arrives at the parking space. is the time when the tractor arrives at the parking position, The waiting time for the tractor. Assemble for the tractor, To allow the vehicle to arrive at the gate at the earliest possible time, To allow the vehicle to arrive at the gate at the latest time, for Type Special Vehicle The time when the service flight arrives at the gate, Waiting time for special vehicles. For flights The distance from the parking space to the parking space, is the driving speed, To fix the time, is the distance from the parking space to the aircraft space, To allow for the earliest possible start time of service, The arrival time of vehicles serving inbound flights. The flight is scheduled to arrive at the gate time. is the completion time of the preceding service, The time when the vehicle arrives at the gate to serve the departing flight.

[0097] Among them, the constraints Indicates that the shuttle bus for the remote departure flight can only start service after the catering truck, cleaning truck, fuel truck and other vehicles have completed their service. Indicates that the cleaning vehicle for the remote-parking-stand inbound flight can only start service after the shuttle bus has completed its service. It means that for outbound flights, the tractor can only start service after other vehicles have completed their services. Indicates that the time for any vehicle to arrive at the gate should be within the specified time window. Indicates that if a vehicle undertakes multiple service tasks, its next departure time should be later than the time when it completed the last service or the time after its rest. Indicates that the service start time of all service vehicles of the flight should be later than the service start time allowed by the flight. The time when a vehicle for an incoming flight starts service is determined by the maximum of the following three factors: the time when the vehicle arrives at the gate, the scheduled arrival time, and the time when the pre-service vehicle completes the service. The so-called pre-service refers to the service that must be completed before the vehicle starts service. For example, for a remote gate inbound flight, the cleaning vehicle must start after the refueling vehicle has completed the service. Constraints The time when the special vehicle service for the departing flight starts is determined by the later of the time when the vehicle arrives at the gate and the time when the preceding service is completed.

[0098] In an exemplary embodiment of the present invention, the resource capacity constraint includes:

[0099]

[0100]

[0101]

[0102] In the formula, For service flights of Type Special Vehicle Do you need to return to your parking space? is the current available resources of the vehicle, is the flight number, For flights Is it necessary Type Special Vehicle Services, For flights resource requirements, For service flights of Type Special Vehicle Is it from another seat? To complete the current flight Next flights served .

[0103] Among them, the constraints This means that if the vehicle returns to the parking space, it needs to be restocked. This means that the existing resources of the vehicle must be greater than the required resources required to serve the flight, otherwise the service cannot be provided. It means that the value of the decision variable can only be 0 or 1.

[0104] In an exemplary embodiment of the present invention, solving the objective function by using an improved genetic algorithm comprises:

[0105] S201: flight number, service sequence and service stage are represented by a three-layer chromosome structure;

[0106] A hybrid method of natural number encoding and symbol encoding is adopted to represent the service information of airport vehicle scheduling through a three-layer chromosome structure, including flight number, service sequence and service stage. Each chromosome is encoded as a tuple of length 24N, divided into three levels, where N represents the number of flights. The first level (1 to 8N) is used to specify the allocation of vehicles, the second level (8N+1 to 16N) represents the service order of vehicles, and the third level (16N+1 to 24N) defines the service stage of vehicles. Here, different stages are represented by different symbols, for example, F represents the departure of the vehicle from the parking space to the parking space, M represents the movement from one parking space to another, and L refers to the return from the parking space to the parking space.

[0107] S202: Calculate the objective function value, convert the objective value into a fitness value, sort according to the fitness value, and set a ranking threshold;

[0108] Calculate the objective function value, convert the objective value into a fitness value, and then sort according to the fitness value, which is a weighted value of the minimum mileage and the minimum waiting time. The population needs to be initialized at the beginning of the calculation, and each subsequent generation of evolution needs to go through selection, crossover, and mutation operations.

[0109] S203: Perform a crossover operation on chromosomes ranked after the ranking threshold, select two chromosomes as parent chromosomes respectively, cross the two chromosome fragments to form two new daughter chromosomes, and compare the fitness values ​​of the daughter chromosomes with the parent chromosome to determine whether to retain them.

[0110] In this embodiment, the ranking threshold is set to 20.

