CN104991446B - A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning - Google Patents
A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning Download PDFInfo
- Publication number
- CN104991446B CN104991446B CN201510264667.7A CN201510264667A CN104991446B CN 104991446 B CN104991446 B CN 104991446B CN 201510264667 A CN201510264667 A CN 201510264667A CN 104991446 B CN104991446 B CN 104991446B
- Authority
- CN
- China
- Prior art keywords
- lon
- lat
- thrust
- angle
- longitudinal
- 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.)
- Expired - Fee Related
Links
Abstract
The invention discloses a kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning, brain emotion learning intelligent control algorithm principle is applied in unmanned plane thrust deflecting control.The present invention controls the horizontal and vertical propulsion of unmanned plane, realizes the operating of yawing moment, improve the performance of unmanned plane respectively by two brain emotion learning controllers.Designed thrust deflecting control method, control law calculates fairly simple, but control parameter has on-line control ability, improves the level of intelligence of flight control system.
Description
Technical field
The present invention relates to a kind of fixed-wing UAV Flight Control technical field, and in particular to one kind is based on brain sentics
The unmanned plane thrust deflecting intelligent control method of habit.
Background technology
Thruster vector control technology is flight control device more advanced at present, is obtained in day jet aircraft
Successfully application.Thrust deflecting control realization side-jet control, when having sufficiently large permissible load factor and sufficiently fast dynamic response
Between, effective interception and attack to high speed, high maneuvering targets can be realized.In addition, it can still be produced under low speed, high dummy status
Very big control moment, can meet that UAV Maneuver is strong and the big requirement of the angle of attack.Thrust Vectoring Technology have on man-machine by
Checking can improve stealth, maneuverability and agility of aircraft etc., therefore the application of Thrust Vectoring Technology turns into nobody
The important trend of machine development.
Similar to the Thrust Vectoring Technology of jet plane, the present invention is directed the thrust deflecting skill of propeller unmanned plane
Art.Thrust deflecting technology has the advantageous feature of Thrust Vectoring Technology, i.e., can improve the controlling of UAV Attitude and track
Can, the function of pneumatic rudder face is compensated, difference is that application is different.
For propeller unmanned plane, pneumatic rudder face is conducive to air maneuver control with thrust deflecting co-ordination.Thrust becomes
To control as auxiliary controls, control is not involved in general.Pneumatic rudder face and the driving efficiency of thrust deflecting are not
Together, in high dynamic pressure, the former efficiency is higher than the latter, then opposite in low dynamic pressure High Angle of Attack.For improve thrust deflecting control from
Adaptability, brain emotion learning algorithm is used in thrust deflecting control.
Brain emotion learning (BEL) Based Intelligent Control is a kind of inspires in the intelligence of mammalian brain inside emotion learning mode
Can control technology.Iranian scholar Moren and Balkenius established brain sentics based on cerebral nerve logistics in 2000
The computation model of habit, it is based on the mode of intelligence transmission is modeled between amygdaloid body and Kuang E cortical tissues in brain.Lucas in
Brain emotion learning intelligent controller is first proposed within 2004, permasyn morot, power system, switch magnetic is applied to
Hinder in motor, the control of voltage-regulating system.
Document《The brain emotion learning Intelligent flight control of change propulsive axis unmanned plane》With《Change propulsive axis unmanned plane flies
Row control technology research》, for Longitudinal Flight gesture stability problem, devise based on the control of pneumatic rudder face, thruster vector control
The hybrid control architecture that control is combined is compensated with brain emotion learning inversion model.
Patent of invention《The attitude control system and control method of thrust unmanned aerial vehicle》It is based on a kind of modern scientist reason
The pneumatic rudder face and thrust deflecting integrated control method of opinion.
There is defect to a certain extent in prior art, it is considered to how to install additional thrust arrangement for deflecting propeller nobody
Machine, research how the autocontrol method of design thrust arrangement for deflecting, become prior art development direction.
The content of the invention
Goal of the invention:In order to overcome the deficiencies in the prior art, the present invention provides a kind of based on brain emotion learning
Unmanned plane thrust deflecting intelligent control method, brain emotion learning Based Intelligent Control principle is applied to the thrust deflecting of unmanned plane
In control, change aircraft stress and moment loading, overcome the deficiencies in the prior art.
