CN114038242A - Multi-agent-based large-scale aircraft motion simulation method and device - Google Patents
Multi-agent-based large-scale aircraft motion simulation method and device Download PDFInfo
- Publication number
- CN114038242A CN114038242A CN202111367165.9A CN202111367165A CN114038242A CN 114038242 A CN114038242 A CN 114038242A CN 202111367165 A CN202111367165 A CN 202111367165A CN 114038242 A CN114038242 A CN 114038242A
- Authority
- CN
- China
- Prior art keywords
- aircraft
- flight
- motion
- state information
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 5
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 3
- 238000012795 verification Methods 0.000 abstract description 3
- 238000013459 approach Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000007726 management method Methods 0.000 description 6
- 238000013519 translation Methods 0.000 description 6
- 239000002245 particle Substances 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000009194 climbing Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/04—Anti-collision systems
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The application provides a large-scale aircraft motion simulation method and device based on multiple intelligent agents, which belong to the field of air traffic, and the method comprises the following steps: configuring flight performance parameters of the aircraft according to the aircraft flight plan; generating a flight intention instruction; converting the generated flight intent instructions into reference flight status information trackable by the aircraft; calculating the aircraft motion state information according to the configured flight performance parameters of the aircraft; closed-loop simulation of the aircraft motion is performed according to the error between the aircraft motion state information and the reference flight state information, the requirements of future air traffic management research simulation and verification can be met, and the method is used for large-scale aircraft motion simulation.
Description
Technical Field
The application belongs to the technical field of air traffic, and particularly relates to a multi-agent-based large-scale aircraft motion simulation method and device.
Background
With the continuous and rapid development of avionic technology, the aircraft gradually changes from a traditional controlled object to an important participant of air traffic management activities, and the cooperation of the whole navigation process is realized. In a traditional air traffic simulation system, an aircraft is mostly regarded as a particle, and the motion simulation of the aircraft is greatly simplified. Although the calculation resources are saved by the aircraft motion simulation method in the traditional air traffic simulation system, the requirements of future air traffic management research simulation and verification cannot be met.
Disclosure of Invention
In order to solve the problems in the related art, the application provides a method and a device for simulating the motion of a large-scale aircraft based on multiple intelligent agents, and the technical scheme is as follows:
in a first aspect, a multi-agent based large-scale aircraft motion simulation method is provided, the method comprising:
configuring flight performance parameters of the aircraft according to the aircraft flight plan;
generating a flight intention instruction;
converting the generated flight intent instructions into reference flight status information trackable by the aircraft;
calculating the aircraft motion state information according to the configured flight performance parameters of the aircraft;
and performing closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information and the reference flight state information.
Wherein configuring flight performance parameters of an aircraft according to an aircraft flight plan comprises:
determining the type and model of the aircraft according to the flight plan;
determining aircraft load and oil mass information according to a flight plan;
and according to the determined type and model of the aircraft and the information of the load and oil mass, configuring flight performance parameters of the aircraft with the corresponding model through automatic table look-up.
Wherein the generating of the flight intent instruction comprises:
and generating a first flight intention instruction which meets the 4D track constraint condition from the door to the door of the aircraft according to the flight plan of the aircraft and the flight performance parameters of the aircraft.
Wherein the generating of the flight intent instruction comprises:
and when an air traffic control instruction is received in the process of aircraft navigation, generating a second flight intention instruction meeting air traffic control according to the air traffic control instruction and the configured aircraft flight performance parameters.
Wherein the generating of the flight intent instruction comprises:
when a possible traffic conflict is predicted during the flight of the aircraft, a third flight intent instruction is generated that achieves no conflict.
When a possible traffic conflict is predicted in the process of aircraft navigation, generating a third flight intention instruction for realizing conflict-free, wherein the third flight intention instruction comprises the following steps:
predicting a first short-term 4D track of surrounding traffic according to air traffic situation information around the aircraft agent;
predicting a second short-term 4D trajectory of the aircraft agent from the first and second flight intent commands;
judging a possible traffic conflict space-time envelope between the aircraft intelligent body and the peripheral aircraft according to the first short-term 4D track and the second short-term 4D track;
establishing a maneuvering action library conforming to the performance constraint of the aircraft according to an aircraft intelligent body motion model, and searching an aircraft optimal maneuvering sequence which can be separated from a conflict space-time envelope by adopting a multi-layer search tree;
and determining an output result obtained after the aircraft optimal maneuvering sequence is input into the aircraft intelligent body motion model as a third flight intention instruction.
