CN114038242B - Large-scale aircraft motion simulation method and device based on multiple intelligent agents - Google Patents
Large-scale aircraft motion simulation method and device based on multiple intelligent agents Download PDFInfo
- Publication number
- CN114038242B CN114038242B CN202111367165.9A CN202111367165A CN114038242B CN 114038242 B CN114038242 B CN 114038242B CN 202111367165 A CN202111367165 A CN 202111367165A CN 114038242 B CN114038242 B CN 114038242B
- 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.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000011160 research Methods 0.000 abstract description 3
- 238000012795 verification Methods 0.000 abstract description 3
- 239000003795 chemical substances by application Substances 0.000 description 49
- 238000004364 calculation method Methods 0.000 description 14
- 230000000694 effects Effects 0.000 description 6
- 238000013519 translation Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 3
- 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
- 239000000446 fuel Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
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 comprise 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 intention instruction into reference flight state information which can be tracked by the aircraft; calculating the motion state information of the aircraft according to the configured flight performance parameters of the aircraft; and performing closed-loop simulation of the motion of the aircraft according to the error between the motion state information of the aircraft and the reference flight state information, and meeting the requirements of future air traffic management research simulation and verification, and the method is used for large-scale motion simulation of the aircraft.
Description
Technical Field
The application belongs to the technical field of air traffic, and particularly relates to a large-scale aircraft motion simulation method and device based on multiple intelligent agents.
Background
With the continuous rapid development of avionics technology, the aircraft gradually changes from a traditional controlled object to an important participant in air traffic management activities, so as to realize the coordination of the whole navigation process. In conventional air traffic simulation systems, aircraft are often considered as particles and motion simulation of the aircraft is greatly simplified. The aircraft motion simulation method in the traditional air traffic simulation system saves operation resources, but cannot meet the simulation and verification requirements of future air traffic management research.
Disclosure of Invention
In order to solve the problems in the related art, the application provides a large-scale aircraft motion simulation method and device based on multiple intelligent agents, wherein 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 intention instruction into reference flight state information which can be tracked by the aircraft;
calculating the motion state information of the aircraft according to the configured flight performance parameters of the aircraft;
and performing closed-loop simulation of the motion of the aircraft according to the error between the motion state information of the aircraft and the reference flight state information.
Wherein the configuring the 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 configuring flight performance parameters of the aircraft with the corresponding model through automatic table lookup according to the determined aircraft type and model, load and oil quantity information.
Wherein the generating flight intent instructions comprises:
and generating a first flight intention instruction meeting the 4D flight path constraint condition from the door to door of the aircraft according to the aircraft flight plan and the flight performance parameters of the aircraft.
Wherein the generating flight intent instructions comprises:
when an air traffic control instruction is received in the navigation process of the aircraft, a second flight intention instruction meeting the air traffic control is generated according to the air traffic control instruction and the configured aircraft flight performance parameter.
Wherein the generating flight intent instructions comprises:
when a possible traffic collision is predicted during the aircraft voyage, a third flight intent instruction is generated to achieve collision-free.
Wherein when a possible traffic collision is predicted during the aircraft voyage, generating a third flight intent instruction to achieve collision-free, comprising:
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 track of the aircraft agent based on the first flight intent instruction and the second flight intent instruction;
judging a space-time envelope of the possible traffic collision between the aircraft intelligent body and the surrounding aircraft according to the first short-term 4D flight path and the second short-term 4D flight path;
establishing a maneuvering action library conforming to the performance constraint of the aircraft according to the aircraft agent motion model, and searching an aircraft optimal maneuvering sequence capable of disengaging from the conflict space-time envelope by adopting a multi-layer search tree;
and determining an output result obtained after inputting the optimal maneuvering sequence of the aircraft into the aircraft agent motion model as a third flight intention instruction.
Wherein calculating aircraft motion state information according to the configured aircraft flight performance parameters comprises:
according to the configured flight performance parameters of the aircraft, selecting a corresponding type of aircraft dynamics model, and configuring aerodynamic and aircraft structure parameters of a corresponding model;
load and oil quantity are configured for the aircraft according to the flight plan;
classifying the aircraft intelligent bodies according to the aerodynamic and aircraft structural parameters and the flight performance parameters, comprehensively calculating resources of the classified aircraft intelligent bodies, calculating the motion state information of the aircraft intelligent bodies in batches, and generating the motion state information of the large-scale aircraft.
