CN109324503A - Multilayer neural network electric system control method based on robust integral - Google Patents
Multilayer neural network electric system control method based on robust integral Download PDFInfo
- Publication number
- CN109324503A CN109324503A CN201810990916.4A CN201810990916A CN109324503A CN 109324503 A CN109324503 A CN 109324503A CN 201810990916 A CN201810990916 A CN 201810990916A CN 109324503 A CN109324503 A CN 109324503A
- Authority
- CN
- China
- Prior art keywords
- formula
- function
- neural network
- robust
- multilayer neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention provides a kind of multilayer neural network electric system control methods based on robust integral, comprising the following steps: step 1, establishes the mathematical model of electric system；Step 2, the multilayer neural network controller of design robust integral；Step 3, carrying out stability with Lyapunov stability theory proves, and obtains half globally asymptotically stable result of system with mean value theorem.
Description
Technical field
The present invention relates to a kind of motor servo control technology, especially a kind of multilayer neural network electricity based on robust integral
Machine system control method.
Background technique
Motor servo system has outstanding advantages of response is fast, easy to maintain, transmission efficiency is high and energy acquisition facilitates,
It is widely used in each key areas, such as robot, lathe, electric car.With the quick hair of modern scientist engineering field
Exhibition, the requirement to motor servo system tracking performance is also higher and higher, but how to design controller to guarantee motor servo system
The high-performance of system is still a problem.This is because motor servo system is a typical nonlinear system, controlled in design
It is uncertain (such as unmodeled interference, non-linear friction) that many modelings can be faced during device processed, these factors may
Make so that the controller of system name modelling is unstable or depression of order.
For the nonlinear Control of motor servo system, many achievements are had been achieved for.Such as modified feedback linearization control side
Method can guarantee the high-performance of system, but with the proviso that the mathematical model established is very accurate, all Nonlinear Dynamics are all
It is known；In order to solve the problems, such as that modeling is uncertain, adaptive robust control method is suggested, which is depositing
Can make in the case where modeling uncertain the tracking error of motor servo system obtain uniform ultimate bounded as a result, such as
Obtaining high tracking performance then must be by improving feedback oscillator to reduce tracking error；Equally, robust control method is integrated
(RISE) the uncertain problem of modeling can also be efficiently solved, and can obtain continuous control input and it is asymptotic with
The performance of track.But the value of the feedback oscillator of the control method is closely related with modeling probabilistic size, once modeling
It is uncertain very big, it will to obtain high gain feedback controller, this does not allow in practice in engineering；Sliding-mode control
Motor servo system can also be made to obtain the performance of asymptotic tracking in the presence of modeling uncertain, but this method
Designed discontinuous controller easily causes the Flutter Problem of sliding-mode surface, to deteriorate the tracking performance of system.It summarizes and
It says, the shortcoming of existing motor servo system control method mainly has the following:
One, ignore system modelling uncertainty.The modeling uncertainty of motor servo system includes non-linear friction and not
Modeling interference etc..Friction is one of the main source of motor servo system damping, stick-slip caused by the presence of friction, pole
The unfavorable factors such as limit ring oscillation have important influence to the performance of system.In addition, actual motor servo system all can be by outer
The interference of load can deteriorate system tracking performance if not taking in；
Two, High Gain Feedback.There is High Gain Feedback in current many control methods, by improve feedback oscillator come
Reduce tracking error.However the high frequency as caused by High Gain Feedback dynamic and measurement noise the problem of will will affect system with
Track performance.
Summary of the invention
The purpose of the present invention is to provide a kind of multilayer neural network electric system control method based on robust integral, packets
Include following steps:
Step 1, the mathematical model of electric system is established；
Step 2, the multilayer neural network controller of design robust integral；
Step 3, carrying out stability with Lyapunov stability theory proves, and obtains system with mean value theorem
Half globally asymptotically stable result.
Compared with prior art, the present invention its remarkable advantage is: efficiently solving traditional robust integral control method and deposit
High Gain Feedback the problem of, obtain better tracking performance.Simulation results show its validity.
The invention will be further described with reference to the accompanying drawings of the specification.
Detailed description of the invention
Fig. 1 is the schematic diagram of electric system of the present invention.
Fig. 2 is hydraulic system ADAPTIVE ROBUST low frequency learning control method schematic illustration.
Fig. 3 is the schematic diagram for the input u that self-adaptive robust controller acts on lower system.
Fig. 4 is that self-adaptive robust controller acts on lower system output to the position tracking schematic diagram of expectation instruction.
Fig. 5 is that the mentioned method of this patent and other methods tracking error compare.