The method for calculating the aircraft motion state information according to the configured flight performance parameters of the aircraft comprises the following steps:
selecting aircraft dynamics models of corresponding categories according to the configured flight performance parameters of the aircraft, and configuring the aerodynamics and aircraft structure parameters of the corresponding models;
configuring the load and oil quantity for the aircraft according to the flight plan;
classifying the aircraft agents according to the aerodynamics, aircraft structure parameters and flight performance parameters, comprehensively calculating resources of the classified aircraft agents, calculating the motion state information of the aircraft agents in batches, and generating large-scale aircraft motion state information.
Wherein the closed loop simulation of the aircraft motion according to the error between the aircraft motion state information and the reference flight state information comprises:
calculating the flight state error between the aircraft motion state information and the reference flight state information;
inputting flight state error information into an aircraft motion automatic controller, and calculating aircraft intelligent body feedback control input parameters in a multi-stage PID mode;
and inputting the feedback control input parameters of the intelligent aircraft body into the motion model of the aircraft to obtain flight path simulation data of the intelligent aircraft body.
In a second aspect, there is provided a multi-agent based large scale aircraft motion simulation apparatus, the apparatus comprising: a flight performance configuration module, an autonomous flight intention generation module, a motion automatic control module and a motion general resolving module,
the flight performance configuration module is used for configuring flight performance parameters of the aircraft according to an aircraft flight plan and outputting the flight performance parameters to the autonomous flight intention generation module and the motion general calculation module;
the autonomous flight intention generation module generates a flight intention instruction;
the autonomous flight intention generation module converts the generated flight intention instruction into reference flight state information which can be tracked by an aircraft and sends the reference flight state information to the motion automatic control module;
the motion general calculation module calculates aircraft motion state information according to configured flight performance parameters of the aircraft and sends the aircraft motion state information to the motion automatic control module;
and the motion automatic control module performs closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information output by the motion general resolving module and the reference flight state information output by the autonomous flight intention generating module.
The multi-agent-based large-scale aircraft motion simulation method and device provided by the application have at least the following effects:
1) the simulation system facing the air traffic navigation does not simplify the aircraft into particles only considering spatial displacement, and the simulated aircraft is added to execute a navigation program according to performance parameters of the simulated aircraft, so that the fidelity of the air traffic simulation is improved;
2) the simulation system facing the air traffic navigation does not simplify the motion of the aircraft into the motion according to a fixed path any more, and the aircraft added with the simulation tracks the reference flight state information through the automatic control module to realize closed-loop aircraft motion simulation;
3) the aircraft in the simulation system facing the air traffic navigation is not a controlled object which is simply controlled by a traffic control instruction any more, and the aircraft added into the simulation can autonomously generate a flight intention instruction according to a verified algorithm to participate in air traffic management activities;
4) the aircraft motion simulation is distributed to corresponding aircraft motion resolving modules according to the types and models of the aircraft, the flight state information of the aircraft is calculated in batches, the reusability of simulation modules is improved, and the aircraft motion simulation efficiency is improved.
Drawings
FIG. 1 is a flow chart of a multi-agent based large-scale aircraft motion simulation method provided by the present application;
fig. 2 is a schematic flow chart of an aircraft autonomous flight intention generation method provided in the present application;
FIG. 3 is a flow chart of a general resolving method for aircraft motion provided by the present application;
fig. 4 is a schematic flow chart of an aircraft motion automatic control method provided in the present application.
Detailed Description
The present application will now be described in further detail with reference to specific embodiments and the accompanying drawings.
For the reader to more clearly understand the technical solution of the present application, a brief description will now be made of the multi-agent system.
The multi-agent system is an important branch of Distributed Artificial Intelligence (Distributed Artificial Intelligence), has autonomy, distribution and coordination, self-organizing capability, learning capability and reasoning capability, has higher problem solving efficiency, and can be used for solving large and complex engineering practical problems. The goal is to build large and complex systems into small, manageable systems that communicate and coordinate with each other.
In the application, the aircraft motion simulation based on the multi-agent considers each aircraft added with the simulation as an agent with sensing and decision-making capabilities, can be used for simulating and verifying the role and the effect of the advanced aircraft in the air traffic management activity, evaluating and analyzing the influence and the efficiency improvement of the coordinated navigation in the whole process on the air navigation, and can meet the requirements of future air traffic management research simulation and verification.
