CN108762098B - Non-minimum phase aircraft neural network control method based on Hybrid Learning - Google Patents
Non-minimum phase aircraft neural network control method based on Hybrid Learning Download PDFInfo
- Publication number
- CN108762098B CN108762098B CN201810950482.5A CN201810950482A CN108762098B CN 108762098 B CN108762098 B CN 108762098B CN 201810950482 A CN201810950482 A CN 201810950482A CN 108762098 B CN108762098 B CN 108762098B
- Authority
- CN
- China
- Prior art keywords
- representing
- formula
- neural network
- design
- angle
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000002131 composite material Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000012886 linear function Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 4
- 238000000844 transformation Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000005312 nonlinear dynamic Methods 0.000 abstract description 6
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 238000000354 decomposition reaction Methods 0.000 abstract 1
- 241000272517 Anseriformes Species 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
Classifications
-
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention relates to a kind of non-minimum phase aircraft neural network control method based on Hybrid Learning, it is first speed subsystem and height subsystem by aircraft vertical passage model decomposition, PID control is used for speed subsystem, is controlled for height subsystem using Backstepping.To height subsystem, the interior dynamic for making unstable interior dynamic become asymptotically stability based on Output Redefinition derives the pitch command for controller design to coordinate conversion is dynamically carried out in the system after Output Redefinition;Estimated for unknown nonlinear dynamics existing for system using neural network, design setting model error signal simultaneously provides Hybrid Learning algorithm in conjunction with tracking error, improves neural network to the approximation capability of nonlinear kinetics.The present invention realizes interior dynamic stability using Output Redefinition, does not know dynamics based on Hybrid Learning neural network estimation aircraft, new thinking can be provided for non-minimum phase flying vehicles control.
Description
Technical Field
The invention relates to an aircraft control method, in particular to a non-minimum phase aircraft neural network control method based on composite learning, and belongs to the field of aircraft control.
Background
In the face of new requirements of military and civil fields on aircraft technology, flight envelopes of modern aircrafts are continuously expanded, aircraft dynamics have the characteristics of complex nonlinearity, strong uncertainty and the like due to innovative configuration design and complex flight environments of the aircrafts, and the aircrafts have non-minimum phase characteristics due to coupling between elevators of the aircrafts and aerodynamic force. The non-minimum phase characteristic enables dynamic inverse design to be incapable of being directly applied, the influence of the elevator on the lift force is mostly compensated by adding the canard wing control surface at present, the system is changed into a minimum phase system, and the aerodynamic heat of the system is aggravated by adding the canard wing. Adaptive parametric model design is carried out on a linear parametric model by adopting an output redefinition method aiming at a hypersonic aircraft non-minimum phase model in the text of adaptive transformed objective tracking for a non-minimum phase parametric model (Lisa Fiorentini, Andrea Serrani, Automatica,2012,48(7):1248 and 1261), but the linear parametric model is not easy to obtain in practice and is not beneficial to engineering application.
Disclosure of Invention
Technical problem to be solved
Aiming at the problem of non-minimum phase aircraft control, the invention designs a non-minimum phase aircraft neural network control method based on composite learning. The method changes unstable internal dynamics into gradually stable internal dynamics based on an output redefinition method, performs coordinate conversion on the output redefined system internal dynamics, and deduces a pitch angle instruction. Aiming at an input-output subsystem, a neural network is adopted to estimate unknown nonlinear dynamics of the system based on a backstepping method frame, a modeling error signal is designed, a composite learning algorithm is given by combining a tracking error signal, the approximation performance of the neural network on the nonlinear dynamics is improved, and finally, control input is fed back to a dynamics model of the system to realize effective tracking of output.