[0111] More specifically, the present invention improves the crossover operation by introducing a local evaluation factor , which is used to evaluate the quality of the parent crossover fragment. This evaluation mechanism can help decide whether to pass on the genes of a certain fragment to the next generation, ensuring that the crossover operation is more accurate and effective.

[0112] Local evaluation factors:

[0113]

[0114] In the formula, and Represent the paternal chromosome and the maternal chromosome, respectively. is the special vehicle driving distance of the parent chromosome, is the special vehicle travel distance of the parent chromosome, The waiting time for the special vehicle of the parent chromosome, Waiting time for special vehicles of parent chromosomes, is the local evaluation factor, is the weight, is the total travel distance of the chromosome fragment, is the total waiting time of chromosome fragments.

[0115] Among them, the mutation operation is to perform segment mutation on the chromosome and randomly exchange the service flights of the vehicle. The model constraint relationship needs to be considered when performing mutation. Since the mutation of a single special vehicle has basically no improvement effect on the three-layer chromosome structure of this embodiment, a collaborative mutation mechanism that considers both population stability and diversity is improved, that is, while maintaining population stability, the diversity of the population is improved, and the exploration ability of the late solution of the optimization model is enhanced. The details are as follows:

[0116] In maintaining population stability, the use of To indicate whether the mutated chromosome is better than the parent chromosome in terms of fitness value.

[0117]

[0118]

[0119] in, is the weighted assessment value of population stability, is the distance evaluation value, is the waiting time evaluation value, is the weighted evaluation value of the parent chromosome population stability, The difference between the offspring and parent population stability assessment values.

[0120] In maintaining population diversity, using To express it, the diversity of the population is defined, that is, the balanced use of vehicles, which can ensure that more special vehicles can participate in the service.

[0121]

[0122]

[0123] in, is the population diversity assessment value, for Type Special Vehicle The number of times it is used, Type of special vehicle The number of times it is used, represent Type Special Vehicle The total number of is the difference between the diversity assessment values ​​of the offspring and parent populations, A weighted estimate of the diversity of the parent chromosome population.

[0124] Further, using Determine whether the chromosome mutation is approaching the optimal solution. When it is greater than 0, the mutated chromosome is saved and enters the next iteration. is the weight for evaluating population stability, Weighted estimates for population stability and diversity.

[0125] Furthermore, the chromosome is simulated and verified using the simulation model every 50 iterations, and the simulation results are fed back to the improved genetic algorithm as the fitness value to guide the evolution of the algorithm. The weighted value of the objective function calculated by the scheduling model is used as the fitness value for the remaining rounds.

[0126] Determine whether the termination condition is met. The termination condition is the maximum number of iterations. Otherwise, continue with the above operations.

[0127] After the dispatch plan is generated, the dispatch center sends it to each fleet, and special vehicles perform the support mission. The support process requires real-time status information to be sent to the virtual model through monitoring equipment such as GPS, sensors and cameras, and the twin special vehicles synchronously update the position, speed and service information in the twin airport. In the monitoring module in the virtual model, potential conflict points are analyzed, and simulation deductions are performed to demonstrate conflict events, provide early warning information to the dispatch center's dispatch personnel, and dynamically adjust the dispatch plan to reduce the possibility of conflict.

[0128] When conflicts cannot be avoided, dynamic adjustments can be made in the following ways.

[0129] For example, the delay propagation problem caused by the vehicle service time exceeding the specified time. When the vehicle service time is extended, it may cause delays to other services on the same flight and the subsequent services of the vehicle. In this case, delay propagation can be divided into two categories:

[0130] First, for different services in the same flight, there are parallel and sequential execution rules. The delay of vehicles in sequential services will affect the timeliness of subsequent services.

[0131] Second, when a vehicle serves multiple flights, if the completion time of this service exceeds the start time of the next service, it will cause an operation conflict for the same vehicle, thus affecting the service of the current and subsequent flights. In order to deal with these delays, the service start time is moved back and a buffer window is adopted.

[0132] For the first scenario, the service time of the affected vehicles will be adjusted based on the completion time of the pre-service and will no longer be limited to the original time window, and any time window violations will be recorded.