The application provides a multi-agent-based large-scale aircraft motion simulation method and device, which can be used for simulating and verifying advanced aircraft air traffic operation scenes, improve the motion simulation efficiency of large-scale aircraft, and realize flight path simulation of 1 to 2000 aircrafts in the national airspace range.
The application provides a multi-agent-based large-scale aircraft motion simulation method, as shown in fig. 1, the method comprises the following steps:
and 150, performing closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information and the reference flight state information.
The method for configuring the flight performance parameters of the aircraft according to the aircraft flight plan comprises the following steps:
determining the type and model of the aircraft according to the flight plan;
determining aircraft load and oil mass information according to a flight plan;
and according to the determined type and model of the aircraft and the information of the load and oil mass, configuring flight performance parameters of the aircraft with the corresponding model through automatic table look-up.
For example, the translation of the generated flight intent instructions into reference flight status information that the aircraft can track may be:
according to a first flight intention command Teo(x，y，z，t1，t2) Current state of motion parameter (x) of the aircraft0，y0，z0) And calculating the time step delta t with the aircraft motion state, and calculating to obtain the reference flight state information which can be tracked by the aircraft through a linear interpolation method.
Wherein generating the flight intent instructions may include three aspects,
in a first aspect, generating an intent-to-fly instruction includes:
and generating a first flight intention instruction which meets the 4D track constraint condition from the door to the door of the aircraft according to the flight plan of the aircraft and the flight performance parameters of the aircraft.
In a second aspect, generating flight intent instructions includes:
and when the air traffic control instruction is received in the aircraft navigation process, generating a second flight intention instruction meeting the air traffic control according to the air traffic control instruction and the configured aircraft flight performance parameters.
In a third aspect, generating an intent-to-fly instruction includes:
when a possible traffic conflict is predicted during the flight of the aircraft, a third flight intent instruction is generated that achieves no conflict.
Specifically, when a possible traffic conflict is predicted during the flight of the aircraft, a third flight intent instruction is generated that achieves conflict-free, including:
predicting a first short-term 4D track of surrounding traffic according to air traffic situation information around the aircraft agent;
predicting a second short-term 4D trajectory of the aircraft agent from the first and second flight intent commands;
judging a possible traffic conflict space-time envelope between the aircraft intelligent body and the peripheral aircraft according to the first short-term 4D track and the second short-term 4D track;
establishing a maneuvering action library conforming to the performance constraint of the aircraft according to an aircraft intelligent body motion model, and searching an aircraft optimal maneuvering sequence which can be separated from a conflict space-time envelope by adopting a multi-layer search tree;
and determining an output result obtained after the aircraft optimal maneuvering sequence is input into the aircraft intelligent body motion model as a third flight intention instruction.
The method for calculating the aircraft motion state information according to the configured flight performance parameters of the aircraft comprises the following steps:
selecting aircraft dynamics models of corresponding categories according to the configured flight performance parameters of the aircraft, and configuring the aerodynamics and aircraft structure parameters of the corresponding models;
configuring the load and oil quantity for the aircraft according to the flight plan;
classifying the aircraft agents according to the aerodynamics, aircraft structure parameters and flight performance parameters, comprehensively calculating resources of the classified aircraft agents, calculating the motion state information of the aircraft agents in batches, and generating large-scale aircraft motion state information.
The closed-loop simulation of the aircraft motion is performed according to the error between the aircraft motion state information and the reference flight state information, and comprises the following steps:
calculating the flight state error between the aircraft motion state information and the reference flight state information;
inputting flight state error information into an aircraft motion automatic controller, and calculating aircraft intelligent body feedback control input parameters in a multi-stage PID mode;
and inputting the feedback control input parameters of the intelligent aircraft body into the motion model of the aircraft to obtain flight path simulation data of the intelligent aircraft body.