Wherein, according to the error between the aircraft motion state information and the reference flight state information, the closed loop simulation of the aircraft motion is performed, including:
calculating a flight state error between the aircraft motion state information and the reference flight state information;
inputting the flight state error information into an aircraft motion automatic controller, and calculating aircraft intelligent feedback control input parameters by adopting a multi-order PID mode;
and inputting the feedback control input parameters of the aircraft agent into the aircraft motion model to obtain aircraft agent flight path simulation data.
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 calculation 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 generating module generates a flight intention instruction;
the autonomous flight intention generating 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 motion of the aircraft according to the error between the motion state information of the aircraft output by the motion general resolving module and the reference flight state information output by the autonomous flight intention generating module.
The large-scale aircraft motion simulation method and device based on the multiple intelligent agents 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 which only consider space displacement, and the simulated aircraft is added to execute a navigation program according to the 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, and the simulated aircraft is added to track and reference the flight state information through the automatic control module, so that the closed-loop aircraft motion simulation is realized;
3) The aircraft in the simulation system facing the air traffic navigation is not a controlled object simply controlled by the 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 the air traffic management activity;
4) The aircraft motion simulation is distributed to corresponding aircraft motion calculation modules according to the types and the models of the aircraft, aircraft flight state information is calculated in batches, reusability of the simulation modules is improved, and 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 application;
FIG. 2 is a schematic flow chart of a method for generating autonomous flight intents of an aircraft according to the present application;
FIG. 3 is a schematic flow chart of a general calculation method for motion of an aircraft according to the present application;
fig. 4 is a schematic flow chart of an automatic control method for aircraft motion provided by the application.
Detailed Description
The application is described in further detail below with reference to specific embodiments and figures.
In order to make the readers more clearly understand the technical scheme of the application, a simple description is made on the multi-agent system.
The multi-agent system is an important branch of the distributed artificial intelligence (Distributed Artificial Intelligence), has autonomy, distributivity and coordination, self-organization 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, inter-communicating and coordinated, manageable systems.
In the application, the simulated aircraft motion simulation based on multiple agents regards each aircraft added into the simulation as an agent with sensing and decision making capability, can be used for simulating and verifying roles and actions of an advanced aircraft in air traffic management activities, and can evaluate and analyze the influence and efficiency improvement generated by the whole process of coordinating navigation in air navigation, thereby meeting the requirements of future air traffic management research simulation and verification.
The application provides a large-scale aircraft motion simulation method and device based on multiple intelligent agents, which can be used for simulating and verifying an advanced aircraft air traffic operation scene, improve the large-scale aircraft motion simulation efficiency and realize the flight path simulation of 1 to 2000 aircraft in the national airspace range.
The application provides a large-scale aircraft motion simulation method based on multiple intelligent agents, which is shown in fig. 1 and comprises the following steps:
step 110, configuring flight performance parameters of the aircraft according to the aircraft flight plan;
step 120, generating a flight intention instruction;
step 130, converting the generated flight intention instruction into reference flight state information which can be tracked by the aircraft;
step 140, calculating the motion state information of the aircraft according to the configured flight performance parameters of the aircraft;
and 150, performing closed-loop simulation of the motion of the aircraft according to the error between the motion state information of the aircraft and the reference flight state information.
Wherein configuring the 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 configuring flight performance parameters of the aircraft with the corresponding model through automatic table lookup according to the determined aircraft type and model, load and oil quantity information.
For example, converting the generated flight intent instructions into aircraft trackable reference flight status information may be:
according to the first flight intention instruction T eo (x，y，z，t 1 ，t 2 ) Current motion state parameters of aircraft (x 0 ，y 0 ，z 0 ) And calculating the time step delta t with the motion state of the aircraft, and calculating by a linear interpolation method to obtain the trackable reference flight state information of the aircraft.