Technical scheme:To achieve the above object, the technical solution adopted by the present invention is:It is a kind of based on brain emotion learning
Unmanned plane thrust deflecting intelligent control method, it is characterised in that including thrust longitudinally deflection control module and thrust lateral deflection
Control module;
Longitudinally deflection control module includes thrust Longitudinal Intelligence control receiver to the thrust;Thrust lateral deflection controls mould
Block includes thrust lateral deflection and controls Intelligent control receiver;
This method comprises the following steps:
1) thrust longitudinally deflects control module step:
1.1) parameter initialization:Set sense organ input function and emotion implies the weight coefficient vector ω of functionlon;Set apricot
Benevolence body tissue A study initial weight Vlon, orbitofrontal cortex tissue O study initial weight Wlon;Setting A-O organizes the tune of weights
Save rate coefficient υlon;
1.2) thrust Longitudinal Intelligence controller receives outside longitudinal input signal, and outside longitudinal input signal includes bowing
Face upward attitude angle value of feedback, pitch attitude angle command value, pitch rate value of feedback and lifting angle of rudder reflection value of feedback;
Outside longitudinal input signal is by obtaining longitudinal sense organ input signal SI after thrust Longitudinal Intelligence controllerlon
With longitudinal prize signal REWlon:
SIlon=ωlon(1)eθ+ωlon(2)θ+ωlon(3)θc+ωlon(4)q+ωlon(5)δe
REWlon=ωlon(5)eθ+ωlon(6)q+ωlon(7)δe
1.3) the lower study initial weight V for updating amygdaloid body tissue A in longitudinal directionlonWith at the beginning of orbitofrontal cortex tissue O study weights
Value Wlon, more new law is expressed as:
Amygdaloid body tissue A study weights turnover rate:
ΔVlon=υlon(1)max(0,REWlon-VlonSIlon), now Vlon=Vlon+ΔVlon;
Orbitofrontal cortex tissue O study weights turnover rate:
ΔWlon=υlon(2)(VlonSIlon-WlonSIlon-REWlon), now Wlon=Wlon+ΔWlon;
1.4) longitudinal direction is lower calculates amygdaloid body tissue and orbitofrontal cortex tissue output signal Alon, and Longitudinal Intelligence control mould
Block output signal Olon, it is respectively:
Alon=VlonSIlon
Olon=WlonSIlon
Difference is longitudinal declination signal Elon=Alon-Olon;
2) thrust lateral deflection control module step:
2.1) parameter initialization:Set sense organ input function and emotion implies the weight coefficient vector ω of functionlat;Set apricot
Benevolence body tissue A study initial weight Vlat, orbitofrontal cortex tissue O study initial weight Wlat;Setting A-O organizes the tune of weights
Save rate coefficient υlat;
2.2) the horizontal intelligent controller of thrust receives outside horizontal input signal, and the outside horizontal input signal includes rolling
Turn attitude angle value of feedback, roll attitude angle command value, roll angle Rate Feedback value and aileron drift angle value of feedback;
The outside horizontal input signal after the horizontal intelligent controller of thrust by obtaining horizontal sense organ input signal SIlat
With horizontal prize signal REWlat:
SIlat=ωlat(1)eφ+ωlat(2)φ+ωlat(3)φc+ωlat(4)p+ωlat(5)δr
REWlat=ωlat(6)eφ+ωlat(7)p+ωlat(8)δr
2.3) the horizontal lower study initial weight V for updating amygdaloid body tissue Alat, at the beginning of orbitofrontal cortex tissue O study weights
Value Wlat, more new law is expressed as:
Amygdaloid body tissue A study weights turnover rate:
ΔVlat=υlat(1)·max(0,REWlat-VlatSIlat), Vlat=Vlat+ΔVlat;
Orbitofrontal cortex tissue O study weights turnover rate:
ΔWlat=υlat(2)(VlatSIlat-WlatSIlat-REWlat), Wlat=Wlat+ΔWlat;
2.4) it is laterally lower to calculate amygdaloid body tissue and orbitofrontal cortex tissue output signal Alat, and laterally intelligence control
Module output signal O processedlat, it is respectively:
Alat=VlatSIlat
Olat=WlatSIlat
Difference is thrust lateral slip angle signal Elat=Alat-Olat;
3) by the longitudinal declination signal E of the thrustlonWith thrust lateral slip angle signal ElatThrust arrangement for deflecting is inputed to hold
Row mechanism, yaw motion is realized by arrangement for deflecting.