Specific embodiment
In conjunction with Fig. 1~2, the present invention is based on the multilayer neural network control methods that robust integrates, comprising the following steps:
Step 1, the mathematical model of hydraulic system is established；
(1.1) according to Newton's second law, the equation of motion of motor position servo system are as follows:
M is inertia load parameter, k in formula (1)iFor torque error constant, B is viscosity friction coefficient,It is to rub
The uncertain item of modeling error and outer interference is wiped, y is the displacement of inertia load, and u is that the control of system inputs, and t is time change
Amount；
(1.2) definition status variable:Then formula (1) equation of motion is converted into state equation:
In formula (2), φ=Bx2/ m,Its
Middle fdIt indicates the function only and system command is related with the derivative of instruction,It is the concentration interference of system, f
(x1,x2, t) it is as above-mentionedx1Indicate the displacement of inertia load, x2Indicate the speed of inertia load.
For convenient for controller design, it is assumed that as follows:
Assuming that 1: system interference d (t) and its derivative bounded
Wherein δ1,δ2For known normal number.
Assuming that 2: desired locations track xd∈C3, and bounded.
Property 1: having the ability of arbitrary smooth function after all according to multilayer neural network, and f can use three-layer neural network table
Show
In formulaV∈R3×10It is bounded, W ∈ R11It is also bounded, activation primitive σ () can be
Sigmoid function, the guidable function such as tanh function, ε () are the reconstructed error of function,
It can be obtained by (4)
HereWrite the parameter Estimation to be designed down, the error between output estimation and really parameter is defined as
Error between output layer is defined as
Self-tuning controller is designed described in step 2, steps are as follows:
(2.1) e is defined1=x1-x1dFor the tracking error of system, x1dIt is that system it is expected the position command tracked and this refers to
Three rank continuously differentiables are enabled, according to first equation in formula (2)Choose x2For virtual controlling, make equationTend to
Stable state；Enabling α is the desired value of virtual controlling, and the error of α and time of day x2 is e2=α-x2, e1 derivation can be obtained:
Design virtual controlling rule:
K in formula (5)1> 0 is adjustable gain, then
Due to e1(s)=G (s) e2(s), G (s)=1/ (s+k in formula1) it is a stable transmission function, work as e2Tend to 0
When, e1Also necessarily tend to 0.So in next design, it will be so that e2Tend to 0 as main design goal.
To e2Derivation can obtain (10):
Due to following auxiliary function
k2> 0 is the adjustable feedback oscillator of system
The expression formula that r can be obtained is
(2.2) according to formula (13), System design based on model device be may be designed as:
K in formula (14)rThe feedback oscillator being positive, uaFor the compensation term based on model, usFor Robust Control Law and wherein us1For
Linear robust feedback term, us2The influence to system performance is used to overcome modeling uncertain and interfered for non linear robust item.
Formula (14) are substituted into formula (13), to r derivation:
Formula (15) can be written as
In formula
Lemma 1: according to mean value theorem
Wherein
Z (t) :=[e1,e2,r]T (19)
ρ (| | z | |) it is non decreasing function.
N:=Nd+NB (20)
NB:=NB1+NB2 (22)
For positive number.
(2.3) it is based on Liapunov stability proof procedure, the on-line parameter of available neural network parameter is adaptive
It should rate:
Carrying out stability to hydraulic system with Lyapunov stability theory described in step 3 proves, and uses
Barbalat lemma obtains the globally asymptotically stable as a result, specific as follows of system:
It introduces with minor function
It chooses
Provable P (t) >=0.
Wherein
Φ (t) >=0 can be obtained.
It is as follows to define liapunov function:
Defined function
Carrying out stability with Lyapunov stability theory proves, and obtains half overall situation of system with mean value theorem
It is asymptotically stable as a result, therefore adjust gain k1、k2、krAnd Γ1、Γ2The tracking error of system is set to tend to be infinite in the time
Under the conditions of go to zero.
Choose positive definite matrix
Meet
It can obtain, the tracking error that designed controller meets system in following convergence domain again tends to infinite condition in the time
Under go to zero,
It is as shown in Figure 2 that electric system robust integrates multilayer neural network control principle schematic diagram.
Embodiment
Motor position servo system parameter is inertia load parameter: m=0.02kg；Viscosity friction coefficient B=10Nm
s/°；Torque error constant ki=6N/V；It is interfered outside time-varying
The position command of system expectation tracking is sinusoidal instruction as shown in Figure 4, and the velocity and acceleration of instruction is at any time
The curve of variation also provides together.
Contrast simulation result: multilayer neural network controller (NNRISE) parameter based on robust integral is chosen: k1=
300；k2=100；β=60；PID controller parameter is chosen: kP=1699；kI=13097；kD=0.