The invention relates to a multi-agent-based large-scale aircraft motion simulation method, which utilizes the multi-agent-based aircraft motion simulation system to carry out large-scale aircraft motion simulation and specifically comprises the following steps:
a, a flight performance configuration module reads information such as the type and model of an aircraft, the load of the aircraft, the oil quantity and the like according to a flight plan, automatically configures aircraft performance parameters and outputs the aircraft performance parameters to an aircraft autonomous flight intention generation module and an aircraft motion general resolving module;
b, generating a first flight intention instruction which meets the 4D track constraint condition from door to door of the aircraft by an aircraft autonomous flight intention generation module according to an aircraft flight plan and input aircraft performance parameters; if the aircraft receives an air traffic control instruction in the navigation process, the module generates a second flight intention instruction meeting the air traffic control according to the air traffic control instruction and the input aircraft flight performance parameters; when a possible traffic conflict is predicted in the navigation process, the module autonomously generates a third flight intention instruction for realizing conflict-free; finally, translating the conflict-free flight intention command into the reference flight state information which can be tracked by the aircraft, and sending the reference flight state information to an aircraft motion automatic control module as shown in the figure 2;
step C, selecting an aircraft dynamics model of a corresponding category by the aircraft motion general calculation module according to the input aircraft flight performance parameters, configuring the aerodynamics of the corresponding model and the aircraft structure parameters, configuring parameters such as load and oil quantity for the aircraft according to a flight plan, calculating aircraft motion state information, and outputting the information to the aircraft motion automatic control module as shown in figure 3;
and D, generating an aircraft motion input instruction by an aircraft motion automatic control module through an automatic control law according to an error between aircraft motion state information output by an aircraft motion general calculation module and reference flight state information output by an aircraft autonomous flight intention generation module, and transmitting the aircraft motion input instruction to the aircraft motion general calculation module to realize closed-loop simulation of aircraft motion, wherein the error is shown in figure 4.
In the invention, the configuration of the aircraft performance parameters is realized according to the following method:
a1, the flight performance configuration module reads the type and model of the aircraft according to the flight plan;
a2, the flight performance configuration module reads the information of the load and the oil mass of the aircraft according to the flight plan;
step A3, the flight performance configuration module configures the flight performance parameters of the corresponding type of aircraft through automatic table lookup.
The aircraft flight intent instructions are generated as follows:
step B1, the aircraft autonomous flight intention generating module generates a global flight intention instruction of the aircraft intelligent body according to the aircraft flight plan and the input aircraft performance parameters;
wherein, the flight plan is to provide the air traffic service unit with the data about the completion of one flight of the aircraft. The basic components of a flight plan include the origin and destination airports, the waypoints and routes for a flight, the category of the flight, the cruising altitude, the amount of oil carried, and the like. And step B1, the flight plan translation sub-module in the aircraft autonomous flight intention generation module identifies the flight plan text in the standard format and translates the flight plan text into a flight intention instruction readable by the aircraft motion simulation system. And D, giving reference motion state information of the aircraft for transition from the current motion state to the target motion state by the flight intention instruction, and driving the aircraft intelligent agent to generate a flight track as the input of the step D.
The working principle of the flight plan translation sub-module is to read a flight plan file, locate and identify flight plan keywords and parameter values, and input the flight plan keywords and parameter values into an initial state item, a target state item, a space constraint item, a time constraint item and an aircraft performance constraint item of each navigation stage of the aircraft. For each flight phase, generating a reference path R according to the planning of a start state item, an end state item, a space constraint item and a performance constraint itemi(x, y, z) wherein i is a subscript number and x, y, z are spatial coordinates. For each flight phase, generating a tracking reference path R according to a time constraint termiReference motion state information of, i.e. flight-intention commands Tet(x，y，z，t1，t2) Wherein t is1As a starting time, t2Is the first end time. The specific implementation steps are as follows:
reading a flight plan of the aircraft, and splitting a flight phase into 6 phases of roll-off taking-off, departure, airline operation, approach, landing and roll-in;
in the stage of sliding out and taking off, taking a position parameter of a taxi path point, geometrical data of a taxiway and a runway on an airport surface, and a position and geometrical parameter of an airport building, which are specified by a flight plan, as space constraint, taking a release scheduling moment as time constraint, and taking performance parameters of an aircraft as performance constraint, planning and generating a virtual taxi path R of an aircraft intelligent body1(x, y, z). According to the scene sliding rule, the sliding waiting position is taken as a node, the aircraft performance parameter is taken as a constraint, and an aircraft sliding intention instruction T between each node is generatede1(x，y，z，t1，t2)；