[0133] For the second case, the service start time of the vehicle will be updated to the completion time of the previous service, and the time parameters of other affected vehicle services will be updated and the relevant violations will be recorded. Although the delay propagation may have a wide impact, due to the service time window and the time buffer between different services, some delays can be absorbed, thus playing a positive role in the adjustment of flight services.

[0134] Each local adjustment of the scheduling plan requires simulation verification. The dispatcher determines whether the plan adjustment is reasonable and selects the optimal plan for execution.

[0135] In addition to monitoring task mismatches caused by service time fluctuations, it is also necessary to monitor uncertain events occurring in the airport in real time, especially those that have a significant impact on the scheduling plan, such as large-scale flight delays due to weather reasons, resource shortages caused by special vehicle failures, etc. These events may directly lead to the failure of the initial scheduling plan. Therefore, real-time perception of the airport's operating status and rapid response to emergencies are capabilities that the digital twin real-time scheduling system needs to have.

[0136] Furthermore, when these events are detected, real-time data is sent to the dispatch center, and the optimal solution is quickly solved using an improved genetic algorithm. The simulation model is used in the virtual model for real-time deduction, and the re-dispatch plan is sent to the fleet for task adjustment. Re-dispatch is generally an adjustment for vehicles that have pre-tasks but have not yet been executed. Vehicles that are currently serving or heading to serve will not have their tasks changed.

[0137] The present invention also provides an airport special vehicle dispatching system based on multi-vehicle collaboration, comprising:

[0138] A model building module is configured to build a special vehicle collaborative scheduling model, wherein the special vehicle collaborative scheduling model includes setting an objective function and a number of constraints, and building a virtual model based on basic data and a three-dimensional model of the airport and the special vehicle, wherein the virtual model is used to collect data in real time and provide data support for the vehicle collaborative scheduling model;

[0139] The solution module is configured to solve the objective function through a genetic algorithm and obtain an optimal solution of the genetic algorithm based on the fitness value; input the optimal solution into the special vehicle collaborative scheduling model to obtain a special vehicle scheduling plan, and feed back data generated by the special vehicle in the implementation of the special vehicle scheduling plan to the virtual model;

[0140] The synchronization module is configured to synchronize the virtual model and adjust the special vehicle dispatch plan according to the real-time dynamic data;

[0141] A main control module, which is connected to the model building module, the solving module and the synchronization module, is used to execute the above-mentioned airport special vehicle scheduling method based on multi-vehicle collaboration.

[0142] 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.