Wherein the selecting step of PID controller parameter is: first the case where ignoring motor servo system Nonlinear Dynamic
Under, a group controller parameter is obtained by pid parameter self-setting function in Matlab, then by the Nonlinear Dynamic of system
State, which is finely adjusted acquired Self-tuning System parameter after adding, makes system obtain optimal tracking performance.kDThe reason of being taken as zero
It is that can influence the performance of system, therefore what is actually obtained is PI control to avoid tachometric survey noise is generated in practice in engineering
Device.
Controller action effect: Fig. 4 indicates the system perspective tracking error under NNRISE controller, and Fig. 5 indicates PID control
The curve comparison that the tracking error of system changes over time under device RISE processed and NNRISE controller action, can from figure
Out, the output feedback robust controller designed by the present invention has very big mention compared to traditional PID controller on tracking performance
It is high.
Claims (5)
1. a kind of multilayer neural network electric system control method based on robust integral, which comprises the following steps:
Step 1, the mathematical model of electric system is established；
Step 2, the multilayer neural network controller of design robust integral；
Step 3, carrying out stability with Lyapunov stability theory proves, and obtains the partly complete of system with mean value theorem
The asymptotically stable result of office.
2. the method according to claim 1, wherein the mathematical model motor position of electric system described in step 1
Set the equation of motion of servo-system are as follows:
M is inertia load parameter, k in formula (1)iFor torque error constant, B is viscosity friction coefficient,It is Friction Modeling
Error and the uncertain item of outer interference, y are the displacement of inertia load, and u is that the control of system inputs, and t is time variable；
State equation is converted by the equation of motion of formula (1):
State variableφ=Bx2/ m, Wherein fdIndicate that derivative of the function only with system command and instruction has
It closes,It is the concentration interference of system, f (x1,x2, t) it is as above-mentionedx1Indicate the position of inertia load
It moves, x2Indicate the speed of inertia load, x1dIt is the position command and the three rank continuously differentiable of instruction of system expectation tracking.
3. according to the method described in claim 2, it is characterized in that, for convenient for controller design, it is assumed that as follows:
Assuming that 1: system interference d (t) and its derivative bounded
Wherein δ1,δ2For known normal number；
Assuming that 2: desired locations track xd∈C3, and bounded；
Property 1: having the ability of arbitrary smooth function after all according to multilayer neural network, and f can be indicated with three-layer neural network
In formulaV∈R3×10It is bounded, W ∈ R11It is bounded (R indicates constant), activation primitive σ () is
Sigmoid function or tanh function, ε () are the reconstructed error of function.
4. according to the method described in claim 3, it is characterized in that, the multilayer neural network control of step 2 design robust integral
The step of device, is as follows:
Step 2.1, e is defined1=x1-x1dFor the tracking error of system, x1dIt is the position command of system expectation tracking and the instruction
Three rank continuously differentiables, according to first equation in formula (2)Choose x2For virtual controlling, make equationTend to be steady
Determine state；
Enabling α is the desired value of virtual controlling, α and time of day x2Error be e2=α-x2；
To e1Derivation can obtain:
Design virtual controlling rule:
K in formula (9)1> 0 is adjustable gain, then
Due to e1(s)=G (s) e2(s), G (s)=1/ (s+k in formula1) it is a stable transmission function, work as e2When tending to 0, e1
Also necessarily tend to 0；
To e2Derivation can obtain
Due to following auxiliary function
k2> 0 is the adjustable feedback oscillator of system,
The expression formula that r can be obtained is
Step 2.2, System design based on model device may be designed as:
In formula (11), krThe adjustable feedback gain being positive, uaFor the compensation term based on model, usFor Robust Control Law, us1It is linear
Robust feedback term, us2The influence to system performance is used to overcome modeling uncertain and interfered for non linear robust item；
Formula (11) are substituted into formula (10), to r derivation:
Formula (12) is written as
In formula
Lemma 1: according to mean value theorem
Wherein
Z (t) :=[e1,e2,r]T (16)
ρ (| | z | |) it is non decreasing function.
N:=Nd+NB (17)
NB:=NB1+NB2 (19)
For positive number；
Step 2.3, it is based on Liapunov stability proof procedure, the on-line parameter of available neural network parameter is adaptive
Rate
Wherein, Γ1And Γ2It is the adaptive gain matrix of positive definite.
