CN112506218A - Reentry aircraft any no-fly-off area fly-around method based on intelligent trajectory prediction - Google Patents

Reentry aircraft any no-fly-off area fly-around method based on intelligent trajectory prediction Download PDF

Info

Publication number
CN112506218A
CN112506218A CN202011331200.7A CN202011331200A CN112506218A CN 112506218 A CN112506218 A CN 112506218A CN 202011331200 A CN202011331200 A CN 202011331200A CN 112506218 A CN112506218 A CN 112506218A
Authority
CN
China
Prior art keywords
aircraft
fly
fly zone
track
flight
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
Application number
CN202011331200.7A
Other languages
Chinese (zh)
Other versions
CN112506218B (en
Inventor
张旭辉
李永远
惠俊鹏
陈海鹏
孙光
宋盛菊
杨旸
刘焱飞
郑雄
刘丙利
王浩亮
高朝辉
姚星合
康磊晶
赵大海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Academy of Launch Vehicle Technology CALT
Original Assignee
China Academy of Launch Vehicle Technology CALT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Academy of Launch Vehicle Technology CALT filed Critical China Academy of Launch Vehicle Technology CALT
Priority to CN202011331200.7A priority Critical patent/CN112506218B/en
Publication of CN112506218A publication Critical patent/CN112506218A/en
Application granted granted Critical
Publication of CN112506218B publication Critical patent/CN112506218B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Pure & Applied Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Medical Informatics (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Mathematical Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)

Abstract

A reentry aircraft arbitrary no-fly zone detouring method based on intelligent trajectory prediction provides a reentry aircraft trajectory rapid prediction method, a prediction trajectory and no-fly zone relation rapid determination method and aircraft inclination angle symbol selection logic aiming at the characteristic that the attack angle and the inclination angle of a reentry aircraft cannot be changed, and guides the aircraft to detour around the no-fly zone of any shape by changing the symbols of the aircraft inclination angles. The invention enables the reentry aircraft to fly around the no-fly area with any shape, thereby avoiding the step of preprocessing the irregular no-fly area and enabling the autonomy of the aircraft to be higher; meanwhile, the defect that the flying area of the aircraft is enlarged due to the fact that the irregular no-fly zone is processed is avoided, and the aircraft has larger residual flying capacity after the flying area is processed. The method has small calculation amount and is suitable for the online use of the aircraft.