Beneficial effect:What the present invention was provided
(1) because the functional form of sense organ input signal and prize signal can may be such that the knot of controller with designed, designed
Structure becomes flexible, various.
(2) pneumatic rudder face includes elevator, aileron and rudder, also accelerator open degree, still using conventional control methods,
Or other advanced methods are used, this ensure that the basic flight performance of unmanned plane, and thrust deflecting control is used as auxiliary control
Make, candidate repays pneumatic rudder effectiveness or even substitutes pneumatic rudder face when necessary so that the remaining of UAV Flight Control System increases
Plus, enhance flying quality and reliability.
(3) the thrust deflecting control method designed by, control law calculates fairly simple, but control parameter has online tune
Energy-conservation power, improves the level of intelligence of flight control system.
Brief description of the drawings
Fig. 1 is angle of pitch control response;
Fig. 2 responds for elevator;
Fig. 3 is roll angle control response;
Fig. 4 responds for aileron;
Fig. 5 is the longitudinal drift angle response of thrust;
Fig. 6 responds for thrust lateral slip angle;
Fig. 7 is the basic structure of brain emotion learning (BEL) computation model;
Embodiment
The present invention is further described below in conjunction with the accompanying drawings.
Moren et al. is according to the mode of intelligence transmission in brain between amygdaloid body tissue and orbitofrontal cortex tissue, it is proposed that
Brain emotion learning model, as shown in Figure 7.Model mainly includes amygdaloid body and orbitofrontal cortex two parts.The study of brain emotion
Process is occurred mainly in amygdaloid body, and orbitofrontal cortex plays supervisory function bit to the esoteric emotion learning process of almond, is kept away
Exempt from it to occur learning and owing study.
Amygdaloid body is the microtissue in central temporo cerebral lobe (Medial Temporal Lobe) in mammalian brain, is
Neutral (Neutral) and emotion carry out the main place of study connection between stimulating, and orbitofrontal cortex is to rely on trama
Etc. (Context) place that this association list reaches is suppressed.Amygdaloid body is different from the conditioning mechanism of cerebellum, and the former is based on sense
The connection relation of official-emotion, learning process of the latter based on S-R.
Amygdaloid body is responsible for the major part of emotion learning.Orbitofrontal cortex tissue is the major part for aiding in emotion learning,
The pace of learning of emotion can be accelerated in amygdaloid body learning process, can be adjusted well when amygdaloid body crosses study or owes study
Save the learning process of brain emotion.
The brain emotion learning algorithm that the present invention is used is calculated than the brain emotion learning algorithm that domestic open source literature is delivered
Simpler, brain emotion learning algorithm computing formula is as follows:
A=SIV
O=SIW
E=A-O
Δ V=υa·max(0,REW-A)
Δ W=υo(E-REW)
In formula, A is the output of amygdaloid body tissue, and O is the output of orbitofrontal cortex tissue, and E is output signal, and SI feels to be outside
Official's input signal or combination, REW are prize signal.V is that the learning process of emotion in amygdaloid body internal learning weights, amygdaloid body is
For the Dynamic Regulating Process of weights, Δ V is weights V regulation rate, represents pace of learning.W is orbitofrontal cortex internal learning weights,
Emotion learning in orbitofrontal cortex realizes that Δ W weights W regulation rate is pace of learning by dynamic regulation weights.υ is
Adjust rate coefficient.
Secondly, based on above-mentioned brain emotion learning intelligent control algorithm principle, derive below in unmanned plane thrust deflecting control
Application in system.