Wherein generating the flight intent instructions may include three aspects,
in a first aspect, generating flight intent instructions includes:
and generating a first flight intention instruction meeting the 4D flight path constraint condition from the door to door of the aircraft according to the aircraft flight plan and the flight performance parameters of the aircraft.
In a second aspect, generating flight intent instructions includes:
when the air traffic control instruction is received in the navigation process of the aircraft, a second flight intention instruction meeting the air traffic control is generated according to the air traffic control instruction and the configured aircraft flight performance parameter.
In a third aspect, generating flight intent instructions includes:
when a possible traffic collision is predicted during the aircraft voyage, a third flight intent instruction is generated to achieve collision-free.
Specifically, when a possible traffic collision is predicted during the aircraft voyage, generating a third flight intent instruction to achieve collision-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 track of the aircraft agent based on the first flight intent instruction and the second flight intent instruction;
judging a space-time envelope of the possible traffic collision between the aircraft intelligent body and the surrounding aircraft according to the first short-term 4D flight path and the second short-term 4D flight path;
establishing a maneuvering action library conforming to the performance constraint of the aircraft according to the aircraft agent motion model, and searching an aircraft optimal maneuvering sequence capable of disengaging from the conflict space-time envelope by adopting a multi-layer search tree;
and determining an output result obtained after inputting the optimal maneuvering sequence of the aircraft into the aircraft agent motion model as a third flight intention instruction.
Wherein calculating aircraft motion state information according to the configured aircraft flight performance parameters comprises:
according to the configured flight performance parameters of the aircraft, selecting a corresponding type of aircraft dynamics model, and configuring aerodynamic and aircraft structure parameters of a corresponding model;
load and oil quantity are configured for the aircraft according to the flight plan;
classifying the aircraft intelligent bodies according to the aerodynamic and aircraft structural parameters and the flight performance parameters, comprehensively calculating resources of the classified aircraft intelligent bodies, calculating the motion state information of the aircraft intelligent bodies in batches, and generating the motion state information of the large-scale aircraft.
Wherein, according to the error between aircraft motion state information and the reference flight state information, carry out the closed loop simulation of aircraft motion, include:
calculating a flight state error between the aircraft motion state information and the reference flight state information;
inputting the flight state error information into an aircraft motion automatic controller, and calculating aircraft intelligent feedback control input parameters by adopting a multi-order PID mode;
and inputting the feedback control input parameters of the aircraft agent into the aircraft motion model to obtain aircraft agent flight path simulation data.
The application relates to a large-scale aircraft motion simulation method based on multiple intelligent agents, which utilizes the aircraft motion simulation system based on the multiple intelligent agents to simulate the motion of a large-scale aircraft, and specifically comprises the following steps:
the method comprises the steps that 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 performance parameters of the aircraft, and outputs the performance parameters to an autonomous flight intention generation module of the aircraft and a general motion calculation module of the aircraft;
b, an autonomous flight intention generating module of the aircraft generates a first flight intention instruction meeting 4D flight path constraint conditions from the door to door according to the aircraft flight plan and the input aircraft performance parameters; if the aircraft receives the air traffic control instruction in the sailing 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 parameter; when possible traffic collision is predicted in the sailing process, the module autonomously generates a third flight intention instruction for realizing collision-free; finally, translating the conflict-free flight intention instructions into reference flight state information which can be tracked by the aircraft, and sending the reference flight state information to an automatic control module of the movement of the aircraft as shown in fig. 2;
step C, an aircraft motion general calculation module selects a corresponding type of aircraft dynamics model according to the input aircraft flight performance parameters, configures corresponding type of aircraft dynamics and aircraft structure parameters, configures parameters such as load, oil quantity and the like for the aircraft according to a flight plan, calculates aircraft motion state information, and outputs the aircraft motion state information to an aircraft motion automatic control module as shown in figure 3;
and D, the aircraft motion automatic control module generates an aircraft motion input instruction through an automatic control law according to the error between the aircraft motion state information output by the aircraft motion general resolving module and the reference flight state information output by the aircraft autonomous flight intention generating module, and transmits the aircraft motion input instruction to the aircraft motion general resolving module to realize closed-loop simulation of the aircraft motion, as shown in fig. 4.