Technical scheme
A non-minimum phase aircraft neural network control method based on composite learning is characterized by comprising the following steps:
step 1: considering an aircraft longitudinal channel dynamics model with non-minimum phase characteristics:
the kinetic model consists of five state variables X ═ V, h, gamma, alpha, q]TAnd two control inputs U ═ δe,Φ]TComposition is carried out; wherein V represents velocity, h represents altitude, γ represents track inclination, α represents angle of attack, q represents pitch angular velocity, δeThe rudder deflection angle is shown, and phi represents the throttle opening; t, D, L and MyyRespectively representing thrust, resistance, lift and pitching rotation moment; m, IyyAnd g represents mass, moment of inertia of pitch axis, and acceleration due to gravity, respectively;
the relevant forces, moments and parameters are defined as follows: whereinRepresenting the dynamic pressure, p representing the air density, are all indicative of a pneumatic parameter,representing the mean aerodynamic chord length, zTRepresenting the length of a thrust moment arm, and S represents an aerodynamic reference area;
step 2: for the velocity subsystem (1), the velocity tracking error is defined as:
in the formula, VdRepresenting a speed command; the design throttle opening phi is as follows:
in the formula, kpV>0,kiV>0 and kdV>0 is a design parameter;
and step 3: defining an altitude tracking error for the altitude subsystems (2) - (5)Design track angle command gammadComprises the following steps:
wherein h isdA height reference instruction is represented which is,representing the first differential, k, of the height reference commandh>0 and ki>0 is a design parameter;
according to time mark separation, regarding the speed as slow dynamic, designing the first-order differential of a track angle instruction as follows:
wherein,a second order differential representing the height reference command;
redefining the output of the attitude subsystem into a pitch angle theta from a track angle gamma, wherein the theta is alpha + gamma; defining a track angle error asThe pose subsystems (3) - (5) are further written as internal dynamic subsystems:
and an input-output subsystem:
wherein f is1And f3Is an unknown smooth non-linear function, g, obtained from an aircraft model12、g22、g13And g23Is a known term derived from an aircraft model;
and 4, step 4: defining coordinate transformationsDesign η2Comprises the following steps:
wherein,
integral eta defining track angle error1Obtained by the following formula:
the pitch angle command is designed as follows:
θcmd=-kθη1+γd (14)
in the formula, kθ∈(0,1]Is a design parameter;
pitch tracking error is defined as:
designing the virtual control quantity of the pitch angle speed as follows:
in the formula, k1>0 is a design parameter of the optical disc,
pitch rate error dynamics are as follows:
in the formula,representing the function of unknown non-linearity,representing a known item;
approximating unknown non-linear functions with neural networks
Wherein,to representIs determined by the estimated value of (c),an estimate representing an optimal weight vector for the neural network,representing the basis function vector, ε, of a neural network1Representing a neural network approximation error;
the rudder deflection angle is designed as follows:
in the formula, k2>0 andin order to design the parameters of the device,the robust term is used for eliminating the influence caused by approximation errors;
the modeling error is defined as:
whereinIs obtained by the following formula:
in the formula, beta1>0 is a design parameter;
design ofThe adaptive law is:
in the formula, gamma1>0,γz1>0 and xi1>0 is a design parameter;
design ofThe update law is as follows:
in the formula, ρ1>0 and delta1>0 is a design parameter;
and 5: from the resulting rudder deflection angle deltaeAnd the throttle opening phi returns to the aircraft dynamics models (1) - (5) to carry out tracking control on the altitude and the speed.
Advantageous effects
Compared with the prior art, the non-minimum phase aircraft neural network control method based on the composite learning has the beneficial effects that:
(1) the invention can directly carry out control design for the non-minimum phase aircraft without additionally increasing a canard wing control surface, and can avoid the problem of aerodynamic heat.
(2) The invention is based on the output redefinition method, which changes the unstable internal dynamic state into the gradually stable internal dynamic state, performs coordinate conversion on the internal dynamic state of the system after output redefinition, and deduces the pitch angle instruction required by the design of the controller.
(3) The invention provides a compound learning method based on the combination of tracking error and modeling error, which can improve the approximation performance of a neural network to unknown nonlinear dynamics, thereby improving the tracking performance of the system.
Drawings
FIG. 1 is a flow chart of a non-minimum phase aircraft neural network control method based on composite learning according to the invention.
Detailed Description
The invention will now be further described with reference to the following examples and drawings:
the technical scheme adopted by the invention for solving the technical problems is as follows: a non-minimum phase aircraft neural network control method based on composite learning is realized by the following steps:
(a) considering an aircraft longitudinal channel dynamics model with non-minimum phase characteristics:
the kinematic model consists of five state quantities X ═ V, h, γ, α, q]TAnd two control inputs U ═ δe,Φ]TComposition is carried out; wherein V represents velocity, h represents altitude, γ represents track inclination, α represents angle of attack, q represents pitch angular velocity, δeThe rudder deflection angle is shown, and phi represents the throttle opening; t, D, L and MyyRespectively representing thrust, resistance, lift and pitching rotation moment; m, IyyAnd g represents mass, moment of inertia of pitch axis, and acceleration due to gravity, respectively.
(b) The dynamics are functionally decoupled into a speed subsystem (1) and height subsystems (2) - (5). For the velocity subsystem, the velocity tracking error is defined as:
in the formula, VdRepresenting a speed command. The design throttle opening phi is as follows:
in the formula, kpV>0,kiV>0 and kdV>0 is a design parameter.
(c) Defining an altitude tracking error for an altitude subsystemDesign track angle command gammadComprises the following steps:
wherein h isdA height reference instruction is represented which is,representing the first differential, k, of the height reference commandh>0 and ki>0 is a design parameter.
According to time mark separation, regarding the speed as slow dynamic, designing the first-order differential of a track angle instruction as follows:
wherein,representing the second order differential of the height reference command.
Redefining the output of the attitude subsystem as a pitch angle theta by a track angle gamma, wherein theta is alpha + gamma. Defining a track angle error asThe pose subsystems (3) - (5) are further written as internal dynamic subsystems:
and an input-output subsystem:
wherein f is1And f3Is an unknown smooth non-linear function, g, obtained from an aircraft model12、g22、g13And g23Are known items derived from aircraft models.
(d) Defining coordinate transformationsDesign η2Comprises the following steps:
wherein,
integral eta defining track angle error1Obtained by the following formula:
the pitch angle command is designed as follows:
θcmd=-kθη1+γd (14)
in the formula, kθ∈(0,1]Are design parameters.
Pitch tracking error is defined as:
designing the virtual control quantity of the pitch angle speed as follows:
in the formula, k1>0 is a design parameter of the optical disc,
pitch rate error dynamics are as follows:
in the formula,representing the function of unknown non-linearity,representing a known item.
Approximating unknown non-linear functions with neural networks
Wherein,to representIs determined by the estimated value of (c),an estimate representing an optimal weight vector for the neural network,representing the basis function vector, ε, of a neural network1Representing the neural network approximation error.
The rudder deflection angle is designed as follows:
in the formula, k2>0 andin order to design the parameters of the device,the robust term is used for eliminating the influence caused by approximation errors.
The modeling error is defined as:
whereinIs obtained by the following formula:
in the formula, beta1>0 is a design parameter.
Design ofThe adaptive law is:
in the formula, gamma1>0,γz1>0 and xi1>0 is a design parameter.
Design ofThe update law is as follows:
in the formula, ρ1>0 and delta1>0 is a design parameter.
(e) From the resulting rudder deflection angle deltaeAnd the throttle opening phi returns to the aircraft dynamics models (1) - (5) to carry out tracking control on the altitude and the speed.
Example (b):
referring to fig. 1, the non-minimum phase aircraft neural network control method based on the composite learning is applied to a hypersonic aircraft and is realized by the following steps:
(a) establishing a non-minimum phase hypersonic aircraft longitudinal channel dynamic model:
wherein V represents velocity, γ represents track inclination, h represents altitude, α represents angle of attack, q represents pitch angle velocity, δeThe rudder deflection angle is shown, and phi represents the throttle opening; t, D, L and MyyRespectively representing thrust, resistance, lift and pitching rotation moment; m, IyyAnd g represents mass, moment of inertia of pitch axis, and acceleration due to gravity, respectively.
The relevant forces, moments and parameters are defined as follows:
whereinRepresenting the dynamic pressure, p representing the air density,representing the mean aerodynamic chord length, zTThe thrust moment arm length is indicated and S represents the aerodynamic reference area.
(b) The dynamics are functionally decoupled into a speed subsystem (1) and height subsystems (2) - (5). For the velocity subsystem, the velocity tracking error is defined as:
in the formula, VdRepresenting a speed command. The design throttle opening phi is as follows:
in the formula, kpV=5,kiV0.001 and kdV=0.001。
(c) Defining an altitude tracking error for an altitude subsystemDesign track angle command gammadComprises the following steps:
in the formula, hdIn order to be a height reference instruction,for first order differentiation of the height reference command, kh0.5 and ki=0.1。
According to time mark separation, regarding the speed as slow dynamic, designing the first-order differential of a track angle instruction as follows:
wherein,is the second order differential of the height reference command.
Redefining the output track angle gamma of the attitude subsystem as a pitch angle theta, wherein theta is alpha + gamma. Defining a track angle error asThe pose subsystems (3) - (5) are further written as internal dynamic subsystems:
and an input-output subsystem:
wherein,
(d) defining coordinate transformationsDesign η2Comprises the following steps:
wherein,
integral eta defining track angle error1Obtained by the following formula:
the pitch angle command is designed as follows:
θcmd=-kθη1+γd (14)
in the formula, kθ=0.9。
Pitch tracking error is defined as:
designing the virtual control quantity of the pitch angle speed as follows:
in the formula, k1=2,
Pitch rate error dynamics are as follows:
in the formula,representing the function of unknown non-linearity,representing a known item.
Approximating unknown functions with neural networks
Wherein,to representIs determined by the estimated value of (c),an estimate representing an optimal weight vector for the neural network,representing the basis function vector, ε, of a neural network1Representing the neural network approximation error.
The rudder deflection angle is designed as follows:
in the formula, k20.8 andthe robust term is used for eliminating the influence caused by approximation errors.
The modeling error is defined as:
whereinIs obtained by the following formula:
in the formula, beta1=2。
Design ofThe adaptive law is:
in the formula, gamma1=5,γz11 and xi1=0.001。
Design ofThe update law is as follows:
in the formula, ρ10.01 and δ1=0.001。
(e) From the resulting rudder deflection angle deltaeAnd the throttle opening phi returns to the dynamic models (1) to (5) of the hypersonic aerocraft, and the altitude and the speed are tracked and controlled.
The method comprises the steps of firstly, decomposing an aircraft longitudinal channel model into a speed subsystem and an altitude subsystem, adopting PID control for the speed subsystem, and adopting a backstepping method for the altitude subsystem. For the height subsystem, changing unstable internal dynamics into gradually stable internal dynamics based on output redefinition, carrying out coordinate conversion on the internal dynamics of the system after output redefinition, and deriving a pitch angle instruction for designing a controller; a neural network is adopted for estimation aiming at unknown nonlinear dynamics of the system, a modeling error signal is designed, a composite learning algorithm is given by combining a tracking error, and the approximation performance of the neural network on the nonlinear dynamics is improved. The invention realizes internal dynamic stability by output redefinition, estimates the uncertain dynamics of the aircraft based on the composite learning neural network, and can provide a new idea for controlling the non-minimum phase aircraft.
Claims (1)
1. A non-minimum phase aircraft neural network control method based on composite learning is characterized by comprising the following steps:
step 1: considering an aircraft longitudinal channel dynamics model with non-minimum phase characteristics:
the kinetic model consists of five state variables X ═ V, h, gamma, alpha, q]TAnd two control inputs U ═ δe,Φ]TComposition is carried out; wherein V represents speed, h represents altitude, and γ represents navigationTrack inclination angle, alpha is angle of attack, q is pitch angle velocity, deltaeThe rudder deflection angle is shown, and phi represents the throttle opening; t, D, L and MyyRespectively representing thrust, resistance, lift and pitching rotation moment; m, IyyAnd g represents mass, moment of inertia of pitch axis, and acceleration due to gravity, respectively;
the relevant forces, moments and parameters are defined as follows: whereinRepresenting the dynamic pressure, p representing the air density, are all indicative of a pneumatic parameter,representing the mean aerodynamic chord length, zTRepresenting the length of a thrust moment arm, and S represents an aerodynamic reference area;
step 2: for the velocity subsystem (1), the velocity tracking error is defined as:
in the formula, VdRepresenting a speed command; is provided withThe opening phi of the metering throttle valve is as follows:
in the formula, kpV>0,kiV>0 and kdV>0 is a design parameter;
and step 3: defining an altitude tracking error for the altitude subsystems (2) - (5)Design track angle command gammadComprises the following steps:
wherein h isdA height reference instruction is represented which is,representing the first differential, k, of the height reference commandh>0 and ki>0 is a design parameter;
according to time mark separation, regarding the speed as slow dynamic, designing the first-order differential of a track angle instruction as follows:
wherein,a second order differential representing the height reference command;
redefining the output of the attitude subsystem into a pitch angle theta from a track inclination angle gamma, wherein the theta is alpha + gamma; defining a track angle error asThe pose subsystems (3) - (5) are further written as internal dynamic subsystems:
and an input-output subsystem:
wherein f is1And f3Is an unknown smooth non-linear function, g, obtained from an aircraft model12、g22、g13And g23Is a known term derived from an aircraft model;
and 4, step 4: defining coordinate transformationsDesign η2Comprises the following steps:
wherein,
integral eta defining track angle error1Obtained by the following formula:
the pitch angle command is designed as follows:
θcmd=-kθη1+γd (14)
in the formula, kθ∈(0,1]Is a design parameter;
pitch tracking error is defined as:
designing the virtual control quantity of the pitch angle speed as follows:
in the formula, k1>0 is a design parameter of the optical disc,
pitch rate error dynamics are as follows:
in the formula,representing the function of unknown non-linearity,representing a known item;
approximating unknown non-linear functions with neural networks
Wherein,to representIs determined by the estimated value of (c),an estimate representing an optimal weight vector for the neural network,representing the basis function vector, ε, of a neural network1Representing a neural network approximation error;
the rudder deflection angle is designed as follows:
in the formula, k2>0 andin order to design the parameters of the device,the robust term is used for eliminating the influence caused by approximation errors;
the modeling error is defined as:
whereinIs obtained by the following formula:
in the formula, beta1>0 is a design parameter;
design ofThe adaptive law is:
in the formula, gamma1>0,γz1>0 and xi1>0 is a design parameter;
design ofThe update law is as follows:
in the formula, ρ1>0 and delta1>0 is a design parameter;
and 5: from the resulting rudder deflection angle deltaeAnd the throttle opening phi returns to the aircraft dynamics models (1) - (5) to carry out tracking control on the altitude and the speed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810950482.5A CN108762098B (en) | 2018-08-20 | 2018-08-20 | Non-minimum phase aircraft neural network control method based on Hybrid Learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810950482.5A CN108762098B (en) | 2018-08-20 | 2018-08-20 | Non-minimum phase aircraft neural network control method based on Hybrid Learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108762098A CN108762098A (en) | 2018-11-06 |
CN108762098B true CN108762098B (en) | 2019-11-01 |
Family
ID=63967366
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810950482.5A Active CN108762098B (en) | 2018-08-20 | 2018-08-20 | Non-minimum phase aircraft neural network control method based on Hybrid Learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108762098B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112859602B (en) * | 2021-01-11 | 2022-03-18 | 电子科技大学 | Non-minimum phase system output redefinition method |
CN114489095B (en) * | 2021-12-11 | 2023-12-26 | 西北工业大学 | Brain-like pulse neural network control method applied to variant aircraft |
CN114296352B (en) * | 2021-12-31 | 2022-10-04 | 北京理工大学 | Global stabilization control method and system for hypersonic aircraft |
CN117687308B (en) * | 2024-02-02 | 2024-04-19 | 北京理工大学 | Variant aircraft fault-tolerant control method based on fixed-time neural network observer |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6332105B1 (en) * | 1999-05-21 | 2001-12-18 | Georgia Tech Research Corporation | Neural network based automatic limit prediction and avoidance system and method |
GB2423377A (en) * | 2002-12-09 | 2006-08-23 | Georgia Tech Res Inst | Adaptive output feedback apparatuses and methods capable of controlling a non-minimum phase system. |
CN103365296A (en) * | 2013-06-29 | 2013-10-23 | 天津大学 | Nonlinear output feedback flight control method for quad-rotor unmanned aerial vehicle |
CN104765272A (en) * | 2014-03-05 | 2015-07-08 | 北京航空航天大学 | Four-rotor aircraft control method based on PID neural network (PIDNN) control |
US9146557B1 (en) * | 2014-04-23 | 2015-09-29 | King Fahd University Of Petroleum And Minerals | Adaptive control method for unmanned vehicle with slung load |
CN106094860A (en) * | 2016-08-29 | 2016-11-09 | 广西师范大学 | Quadrotor and control method thereof |
CN106647781A (en) * | 2016-10-26 | 2017-05-10 | 广西师范大学 | Neural-fuzzy PID control method of four-rotor aircraft based on repetitive control compensation |
CN107368091A (en) * | 2017-08-02 | 2017-11-21 | 华南理工大学 | A kind of stabilized flight control method of more rotor unmanned aircrafts based on finite time neurodynamics |
CN107450584A (en) * | 2017-08-29 | 2017-12-08 | 浙江工业大学 | Aircraft self-adaptive attitude control method based on fixed time sliding mode |
CN107450324A (en) * | 2017-09-05 | 2017-12-08 | 西北工业大学 | Consider the hypersonic aircraft adaptive fusion method of angle of attack constraint |
CN107479383A (en) * | 2017-09-05 | 2017-12-15 | 西北工业大学 | Hypersonic aircraft neutral net Hybrid Learning control method based on robust designs |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050137724A1 (en) * | 2003-10-10 | 2005-06-23 | Georgia Tech Research Corporation | Adaptive observer and related method |
-
2018
- 2018-08-20 CN CN201810950482.5A patent/CN108762098B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6332105B1 (en) * | 1999-05-21 | 2001-12-18 | Georgia Tech Research Corporation | Neural network based automatic limit prediction and avoidance system and method |
GB2423377A (en) * | 2002-12-09 | 2006-08-23 | Georgia Tech Res Inst | Adaptive output feedback apparatuses and methods capable of controlling a non-minimum phase system. |
CN103365296A (en) * | 2013-06-29 | 2013-10-23 | 天津大学 | Nonlinear output feedback flight control method for quad-rotor unmanned aerial vehicle |
CN104765272A (en) * | 2014-03-05 | 2015-07-08 | 北京航空航天大学 | Four-rotor aircraft control method based on PID neural network (PIDNN) control |
US9146557B1 (en) * | 2014-04-23 | 2015-09-29 | King Fahd University Of Petroleum And Minerals | Adaptive control method for unmanned vehicle with slung load |
CN106094860A (en) * | 2016-08-29 | 2016-11-09 | 广西师范大学 | Quadrotor and control method thereof |
CN106647781A (en) * | 2016-10-26 | 2017-05-10 | 广西师范大学 | Neural-fuzzy PID control method of four-rotor aircraft based on repetitive control compensation |
CN107368091A (en) * | 2017-08-02 | 2017-11-21 | 华南理工大学 | A kind of stabilized flight control method of more rotor unmanned aircrafts based on finite time neurodynamics |
CN107450584A (en) * | 2017-08-29 | 2017-12-08 | 浙江工业大学 | Aircraft self-adaptive attitude control method based on fixed time sliding mode |
CN107450324A (en) * | 2017-09-05 | 2017-12-08 | 西北工业大学 | Consider the hypersonic aircraft adaptive fusion method of angle of attack constraint |
CN107479383A (en) * | 2017-09-05 | 2017-12-15 | 西北工业大学 | Hypersonic aircraft neutral net Hybrid Learning control method based on robust designs |
Non-Patent Citations (5)
Title |
---|
《Adaptive Dynamic Surface Control for a Hypersonic Aircraft Using Neural Networks》;Jongho Shin;《IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS》;20171010;第53卷(第5期);全文 * |
《Neural Control for Longitudinal Dynamics of Hypersonic Aircraft》;Bin Xu;《2013 International Conference on Unmanned Aircraft Systems (ICUAS)》;20130531;全文 * |
《RBF Neural Network based Adaptive Sliding Mode Control for Hypersonic Flight Vehicles》;Jianmin Wang;《Proceedings of 2016 IEEE Chinese Guidance, Navigation and Control Conference》;20160815;全文 * |
《基于RBF 神经网络自适应PID四旋翼飞行器控制》;李砚浓;《控制工程》;20160331;第23卷(第3期);全文 * |
《基于混合神经网络的鲁棒自适应飞行控制器的设计》;王丽;《电光与控制》;20161130;第23卷(第11期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN108762098A (en) | 2018-11-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111665857B (en) | Variant aircraft control method based on composite intelligent learning | |
CN110377045B (en) | Aircraft full-profile control method based on anti-interference technology | |
CN108762098B (en) | Non-minimum phase aircraft neural network control method based on Hybrid Learning | |
CN107479384B (en) | The non-backstepping control method of hypersonic aircraft neural network Hybrid Learning | |
CN108828957B (en) | Aircraft overall situation finite time neural network control method based on handover mechanism | |
CN107450324B (en) | Consider the hypersonic aircraft adaptive fusion method of angle of attack constraint | |
CN109062234B (en) | A kind of non-minimum phase aircraft Hybrid Learning sliding-mode control | |
CN107479383B (en) | Hypersonic aircraft neural network Hybrid Learning control method based on robust designs | |
CN111679583B (en) | Adaptive control method of variant aircraft based on aerodynamic parameter estimation | |
CN109144084B (en) | A kind of VTOL Reusable Launch Vehicles Attitude tracking control method based on set time Convergence monitoring device | |
CN110908278B (en) | Dynamics modeling and stability control method of folding wing aircraft | |
CN107390531B (en) | The hypersonic aircraft control method of parameter learning finite time convergence control | |
CN109460050B (en) | Composite layered anti-interference control method for variant unmanned aerial vehicle | |
CN110568765A (en) | Asymmetric output limited control method for hypersonic aircraft facing attack angle tracking | |
CN112346470A (en) | Four-rotor attitude control method based on improved active disturbance rejection control | |
CN110456636B (en) | Self-adaptive control method of aircraft discrete sliding mode based on uncertainty upper bound estimation | |
CN109828602B (en) | Track loop nonlinear model transformation method based on observation compensation technology | |
CN104199286A (en) | Hierarchical dynamic inverse control method for flight vehicle based on sliding mode interference observer | |
CN110187715B (en) | Hypersonic aircraft coordination control method based on dynamic coupling analysis | |
CN111273681B (en) | Hypersonic aircraft high-safety anti-interference control method considering limited attack angle | |
CN107632518A (en) | Hypersonic aircraft neutral net Hybrid Learning control method based on High-gain observer | |
CN113778129A (en) | Hypersonic speed variable sweepback wing aircraft tracking control method with interference compensation | |
CN110320794A (en) | Elastic Vehicles singular perturbation Hybrid Learning control method based on disturbance-observer | |
CN114721266B (en) | Self-adaptive reconstruction control method under condition of structural failure of control surface of airplane | |
Lee et al. | Linear parameter-varying control of variable span-sweep morphing aircraft |
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 |