In the departure stage, a departure program specified by a flight plan is taken as a space constraint, departure sequence is taken as a time constraint, aircraft performance parameters are taken as a performance constraint, and a virtual departure path R of the aircraft intelligent body is planned and generated2(x, y, z). According to the departure program, the aircraft departure intention instruction T is generated by taking the aircraft performance parameters as constraintse2(x，y，z，t1，t2)；
In the course operation stage, taking the course section specified by the flight plan as a space constraint, taking the RTA specified by the flight plan as a time constraint, taking the performance parameters of the aircraft as a performance constraint, and planning and generating a virtual flight operation path R of the aircraft intelligent body3(x, y, z). According to the flight line operation rule, taking the aircraft performance parameters as constraints, generating an aircraft departure intention instruction Te3(x，y，z，t1，t2)；
In the approach stage, an approach program specified by a flight plan is taken as a space constraint, an approach sequence is taken as a time constraint, aircraft performance parameters are taken as performance constraints, and a virtual approach path R of the aircraft intelligent body is planned and generated4(x，y，z). According to the approach procedure, an aircraft approach intention instruction T is generated by taking aircraft performance parameters as constraintse4(x，y，z，t1，t2)；
In the landing stage, a landing program specified by a flight plan is taken as a space constraint, and the aircraft performance parameters are taken as performance constraints to plan and generate a virtual landing path R of an aircraft intelligent body5(x, y, z). Generating an aircraft landing intention instruction T by taking the aircraft performance parameters as constraints according to a landing programe5(x，y，z，t1，t2)；
In the sliding-in stage, the position parameters of the sliding path points, airport surface taxiways, geometrical data of runways, airport building positions and geometrical parameters specified by the flight plan are taken as space constraints, and the performance parameters of the aircraft are taken as performance constraints to plan and generate the virtual sliding path R of the aircraft intelligent body6(x, y, z). According to the scene sliding rule, the sliding waiting position is taken as a node, the aircraft performance parameter is taken as a constraint, and an aircraft sliding intention instruction T between each node is generatede6(x，y，z，t1，t2)；
Merging the flight intentions of the aircraft in the navigation phases to generate a first flight intention instruction T of the aircraft agenteo(x，y，z，t1，t2)；
Step B2, the aircraft autonomous flight intention generation module judges whether the aircraft intelligent body receives the air traffic control instruction;
step B3, if the aircraft intelligent body receives the control instruction, generating a flight intention instruction meeting the air traffic control according to the air traffic control instruction and the input aircraft flight performance parameters;
receiving the control instruction, converting into a standard format control intention instruction T according to the control rule baseo(x，y，z，t1，t2) Generating a second intention instruction T of the aircraft based on the control instruction by taking the performance parameters of the aircraft as constraintseo(x，y，z，t1，t2)；
Step B4, generating model of autonomous flight intention of aircraftThe block predicts a first short-term 4D trajectory L of surrounding traffic based on air traffic situation information surrounding the aircraft agentst(x，y，z，t1，t2) Wherein t is3Is a second endpoint time;
step B5, the aircraft autonomous flight intention generation module predicts the short-term 4D track of the aircraft agent by combining the flight intention commands generated in the steps B1 and B3;
fuse aircraft agent global flight intention instruction Teo(x，y，z，t1，t2) And an aircraft intention instruction T based on the control instructioneo(x，y，z，t1，t2) Calculating a second short-term 4D track L of the aircraft agentsa(x，y，z，t1，t2)；
Step B6, the autonomous flight intention generation module of the aircraft prejudges the possible traffic conflict between the intelligent agent of the aircraft and the surrounding aircraft;
according to Lsa(x，y，z，t1，t2) And Lst(x，y，z，t1T2) determining a space-time envelope of a possible traffic conflict between the aircraft agent and the surrounding aircraft.
Step B7, the aircraft autonomous flight intention generation module generates a flight intention instruction for the aircraft intelligent agent to be out of conflict by adopting a multi-layer search tree method based on a maneuvering action library;
establishing a maneuvering action library conforming to the aircraft performance constraint according to an aircraft intelligent body movement model, and searching an aircraft optimal maneuvering sequence A capable of being separated from a conflict envelope by adopting a multi-layer search treel(K，t1，t2) Where K is a maneuver instruction, thereby generating a third intent instruction T for the aircraft to resolve the conflictea(x，y，z，t1，t4) Wherein t is4Is the third endpoint time.
And step B8, translating the conflict resolution flight intention instruction into the reference flight state information which can be tracked by the aircraft intelligent body by the aircraft autonomous flight intention generation module.
The batch aircraft motion state calculation is realized according to the following method:
step C1, selecting an aircraft dynamics model of a corresponding category by the aircraft motion general resolving module according to the input aircraft flight performance parameters, and configuring the aerodynamics of the corresponding model and the aircraft structure parameters;
step C2, configuring parameters such as load, oil quantity and the like for the aircraft by the aircraft motion general calculation module according to the flight plan;
and step C3, classifying the aircraft intelligent bodies according to the input parameters by the aircraft motion general resolving module, overall calculating resources, calculating the motion state information of the aircraft intelligent bodies in batches, and generating large-scale aircraft motion state information.