In the application, the configuration of the performance parameters of the aircraft 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 load and oil quantity information of the aircraft according to the flight plan;
and A3, the flight performance configuration module configures flight performance parameters of the aircraft with the corresponding model through automatic table lookup.
The aircraft flight intent instructions are generated according to the following method:
step B1, an autonomous flight intention generating module of the aircraft generates a global flight intention instruction of the intelligent agent of the aircraft according to the flight plan of the aircraft and the input performance parameters of the aircraft;
wherein, the flight plan refers to providing information about the completion of one flight of the aircraft to an air traffic service unit. The basic components of the flight plan include the origin and destination airports, voyage waypoints and routes, voyage categories, cruising altitude, carried fuel, etc. And B1, a flight plan translation sub-module in the autonomous flight intention generation module of the aircraft recognizes flight plan texts in a standard format and translates the flight plan texts into flight intention instructions readable by an aircraft motion simulation system. The flight intention instruction gives reference motion state information of the aircraft transitioning from the current motion state to the target motion state, and the reference motion state information is used as input of the step D to drive the aircraft agent to generate a flight track.
The working principle of the flight plan translation submodule is that a flight plan file is read, a flight plan keyword and a parameter value are positioned and identified, and the flight plan keyword and the parameter value are input 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. Generating a reference path R according to the start-end state item, the space constraint item and the performance constraint item plan for each flight stage i (x, y, z), where i is the index number and x, y, z is the spatial coordinates. Generating a tracking reference path R according to time constraint terms for each flight phase i Reference motion state information of (a), i.e. flight intention instruction T et (x，y，z，t 1 ，t 2 ) Wherein t is 1 For the start time, t 2 Is the first endpoint time. The specific implementation steps are as follows:
reading the flight plan of the aircraft, and splitting the flight phase into 6 phases of sliding out and taking off, leaving a field, operating a route, entering the field, landing and sliding in;
in the stage of sliding out and taking off, the virtual taxi path R of the aircraft intelligent body is planned and generated by taking the taxi path point position parameter, airport scene taxi track and runway geometric data, airport building position and geometric parameter specified by a flight plan as space constraint, taking the release scheduling moment as time constraint and taking the aircraft performance parameter as performance constraint 1 (x, y, z). Generating aircraft taxiing intention among nodes by taking taxiing waiting positions as nodes and taking aircraft performance parameters as constraints according to scene taxiing rulesInstruction T e1 (x，y，z，t 1 ，t 2 )；
In the departure stage, a departure program specified by a flight plan is taken as a space constraint, departure sequencing is taken as a time constraint, an aircraft performance parameter is taken as a performance constraint, and a virtual departure path R of the aircraft agent is planned and generated 2 (x, y, z). Generating an aircraft departure intention instruction T by taking aircraft performance parameters as constraints according to an departure program e2 (x，y，z，t 1 ，t 2 )；
In the course operation stage, a virtual sailing operation path R of an aircraft intelligent agent is planned and generated by taking a course section specified by a flight plan as a space constraint, RTA specified by the flight plan as a time constraint and an aircraft performance parameter as a performance constraint 3 (x, y, z). Generating an aircraft departure intention instruction T by taking aircraft performance parameters as constraints according to an air route operation rule e3 (x，y，z，t 1 ，t 2 )；
In the approach stage, an approach program specified by a flight plan is taken as a space constraint, approach sequence is taken as a time constraint, and an aircraft performance parameter is taken as a performance constraint, so that a virtual approach path R of the aircraft intelligent body is planned and generated 4 (x, y, z). Generating an aircraft approach intent instruction T by taking aircraft performance parameters as constraints according to an approach program e4 (x，y，z，t 1 ，t 2 )；
In the landing stage, a landing program specified by a flight plan is taken as a space constraint, and an aircraft performance parameter is taken as a performance constraint, so that a virtual landing path R of the aircraft intelligent body is planned and generated 5 (x, y, z). Generating an aircraft landing intention instruction T by taking aircraft performance parameters as constraints according to a landing program e5 (x，y，z，t 1 ，t 2 )；