[0143] 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 storage medium. The computer software product is stored in a storage medium, including a number of 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 methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0144] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The airport special vehicle dispatching method based on multi-vehicle collaboration is characterized by: include: Constructing a special vehicle collaborative dispatching model, which includes setting an objective function and several constraints, and constructing a virtual model based on basic data and three-dimensional models of airports and special vehicles, and the virtual model is used to collect data in real time and provide data support for the vehicle collaborative dispatching model; Solve the objective function through genetic algorithm and obtain the optimal solution of genetic algorithm based on the fitness value; The optimal solution is input into the special vehicle collaborative scheduling model to obtain the special vehicle scheduling plan, and the data generated by the implementation of the special vehicle according to the special vehicle scheduling plan is fed back to the virtual model; The virtual model is updated synchronously to adjust the special vehicle dispatch plan according to real-time dynamic data; The objective of the objective function is to minimize the total mileage and waiting time of special vehicles, including: In the formula, To minimize the total mileage function of special vehicles, To minimize the waiting time function of special vehicles, A collection of special vehicle types. For flight collection, For flights Is it necessary Type Special Vehicle Services, For service flights of Type Special Vehicle Whether it comes from other seats, is the distance from the parking space to the aircraft space, For service seats of Type Special Vehicle Do you need to return to the parking space? The distance from the aircraft to the parking space, To complete the current flight Next flights served , For flights Parking to flight The distance to the parking space, is the penalty coefficient for waiting service time for incoming flights, Waiting time for special vehicles for incoming flights, is the penalty coefficient for waiting service time of departing flights, Waiting time for special vehicles to depart from Hong Kong. is the flight number, For special vehicle types; The several constraints include service constraints, parking constraints, time window constraints and resource capacity constraints; The service constraints include: In the formula, in the formula, For flights quilt Type Special Vehicle Serve, for Number of special vehicles of type, Assemble for departing and arriving flights, For flights Several special vehicles are needed. is the maximum capacity, Gather for the shuttle bus, Assemble for luggage carts, Assemble for the fuel truck; The parking constraints include: In the formula, It is a sign for counting vehicles going to the parking space. Counting mark for the vehicle returning to the parking position. Numbering of special vehicles; The time window constraints include: ; ; ; ; ; ; ; In the formula, The shuttle bus for flights departing from remote parking positions can only start service after the catering truck, cleaning truck and refueling truck have completed their service. is the actual arrival time at the aircraft stand. Waiting time for special vehicles. is the average service time, is the actual arrival time of the shuttle bus at the aircraft stand. The waiting time for the inbound shuttle bus. For non-shuttle vehicle numbers, The shuttle bus vehicle number, Gather for the shuttle bus, The time when the inbound shuttle bus arrives at the aircraft stand. Waiting time for the outbound shuttle bus. For service time, The time when the cleaning vehicle arrives at the aircraft stand. Waiting time for cleaning car, Assemble for the cleaning car, The latest service completion time for vehicles other than the tractor, The time when the non-tractor vehicle arrives at the parking space. is the time when the tractor arrives at the parking position, The waiting time for the tractor. Assemble for the tractor, To allow the vehicle to arrive at the gate at the earliest possible time, To allow the vehicle to arrive at the gate at the latest time, for Type Special Vehicle The time when the service flight arrives at the gate, Waiting time for special vehicles. For flights The distance from the parking space to the parking space, is the driving speed, To fix the time, is the distance from the parking space to the aircraft space, To allow for the earliest possible start time of service, The arrival time of vehicles serving inbound flights. The flight is scheduled to arrive at the gate time. is the completion time of the preceding service, Arrival time of vehicles serving departing flights; The resource capacity constraints include: In the formula, For service flights of Type Special Vehicle Do you need to return to your parking space? is the current available resources of the vehicle, is the flight number, For flights Is it necessary Type Special Vehicle Services, For flights resource requirements, For service flights of Type Special Vehicle Is it from another seat? To complete the current flight Next flights served ; The solving of the objective function by genetic algorithm comprises: The flight number, service sequence and service phase are represented by a three-layer chromosome structure; Calculate the objective function value, convert the objective value into a fitness value, sort according to the fitness value, and set the ranking threshold; Perform a crossover operation on chromosomes ranked after the ranking threshold, select two chromosomes as parent chromosomes, cross the two chromosome fragments to form two new daughter chromosomes, and compare the fitness values ​​of the daughter chromosomes with the parent chromosomes to determine whether to keep them; The crossover operation also includes: Establish local evaluation factors: In the formula, and Represent the paternal chromosome and the maternal chromosome, respectively. is the special vehicle driving distance of the parent chromosome, is the special vehicle travel distance of the parent chromosome, The waiting time for the special vehicle of the parent chromosome, Waiting time for special vehicles of parent chromosomes, is the local evaluation factor, is the weight, is the total travel distance of the chromosome fragment, is the total waiting time of chromosome fragments.

2. Airport special vehicle dispatching system based on multi-vehicle collaboration, characterized by: include: A model building module is configured to build a special vehicle collaborative scheduling model, wherein the special vehicle collaborative scheduling model includes setting an objective function and a number of constraints, and building a virtual model based on basic data and a three-dimensional model of the airport and the special vehicle, wherein the virtual model is used to collect data in real time and provide data support for the vehicle collaborative scheduling model; The solution module is configured to solve the objective function through a genetic algorithm and obtain an optimal solution of the genetic algorithm based on the fitness value; input the optimal solution into the special vehicle collaborative scheduling model to obtain a special vehicle scheduling plan, and feed back data generated by the special vehicle in the implementation of the special vehicle scheduling plan to the virtual model; The synchronization module is configured to synchronize the virtual model and adjust the special vehicle dispatch plan according to the real-time dynamic data; A main control module, which is connected to the model building module, the solving module and the synchronization module, and is used to execute the airport special vehicle scheduling method based on multi-vehicle collaboration as described in claim 1.