The automatic control of the aircraft motion is realized according to the following method:
d1, inputting the aircraft motion state information output by the aircraft motion general resolving module into the aircraft motion automatic control module;
step D2, inputting the reference flight state information output by the aircraft autonomous flight intention generation module into the aircraft motion automatic control module;
d3, calculating the error between the aircraft motion state information and the reference flight state information by the aircraft motion automatic control module;
d4, the aircraft motion automatic control module inputs the flight state error information to the aircraft motion automatic controller, and the aircraft intelligent body feedback control input parameters are calculated by adopting a multi-stage PID method;
and D5, the aircraft motion automatic control module inputs the control input parameters to the aircraft motion general resolving module to realize the closed-loop automatic control of the aircraft intelligent body and generate the flight path simulation data of the aircraft intelligent body.
The application also provides a large-scale aircraft motion simulation device based on multi-agent, the device includes: a flight performance configuration module, an autonomous flight intention generation module, a motion automatic control module and a motion general resolving module,
the flight performance configuration module is used for configuring flight performance parameters of the aircraft according to the aircraft flight plan and outputting the flight performance parameters to the autonomous flight intention generation module and the motion general calculation module;
the autonomous flight intention generation module generates a flight intention instruction;
the autonomous flight intention generation module converts the generated flight intention instruction into reference flight state information which can be tracked by the aircraft and sends the reference flight state information to the motion automatic control module;
the motion general resolving module calculates the motion state information of the aircraft according to the configured flight performance parameters of the aircraft and sends the motion state information of the aircraft to the motion automatic control module;
and the motion automatic control module performs closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information output by the motion general resolving module and the reference flight state information output by the autonomous flight intention generating module.
The aircraft autonomous flight intent generation module includes the following sub-modules:
the flight plan translation module is used for identifying 4D track constraint conditions of the aircraft in the flight stages of push-out, sliding, take-off, climbing, cruising, descending, approach, landing, sliding, bridge approach and the like according to the aircraft flight plan, and translating and generating flight intention instructions meeting the space-time constraint of the flight plan according to input aircraft flight performance parameters;
the control instruction translation module is used for translating and generating a flight intention instruction meeting air traffic control according to an air traffic control instruction received by an aircraft in a flight phase and input aircraft flight performance parameters;
the traffic situation perception module predicts the short-term 4D track of surrounding traffic according to the air traffic situation information around the aircraft, predicts the short-term 4D track of the aircraft by combining the generated flight intention instruction, pre-judges possible traffic conflicts and autonomously generates a conflict-free flight intention instruction;
and the flight intention translation module is used for translating and generating reference flight state information which can be tracked by the aircraft according to the flight intention instruction generated by the sub-module and sending the reference flight state information to the aircraft motion general calculation module.
The multi-agent-based large-scale aircraft motion simulation method and device provided by the application have at least the following effects:
the simulation system facing the air traffic navigation does not simplify the aircraft into particles only considering spatial displacement, and the simulated aircraft is added to execute a navigation program according to performance parameters of the simulated aircraft, so that the fidelity of the air traffic simulation is improved;
the simulation system facing the air traffic navigation does not simplify the motion of the aircraft into the motion according to a fixed path any more, and the aircraft added with the simulation tracks the reference flight state information through the automatic control module to realize closed-loop aircraft motion simulation;
the aircraft in the simulation system facing the air traffic navigation is not a controlled object which is simply controlled by a traffic control instruction any more, and the aircraft added into the simulation can autonomously generate a flight intention instruction according to a verified algorithm to participate in air traffic management activities;
the aircraft motion simulation is distributed to corresponding aircraft motion resolving modules according to the types and models of the aircraft, the flight state information of the aircraft is calculated in batches, the reusability of simulation modules is improved, and the aircraft motion simulation efficiency is improved.
The foregoing merely represents embodiments of the present application, which are described in greater detail and detail, and therefore should not be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application.
Claims (9)
1. A multi-agent based large-scale aircraft motion simulation method, the method comprising:
configuring flight performance parameters of the aircraft according to the aircraft flight plan;
generating a flight intention instruction;
converting the generated flight intent instructions into reference flight status information trackable by the aircraft;
calculating the aircraft motion state information according to the configured flight performance parameters of the aircraft;
and performing closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information and the reference flight state information.
2. The method of claim 1, wherein configuring flight performance parameters of the aircraft according to the aircraft flight plan comprises:
determining the type and model of the aircraft according to the flight plan;
determining aircraft load and oil mass information according to a flight plan;
and according to the determined type and model of the aircraft and the information of the load and oil mass, configuring flight performance parameters of the aircraft with the corresponding model through automatic table look-up.