Description

Reentry aircraft any no-fly-off area fly-around method based on intelligent trajectory prediction
Technical Field
The invention relates to a reentry vehicle arbitrary no-fly zone around-fly method based on intelligent trajectory prediction, and belongs to the technical field of guidance and control.
Background
The reentry aircraft has various execution tasks and complex flight environment, and may be threatened by weather, enemy interception weapons and the like in the flight process. In order to ensure the flight safety of the aircraft, the threat areas are usually defined as no-fly areas, and the flight tracks are adjusted to enable the aircraft to bypass the no-fly areas. These no-fly zones are often complex and irregular in shape and difficult to interpret analytically. At present, the no-fly zone is often regarded as a standard circle, although the process of penetration is simplified, the no-fly zone around the aircraft is larger than the actual no-fly zone, and the capacity loss of the aircraft is caused.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method is characterized in that a reentry aircraft trajectory rapid prediction method, a prediction trajectory and forbidden flight area relation rapid determination method and aircraft inclination angle symbol selection logic are provided aiming at the characteristic that the attack angle and the inclination angle of a reentry aircraft cannot be changed, and the aircraft is guided to fly around forbidden flight areas of any shapes by changing the symbol of the aircraft inclination angle. The invention enables the reentry aircraft to fly around the no-fly area with any shape, thereby avoiding the step of preprocessing the irregular no-fly area and enabling the autonomy of the aircraft to be higher; meanwhile, the defect that the flying area of the aircraft is enlarged due to the fact that the irregular no-fly zone is processed is avoided, and the aircraft has larger residual flying capacity after the flying area is enlarged. The method has small calculation amount and is suitable for the online use of the aircraft.
The purpose of the invention is realized by the following technical scheme:
a reentry aircraft arbitrary no-fly zone fly-around method based on intelligent trajectory prediction comprises the following steps:
s1, establishing a reentry aircraft flight dynamics model;
s2, selecting different initial parameters of the aircraft, setting an attack angle and a roll angle at the same time, and simulating by using the flight dynamics model of S1 to obtain the terminal position of the aircraft; the initial parameters comprise height, speed, longitude, latitude, track angle and course angle;
s3, taking initial parameters, an attack angle, a roll angle and time of the aircraft as input, taking the terminal position of the aircraft as output, and training by adopting a BP neural network to obtain a trained neural network model;
s4, determining the position of the no-fly zone; predicting a flight track by using the trained neural network model according to the current attack angle and the current roll angle of the aircraft;
and S5, judging the position relation between the flight track and the no-fly zone, and adjusting the roll angle of the aircraft when the aircraft is influenced by the no-fly zone.
According to the reentry vehicle arbitrary no-fly zone fly-around method based on intelligent trajectory prediction, preferably, the no-fly zone is in an irregular shape.
In the above-mentioned reentry vehicle approach to the no-fly zone based on the intelligent prediction of the trajectory, preferably, in S2, the attack angle and the roll angle are both functions with the speed as an independent variable.
Preferably, in S4, according to the longitude and latitude information of the no-fly zone, the position information of the no-fly zone in the geocentric coordinate system is calculated, and then according to the transformation matrix between the geocentric coordinate system and the aircraft position coordinate system, the coordinate information of the no-fly zone in the aircraft position coordinate system is calculated, that is, the position of the no-fly zone is determined.
In the above method for winding around the reentry vehicle in any no-fly zone based on intelligent trajectory prediction, preferably, in S4, the method for predicting the flight trajectory by using the trained neural network model includes:
s41, acquiring the current altitude, speed, longitude, latitude, track angle and course angle of the aircraft;
s42, setting the flight time of the aircraft;
and S43, taking the current altitude, speed, longitude, latitude, track angle, course angle of the aircraft and the flight time of the aircraft as input parameters, and predicting the flight track by using the trained neural network model.
In the above method for reentry of the aircraft to go around the flight in any no-flight-restricted area based on the intelligent prediction of the trajectory, preferably, in S5, the position relationship between the flight trajectory and the no-flight-restricted area is determined, and when the aircraft is affected by the no-flight-restricted area, the method for adjusting the roll angle of the aircraft is as follows:
s51, the flight path is approximately a segment of circular arc relative to the earth radius, and the current position of the aircraft is a path starting point pSThe other end of the arc is a track end point pEThe no-fly zone is represented by a plurality of characteristic points which are connected in sequence; calculating the distances between the track end point and all the characteristic points of the no-fly area; selecting the characteristic point p with the minimum distance and two characteristic points p connected with the point p1And p2；
S52, calculating a line segment p1p、p2p、pSp、pEThe angle of p with respect to the reference direction is respectively noted
Figure BDA0002795884420000031
Figure BDA0002795884420000032
S53, if
Figure BDA0002795884420000033
Is at the size of
Figure BDA0002795884420000034
And
Figure BDA0002795884420000035
in between, the arc end point is in the no-fly zone; otherwise, the track end point is outside the no-fly zone;
s54, if the track end point is outside the no-fly zone, recording the flight time t of the aircraft at the moment, and switching to S57, otherwise, switching to S55;
s55, calculating the track end point relative to the line segment p1p、p2Selecting a smaller value as the distance of the aircraft relative to the no-fly zone, and recording as d;
