CN107479383B - Hypersonic aircraft neural network Hybrid Learning control method based on robust designs - Google Patents
Hypersonic aircraft neural network Hybrid Learning control method based on robust designs Download PDFInfo
- Publication number
- CN107479383B CN107479383B CN201710789243.1A CN201710789243A CN107479383B CN 107479383 B CN107479383 B CN 107479383B CN 201710789243 A CN201710789243 A CN 201710789243A CN 107479383 B CN107479383 B CN 107479383B
- Authority
- CN
- China
- Prior art keywords
- neural network
- follows
- hypersonic aircraft
- designs
- design
- 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
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
Abstract
The technical issues of hypersonic aircraft neural network Hybrid Learning control method based on robust designs that the invention discloses a kind of, the practicability is poor for solving existing hypersonic aircraft control method.Technical solution is converted to posture subsystem Strict-feedback form, obtains output feedback form, new defined variable is estimated with High-gain observer, provides basis for subsequent controllers design；Controller considers that the lump of system is uncertain, it is only necessary to which a neural network is approached, and controller design is simple, is convenient for Project Realization；Consider that control gain function is unknown, introduce lower bound information thereon, designs robust item to guarantee that system is stablized.Since Strict-feedback form is converted to output feedback form, effectively prevent approaching virtual controlling amount needed for future using neural network；For systematic uncertainty, robust item is designed, guarantees system stability；It constructs modeling error and designs neural network Hybrid Learning more new law, improve neural network learning speed.
Description
Technical field
The present invention relates to a kind of hypersonic aircraft control method, in particular to a kind of high ultrasound based on robust designs
Fast aircraft neural network Hybrid Learning control method.
Background technique
Hypersonic aircraft causes many military powers as a kind of advanced weapons with prompt strike capabilities
Great attention.Since itself uses the integrated design of engine/body, complicated kinetic model and flying ring in addition
Border, hypersonic aircraft have the characteristics such as strong nonlinearity and strong uncertainty.These features make hypersonic aircraft control
Device processed designs faces enormous challenge.Therefore, probabilistic processing is most important to hypersonic aircraft safe flight.
Backstepping is widely used in hypersonic aircraft control as a kind of typical control method.But traditional contragradience
There are inherent shortcomings for method design.Controller is designed using Backstepping, needs to carry out differential repeatedly for virtual controlling amount, this can make
At following problems: (1) differential will cause control design case " complexity explosion " problem repeatedly；(2) controller design process is more multiple
It is miscellaneous, it is unfavorable for Project Realization.Current dynamic surface and instruction filtering method are made to solve " complexity explosion " problem, but still need to anti-
Virtual controlling amount is designed again, and process is cumbersome.
《Neural network based dynamic surface control of hypersonic flight
Dynamics using small-gain theorem " (Bin Xu, Qi Zhang, Yongping Pan,
" Neurocomputing ", the 3rd phase of volume 173 in 2016) one text by design virtual controlling amount (pitch angle, rate of pitch)
It realizes the control to flight-path angle and pitch angle, finally controls rate of pitch using angle of rudder reflection；The Dynamic Surface Design still needs to gradually
Design virtual controlling amount is simultaneously handled the uncertainty in each channel, and design process is cumbersome, is unfavorable for Project Realization.
Summary of the invention
In order to overcome the shortcomings of existing hypersonic aircraft control method, the practicability is poor, and the present invention provides a kind of based on Shandong
The hypersonic aircraft neural network Hybrid Learning control method of stick design.This method is to posture subsystem Strict-feedback form
It is converted, obtains output feedback form, new defined variable is estimated with High-gain observer, is set for subsequent controllers
Meter provides basis；Controller considers that the lump of system is uncertain, it is only necessary to which a neural network is approached, controller design letter
It is single, it is convenient for Project Realization；Consider that control gain function is unknown, introduce lower bound information thereon, designs robust item to guarantee that system is steady
It is fixed.Since Strict-feedback form is converted to output feedback form, effectively prevent using neural network to virtual needed for future
Control amount is approached；For systematic uncertainty, control gain function bound information is made full use of, robust item is designed, is guaranteed
System stability；It constructs modeling error and designs neural network Hybrid Learning more new law, improve neural network learning speed, practicability
It is good.