In the sliding-in stage, the virtual sliding path R of the aircraft intelligent body is planned and generated by taking the position parameters of sliding path points, airport surface sliding ways, runway geometric data and airport building positions and geometric parameters specified by a flight plan as space constraints and taking the performance parameters of the aircraft as performance constraints 6 (x, y, z). According to the rules of the scene sliding,generating an aircraft taxi intention instruction T between nodes by taking taxi waiting positions as nodes and taking aircraft performance parameters as constraints e6 (x，y，z，t 1 ，t 2 )；
Combining the flight intentions of the aircraft at each navigation stage to generate a first flight intention instruction T of the aircraft agent eo (x，y，z，t 1 ，t 2 )；
Step B2, an autonomous flight intention generating module of the aircraft judges whether the aircraft agent receives an air traffic control instruction;
step B3, if the aircraft agent 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 parameter;
receiving a control instruction, and converting the control instruction into a standard format control intention instruction T according to a control rule base o (x，y，z，t 1 ，t 2 ) Generating a second aircraft intention instruction T based on the control instruction with the aircraft performance parameter as a constraint eo (x，y，z，t 1 ，t 2 )；
Step B4, an autonomous flight intention generating module of the aircraft predicts a first short-term 4D track L of surrounding traffic according to air traffic situation information around the aircraft intelligent body st (x，y，z，t 1 ，t 2 ) Wherein t is 3 Is the second endpoint time;
step B5, the autonomous flight intention generating module of the aircraft predicts a short-term 4D track of the intelligent agent of the aircraft by combining the flight intention instruction generated in the step B1 and the step B3;
fusion aircraft agent global flight intent instruction T eo (x，y，z，t 1 ，t 2 ) And aircraft intent instruction T based on regulatory instructions eo (x，y，z，t 1 ，t 2 ) Estimating a second short-term 4D track L of the aircraft agent sa (x，y，z，t 1 ，t 2 )；
Step B6, the autonomous flight intention generating module of the aircraft prejudges the possible traffic conflict between the aircraft agent and surrounding aircraft;
according to L sa (x，y，z，t 1 ，t 2 ) And L is equal to st (x，y，z，t 1 T 2) judging the space-time envelope of the possible traffic collision between the aircraft intelligent agent and the surrounding aircraft.
Step B7, an autonomous flight intention generating module of the aircraft adopts a multilayer search tree method based on a maneuver library to generate a flight intention instruction of the aircraft agent for breaking away from conflict;
according to an aircraft agent motion model, a maneuvering motion library conforming to aircraft performance constraint is established, and a multilayer search tree is adopted to search an aircraft optimal maneuvering sequence A capable of being separated from a conflict envelope l (K，t 1 ，t 2 ) Where K is a maneuver instruction, generating a deconflict aircraft third intent instruction T ea (x，y，z，t 1 ，t 4 ) Wherein t is 4 Is the third endpoint time.
And step B8, the autonomous flight intention generation module of the aircraft translates the conflict-resolved flight intention instructions into trackable reference flight state information of the intelligent agent of the aircraft.
The motion state calculation of the batch aircrafts is realized according to the following method:
step C1, an aircraft motion general calculation module selects a corresponding type of aircraft dynamics model according to the input aircraft flight performance parameters, and configures aerodynamic and aircraft structure parameters of a corresponding model;
step C2, an aircraft motion general resolving module configures parameters such as load, oil quantity and the like for the aircraft according to a flight plan;
and C3, classifying the aircraft agents according to the input parameters by the general calculation module for the movement of the aircraft agents, comprehensively calculating resources, calculating the movement state information of the aircraft agents in batches, and generating large-scale movement state information of the aircraft.
The automatic control of the motion of the aircraft is realized according to the following method:
step D1, inputting the aircraft motion state information output by the aircraft motion general resolving module to an aircraft motion automatic control module;
step D2, inputting the reference flight state information output by the autonomous flight intention generating module of the aircraft to the automatic motion control module of the aircraft;
step D3, an aircraft motion automatic control module calculates errors between the aircraft motion state information and the reference flight state information;
step D4, the aircraft motion automatic control module inputs the flight state error information to the aircraft motion automatic controller, and a multi-order PID method is adopted to calculate the feedback control input parameters of the aircraft intelligent body;
and D5, the automatic control module for the movement of the aircraft inputs the control input parameters to the general calculation module for the movement of the aircraft, so that the closed-loop automatic control of the aircraft agent is realized, and the flight path simulation data of the aircraft agent are generated.