Because thrust deflecting control includes two controlled quentity controlled variables, it is therefore desirable to design two brain emotion learning Based Intelligent Controls
Device.Brain emotion learning algorithm is when real system is combined, it is necessary to the letter of sense organ input signal and prize signal is determined in advance
Number form formula, they are mainly relevant with the factor such as the input and output of system, controlled quentity controlled variable and tracking error.
The design problem of control law is longitudinally deflected for thrust, sense organ input function and emotion imply that function can be separately designed
For
SIlon=f (eθ,θ,θc,q,δe)
REWlon=J (eθ,q,δe)
For the design problem of thrust lateral deflection control law, sense organ input function and emotion imply that function can be separately designed
For
SIlat=f (eφ,φ,φc,p,δr)
REWlat=J (eφ,p,δr)
In formula, eθ=θ-θcFor pitching angle error, θ is the angle of pitch, θcInstructed for the angle of pitch, q is pitch rate, δeFor
Lift angle of rudder reflection.eφ=φ-φcFor rolling angle error, φ is roll angle, φcRoll angle is instructed, and p is rolling angular speed, δaFor
Aileron drift angle.
A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning, it is characterised in that including thrust
Longitudinal direction deflection control module and thrust lateral deflection control module;
Longitudinally deflection control module includes thrust Longitudinal Intelligence control receiver to the thrust;Thrust lateral deflection controls mould
Block includes thrust lateral deflection and controls Intelligent control receiver;
This method comprises the following steps:
1) thrust longitudinally deflects control module step:
1.1) parameter initialization:Set sense organ input function and emotion implies the weight coefficient vector ω of functionlon;Set apricot
Benevolence body tissue A study initial weight Vlon, orbitofrontal cortex tissue O study initial weight Wlon;Setting A-O organizes the tune of weights
Save rate coefficient υlon;
1.2) thrust Longitudinal Intelligence controller receives outside longitudinal input signal, and outside longitudinal input signal includes bowing
Face upward attitude angle value of feedback, pitch attitude angle command value, pitch rate value of feedback and lifting angle of rudder reflection value of feedback;
Outside longitudinal input signal is by obtaining longitudinal sense organ input signal SI after thrust Longitudinal Intelligence controllerlon
With longitudinal prize signal REWlon:
SIlon=ωlon(1)eθ+ωlon(2)θ+ωlon(3)θc+ωlon(4)q+ωlon(5)δe
REWlon=ωlon(5)eθ+ωlon(6)q+ωlon(7)δe
1.3) the lower study initial weight V for updating amygdaloid body tissue A in longitudinal directionlonWith at the beginning of orbitofrontal cortex tissue O study weights
Value Wlon, more new law is expressed as:
Amygdaloid body tissue A study weights turnover rate:
ΔVlon=υlon(1)max(0,REWlon-VlonSIlon), now Vlon=Vlon+ΔVlon;
Orbitofrontal cortex tissue O study weights turnover rate:
ΔWlon=υlon(2)(VlonSIlon-WlonSIlon-REWlon), now Wlon=Wlon+ΔWlon;
1.4) longitudinal direction is lower calculates amygdaloid body tissue and orbitofrontal cortex tissue output signal Alon, and Longitudinal Intelligence control mould
Block output signal Olon, it is respectively:
Alon=VlonSIlon
Olon=WlonSIlon
Difference is longitudinal declination signal Elon=Alon-Olon;
2) thrust lateral deflection control module step:
2.1) parameter initialization:Set sense organ input function and emotion implies the weight coefficient vector ω of functionlat;Set apricot
Benevolence body tissue A study initial weight Vlat, orbitofrontal cortex tissue O study initial weight Wlat;Setting A-O organizes the tune of weights
Save rate coefficient υlat;
2.2) the horizontal intelligent controller of thrust receives outside horizontal input signal, and the outside horizontal input signal includes rolling
Turn attitude angle value of feedback, roll attitude angle command value, roll angle Rate Feedback value and aileron drift angle value of feedback;