3. The method of claim 1, wherein the generating the flight intent instruction comprises:
and generating a first flight intention instruction which meets the 4D track constraint condition from the door to the door of the aircraft according to the flight plan of the aircraft and the flight performance parameters of the aircraft.
4. The method of claim 1, wherein the generating the flight intent instruction comprises:
and when an air traffic control instruction is received in the process of aircraft navigation, generating a second flight intention instruction meeting air traffic control according to the air traffic control instruction and the configured aircraft flight performance parameters.
5. The method of claim 4, wherein the generating the flight intent instructions comprises:
when a possible traffic conflict is predicted during the flight of the aircraft, a third flight intent instruction is generated that achieves no conflict.
6. The method of claim 5, wherein generating a third flight intent instruction to achieve collision free when a possible traffic collision is predicted during the flight of the aircraft comprises:
predicting a first short-term 4D track of surrounding traffic according to air traffic situation information around the aircraft agent;
predicting a second short-term 4D trajectory of the aircraft agent from the first and second flight intent commands;
judging a possible traffic conflict space-time envelope between the aircraft intelligent body and the peripheral aircraft according to the first short-term 4D track and the second short-term 4D track;
establishing a maneuvering action library conforming to the performance constraint of the aircraft according to an aircraft intelligent body motion model, and searching an aircraft optimal maneuvering sequence which can be separated from a conflict space-time envelope by adopting a multi-layer search tree;
and determining an output result obtained after the aircraft optimal maneuvering sequence is input into the aircraft intelligent body motion model as a third flight intention instruction.
7. The method of claim 1, wherein calculating aircraft motion state information from the configured flight performance parameters of the aircraft comprises:
selecting aircraft dynamics models of corresponding categories according to the configured flight performance parameters of the aircraft, and configuring the aerodynamics and aircraft structure parameters of the corresponding models;
configuring the load and oil quantity for the aircraft according to the flight plan;
classifying the aircraft agents according to the aerodynamics, aircraft structure parameters and flight performance parameters, comprehensively calculating resources of the classified aircraft agents, calculating the motion state information of the aircraft agents in batches, and generating large-scale aircraft motion state information.
8. The method of claim 1, wherein performing closed loop simulation of aircraft motion based on an error between aircraft motion state information and reference flight state information comprises:
calculating the flight state error between the aircraft motion state information and the reference flight state information;
inputting flight state error information into an aircraft motion automatic controller, and calculating aircraft intelligent body feedback control input parameters in a multi-stage PID mode;
and inputting the feedback control input parameters of the intelligent aircraft body into the motion model of the aircraft to obtain flight path simulation data of the intelligent aircraft body.
9. A multi-agent based large scale aircraft motion simulation apparatus, the apparatus comprising: a flight performance configuration module, an autonomous flight intention generation module, a motion automatic control module and a motion general resolving module,
the flight performance configuration module is used for configuring flight performance parameters of the aircraft according to an aircraft flight plan and outputting the flight performance parameters to the autonomous flight intention generation module and the motion general calculation module;
the autonomous flight intention generation module generates a flight intention instruction;
the autonomous flight intention generation module converts the generated flight intention instruction into reference flight state information which can be tracked by an aircraft and sends the reference flight state information to the motion automatic control module;
the motion general calculation module calculates aircraft motion state information according to configured flight performance parameters of the aircraft and sends the aircraft motion state information to the motion automatic control module;
and the motion automatic control module performs closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information output by the motion general resolving module and the reference flight state information output by the autonomous flight intention generating module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111367165.9A CN114038242B (en) | 2021-11-18 | 2021-11-18 | Large-scale aircraft motion simulation method and device based on multiple intelligent agents |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111367165.9A CN114038242B (en) | 2021-11-18 | 2021-11-18 | Large-scale aircraft motion simulation method and device based on multiple intelligent agents |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114038242A true CN114038242A (en) | 2022-02-11 |