The application also provides a large-scale aircraft motion simulation device based on multiple intelligent agents, which comprises: a flight performance configuration module, an autonomous flight intention generation module, a motion automatic control module and a motion general calculation 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 generating module generates a flight intention instruction;
the autonomous flight intention generating 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 motion of the aircraft according to the error between the motion state information of the aircraft output by the motion general resolving module and the reference flight state information output by the autonomous flight intention generating module.
The autonomous flight intention generation module of the aircraft comprises the following submodules:
the flight plan translation module is used for identifying 4D flight path constraint conditions of the aircraft in the flight stages of pushing out, taxiing, taking off, climbing, cruising, descending, approaching, landing, taxiing, leaning on a bridge and the like according to the aircraft flight plan, and translating and generating flight intention instructions meeting the flight plan space-time constraint according to the input aircraft flight performance parameters;
the control instruction translation module translates and generates a flight intention instruction meeting air traffic control according to an air traffic control instruction received by the aircraft in a flight stage and the input aircraft flight performance parameter;
the traffic situation awareness module predicts short-term 4D tracks of surrounding traffic according to air traffic situation information around the aircraft, predicts short-term 4D tracks of the aircraft by combining the generated flight intention instructions, predicts possible traffic conflicts, and autonomously generates flight intention instructions without conflicts;
and the flight intention translation module translates and generates reference flight state information which can be tracked by the aircraft according to the flight intention instruction generated by the submodule and sends the reference flight state information to the general aircraft movement calculation module.
The large-scale aircraft motion simulation method and device based on the multiple intelligent agents 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 which only consider space displacement, and the simulated aircraft is added to execute a navigation program according to the 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, and the simulated aircraft is added to track and reference the flight state information through the automatic control module, so that the closed-loop aircraft motion simulation is realized;
the aircraft in the simulation system facing the air traffic navigation is not a controlled object simply controlled by the 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 the air traffic management activity;
the aircraft motion simulation is distributed to corresponding aircraft motion calculation modules according to the types and the models of the aircraft, aircraft flight state information is calculated in batches, reusability of the simulation modules is improved, and aircraft motion simulation efficiency is improved.
The foregoing has outlined rather broadly the more detailed description of the application in order that the detailed description thereof that follows may be better understood, and in order that the present application may be better understood. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application.
Claims (4)
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 intention instruction into reference flight state information which can be tracked by the aircraft;
calculating the motion state information of the aircraft according to the configured flight performance parameters of the aircraft;
performing closed-loop simulation of the motion of the aircraft according to the error between the motion state information of the aircraft and the reference flight state information;
the configuration of the 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; according to the determined aircraft category and model, load and oil quantity information, configuring flight performance parameters of the aircraft with the corresponding model through automatic table lookup;
the generating flight intent instructions includes: generating a first flight intention instruction meeting 4D flight path constraint conditions from the door to door of the aircraft according to the aircraft flight plan and the flight performance parameters of the aircraft;
when the generated flight intention instruction is converted into the reference flight state information which can be tracked by the aircraft, calculating a time step according to the first flight intention instruction, the current motion state parameter of the aircraft and the motion state of the aircraft, and obtaining the reference flight state information which can be tracked by the aircraft through a linear interpolation method;
calculating aircraft motion state information according to the configured aircraft flight performance parameters, including: according to the configured flight performance parameters of the aircraft, selecting a corresponding type of aircraft dynamics model, and configuring aerodynamic and aircraft structure parameters of a corresponding model; load and oil quantity are configured for the aircraft according to the flight plan; classifying the aircraft intelligent bodies according to the aerodynamic and aircraft structural parameters and the flight performance parameters, comprehensively calculating resources of the classified aircraft intelligent bodies, calculating the motion state information of the aircraft intelligent bodies in batches, and generating large-scale aircraft motion state information;
the performing closed-loop simulation of the aircraft motion according to the error between the aircraft motion state information and the reference flight state information comprises the following steps: calculating a flight state error between the aircraft motion state information and the reference flight state information; inputting the flight state error information into an aircraft motion automatic controller, and calculating aircraft intelligent feedback control input parameters by adopting a multi-order PID mode; and inputting the feedback control input parameters of the aircraft agent into the aircraft motion model to obtain aircraft agent flight path simulation data.