A kind of the technical solution adopted by the present invention to solve the technical problems: hypersonic aircraft based on robust designs
Neural network Hybrid Learning control method, its main feature is that the following steps are included:
(a) hypersonic aircraft vertical passage kinetic model is established are as follows:
The vertical passage kinetic model is by five state variable X=[V, h, α, γ, q]TU is inputted with two controls
=[δe,β]TComposition；Wherein, V indicates speed, and γ indicates that flight path angle, h indicate height, and α indicates that the angle of attack, q indicate pitch angle speed
Degree, δeIt is angle of rudder reflection, β is throttle valve opening；T, D, L and MyyRespectively represent thrust, resistance, lift and pitch rotation torque；m,
Iyy, μ and r representation quality, the rotary inertia of pitch axis, gravitational coefficients and the distance away from the earth's core；
(b) height tracing error is definedWherein hdFor elevation references instruction；
It designs flight-path angle and instructs γdAre as follows:
Wherein, kh> 0 and ki> 0 is given by designer,For the first derivative of elevation references instruction；
According to time-scale separation, regard speed as slow dynamics, the first derivative of design flight-path angle instruction are as follows:
Wherein,For the second dervative of elevation references instruction；
In view of the flight-path angle variation of cruise section hypersonic aircraft is smaller, therefore two, three ranks that flight-path angle instructs are led
Number is considered as zero；
(c) posture X is defineda=[x1,x2,x3]T, wherein x1=γ, x2=θp, x3=q, θp=α+γ；Because Tsin α is remote
Less than L, approximation is ignored during controller design；
Write as following Strict-feedback form in posture subsystem (3)-(5):
Wherein, fi, i=1,2,3 and gi, i=1, the unknown that (3)-(5) formula obtains according to 2,3, andKnown quantityWithg iRespectively function giBound；
(d) new quantity of state Z=[z is defined1,z2,z3]T, wherein
Wherein a2, b2For fi, gi, i=1,2 complicated expression, are pilot process variable；
Posture subsystem (8) is converted into following output feedback form:
Wherein a3It is the unknown function of X, b3=g1g2g3；
(e) design High-gain observer is as follows
Wherein, ε > 0, d1> 0, d2>0；
Using High-gain observer to quantity of state Z=[z1,z2,z3]TEstimated, obtains its estimated valueWherein
(f) it is directed to posture subsystem, defines YdIt is as follows:
Then the estimated value of vector E and filter tracking error S are as follows:
Wherein, Λ=[λ2,2λ]T, λ > 0；
For unknown function a3(X), it is approached with neural network
Wherein,It is the estimated value of neural network optimal weights vector, θaIt (X) is Base Function vector；
For controlling gain function b3, meetWhereinWithb 3It is b respectively3's
The upper bound and lower bound, definitionThen b3It is represented by
b3=bmΔb (15)
Wherein, Δ b is multiplying property uncertainty and meets
Design controller
Wherein, kA> 0 is control gain parameter；Robust item urIt designs as follows:
Define modeling error zNNIt is as follows:
WhereinIt is obtained by following formula
Neural network weightMore new law it is as follows:
Wherein, γa, γz, γka, δaIt is positive parameter；
(g) speed tracing error Z is definedV=V-Vd, wherein VdFor speed reference instruction；
Desin speed controller is as follows:
β=- kVZV-lVsgn(ZV) (21)
Wherein, kV,lVIt is the positive parameter given by designer；
(h) according to obtained angle of rudder reflection δeWith throttle valve opening β, back to the kinetic model of hypersonic aircraft
(1)-(5) carry out tracing control to height and speed.
The beneficial effects of the present invention are: this method converts posture subsystem Strict-feedback form, it is anti-to obtain output
Feedback form estimates new defined variable with High-gain observer, provides basis for subsequent controllers design；Controller is examined
The lump of worry system is uncertain, it is only necessary to which a neural network is approached, and controller design is simple, is convenient for Project Realization；It examines
It is unknown to consider control gain function, introduces lower bound information thereon, designs robust item to guarantee that system is stablized.Due to by Strict-feedback shape
Formula is converted to output feedback form, effectively prevents approaching virtual controlling amount needed for future using neural network；For being
System is uncertain, makes full use of control gain function bound information, designs robust item, guarantees system stability；Construction modeling
Tolerance design neural network Hybrid Learning more new law, improves neural network learning speed, and practicability is good.
It elaborates with reference to the accompanying drawings and detailed description to the present invention.
Detailed description of the invention
Fig. 1 is the process of the hypersonic aircraft neural network Hybrid Learning control method the present invention is based on robust designs
Figure.
Specific embodiment
Referring to Fig.1.The present invention is based on the hypersonic aircraft neural network Hybrid Learning control method of robust designs tools
Steps are as follows for body:
(a) hypersonic aircraft vertical passage kinetic model is established:
The vertical passage kinetic model is by five state variable X=[V, h, α, γ, q]TU=is inputted with two controls
[δe,β]TComposition；Wherein, V indicates speed, and γ indicates that flight path angle, h indicate height, and α indicates that the angle of attack, q indicate rate of pitch,
δeIt is angle of rudder reflection, β is throttle valve opening；T, D, L and MyyRespectively represent thrust, resistance, lift and pitch rotation torque；m,Iyy、μ
With r representation quality, the rotary inertia of pitch axis, gravitational coefficients and away from the distance in the earth's core；
Relevant torque and parameter definition are as follows:
CM(α)=- 0.035 α2+0.036617α+5.3261×10-6,
CM(δe(the δ of)=0.0292e- α),
Wherein, ρ indicates atmospheric density, and S indicates pneumatic area of reference,Indicate mean aerodynamic chord, Cx, x=L, D, T, M
Indicate power and kinematic coefficient；
(b) height tracing error is definedWherein hdFor elevation references instruction, given by designer；
It designs flight-path angle and instructs γdAre as follows:
Wherein, kh> 0 and ki> 0 is given by designer,For the first derivative of elevation references instruction；
According to time-scale separation, regard speed as slow dynamics, the first derivative of design flight-path angle instruction are as follows:
Wherein,For the second dervative of elevation references instruction；
In view of the flight-path angle variation of cruise section hypersonic aircraft two, three ranks that are smaller, therefore flight-path angle being instructed
Derivative is considered as zero；
(c) posture X is defineda=[x1,x2,x3]T, wherein x1=γ, x2=θp, x3=q, θp=α+γ；Because Tsin α is remote
Less than L, approximation is ignored during controller design；
Write as following Strict-feedback form in posture subsystem (3)-(5):
Wherein,
AndWhereinWithg i> 0 is respectively function giAbsolute value bound, for
Know；
(d) new quantity of state Z=[z is defined1,z2,z3]T, wherein
z2And z3To the time, derivation obtains following formula respectively:
Wherein,
Wherein,
Control gain function b3MeetWhereinWithb 3It is b respectively3The upper bound and
Lower bound；Posture subsystem (8) is converted into following output feedback form:
Wherein a3It is unknown, b3=g1g2g3；
(e) design High-gain observer is as follows
Wherein, parameter ε > 0, d1> 0, d2> 0 is given by designer；
Using High-gain observer to quantity of state Z=[z1,z2,z3]TEstimated, obtains its estimated value
(f) it is directed to posture subsystem, defines YdIt is as follows:
Then the estimated value of vector E and filter tracking error S are as follows:
Wherein, Λ=[λ2,2λ]T, λ > 0 is given by designer；
For unknown function a3(X), it is approached with neural network；
Wherein,It is the estimated value of neural network optimal weights vector, θaIt (X) is Base Function vector；
For function b3, definitionThen b3It is represented by
b3=bmΔb (15)
Wherein, Δ b is multiplying property uncertainty and meets
Design controller
Wherein, kA> 0 is the control gain parameter given by designer；Robust item urIt designs as follows:
Define modeling error zNNIt is as follows:
WhereinIt can be obtained by following formula
Wherein, γz> 0 is given by designer；
Neural network weightComplex updates rule it is as follows:
Wherein, γa, γka, δaIt is the positive parameter given by designer；
(g) speed tracing error Z is definedV=V-Vd, wherein VdFor speed reference instruction, given by designer；
It is as follows to design controller:
β=- kVZV-lVsgn(ZV) (21)
Wherein, kV,lVIt is the positive parameter given by designer；
(h) according to obtained angle of rudder reflection δeWith throttle valve opening β, back to the kinetic model of hypersonic aircraft
(1)-(5) carry out tracing control to height and speed.
Unspecified part of the present invention belongs to field technical staff's common knowledge.
Claims (1)
1. a kind of hypersonic aircraft neural network Hybrid Learning control method based on robust designs, it is characterised in that including
Following steps:
(a) hypersonic aircraft vertical passage kinetic model is established are as follows:
The vertical passage kinetic model is by five state variable X=[V, h, α, γ, q]TU=is inputted with two controls
[δe,β]TComposition；Wherein, V indicates speed, and γ indicates that flight path angle, h indicate height, and α indicates that the angle of attack, q indicate rate of pitch,
δeIt is angle of rudder reflection, β is throttle valve opening；T, D, L and MyyRespectively represent thrust, resistance, lift and pitch rotation torque；m,Iyy、μ
With r representation quality, the rotary inertia of pitch axis, gravitational coefficients and away from the distance in the earth's core；
(b) height tracing error is definedWherein hdFor elevation references instruction；
It designs flight-path angle and instructs γdAre as follows:
Wherein, kh> 0 and ki> 0 is given by designer,For the first derivative of elevation references instruction；
According to time-scale separation, regard speed as slow dynamics, the first derivative of design flight-path angle instruction are as follows:
Wherein,For the second dervative of elevation references instruction；
In view of the flight-path angle variation of cruise section hypersonic aircraft is smaller, therefore two, three order derivatives of flight-path angle instruction are regarded
It is zero；
(c) posture X is defineda=[x1,x2,x3]T, wherein x1=γ, x2=θp, x3=q, θp=α+γ；Because Tsin α is much smaller than L,
Ignore during controller design；
Write as following Strict-feedback form in posture subsystem (3)-(5):
Wherein, f1, f2, f3, g1, g3According to the obtained the unknown of (3)-(5) formula, g2=1, and?
The amount of knowingWithg iRespectively function giBound；
(d) new quantity of state Z=[z is defined1,z2,z3]T, wherein
Wherein a2, b2It is by f1+g1x2The pilot process variable that derivation obtains, is about f1, f2, g1, g2Function；
Posture subsystem (8) is converted into following output feedback form:
Wherein a3It is the unknown function of X, b3=g1g2g3；
(e) design High-gain observer is as follows
Wherein, ε > 0, d1> 0, d2> 0；
Using High-gain observer to quantity of state Z=[z1,z2,z3]TEstimated, obtains its estimated valueIts
In
(f) it is directed to posture subsystem, defines YdIt is as follows:
Then the estimated value of vector E and filter tracking error S are as follows:
Wherein, Λ=[λ2,2λ]T, λ > 0；
For unknown function a3(X), it is approached with neural network
Wherein,It is the estimated value of neural network optimal weights vector, θaIt (X) is Base Function vector；
For controlling gain function b3, meetWhereinAnd b3It is b respectively3The upper bound
And lower bound, definitionThen b3It is represented by
b3=bmΔb (15)
Wherein, Δ b is multiplying property uncertainty and meets
Design controller
Wherein, kA> 0 is control gain parameter；Robust item urIt designs as follows:
Define modeling error zNNIt is as follows:
WhereinIt is obtained by following formula
Neural network weightMore new law it is as follows:
Wherein, γa, γz,δaIt is positive parameter；
(g) speed tracing error Z is definedV=V-Vd, wherein VdFor speed reference instruction；
Desin speed controller is as follows:
β=- kVZV-lVsgn(ZV) (21)
Wherein, kV,lVIt is the positive parameter given by designer；
(h) according to obtained angle of rudder reflection δeWith throttle valve opening β, back to the kinetic model (1)-of hypersonic aircraft
(5), tracing control is carried out to height and speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710789243.1A CN107479383B (en) | 2017-09-05 | 2017-09-05 | Hypersonic aircraft neural network Hybrid Learning control method based on robust designs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710789243.1A CN107479383B (en) | 2017-09-05 | 2017-09-05 | Hypersonic aircraft neural network Hybrid Learning control method based on robust designs |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107479383A CN107479383A (en) | 2017-12-15 |
| CN107479383B true CN107479383B (en) | 2019-10-22 |
Family
ID=60604456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710789243.1A Active CN107479383B (en) | 2017-09-05 | 2017-09-05 | Hypersonic aircraft neural network Hybrid Learning control method based on robust designs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107479383B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108828957B (en) * | 2018-08-20 | 2019-11-05 | 西北工业大学 | Aircraft overall situation finite time neural network control method based on handover mechanism |
| CN108897227B (en) * | 2018-08-20 | 2019-09-24 | 西北工业大学 | Non-linear strict feedback systems overall situation finite time neural network control method |
| CN109062234B (en) * | 2018-08-20 | 2019-11-05 | 西北工业大学 | A kind of non-minimum phase aircraft Hybrid Learning sliding-mode control |
| CN109062049B (en) * | 2018-08-20 | 2019-09-24 | 西北工业大学 | Strict feedback systems neural network control method based on the compound estimation of lump |
| CN108663940B (en) * | 2018-08-20 | 2019-09-24 | 西北工业大学 | Aircraft neural network lea rning control method based on the compound estimation of lump |
| CN108762098B (en) * | 2018-08-20 | 2019-11-01 | 西北工业大学 | Non-minimum phase aircraft neural network control method based on Hybrid Learning |
| CN109062055A (en) * | 2018-09-10 | 2018-12-21 | 南京航空航天大学 | A kind of Near Space Flying Vehicles control system based on Back-stepping robust adaptive dynamic surface |
| CN109514558B (en) * | 2018-12-24 | 2022-03-15 | 中国航空工业集团公司西安飞机设计研究所 | Flexible mechanical arm time scale separation robust control method based on singular perturbation |
| CN110488852B (en) * | 2019-08-28 | 2020-12-01 | 北京航空航天大学 | Full-profile self-adaptive control method for hypersonic aircraft |
| CN113093539B (en) * | 2021-03-29 | 2022-08-09 | 西北工业大学 | Wide-area flight robust self-adaptive switching control method based on multi-mode division |
| 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 |
| CN114397819B (en) * | 2022-01-13 | 2023-10-13 | 大连理工大学 | Event triggering self-adaptive control method of aero-engine actuating mechanism |
| CN114779636B (en) * | 2022-04-17 | 2023-08-01 | 西北工业大学 | Aircraft robust self-adaptive control method considering pneumatic servo elasticity |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2423377B (en) * | 2002-12-09 | 2007-04-18 | Georgia Tech Res Inst | Adaptive Output Feedback Apparatuses And Methods Capable Of Controlling A Non-Minimum Phase System |
| US20050137724A1 (en) * | 2003-10-10 | 2005-06-23 | Georgia Tech Research Corporation | Adaptive observer and related method |
| US8285659B1 (en) * | 2009-08-18 | 2012-10-09 | The United States of America as represented by the Administrator of the National Aeronautics & Space Administration (NASA) | Aircraft system modeling error and control error |
| CN102880055B (en) * | 2012-09-29 | 2014-11-26 | 西北工业大学 | Method for controlling neural network of hypersonic aerocraft on basis of prediction model |
| CN102880052B (en) * | 2012-09-29 | 2014-12-31 | 西北工业大学 | Time scale function decomposition based hypersonic aircraft actuator saturation control method |
| CN102929141B (en) * | 2012-10-10 | 2015-03-18 | 西北工业大学 | Aircraft time lag varying model approximation and controller designing method |
| CN103365296B (en) * | 2013-06-29 | 2015-12-09 | 天津大学 | A kind of four rotor unmanned aircraft nonlinear object feedback flight control methods |
| 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 |
| CN104022742B (en) * | 2014-06-19 | 2017-12-12 | 金陵科技学院 | Attitude of flight vehicle robust inverting fault tolerant control method based on Neural Network Observer |
-
2017
- 2017-09-05 CN CN201710789243.1A patent/CN107479383B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107479383A (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107479383B (en) | Hypersonic aircraft neural network Hybrid Learning control method based on robust designs | |
| CN107479384B (en) | The non-backstepping control method of hypersonic aircraft neural network Hybrid Learning | |
| CN107632518B (en) | Hypersonic aircraft neural network Hybrid Learning control method based on High-gain observer | |
| CN107450324B (en) | Consider the hypersonic aircraft adaptive fusion method of angle of attack constraint | |
| CN107390531B (en) | The hypersonic aircraft control method of parameter learning finite time convergence control | |
| CN107526296B (en) | Hypersonic aircraft neural network lea rning control method based on prediction modeling | |
| CN108828957B (en) | Aircraft overall situation finite time neural network control method based on handover mechanism | |
| CN111694375B (en) | Parafoil system track planning method and system, and track tracking control method and system | |
| Wang et al. | Fuzzy radial basis function neural network PID control system for a quadrotor UAV based on particle swarm optimization | |
| CN108776434B (en) | Rapid self-adaptive sliding mode fault-tolerant control method for hypersonic aircraft | |
| CN103853050A (en) | PID optimization control method of four-rotor aircraft | |
| Lawrance et al. | A guidance and control strategy for dynamic soaring with a gliding UAV | |
| CN111880555B (en) | Parafoil system obstacle avoidance flight path planning method and system | |
| CN114355777B (en) | Dynamic gliding method and system based on distributed pressure sensor and sectional attitude control | |
| CN109828602A (en) | A kind of track circuit nonlinear model transform method based on observation compensation technique | |
| AliKhan et al. | Flight dynamics and optimization of three-dimensional perching maneuver | |
| CN108089589A (en) | A kind of underwater robot attitude control method | |
| CN107479382B (en) | Hypersonic aircraft neural network control method based on online data study | |
| CN110187715A (en) | A kind of hypersonic aircraft control method for coordinating based on dynamic Coupling Analysis | |
| CN108762098B (en) | Non-minimum phase aircraft neural network control method based on Hybrid Learning | |
| CN108303889A (en) | A kind of time-scale separation aircraft elasticity body controlling means based on nonlinear transformations | |
| Langelaan | Biologically inspired flight techniques for small and micro unmanned aerial vehicles | |
| CN110347036A (en) | The autonomous wind resistance intelligent control method of unmanned plane based on fuzzy sliding mode tracking control | |
| US20220319257A1 (en) | Aircraft motion observer configured for use in electric aircraft | |
| CN110376887B (en) | Aircraft discrete sliding mode intelligent control method based on time-varying sliding mode gain |
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 |