The outside horizontal input signal after the horizontal intelligent controller of thrust by obtaining horizontal sense organ input signal SIlat
With horizontal prize signal REWlat:
SIlat=ωlat(1)eφ+ωlat(2)φ+ωlat(3)φc+ωlat(4)p+ωlat(5)δr
REWlat=ωlat(6)eφ+ωlat(7)p+ωlat(8)δr
2.3) the horizontal lower study initial weight V for updating amygdaloid body tissue Alat, at the beginning of orbitofrontal cortex tissue O study weights
Value Wlat, more new law is expressed as:
Amygdaloid body tissue A study weights turnover rate:
ΔVlat=υlat(1)·max(0,REWlat-VlatSIlat), Vlat=Vlat+ΔVlat;
Orbitofrontal cortex tissue O study weights turnover rate:
ΔWlat=υlat(2)(VlatSIlat-WlatSIlat-REWlat), Wlat=Wlat+ΔWlat;
2.4) it is laterally lower to calculate amygdaloid body tissue and orbitofrontal cortex tissue output signal Alat, and laterally intelligence control
Module output signal O processedlat, it is respectively:
Alat=VlatSIlat
Olat=WlatSIlat
Difference is thrust lateral slip angle signal Elat=Alat-Olat;
3) by the longitudinal declination signal E of the thrustlonWith thrust lateral slip angle signal ElatThrust arrangement for deflecting is inputed to hold
Row mechanism, yaw motion is realized by arrangement for deflecting.
Simulating, verifying has been carried out for certain propeller unmanned plane.Unmanned plane model describes for non-linear full dose equation.Aircraft
By 20m/s lasting wind disturbance, made jointly using pneumatic rudder face controller, throttle control and thrust deflecting intelligent controller
With having obtained the tracking response result of unmanned plane angle of pitch attitude and roll angle attitude, as shown in figs 1 to 6.
The above is only the preferred embodiment of the present invention, it should be pointed out that:For the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (1)
1. a kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning, it is characterised in that vertical including thrust
To deflection control module and thrust lateral deflection control module;
Longitudinally deflection control module includes thrust Longitudinal Intelligence control receiver to the thrust;Thrust lateral deflection control module bag
Include thrust lateral deflection control Intelligent control receiver;
This method comprises the following steps:
1) thrust longitudinally deflects control module step:
1.1) parameter initialization:Set sense organ input function and emotion implies the weight coefficient vector ω of functionlon;Set amygdaloid body
Organize A study initial weight Vlon, orbitofrontal cortex tissue O study initial weight Wlon;Setting A-O organizes the regulation rate of weights
Coefficient υlon;
1.2) thrust Longitudinal Intelligence controller receives outside longitudinal input signal, and outside longitudinal input signal includes pitching appearance
State angle value of feedback, pitch attitude angle command value, pitch rate value of feedback and lifting angle of rudder reflection value of feedback;
Outside longitudinal input signal is by obtaining longitudinal sense organ input signal SI after thrust Longitudinal Intelligence controllerlonWith it is vertical
To prize signal REWlon:
SIlon=ωlon(1)eθ+ωlon(2)θ+ωlon(3)θc+ωlon(4)q+ωlon(5)δe
REWlon=ωlon(5)eθ+ωlon(6)q+ωlon(7)δe
1.3) the lower study initial weight V for updating amygdaloid body tissue A in longitudinal directionlonWith orbitofrontal cortex tissue O study initial weight
Wlon, more new law is expressed as:
Amygdaloid body tissue A study weights turnover rate:
ΔVlon=υlon(1)max(0,REWlon-VlonSIlon), now Vlon=Vlon+ΔVlon;
Orbitofrontal cortex tissue O study weights turnover rate:
ΔWlon=υlon(2)(VlonSIlon-WlonSIlon-REWlon), now Wlon=Wlon+ΔWlon;
1.4) longitudinal direction is lower calculates amygdaloid body tissue and orbitofrontal cortex tissue output signal Alon, and Longitudinal Intelligence control module is defeated
Go out signal Olon, it is respectively:
Alon=VlonSIlon
Olon=WlonSIlon
Difference is longitudinal declination signal Elon=Alon-Olon;
2) thrust lateral deflection control module step:
2.1) parameter initialization:Set sense organ input function and emotion implies the weight coefficient vector ω of functionlat;Set amygdaloid body
Organize A study initial weight Vlat, orbitofrontal cortex tissue O study initial weight Wlat;Setting A-O organizes the regulation rate of weights
Coefficient υlat;
2.2) the horizontal intelligent controller of thrust receives outside horizontal input signal, and the outside horizontal input signal includes rolling appearance
State angle value of feedback, roll attitude angle command value, roll angle Rate Feedback value and aileron drift angle value of feedback;
The outside horizontal input signal after the horizontal intelligent controller of thrust by obtaining horizontal sense organ input signal SIlatAnd horizontal stroke
To prize signal REWlat:
SIlat=ωlat(1)eφ+ωlat(2)φ+ωlat(3)φc+ωlat(4)p+ωlat(5)δr
REWlat=ωlat(6)eφ+ωlat(7)p+ωlat(8)δr
In formula, eθ=θ-θcFor pitching angle error, θ is the angle of pitch, θcInstructed for the angle of pitch, q is pitch rate, δeFor elevator
Drift angle, eφ=φ-φcFor rolling angle error, φ is roll angle, φcRoll angle is instructed, and p is rolling angular speed, δrIt is inclined for aileron
Angle;
2.3) the horizontal lower study initial weight V for updating amygdaloid body tissue Alat, orbitofrontal cortex tissue O study initial weight
Wlat, more new law is expressed as:
Amygdaloid body tissue A study weights turnover rate:
ΔVlat=υlat(1)·max(0,REWlat-VlatSIlat), Vlat=Vlat+ΔVlat;
Orbitofrontal cortex tissue O study weights turnover rate:
ΔWlat=υlat(2)(VlatSIlat-WlatSIlat-REWlat), Wlat=Wlat+ΔWlat;
2.4) it is laterally lower to calculate amygdaloid body tissue and orbitofrontal cortex tissue output signal Alat, and horizontal Based Intelligent Control mould
Block output signal Olat, it is respectively:
Alat=VlatSIlat
Olat=WlatSIlat
Difference is thrust lateral slip angle signal Elat=Alat-Olat;
3) by the longitudinal declination signal E of the thrustlonWith thrust lateral slip angle signal ElatInput to thrust arrangement for deflecting and perform machine
Structure, yaw motion is realized by arrangement for deflecting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510264667.7A CN104991446B (en) | 2015-05-21 | 2015-05-21 | A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510264667.7A CN104991446B (en) | 2015-05-21 | 2015-05-21 | A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104991446A CN104991446A (en) | 2015-10-21 |
CN104991446B true CN104991446B (en) | 2017-07-18 |
Family
ID=54303268
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510264667.7A Expired - Fee Related CN104991446B (en) | 2015-05-21 | 2015-05-21 | A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104991446B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107392315B (en) * | 2017-07-07 | 2021-04-09 | 中南大学 | Breast cancer data classification method for optimizing brain emotion learning model |
CN107450321A (en) * | 2017-08-30 | 2017-12-08 | 北京石油化工学院 | A kind of Mechanical arm control method based on brain emotion learning |
CN108958037B (en) * | 2018-08-15 | 2021-06-15 | 厦门理工学院 | Wavelet fuzzy brain emotion learning control method, device, equipment and storage medium |
CN109709803B (en) * | 2018-12-20 | 2020-09-04 | 北京航空航天大学 | Automobile IMT speed control method based on PSO improved brain emotion learning intelligent controller |
CN111844049B (en) * | 2020-08-04 | 2021-08-17 | 河北省科学院应用数学研究所 | Dexterous hand grabbing control method and device and terminal equipment |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103197683A (en) * | 2013-04-18 | 2013-07-10 | 南京航空航天大学 | Method for intelligently controlling flight heights and attitudes of quad-rotor unmanned helicopters |
-
2015
- 2015-05-21 CN CN201510264667.7A patent/CN104991446B/en not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103197683A (en) * | 2013-04-18 | 2013-07-10 | 南京航空航天大学 | Method for intelligently controlling flight heights and attitudes of quad-rotor unmanned helicopters |
Non-Patent Citations (7)
Title |
---|
A Review of Emotional Learning And It"s Utilization in Control Engineering;Zahra Beheshti,etc;《Int.J.Advance.Soft Comput.Appl.》;20100731;第2卷(第2期);第191-208页 * |
Attitude control of a Quadrotor using Brain Emotional Learning Based Intelligent Controller;Mohammad Jafari,etc;《2013 13th Iranian Conference on Fuzzy Systems(IFSC)》;20131202;第1-5页 * |
Multi-sensor Information Fusion for Aircraft Attitude Determination System;Zhen Ziyang,etc;《2009 World Congress on Computer Science and Information Engineering》;20090724;第474-478页 * |
UAV flight trajectory control based on information fusion control method;Ziyang Zhen,etc;《2010 International Conference on Networking,Sensing and Control(ICNSC)》;20100506;第337-341页 * |
变推力轴线无人机飞行控制技术研究;黄国勇;《中国博士学位论文全文数据库工程科技Ⅱ辑(月刊)》;20110615(第06期);第C031-15页 * |
四旋翼无人直升机先进飞行控制方法及实现研究;陈琦;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑(月刊)》;20140715(第07期);第C031-107页 * |
基于大脑情感学习的推力矢量无人机姿态控制;黄国勇,等;《系统工程与电子技术》;20091231;第31卷(第12期);第2954-2957页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104991446A (en) | 2015-10-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104991446B (en) | A kind of unmanned plane thrust deflecting intelligent control method based on brain emotion learning | |
CN109782795B (en) | Transverse control method and control system for coupled surface-symmetric hypersonic aircraft | |
CN105653827B (en) | Hypersonic aircraft Terminal sliding mode controller design method | |
CN109597303A (en) | A kind of composite rotor craft syntype flight control method | |
CN105138003B (en) | Many control surface unmanned plane direct lift force control methods | |
CN111240212B (en) | Tilt rotor unmanned aerial vehicle control distribution method based on optimization prediction | |
CN111984020B (en) | SDRE-based self-adaptive optimal sliding mode control method for transition flight mode of tilt-four-rotor unmanned aerial vehicle | |
CN105652879A (en) | Autonomous flight control method for unmanned plane without ailerons | |
CN102929283A (en) | Method for controlling reentry vehicle self-adapting optimal sliding mode attitude based on SDRE (state dependence matrix Riccati equation) | |
CN111290278B (en) | Hypersonic aircraft robust attitude control method based on prediction sliding mode | |
Buckner et al. | F-16 high-alpha flight control characteristics and control system concept | |
CN105759609B (en) | A kind of carrier-borne aircraft autonomous landing on the ship method based on explicit non-linear Model Predictive Control | |
Flores-Colunga et al. | A nonlinear control law for hover to level flight for the quad tilt-rotor uav | |
CN113485377B (en) | Unmanned sailing boat self-adaptive path tracking control method of double-layer virtual guiding mechanism | |
CN111045440B (en) | Hypersonic aircraft nose-down section rapid rolling control method | |
CN115755956B (en) | Knowledge and data collaborative driving unmanned aerial vehicle maneuvering decision method and system | |
CN114637319A (en) | Semi-rolling reverse maneuvering flight control method of two-channel unmanned aerial vehicle | |
CN109703769A (en) | It is a kind of that control method is docked based on the air refuelling for taking aim at strategy in advance | |
CN110576965B (en) | Unmanned aerial vehicle layout with least control surface configuration and control method thereof | |
CN109460055A (en) | A kind of flying vehicles control capacity judging method, device and electronic equipment | |
CN114721266A (en) | Self-adaptive reconstruction control method under structural missing fault condition of airplane control surface | |
Lyu et al. | Dynamic surface control design of post-stall maneuver under unsteady aerodynamics | |
CN104656659B (en) | Shipboard aircraft ski-jump take-off automatic flight control method | |
CN114756959A (en) | Design method of aircraft short-distance air combat maneuver intelligent decision machine model | |
CN111897219B (en) | Optimal robust control method for transitional flight mode of tilting quad-rotor unmanned aerial vehicle based on online approximator |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170718 Termination date: 20190521 |