2. The method of claim 1, wherein the generating the flight intent instruction comprises:
when an air traffic control instruction is received in the navigation process of the aircraft, a second flight intention instruction meeting the air traffic control is generated according to the air traffic control instruction and the configured aircraft flight performance parameter.
3. The method of claim 2, wherein the generating the flight intent instruction comprises:
when a possible traffic collision is predicted during the aircraft voyage, a third flight intent instruction is generated to achieve collision-free.
4. A method according to claim 3, wherein generating a third flight intent instruction to achieve collision-free when a possible traffic collision is predicted during the aircraft voyage 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 track of the aircraft agent based on the first flight intent instruction and the second flight intent instruction;
judging a space-time envelope of the possible traffic collision between the aircraft intelligent body and the surrounding aircraft according to the first short-term 4D flight path and the second short-term 4D flight path;
establishing a maneuvering action library conforming to the performance constraint of the aircraft according to the aircraft agent motion model, and searching an aircraft optimal maneuvering sequence capable of disengaging from the conflict space-time envelope by adopting a multi-layer search tree;
and determining an output result obtained after inputting the optimal maneuvering sequence of the aircraft into the aircraft agent motion model as a third flight intention instruction.
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 CN114038242A (en) | 2022-02-11 |
| CN114038242B true 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2482269B1 (en) * | 2011-01-28 | 2017-03-22 | The Boeing Company | Providing data for predicting aircraft trajectory |
| EP2667274A1 (en) * | 2012-05-24 | 2013-11-27 | The Boeing Company | Method for providing a description of aircraft intent using a decomposition of flight intent into flight segments |
-
2021
- 2021-11-18 CN CN202111367165.9A patent/CN114038242B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|---|
| CN114038242A (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sastry et al. | Hybrid control in air traffic management systems | |
| Granger et al. | Optimal resolution of en route conflicts | |
| CN112818599B (en) | Air control method based on reinforcement learning and four-dimensional track | |
| US20220415189A1 (en) | Decision assistance device and method for managing aerial conflicts | |
| Wang et al. | Virtual reality technology of multi uavearthquake disaster path optimization | |
| Rodionova et al. | Learning-to-fly: Learning-based collision avoidance for scalable urban air mobility | |
| Toratani | Study on simultaneous optimization method for trajectory and sequence of air traffic management | |
| Hentati et al. | Cooperative UAVs framework for mobile target search and tracking | |
| Ryan et al. | A systems analysis of the introduction of unmanned aircraft into aircraft carrier operations | |
| Preis et al. | Ground operation on vertiports–introduction of an agent-based simulation framework | |
| Degas et al. | Cooperative multi-agent model for collision avoidance applied to air traffic management | |
| Clark et al. | Flight test results for UAVs using boid guidance algorithms | |
| CN110347035A (en) | Method for autonomous tracking and device, electronic equipment, storage medium | |
| Chen et al. | Autonomous planning of optimal four-dimensional trajectory for real-time en-route airspace operation with solution space visualisation | |
| Sáez et al. | A fast and flexible emergency trajectory generator enhancing emergency geometric planning with aircraft dynamics | |
| CN114038242B (en) | Large-scale aircraft motion simulation method and device based on multiple intelligent agents | |
| 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 | |
| Guo et al. | Research on multi-UAV formation and semi-physical simulation with virtual structure | |
| Frontera et al. | Generation of aircraft intent based on a microstrategy search tree | |
| Başpinar et al. | Mission planning and control of multi-aircraft systems with signal temporal logic specifications | |
| López Leonés et al. | Air-ground trajectory synchronization through exchange of aircraft intent information | |
| Mettler et al. | Receding horizon trajectory planning with an environment-based cost-to-go function | |
| Erzberger et al. | Concepts and algorithms for terminal-area traffic management | |
| Lunlong et al. | Analysis of requirements and architecture of the next generation flight management system |
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 |