s56, adjusting the track prediction time t by adopting a dichotomy, and calculating the corresponding track end point position p'ERepeating S52-S55 to determine the distance d 'of the aircraft relative to the no-fly zone after the track prediction time is adjusted until d' is smaller than a set threshold value delta d;
s57, determining the track prediction time t when the track intersects with the no-fly zone⊥＝t′；
S58, setting track prediction threshold tthresholdComparing the time t when the trajectory intersects the no-fly zone⊥1And t⊥2And tthresholdThe magnitude relationship of (1); if t⊥1And t⊥2Are all greater than tthresholdThe aircraft keeps flying at the current roll angle; if t⊥1And t⊥2At least one of which is less than tthresholdThen aircraft follows t⊥1And t⊥2The larger of which determines the roll angle sign.
Compared with the prior art, the invention has the following beneficial effects:
aiming at the characteristic that the attack angle and the roll angle of the reentry vehicle cannot be changed, the method designs a reentry vehicle track rapid prediction method, a prediction track and no-fly zone relation rapid determination method and vehicle roll angle symbol selection logic, and guides the vehicle to fly around the no-fly zone with any shape by changing the symbol of the roll angle of the vehicle. The invention enables the reentry aircraft to fly around the no-fly area with any shape, thereby avoiding the step of preprocessing the irregular no-fly area and enabling the autonomy of the aircraft to be higher; meanwhile, the defect that the flying-around area of the aircraft is enlarged due to the fact that irregular flying-off forbidden areas are processed is avoided, and the aircraft has larger residual flying capacity after flying-around flying-off forbidden areas. The method has small calculation amount and is suitable for the online use of the aircraft.
Drawings
Fig. 1 is a flowchart of a method for winding around any no-fly zone according to the present invention;
FIG. 2 is a schematic diagram of a method for fast track prediction according to the present invention;
fig. 3 is a schematic diagram of a method for determining a position relationship between an aircraft position and a no-fly zone according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1 and 2, the reentry aircraft arbitrary no-fly zone detouring method based on trajectory intelligent prediction can be divided into two modules, namely trajectory intelligent prediction network offline training and arbitrary no-fly zone online detouring.
The off-line training module of the intelligent trajectory prediction network comprises the following steps:
step 1: determining parameters of the reentry vehicle, and establishing a flight dynamics model of the reentry vehicle;
step 2: setting different positions, speeds, attack angles, inclination angles and flight times of the aircrafts according to the parameters of the reentry vehicles, namely setting different parameter values, and performing simulation to obtain flight trajectories of a series of aircrafts to be used as training samples;
and step 3: and training the sample by adopting a BP neural network, taking the state, the attack angle, the inclination angle and the time of the aircraft as input, and taking the predicted position of the aircraft as output.
Further, the reentry vehicle dynamics model of step 1 is
Figure BDA0002795884420000051
Figure BDA0002795884420000052
Figure BDA0002795884420000053
Figure BDA0002795884420000054
Figure BDA0002795884420000055
Figure BDA0002795884420000056
Where, is the derivation, α is the angle of attack, R is the earth's center radius, and its dimensionless parameter is the earth's radius R06378 km; theta and phi are longitude and latitude respectively; v is the aircraft speed, with dimensionless parameters of
Figure RE-GDA0002885817960000057
And g is0＝9.81m/s2(ii) a Gamma is a flight path angle and is an included angle between a speed vector and the local horizontal plane; psi is the heading angle, measured clockwise from the true north of the locality; sigma is a roll angle;
Figure RE-GDA0002885817960000058
is time, with a dimensionless parameter of
Figure RE-GDA0002885817960000059
Omega is the rotational angular velocity of the earth, and the dimensionless parameter is
Figure RE-GDA00028858179600000510
P＝Feng/mg0Is the thrust acceleration of the solid pulse engine; nondimensionalized drag acceleration D ═ ρ (V)cV)2SrefCD/(2mg0)，CDFor damping coefficient, lift acceleration L ═ ρ (V)cV)2SrefCL/(2mg0)，CLIs the coefficient of lift, where ρ is the atmospheric density, SrefIs the reference area and m is the aircraft mass.
Further, the sample construction method in step 2 comprises:
setting the value range of initial state variables (height, speed, longitude, latitude, track angle, course angle and flight time), and uniformly selecting state points from the value range as initial states.
Angle of attack and roll angle are designed as a function of speed
Figure BDA00027958844200000511
Figure BDA0002795884420000061
In the formula, V1、Vmid、V2、αmax、σmidDetermined from aircraft characteristics and flight profile, where V1、 Vmid、V2All according to the aerodynamic characteristics of the aircraft, the switching speed of the attack angle profile is selected, and V is the task of rail reentry1The value of (A) is 5500-6000 m/s, V2The value of (A) is between 2000 and 3000m/s, VmidThe value of (a) is 4000-5000 m/s; alpha is alphamaxIs the maximum available angle of attack, alpha, of the aircraftL/DmaxThe maximum lift-drag ratio attack angle of the aircraft is obtained; sigmamidThe switching point roll angle, typically taken as σmid＝45°、σ1To the initial flight roll angle, σ1＝60～80、σ1For end flight roll angle, σ2＝20-40。
And thirdly, simulating by using the initial condition, the attack angle and the roll angle section shown in the formulas (2) and (3), and storing an initial state and the aircraft terminal position to form a training sample, wherein the initial state is sample input, and the aircraft terminal position is sample output.
The online fly-around module of any no-fly zone comprises the following four steps:
step 10: calculating the position information of the no-fly zone under the geocentric coordinate system according to the longitude and latitude information of the no-fly zone, and calculating the coordinate information of the no-fly zone in the position coordinate system of the aircraft according to a conversion matrix between the geocentric coordinate system and the position coordinate system of the aircraft;
step 20: according to the current attack angle and the current roll angle of the aircraft, quickly predicting the flight track by using an offline-trained neural network;
step 30: judging whether the estimated aircraft track intersects with the no-fly zone or not and the intersection time of the estimated aircraft track and the no-fly zone, and analyzing the influence degree of the aircraft on the no-fly zone as a basis for judging the inclination angle symbol;
step 40: and according to a set inclination angle symbol judgment rule, deciding the inclination angle symbol of the aircraft, and guiding the aircraft to bypass the no-fly zone.
Further, the coordinate system in step 10 is defined as:
firstly, the geocentric coordinate system OE-XEYEZE: origin OELocated in the earth's center, OEXEAxis pointing to spring equinox, OEZEAxial north pole, OEYEThe axis and the other two axes form a right-hand coordinate system;
position coordinate system OP-XPYPZP: origin OPAt the center of mass of the aircraft, OPXPThe axis points to the north, OPYPThe axis points along the geocentric radial direction to the sky, OPZPThe axes and the other two axes form a right-hand coordinate system pointing east.
Further, the method for solving the coordinates of the geocentric coordinate system according to the longitude and latitude comprises
Figure BDA0002795884420000071
Wherein R iseIs the earth radius, phi is latitude, and theta is longitude.
Further, the conversion method from the geocentric coordinate system to the position coordinate system is
Figure BDA0002795884420000072
Wherein phipAnd ΘpRespectively, the longitude and latitude of the aircraft's center of mass. L (phi)p,Θp) In the form of
Figure BDA0002795884420000073
For the irregular no-fly zone, the irregular no-fly zone is usually represented by a series of discrete characteristic points, and for each discrete point, the coordinates of the discrete point in the aircraft position coordinate system are obtained according to the conversion method.
Further, the specific method for quickly predicting the flight trajectory in step 20 is as follows:
firstly, acquiring the motion state of the current aircraft, including position, speed, track angle and course angle;
setting the flight time of the aircraft;
and thirdly, inputting the parameters into the trained neural network to obtain the output aircraft terminal position.
Further, the specific method for analyzing the threat situation of the aircraft in step 30 is (as shown in fig. 3):
calculating the distance between the track prediction end point and each characteristic point of the no-fly zone, selecting the characteristic point with the minimum distance, and recording the characteristic point as p, and recording two adjacent characteristic points as p1And p2. Note that the starting point of the track is pSEnd point is pE。
② calculating the line segment p1p、p2p、pSp、pEp is relative to a reference direction (the reference direction being the true north direction, i.e. O of the position coordinate system)PXPAxis) of the shaft, respectively
Figure BDA0002795884420000081
And thirdly, judging the relationship between the track end point and the no-fly area according to the size of the angle. If it is
Figure BDA0002795884420000082
Is at the size of
Figure BDA0002795884420000083
And
Figure BDA0002795884420000084
if the track end point is in the no-fly zone, the track end point is in the no-fly zone; otherwise, the track endsOutside the no-fly zone.
And fourthly, if the terminal point of the track is not in the no-fly area, recording the flight time t of the aircraft at the moment, and executing the seventh step, otherwise, executing the fifth step.
If the track end point is in the no-fly zone, calculating the track end point relative to the line segment p1p、p2And selecting a smaller value as the distance of the aircraft relative to the no-fly zone, and recording the distance as d.
Sixthly, changing the track prediction time t by using a dichotomy method, and calculating the corresponding track end point position p'EAnd repeating the process to solve the distance d 'relative to the no-fly area until the distance d' is smaller than the set threshold value deltad.
Recording the time t for evaluating the threat level of the aircraft⊥And t' (i is 1,2, i is 1 corresponding to the track with the positive sign of the roll angle, i is 2 corresponding to the track with the negative sign of the roll angle), and the analysis of the threat situation of the aircraft is finished.
Furthermore, the sizes of the attack angle and the roll angle of the aircraft are determined during the track design, and cannot be changed, and the lateral track of the aircraft can be changed only by changing the sign of the roll angle, so that the aircraft bypasses a no-fly zone. The specific method for judging the aircraft roll angle symbol in the fourth step is as follows:
setting a track prediction time threshold tthreshold(0＜tthreshold) Comparing the time t when the trajectory intersects the no-fly zone⊥1And t⊥2And tthresholdThe magnitude relationship of (1);
if t⊥1And t⊥2Are all greater than tthresholdIf the aircraft keeps the current roll angle flight, the current flight roll angle sign is changed;
③ if t⊥1And t⊥2At least one of which is less than tthresholdThen aircraft follows t⊥1And t⊥2The larger of which determines the roll angle sign. If the original direction is t predicted⊥1And t⊥2If the smaller direction is consistent, the current inclination angle symbol needs to be multiplied by-1, and the current flight direction needs to be changed; otherwise, it is multiplied by 1.
The invention provides a method for quickly predicting an aircraft track, a method for quickly judging the relation between a predicted track and a no-fly zone and aircraft inclination angle symbol selection logic, aiming at the defect that the existing reentry aircraft can only go around a no-fly zone with a regular shape. The capability of the reentry aircraft to autonomously detour the no-fly zone and the residual flight capability after the reentry aircraft detours the no-fly zone are effectively improved.
Those skilled in the art will appreciate that those matters not described in detail in the present specification are well known in the art.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to limit the present invention, and those skilled in the art can make variations and modifications of the present invention without departing from the spirit and scope of the present invention by using the methods and technical contents disclosed above, and therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are within the protection scope of the present invention.

Claims (6)

1. A reentry aircraft arbitrary no-fly zone fly-around method based on intelligent trajectory prediction is characterized by comprising the following steps:
s1, establishing a reentry aircraft flight dynamics model;
s2, selecting different initial parameters of the aircraft, setting an attack angle and a roll angle at the same time, and simulating by using the flight dynamics model of S1 to obtain the terminal position of the aircraft; the initial parameters comprise height, speed, longitude, latitude, track angle and course angle;
s3, taking initial parameters, an attack angle, a roll angle and time of the aircraft as input, taking the terminal position of the aircraft as output, and training by adopting a BP neural network to obtain a trained neural network model;
s4, determining the position of the no-fly zone; predicting a flight track by using the trained neural network model according to the current attack angle and the current roll angle of the aircraft;
and S5, judging the position relation between the flight track and the no-fly zone, and adjusting the roll angle of the aircraft when the aircraft is influenced by the no-fly zone.
2. The method for winding any no-fly-off area of the reentry vehicle based on intelligent trajectory prediction as claimed in claim 1, wherein the no-fly-off area is irregular.
3. The method for winding the flight in any no-fly-zone of the reentrant aircraft based on the intelligent prediction of the track as claimed in claim 1, wherein in S2, the attack angle and the roll angle are both functions with speed as an independent variable.
4. The method according to claim 1, wherein in S4, the position information of the no-fly zone in the geocentric coordinate system is calculated according to the latitude and longitude information of the no-fly zone, and the coordinate information of the no-fly zone in the aircraft position coordinate system is calculated according to the transformation matrix between the geocentric coordinate system and the aircraft position coordinate system, so as to determine the position of the no-fly zone.
5. The method for winding the flight in any no-fly-off area of the reentry aircraft based on the intelligent prediction of the trajectory as claimed in claim 1, wherein in S4, the method for predicting the flight trajectory by using the trained neural network model comprises:
s41, acquiring the current altitude, speed, longitude, latitude, track angle and course angle of the aircraft;
s42, setting the flight time of the aircraft;
and S43, taking the current altitude, speed, longitude, latitude, track angle, course angle of the aircraft and the flight time of the aircraft as input parameters, and predicting the flight track by using the trained neural network model.
6. The method according to claim 1, wherein in step S5, the position relationship between the flight trajectory and the no-fly zone is determined, and when the aircraft is affected by the no-fly zone, the method for adjusting the roll angle of the aircraft is as follows:
s51, the flight path is approximately a segment of circular arc relative to the earth radius, and the current position of the aircraft is a path starting point pSThe other end of the arc is a track end point pEThe no-fly zone is represented by a plurality of characteristic points which are connected in sequence; calculating the distances between the track end point and all the characteristic points of the no-fly area; selecting the characteristic point p with the minimum distance and two characteristic points p connected with the point p1And p2；
S52, calculating a line segment p1p、p2p、pSp、pEThe angle of p with respect to the reference direction is respectively noted
Figure FDA0002795884410000021
Figure FDA0002795884410000022
S53, if
Figure FDA0002795884410000023
Is at the size of
Figure FDA0002795884410000024
And
Figure FDA0002795884410000025
in between, the arc end point is in the no-fly zone; otherwise, the track end point is outside the no-fly zone;
s54, if the track end point is outside the no-fly zone, recording the flight time t of the aircraft at the moment, and switching to S57, otherwise, switching to S55;
s55, calculating the track end point relative to the line segment p1p、p2Selecting a smaller value as the distance of the aircraft relative to the no-fly zone, and recording as d;
s56, adjusting the track prediction time t by adopting a dichotomy, and calculating the corresponding track end point position p'ERepeating S52-S55 to determine an adjusted trajectory predictionThe distance d 'of the aircraft relative to the no-fly zone after the time is up to the point that d' is smaller than a set threshold value delta d;
s57, determining the track prediction time t when the track intersects with the no-fly zone⊥＝t′；
S58, setting track prediction threshold tthresholdComparing the time t when the trajectory intersects the no-fly zone⊥1And t⊥2And tthresholdThe magnitude relationship of (1); if t⊥1And t⊥2Are all greater than tthresholdThe aircraft keeps flying at the current roll angle; if t⊥1And t⊥2At least one of which is less than tthresholdThen aircraft follows t⊥1And t⊥2The larger of which determines the roll angle sign.
CN202011331200.7A 2020-11-24 2020-11-24 Reentry vehicle any no-fly zone around-flying method based on intelligent trajectory prediction Active CN112506218B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011331200.7A CN112506218B (en) 2020-11-24 2020-11-24 Reentry vehicle any no-fly zone around-flying method based on intelligent trajectory prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011331200.7A CN112506218B (en) 2020-11-24 2020-11-24 Reentry vehicle any no-fly zone around-flying method based on intelligent trajectory prediction

Publications (2)

Publication Number Publication Date
CN112506218A true CN112506218A (en) 2021-03-16
CN112506218B CN112506218B (en) 2023-04-14

Family

ID=74958347

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011331200.7A Active CN112506218B (en) 2020-11-24 2020-11-24 Reentry vehicle any no-fly zone around-flying method based on intelligent trajectory prediction

Country Status (1)

Country Link
CN (1) CN112506218B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114035603A (en) * 2021-08-08 2022-02-11 中国航空工业集团公司沈阳飞机设计研究所 Dynamic detection and alarm method for threat area of unmanned aerial vehicle
CN114637311A (en) * 2022-03-17 2022-06-17 北京航空航天大学 Guidance method and system based on maneuver avoidance multi-forbidden flight area
CN115017747A (en) * 2022-08-09 2022-09-06 安胜（天津）飞行模拟系统有限公司 Multi-speed simulation repositioning operation method of eVTOL (electric virtual plane)
CN116929308A (en) * 2023-09-18 2023-10-24 众芯汉创(江苏)科技有限公司 Unmanned aerial vehicle around-flight photographing method and system based on arbitrary point position information of tower

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107491090A (en) * 2017-08-25 2017-12-19 中国人民解放军火箭军工程大学 Based on the quick planing method of aircraft reentry trajectory for detecting point self-adapted pseudo- spectrometry
CN108387140A (en) * 2018-01-19 2018-08-10 北京航空航天大学 A kind of parsing reentry guidance method considering multiple no-fly zone constraints
CN109508030A (en) * 2018-11-27 2019-03-22 北京航空航天大学 A kind of collaboration parsing reentry guidance method considering more no-fly zone constraints
CN111783358A (en) * 2020-07-02 2020-10-16 哈尔滨工业大学 Bayesian estimation-based long-term trajectory prediction method for hypersonic aircraft

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107491090A (en) * 2017-08-25 2017-12-19 中国人民解放军火箭军工程大学 Based on the quick planing method of aircraft reentry trajectory for detecting point self-adapted pseudo- spectrometry
CN108387140A (en) * 2018-01-19 2018-08-10 北京航空航天大学 A kind of parsing reentry guidance method considering multiple no-fly zone constraints
CN109508030A (en) * 2018-11-27 2019-03-22 北京航空航天大学 A kind of collaboration parsing reentry guidance method considering more no-fly zone constraints
CN111783358A (en) * 2020-07-02 2020-10-16 哈尔滨工业大学 Bayesian estimation-based long-term trajectory prediction method for hypersonic aircraft

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
王子瑶等: "多路径约束下的高超声速滑翔飞行器再入制导", 《导弹与航天运载技术》 *
赵江等: "基于倾侧角反馈控制的预测校正再入制导方法", 《兵工学报》 *
赵江等: "考虑禁飞区规避的预测校正再入制导方法", 《北京航空航天大学学报》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114035603A (en) * 2021-08-08 2022-02-11 中国航空工业集团公司沈阳飞机设计研究所 Dynamic detection and alarm method for threat area of unmanned aerial vehicle
CN114035603B (en) * 2021-08-08 2023-11-28 中国航空工业集团公司沈阳飞机设计研究所 Unmanned aerial vehicle threat zone dynamic detection and alarm method
CN114637311A (en) * 2022-03-17 2022-06-17 北京航空航天大学 Guidance method and system based on maneuver avoidance multi-forbidden flight area
CN114637311B (en) * 2022-03-17 2024-06-07 北京航空航天大学 Guidance method and system based on maneuver avoidance of multiple forbidden zones
CN115017747A (en) * 2022-08-09 2022-09-06 安胜（天津）飞行模拟系统有限公司 Multi-speed simulation repositioning operation method of eVTOL (electric virtual plane)
CN116929308A (en) * 2023-09-18 2023-10-24 众芯汉创(江苏)科技有限公司 Unmanned aerial vehicle around-flight photographing method and system based on arbitrary point position information of tower
CN116929308B (en) * 2023-09-18 2023-11-28 众芯汉创(江苏)科技有限公司 Unmanned aerial vehicle around-flight photographing method and system based on arbitrary point position information of tower

Also Published As

Publication number Publication date
CN112506218B (en) 2023-04-14

Similar Documents

Publication Publication Date Title
CN112506218B (en) Reentry vehicle any no-fly zone around-flying method based on intelligent trajectory prediction
CN109753068B (en) Multi-USV group collaborative collision avoidance planning method considering communication situation
CN109740198B (en) Analytic prediction-based three-dimensional reentry guidance method for gliding aircraft
CN102759928B (en) Control method for flight path of airship on stratosphere
CN109871031B (en) Trajectory planning method for fixed-wing unmanned aerial vehicle
CN111399541B (en) Unmanned aerial vehicle whole-region reconnaissance path planning method of unsupervised learning type neural network
CN111273670B (en) Unmanned ship collision prevention method for fast moving obstacle
CN114330115B (en) Neural network air combat maneuver decision-making method based on particle swarm search
CN111881518A (en) Intelligent reentry maneuver guidance method and system for hypersonic aircraft
CN112947592A (en) Reentry vehicle trajectory planning method based on reinforcement learning
CN108491650B (en) Mars entering terminal state efficient evaluation method based on intelligent learning
CN113538973B (en) Automatic ship collision avoidance method based on improved particle swarm optimization
CN107367941B (en) Method for observing attack angle of hypersonic aircraft
CN113625569B (en) Small unmanned aerial vehicle prevention and control decision method and system based on hybrid decision model
CN114442673B (en) Intelligent aircraft trajectory planning method based on chaotic model and DNN
CN112162567A (en) Avoidance guidance method suitable for online no-fly zone of aircraft
CN113671825A (en) Maneuvering intelligent decision missile avoidance method based on reinforcement learning
CN113093733A (en) Sea-hitting method for unmanned boat cluster
CN116430900B (en) Game track planning method of hypersonic warhead based on deep reinforcement learning
CN115542746B (en) Energy control reentry guidance method and device for hypersonic aircraft
CN117313233A (en) Neural network-based boosting gliding aircraft emission data calculation method
Zhu et al. Path planning of mobile robot based on deep reinforcement learning with transfer learning strategy
CN117726089A (en) Cluster navigational task allocation method and system for optimizing K-means threat target clustering
CN106950833B (en) Based on the attitude of satellite dynamic programming method for improving PIO algorithm
CN112925344B (en) Unmanned aerial vehicle flight condition prediction method based on data driving and machine learning

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