| CN114038242B CN114038242B (en) | 2023-12-12 |
Family
ID=80144814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111367165.9A Active CN114038242B (en) | 2021-11-18 | 2021-11-18 | Large-scale aircraft motion simulation method and device based on multiple intelligent agents |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114038242B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120290154A1 (en) * | 2011-01-28 | 2012-11-15 | The Boeing Company | Providing data for predicting aircraft trajectory |
| CN103336863A (en) * | 2013-06-24 | 2013-10-02 | 北京航空航天大学 | Radar flight path observation data-based flight intention recognition method |
| US20130317672A1 (en) * | 2012-05-24 | 2013-11-28 | The Boeing Company | Providing a description of aircraft intent |
| CN103617749A (en) * | 2013-11-15 | 2014-03-05 | 中国航空无线电电子研究所 | Onboard system and method for managing land-air commands |
| CN104252797A (en) * | 2014-09-22 | 2014-12-31 | 北京航空航天大学 | Virtual controller-based airspace simulation method and device thereof |
| CN105679102A (en) * | 2016-03-03 | 2016-06-15 | 南京航空航天大学 | National flight flow space-time distribution prediction deduction system and method |
| CN110781757A (en) * | 2019-09-29 | 2020-02-11 | 中国航空无线电电子研究所 | Airport pavement foreign matter identification and positioning method and system |
-
2021
- 2021-11-18 CN CN202111367165.9A patent/CN114038242B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120290154A1 (en) * | 2011-01-28 | 2012-11-15 | The Boeing Company | Providing data for predicting aircraft trajectory |
| US20130317672A1 (en) * | 2012-05-24 | 2013-11-28 | The Boeing Company | Providing a description of aircraft intent |
| CN103336863A (en) * | 2013-06-24 | 2013-10-02 | 北京航空航天大学 | Radar flight path observation data-based flight intention recognition method |
| CN103617749A (en) * | 2013-11-15 | 2014-03-05 | 中国航空无线电电子研究所 | Onboard system and method for managing land-air commands |
| CN104252797A (en) * | 2014-09-22 | 2014-12-31 | 北京航空航天大学 | Virtual controller-based airspace simulation method and device thereof |
| CN105679102A (en) * | 2016-03-03 | 2016-06-15 | 南京航空航天大学 | National flight flow space-time distribution prediction deduction system and method |
| CN110781757A (en) * | 2019-09-29 | 2020-02-11 | 中国航空无线电电子研究所 | Airport pavement foreign matter identification and positioning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114038242B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Morris et al. | Planning, scheduling and monitoring for airport surface operations | |
| Cobano et al. | Path planning based on genetic algorithms and the monte-carlo method to avoid aerial vehicle collisions under uncertainties | |
| Wu et al. | Multi UAV cluster control method based on virtual core in improved artificial potential field | |
| US20220415189A1 (en) | Decision assistance device and method for managing aerial conflicts | |
| Pechoucek et al. | Agent-based approach to free-flight planning, control, and simulation | |
| Rodionova et al. | Learning-to-fly: Learning-based collision avoidance for scalable urban air mobility | |
| Ryan et al. | A systems analysis of the introduction of unmanned aircraft into aircraft carrier operations | |
| Zhang et al. | Intelligent amphibious ground-aerial vehicles: State of the art technology for future transportation | |
| Clark et al. | Flight test results for UAVs using boid guidance algorithms | |
| Bueno et al. | Project AURORA: Towards an autonomous robotic airship | |
| Quan et al. | How far two UAVs should be subject to communication uncertainties | |
| Gillet et al. | Enhancement in realism of ATC simulations by improving aircraft behaviour models | |
| Chen et al. | Autonomous planning of optimal four-dimensional trajectory for real-time en-route airspace operation with solution space visualisation | |
| Ippolito et al. | An autonomy architecture for high-density operations of small uas in low-altitude urban environments | |
| Xiang et al. | Autonomous eVTOL: A summary of researches and challenges | |
| Liu et al. | Vision-guided planning and control for autonomous taxiing via convolutional neural networks | |
| CN114038242A (en) | Multi-agent-based large-scale aircraft motion simulation method and device | |
| Frontera et al. | Generation of aircraft intent based on a microstrategy search tree | |
| López Leonés et al. | Air-ground trajectory synchronization through exchange of aircraft intent information | |
| Enayatollahi et al. | PBN-based time-optimal terminal air traffic control using cellular automata | |
| Pérez Batlle et al. | Evaluation of separation strategies for unmanned aerial sytems | |
| KrisshnaKumar et al. | Fast Decision Support for Air Traffic Management at Urban Air Mobility Vertiports using Graph Learning | |
| Zhou et al. | A scalable cloud-based uav fleet management system | |
| Xie et al. | Hybrid AI-based Dynamic Re-routing Method for Dense Low-Altitude Air Traffic Operations | |
| Zeng et al. | Regulating arrival UAV flows between the AirMatrix and the droneport using a dynamic carousel circuit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |