CN106200383B - A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network - Google Patents

A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network Download PDF

Info

Publication number
CN106200383B
CN106200383B CN201610645413.4A CN201610645413A CN106200383B CN 106200383 B CN106200383 B CN 106200383B CN 201610645413 A CN201610645413 A CN 201610645413A CN 106200383 B CN106200383 B CN 106200383B
Authority
CN
China
Prior art keywords
neural network
control
frame
adaptive neural
interference
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
Application number
CN201610645413.4A
Other languages
Chinese (zh)
Other versions
CN106200383A (en
Inventor
李志毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Yu Ying Technology Co Ltd
Original Assignee
Beijing Yu Ying Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Yu Ying Technology Co Ltd filed Critical Beijing Yu Ying Technology Co Ltd
Priority to CN201610645413.4A priority Critical patent/CN106200383B/en
Publication of CN106200383A publication Critical patent/CN106200383A/en
Application granted granted Critical
Publication of CN106200383B publication Critical patent/CN106200383B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04Adaptive 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
    • G05B13/042Adaptive 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

A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network, it is related to the Disturbance Rejection design of control parameter On-line Estimation and extended state observer based on adaptive neural network, first, according to three axis inertially stabilized platform kinetic models, for the uncertain caused feedback control parameters time-varying characteristics of three axis inertially stabilized platform kinetic parameters, it constructs adaptive neural network and On-line Estimation is carried out to feedback control matrix parameter, three axis inertially stabilized platforms control precision is made to approach expectational model control precision;Secondly, influence for adaptive neural network evaluated error and the interference compensation control amount of the upper bound building of three axis inertially stabilized platforms interference to control precision, building extended state observer is estimated and is inhibited to interference, realizes three axis inertially stabilized platform high-precision controls under complex environment.The present invention has many advantages, such as that real-time is good, dynamic parameter response is fast, it is adaptable to interfere multi-source, can be used for high-precision control etc. of the three axis inertially stabilized platforms under complicated multi-source interference environment.

Description

A kind of three axis inertially stabilized platforms control based on model reference adaptive neural network Method
Technical field
The three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network that the present invention relates to a kind of are fitted For aerial mapping stabilized platform high-precision control field.
Background technique
Three axis inertially stabilized platforms are fixed on flight carrier by pedestal, support and stablize remotely sensed image load, be isolated more The influence to the remotely sensed image load optical axis is interfered in source, is improved remote sensing load pointing accuracy over the ground, is with a wide range of applications.
Three axis inertially stabilized platforms interference type multiplicity during the work time, do not disturb there is only uncertain RANDOM WIND and Caused angular movement interference is vibrated by aircraft body, there is also due to load system mass center be not overlapped with system origin it is caused not Trimming moment, internal interference caused by platform sensor part measurement error, therefore, the complicated high-precision control sides disturbed under environment more Method has become one of the key technology of three axis inertially stabilized platform researchs.
To improve performance, PID control method, robust control, intelligent control method are used for three axis inertially stabilized platforms High-precision control.PID controller structure is simple, but poor anti jamming capability, it is difficult to ensure that three axis inertia under multi-source interference effect Platform stable precision.Robust control can inhibit system model parameter uncertainty and multi-source to interfere the influence to control precision, But controlling precision has biggish conservative.By a large amount of sample training, neural network infinite can approach nonlinear system, To solve the non-linear of three axis inertially stabilized platform kinetic models, high-precision gesture stability, but traditional nerve are realized Network needs a large amount of sample data to be trained, and has the shortcomings that real-time is poor.
Summary of the invention
Technical problem solved by the present invention is three axis inertially stabilized platforms control precision by system model is non-linear and multi-source The influence of interference solves the non-linear of model by adaptive neural network real-time estimation feedback control parameters, and constructs expansion Observer improves the anti-interference ability of system, realizes three axis inertially stabilized platform high-precision controls under complex environment.
The technical solution of invention are as follows: kinetic model is established first against three axis inertially stabilized platforms, according to expectation System performance index constructs three axis inertially stabilized platform reference driving force models, is fed back and is controlled in line tracking by adaptive network Parameter processed approaches three axis inertially stabilized platform kinetic models and reference model;Secondly, building expansion observer, reduces certainly Adapt to influence of the sign function gain of the upper bound building of neural network evaluated error and external disturbance to system control precision.Its Realize that steps are as follows:
(1) according to three axis inertially stabilized platform kinetic models, design reference model and feedback controller, feedback control is solved Parameter processedIt is special for the uncertain caused feedback control parameters time-varying of three axis inertially stabilized platform kinetic parameters Property, the feedback control parameters of adaptive neural network On-line Estimation time-variant nonlinear function are constructed,
Wherein,It is the weight matrix of adaptive neural network,It is adaptive neural network Basic function, l are the number of nodes of adaptive neural network hidden layer,For the state variable of system, n=6 is state variable Dimension, εjIt is the approximate error of adaptive neural network jth row, when j=1 indicates roll frame, j=2 pitching frame, table when j=3 Show orientation frame, three axis inertially stabilized platforms control precision is made to approach expectational model control precision;
(2) interference for the upper bound building interfered for adaptive neural network evaluated error and three axis inertially stabilized platforms is mended Influence of the control amount to system control precision is repaid, building extended state observer is estimated and is inhibited to interference,
Wherein,WithRespectively state variable z1And z2Estimated value, z1=e, z2=Δ=B ε x+Dd, e is current shape The state variable x of state amount x and reference modelmmDifference,It is adaptive neural network weight square real-time estimation value, For the coefficient matrix of frame input, m=3 is the dimension of system input, and ε is the approximate error of adaptive neural network, and d is system Frame interference, For the state equation of reference model Matrix,WithIt is that POLE PLACEMENT USING principle is based on according to dynamic performance requirement The matrix artificially designed, r are interference compensation control amount, w0> 0 is design variable, realizes three axis stable inertias under complex environment Platform high-precision control;
The three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network of the invention, wherein described Step (1) is for the uncertain caused feedback control parameters time-varying characteristics of three axis inertially stabilized platform kinetic parameters, structure Build the feedback control parameters of adaptive neural network On-line Estimation time-variant nonlinear functionThree axis inertially stabilized platforms are moved Mechanical model is expressed as
Wherein, x=[θj ωj]T,H=03×3, F=(fjk), j, k=1,2,3,
U=[u1 u2 u3]T, g=[g1 g2 g3]T, d=[d1 d2 d3]T,
Wherein, θjFor corresponding j frame angle, ωjFor corresponding j frame angular speed,What it is for state variable is Matrix number, ujFor the input of corresponding j frame voltage, g is the estimated value of the gimbal moment of intertia, djFor the interference of system j frame, by The perturbation value △ g of system interference, the gimbal moment of intertiajWith the control input perturbation △ b as caused by measurement noisejIt constitutes, bjFor frame The ideal control coefrficient of the corresponding j column of the coefficient matrix B of frame input, F are the corresponding perfect condition variable system with time-varying characteristics Matrix number;
Design reference model
WhereinIt is the control input of desired reference model;
Design of feedback controller
Wherein r=[r1 r2 r3]TIt is the control amount interfering d for compensation and designing, meets It is feedback control parameters;
Then system
Feedback control parameters
Due to hjk,fjk, k, j=1,2,3 be time-variant nonlinear function,It is also time-variant nonlinear function, therefore, utilizes The infinite extensive approximation capability of adaptive neural network carrys out On-line Estimation time-variant nonlinear function
Control based on model reference adaptive ANN Control inputs uj, adaptive neural network turnover rateWith Interference compensation control amount rjExpression formula be respectively
rj=-δjsgn(eTPB*j)
Wherein, B*jFor the jth column of the coefficient matrix B of frame input, matrix P is the positive definite symmetric solution of state equation,
PAmm+AmmTP=-Q
WhereinIt is positive definite symmetrical matrix,It is adaptive law gain matrix, adaptive neural network is estimated The upper bound of meter error and external disturbance is
δj>|εjx+dj/bj|
Wherein, εjIt is the approximate error of adaptive neural network;
The three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network of the invention, wherein described Step (2) building extended state observer is estimated and is inhibited to interference, realizes that three axis stable inertias under complex environment are flat Platform high-precision control, three axis inertially stabilized platform error state equations are
Wherein,S is the rate of change of Δ, and the extended state observer of building is,
Revised interference compensation control amount rjExpression formula be
Wherein, bjFor the ideal control coefrficient of the coefficient matrix B corresponding j column of frame input,It isJth+3 A component,Residual error B ε x and system interference Dd and disturbance estimated value z are estimated for system self-adaption neural network2It is residual DifferencedjFor the interference of system j frame, by the perturbation value △ of system interference, the gimbal moment of intertia gjWith the control input perturbation △ b as caused by measurement noisejIt constitutes, εjIt is the approximate error of adaptive neural network, table when j=1 Show roll frame, j=2 pitching frame, when j=3 indicates orientation frame, B*jFor the jth column of the coefficient matrix B of frame input, matrix P is shape The positive definite symmetric solution of state equation,
PAmm+AmmTP=-Q
WhereinIt is positive definite symmetrical matrix;
Corresponding system, which inputs, is
Wherein,It is the corresponding j column control input of desired reference model, gjFor the estimation of the corresponding j gimbal moment of intertia Value.
The advantages of the present invention over the prior art are that:
(1) present invention passes through the infinite extensive approximation capability of adaptive neural network, the feedback control of real-time estimation system Parameter, solve the problems, such as due to model parameter it is non-linear, it is uncertain caused by feedback control parameters time-variant nonlinears, make practical mould Type approaches reference model, and control method structure is simple, strong antijamming capability;
(2) present invention is further estimated using expansion observer in the case where adaptive neural network guarantees that system is stablized Disturbance suffered in the three axis inertially stabilized platform courses of work is counted and inhibits, control precision is high, can satisfy three axis stable inertias The high-precision control demand of platform;
(3) present invention only requires according to the status information in the three axis inertially stabilized platform courses of work, Li Yapunuo is utilized Husband's function designs adaptive neural network right value update matrix, can not be needed with the weight of online updating adaptive neural network Any sample training has the advantages that data acquisition is convenient, it is simple to calculate.
Detailed description of the invention
Fig. 1 is three axis inertially stabilized platform control flows;
Fig. 2 is three axis inertially stabilized platform pitch channel control effects in flight experiment;
Fig. 3 is three axis inertially stabilized platform roll channel control effects in flight experiment;
Fig. 4 is three axis inertially stabilized platform azimuthal channel control effects in flight experiment.
Specific embodiment
As shown in Figure 1, of the invention is implemented as follows
(1) building is based on model reference adaptive neural network
Based on Newton-Euler equation, the kinetics equation of three axis inertially stabilized platforms is expressed as
Wherein, x=[θj ωj]T,H=03×3, F=(fjk), j, k=1,2,3,
U=[u1 u2 u3]T,G= [g1 g2 g3]T, d=[d1 d2 d3]T,
Wherein, indicate that roll frame, j=2 pitching frame indicate orientation frame when j=3 when j=1,For the state of system Variable, n=6 are the dimension of state variable, θjFor corresponding j frame angle, ωjFor corresponding j frame angular speed, For the coefficient matrix of state variable,For the coefficient matrix of frame input, m=3 is the dimension of system input, ujFor phase The j frame voltage input answered, g are the estimated value of the gimbal moment of intertia, and d is system framework interference, by system interference, frame member The perturbation value △ g of inertiajWith the control input perturbation △ b as caused by measurement noisejIt constitutes, bjFor the coefficient matrix B of frame input The ideal control coefrficient of corresponding j column, F are corresponding perfect condition variation coefficient matrix, wherein
f31=f32=0,
Wherein, N indicates motor drive ratio, KeIndicate back electromotive force constant, KtIndicate motor torque coefficient, RmIndicate motor Resistance, JmIndicate the rotary inertia of motor, Ja=diag (Jax,Jay,Jaz) it is the rotary inertia of orientation frame in orientation frame coordinate system Projection on the direction x, y, z, Jp=diag (Jpx,Jpy,Jpz) it is the rotary inertia of pitching frame in pitching frame coordinate system x, y, the side z Upward projection, Jr=diag (Jrx,Jry,Jrz) be roll frame rotary inertia in roll frame in the direction roll coordinate system x, y, z On projection,For k system relative inertness space angular speed in k system x, y, the side z Downward mapping;Respectively roll frame opposite base exists in roll coordinate system, pitching frame with respect to roll frame The angular speed of pitching coordinate system, orientation frame with respect to pitching frame in azimuthal coordinates system, θrIndicate roll frame opposite base corner, θpTable Show corner of the pitching frame with respect to roll frame, θaCorner of the orientation frame with respect to pitching frame is indicated, by the code-disc being mounted on gimbal axis Measurement obtains, TdmTo act on the disturbance torque on motor, TdjFor the disturbance torque acted on j frame, rotary inertia is
J1=Jaz+N2Jm,
J2=Jpx+Jax+N2Jm,
J3=Jry+(Jay+Jpy)cos2θp+(Jaz+Jpz)sin2θp+N2Jm
Design reference model
WhereinFor the state equation matrix of reference model, WithIt is the matrix artificially designed according to dynamic performance requirement based on POLE PLACEMENT USING principle,It is the control input of desired reference model,
Design of feedback controller
Wherein r=[r1 r2 r3]TIt is the control amount interfering d for compensation and designing, meets It is feedback control parameters, then system
IfThen real system is infinite approaches desired reference model;
Therefore, feedback control parameters
Due to hjk,fjk, k, j=1,2,3 be time-variant nonlinear function,It is also time-variant nonlinear function, therefore, benefit With the infinite extensive approximation capability of adaptive neural network come On-line Estimation time-variant nonlinear function
Wherein,It is the weight matrix of adaptive neural network,It is adaptive neural network Basic function, l are the number of nodes of adaptive neural network hidden layer, εjIt is the approximate error of adaptive neural network;
Wherein,It is adaptive neural network ideal weight matrixJth row real-time estimation value,It is The basic function of adaptive neural network, l are the number of nodes of adaptive neural network hidden layer, εjIt is forcing for adaptive neural network Nearly error;
Therefore, the control based on model reference adaptive ANN Control inputs uj, adaptive neural network weight is more New matrix update ruleWith interference compensation control amount rjExpression formula be respectively
rj=-δjsgn(eTPB*j)
Wherein, e is the state variable x of current quantity of state x and expectational modelmmDifference, matrix P is the positive definite of state equation Symmetric solution,
PAmm+AmmTP=-Q
WhereinIt is positive definite symmetrical matrix,It is adaptive law gain matrix, B*jIt is the jth of B matrix The upper bound of column, adaptive neural network evaluated error and external disturbance is
δj>|εjx+dj/bj|
Wherein, εjIt is the approximate error of adaptive neural network, djFor the interference of system j frame;
(2) adaptive neural network is constructed
For the interference compensation control amount r of the upper bound of adaptive neural network evaluated error and external disturbance buildingjTo being The influence of system control precision, building extended state observer is estimated and is inhibited to interference, realizes three axis under complex environment Inertially stabilized platform high-precision control,
Definition status variable z1=e, z2=Δ=B ε x+Dd, then three axis inertially stabilized platform error state equations be
By z2Error state equation is introduced, and
Wherein, s is the rate of change of Δ, and the extended state observer of building is
Wherein,WithRespectively state variable z1And z2Estimated value, w0> 0 is design variable;
Pass through suitable Selecting All Parameters w0It can makeWithTight tracking e and Δ within the limited time,
Revised interference compensation control amount rjExpression formula be
Wherein,Residual error B ε x and system interference Dd and disturbance estimated value are estimated for system self-adaption neural network z2Residual error
Corresponding system, which inputs, is
Wherein,It is+ 3 components of jth.
(3) flight example
In flight course, according to the angle information of high-precision attitude measuring unit, three axis inertially stabilized platform frame systems System is adjusted correspondingly, and guarantees that the remote sensing load optical axis is vertical over the ground, flight result such as Fig. 2, Fig. 3 and Fig. 4 institute of certain experiment Show.
Three axis inertially stabilized platforms realize high-precision control, and the standard deviation of pitch channel is 0.0183 degree, and roll is logical The standard deviation in road is 0.0157, and the standard deviation of azimuthal channel is 0.0214.
The present invention is based on three axis Inertially-stabilizeplatform platform control methods of model reference adaptive neural network overcome it is existing High-precision control of the three axis inertially stabilized platforms in the case where disturbing environment complexity may be implemented in the deficiency of control method more.
The content that description in the present invention is not described in detail belongs to the prior art well known to professional and technical personnel in the field.

Claims (3)

1. a kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network, it is characterised in that realize Following steps:
(1) according to three axis inertially stabilized platform kinetic models, design reference model and feedback controller, feedback control ginseng is solved NumberFor the uncertain caused feedback control parameters time-varying characteristics of three axis inertially stabilized platform kinetic parameters, structure The feedback control parameters of adaptive neural network On-line Estimation time-variant nonlinear function are built,
Wherein,It is the weight matrix of adaptive neural network,It is the base letter of adaptive neural network Number, l is the number of nodes of adaptive neural network hidden layer,For the state variable of system, n=6 is the dimension of state variable Number, εjIt is the approximate error of adaptive neural network jth row, when j=1 indicates roll frame, j=2 pitching frame, expression side when j=3 Position frame makes three axis inertially stabilized platforms control precision approach expectational model control precision;
(2) the interference compensation control for the upper bound building interfered for adaptive neural network evaluated error and three axis inertially stabilized platforms Influence of the amount processed to system control precision constructs extended state observer and interference is estimated and inhibited,
Wherein,WithRespectively state variable z1And z2Estimated value, z1=e, z2=Δ=B ε x+Dd, e is current quantity of state x With the state variable x of reference modelmmDifference,It is adaptive neural network weight square real-time estimation value,For frame The coefficient matrix of frame input, m=3 are the dimensions of system input, and ε is the approximate error of adaptive neural network, and d is system framework Interference, For the state equation matrix of reference model,WithIt is artificial based on POLE PLACEMENT USING principle according to dynamic performance requirement The matrix of design, r are interference compensation control amount, w0> 0 is design variable, realizes three axis inertially stabilized platforms under complex environment High-precision control.
2. the three axis inertially stabilized platform controlling parties according to claim 1 based on model reference adaptive neural network Method, it is characterised in that: the step (1) is for the uncertain caused feedback control of three axis inertially stabilized platform kinetic parameters Parameter time varying characteristic processed constructs the feedback control parameters of adaptive neural network On-line Estimation time-variant nonlinear functionThree The kinetic model of axis inertially stabilized platform is expressed as
Wherein, x=[θj ωj]T,H=03×3, F=(fjk), j, k=1,2,3,
U=[u1 u2 u3]T, g=[g1 g2 g3]T, d=[d1 d2 d3]T,
Wherein, θjFor corresponding j frame angle, ωjFor corresponding j frame angular speed,For the coefficient square of state variable Battle array, ujFor the input of corresponding j frame voltage, g is the estimated value of the gimbal moment of intertia, djFor the interference of system j frame, by system It interferes, the perturbation value △ g of the gimbal moment of intertiajWith the control input perturbation △ b as caused by measurement noisejIt constitutes, bjIt is defeated for frame The ideal control coefrficient of the corresponding j column of the coefficient matrix B entered, F are the corresponding perfect condition variation coefficient square with time-varying characteristics Battle array;
Design reference model
WhereinIt is the control input of desired reference model;
Design of feedback controller
Wherein rjIt is the control amount for the corresponding frame interfering d for compensation and designing, meets It is Feedback control parameters;
Then system
Feedback control parameters
Due to hjk,fjk, k, j=1,2,3 be time-variant nonlinear function,It is also time-variant nonlinear function, therefore, utilization is adaptive The infinite extensive approximation capability of neural network is answered to carry out On-line Estimation time-variant nonlinear function
Control based on model reference adaptive ANN Control inputs uj, adaptive neural network more new lawIt is mended with interference Repay control amount rjExpression formula be respectively
rj=-δjsgn(eTPB*j)
Wherein, B*jFor the jth column of the coefficient matrix B of frame input, matrix P is the positive definite symmetric solution of state equation,
PAmm+AmmTP=-Q
WhereinIt is positive definite symmetrical matrix,It is adaptive law gain matrix, adaptive neural network estimation misses The upper bound of difference and external disturbance is
δj>|εjx+dj/bj|
Wherein, εjIt is the approximate error of adaptive neural network.
3. the three axis inertially stabilized platform controlling parties according to claim 1 based on model reference adaptive neural network Method, it is characterised in that: step (2) the building extended state observer is estimated and inhibited to interference, realizes complex environment Under three axis inertially stabilized platform high-precision controls, three axis inertially stabilized platform error state equations are
By z2Error state equation is introduced, andWherein, s is the rate of change of Δ, and the extended state observer of building is
Revised interference compensation control amount rjExpression formula be
Wherein, bjFor the ideal control coefrficient of the coefficient matrix B corresponding j column of frame input,It is+ 3 components of jth,Residual error B ε x and system interference Dd and disturbance estimated value z are estimated for system self-adaption neural network2Residual errordjFor the interference of system j frame, by the perturbation value △ g of system interference, the gimbal moment of intertiajWith Input perturbation △ b is controlled as caused by measurement noisejIt constitutes, εjIt is the approximate error of adaptive neural network, when j=1 indicates horizontal Frame is rolled, j=2 pitching frame indicates orientation frame, B when j=3*jFor the jth column of the coefficient matrix B of frame input, matrix P is state side The positive definite symmetric solution of journey,
PAmm+AmmTP=-Q
WhereinIt is positive definite symmetrical matrix;
Corresponding system, which inputs, is
Wherein,It is the corresponding j column control input of desired reference model, gjFor the estimated value of the corresponding j gimbal moment of intertia.
CN201610645413.4A 2016-08-08 2016-08-08 A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network Active CN106200383B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610645413.4A CN106200383B (en) 2016-08-08 2016-08-08 A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610645413.4A CN106200383B (en) 2016-08-08 2016-08-08 A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network

Publications (2)

Publication Number Publication Date
CN106200383A CN106200383A (en) 2016-12-07
CN106200383B true CN106200383B (en) 2019-10-18

Family

ID=57514611

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610645413.4A Active CN106200383B (en) 2016-08-08 2016-08-08 A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network

Country Status (1)

Country Link
CN (1) CN106200383B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107894713B (en) * 2017-10-20 2020-11-06 东南大学 High-precision control method for two-axis inertial stabilization platform without coding sensing
CN108469269A (en) * 2018-01-19 2018-08-31 天津大学 A kind of resonance point test system of wideband inertial reference stabilized platform

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1790197A (en) * 2005-12-22 2006-06-21 安徽工业大学 Simple method for neural network decoupling of multi-variable system based on model reference adaptive control
CN102053628A (en) * 2009-10-27 2011-05-11 北京航空航天大学 Neural network-based servo control system and method
CN102298315A (en) * 2011-06-21 2011-12-28 河海大学常州校区 Adaptive control system based on radial basis function (RBF) neural network sliding mode control for micro-electromechanical system (MEMS) gyroscope
CN102437816A (en) * 2011-10-25 2012-05-02 武汉鑫通科创科技发展有限公司 Adaptive motor motion control apparatus based on neural network
CN102508503A (en) * 2011-11-01 2012-06-20 北京航空航天大学 Compensation method based on generalized inner module for eccentric torque of three-shaft inertially stabilized platform
CN105785762A (en) * 2016-03-17 2016-07-20 北京航空航天大学 Bi-axis inertially-stabilized platform high-precision control method based on self-adaptive backstepping sliding mode

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1790197A (en) * 2005-12-22 2006-06-21 安徽工业大学 Simple method for neural network decoupling of multi-variable system based on model reference adaptive control
CN102053628A (en) * 2009-10-27 2011-05-11 北京航空航天大学 Neural network-based servo control system and method
CN102298315A (en) * 2011-06-21 2011-12-28 河海大学常州校区 Adaptive control system based on radial basis function (RBF) neural network sliding mode control for micro-electromechanical system (MEMS) gyroscope
CN102437816A (en) * 2011-10-25 2012-05-02 武汉鑫通科创科技发展有限公司 Adaptive motor motion control apparatus based on neural network
CN102508503A (en) * 2011-11-01 2012-06-20 北京航空航天大学 Compensation method based on generalized inner module for eccentric torque of three-shaft inertially stabilized platform
CN105785762A (en) * 2016-03-17 2016-07-20 北京航空航天大学 Bi-axis inertially-stabilized platform high-precision control method based on self-adaptive backstepping sliding mode

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
A compound control method based on the adaptive neural network and sliding mode control for inertial stable platform;YingZou,等;《Neurocomputing》;20150107(第155期);第286-294页 *
三轴式无人旋翼飞行器及自适应飞行控制系统设计;夏青元,等;《航空学报》;20130325;第34卷(第3期);第495-508页 *
基于PMI的三轴惯性稳定平台干扰力矩补偿方法研究;钟麦英,等;《仪器仪表学报》;20140430;第35卷(第4期);第782-787页 *

Also Published As

Publication number Publication date
CN106200383A (en) 2016-12-07

Similar Documents

Publication Publication Date Title
Xu et al. Neural network based dynamic surface control of hypersonic flight dynamics using small-gain theorem
CN105353615B (en) A kind of Active Fault-tolerant Control Method of the quadrotor based on sliding mode observer
Hamel et al. Evolution of flight vehicle system identification
Liu et al. Tracking control of small-scale helicopters using explicit nonlinear MPC augmented with disturbance observers
CN102862686B (en) Optical-integral sliding-mode attitude control method of reentry vehicle and controller
CN106325291B (en) Sliding mode control law and ESO (electronic stability program) based four-rotor aircraft attitude control method and system
CN105911866B (en) The finite time full-order sliding mode control method of quadrotor unmanned vehicle
Ren et al. A multi-position self-calibration method for dual-axis rotational inertial navigation system
CN103913181B (en) A kind of airborne distributed POS Transfer Alignments based on parameter identification
CN103616818B (en) The neural overall fast terminal sliding-mode control of adaptive fuzzy of gyroscope
CN105629732B (en) A kind of spacecraft attitude output Tracking Feedback Control method for considering Control constraints
CN102252673B (en) Correction method for on-track aberration of star sensor
CN105094138A (en) Low-altitude autonomous navigation system for rotary-wing unmanned plane
CN104281056B (en) The gyroscope Robust Adaptive Control method learnt based on the neutral net upper bound
CN103336435B (en) Gyroscope is based on the method for adaptive fuzzy sliding mode control of Attitude rate estimator
Luis et al. Design of a trajectory tracking controller for a nanoquadcopter
CN105759832A (en) Four-rotor aircraft sliding mode variable structure control method based on inversion method
CN102073755B (en) Motion control simulation method for near-space hypersonic aircraft
CN105159305B (en) A kind of quadrotor flight control method based on sliding moding structure
CN103900559B (en) A kind of high-precision attitude resolving system based on Interference Estimation
CN102506892B (en) Configuration method for information fusion of a plurality of optical flow sensors and inertial navigation device
CN103344243B (en) A kind of aerial remote sensing inertial-stabilized platform friction parameter discrimination method
CN103365296A (en) Nonlinear output feedback flight control method for quad-rotor unmanned aerial vehicle
CN105806365B (en) Rapid Alignment Technology between a kind of vehicle-mounted inertial navigation based on Active Disturbance Rejection Control is advanced
CN107608367B (en) Multivariable interference compensation quadrotor unmanned aerial vehicle trajectory and attitude cooperative control method

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
GR01 Patent grant