5. according to the method described in claim 4, it is characterized in that, the detailed process of step 3 is specific as follows:
It introduces with minor function
It chooses
Provable P (t) >=0；
Wherein
Φ (t) >=0 can be obtained；
It is as follows to define liapunov function:
Defined function
Carrying out stability with Lyapunov stability theory proves, and obtains half Global Asymptotic of system with mean value theorem
It is stable as a result, therefore adjusting gain k1、k2、krAnd Γ1、Γ2Make the tracking error of system under conditions of the time tending to be infinite
It goes to zero.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810990916.4A CN109324503B (en) | 2018-08-28 | 2018-08-28 | Multilayer neural network motor system control method based on robust integration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810990916.4A CN109324503B (en) | 2018-08-28 | 2018-08-28 | Multilayer neural network motor system control method based on robust integration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109324503A true CN109324503A (en) | 2019-02-12 |
| CN109324503B CN109324503B (en) | 2022-02-15 |
Family
ID=65263514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810990916.4A Active CN109324503B (en) | 2018-08-28 | 2018-08-28 | Multilayer neural network motor system control method based on robust integration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109324503B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110703609A (en) * | 2019-11-18 | 2020-01-17 | 南京工业大学 | Intelligent motion control method for motor servo system |
| CN113359440A (en) * | 2021-05-24 | 2021-09-07 | 华南理工大学 | Multi-rotor unmanned aerial vehicle controller design method based on multilayer integral neurodynamics |
Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101725468A (en) * | 2008-10-28 | 2010-06-09 | 西门子公司 | Wind turbine arrangement and method for aligning a wind turbine with the wind direction |
| CN101917150A (en) * | 2010-06-24 | 2010-12-15 | 江苏大学 | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof |
| CN102361429A (en) * | 2011-09-13 | 2012-02-22 | 江苏大学 | Bearing-free asynchronous motor control method based on neural network inverse system theory |
| CN102710214A (en) * | 2012-06-11 | 2012-10-03 | 桂林电子科技大学 | Nonlinear interference control method and control system for permanent magnet linear synchronous motor |
| US20130024409A1 (en) * | 2011-07-21 | 2013-01-24 | Qualcomm Incorporated | Method and apparatus of robust neural temporal coding, learning and cell recruitments for memory using oscillation |
| CN103197562A (en) * | 2013-04-11 | 2013-07-10 | 浙江工业大学 | Rotary-table servo system neural network control method |
| WO2014096507A1 (en) * | 2012-12-21 | 2014-06-26 | Metso Automation Oy | Controller and method for controlling a property of an object |
| CN104270053A (en) * | 2014-10-21 | 2015-01-07 | 南京理工大学 | Output feedback control method of motor position servo system based on state estimation |
| CN104333280A (en) * | 2014-09-17 | 2015-02-04 | 南京理工大学 | Robustness adaptive control (RAC) method of direct driving motor system |
| CN104460321A (en) * | 2014-12-15 | 2015-03-25 | 南京理工大学 | Hydraulic motor preset performance tracking control method with hysteresis compensating |
| CN104570733A (en) * | 2014-12-15 | 2015-04-29 | 南京理工大学 | Method for tracking control of preset performance in magnetic hysteresis compensation-containing motor servo system |
| CN104656442A (en) * | 2014-12-30 | 2015-05-27 | 河海大学常州校区 | Dynamic PID global sliding mode control method of micro gyroscope neural network |
| KR20150118456A (en) * | 2014-04-14 | 2015-10-22 | 엘에스산전 주식회사 | Method for partial discharge diagnosis of monitoring apparatus |
| CN105186958A (en) * | 2015-09-08 | 2015-12-23 | 江苏大学 | Neural network inverse system-based internal model control method for five-phase fault-tolerant permanent magnet motor |
| CN105223808A (en) * | 2015-06-24 | 2016-01-06 | 浙江工业大学 | Based on the mechanical arm system saturation compensation control method that neural network dynamic face sliding formwork controls |
| CN105278331A (en) * | 2015-05-26 | 2016-01-27 | 河海大学常州校区 | Robust-adaptive neural network H-infinity control method of MEMS gyroscope |
| EP2999940A2 (en) * | 2013-05-22 | 2016-03-30 | Neurala Inc. | Methods and apparatus for early sensory integration and robust acquisition of real world knowledge |
| CN105629734A (en) * | 2016-02-14 | 2016-06-01 | 济南大学 | Trajectory tracking control method for NSV (Near Space Vehicle) |
| CN105700348A (en) * | 2014-12-15 | 2016-06-22 | 南京理工大学 | Electric turntable position tracking control method based on disturbance upper bound estimation |
| EP3070649A2 (en) * | 2015-03-18 | 2016-09-21 | International Business Machines Corporation | Implementing a neural network algorithm on a neurosynaptic substrate based on criteria related to the neurosynaptic substrate |
| CN106059418A (en) * | 2016-06-17 | 2016-10-26 | 清华大学 | Neural network adaptive trajectory tracking control method for permanent magnet synchronous linear motor |
| CN106354022A (en) * | 2016-12-02 | 2017-01-25 | 湖南大学 | Brushless direct current motor and control method and system thereof |
| CN106470005A (en) * | 2015-08-11 | 2017-03-01 | 南京理工大学 | There is the implementation method of the motor servo system robust position controller of input constraint |
| US20170323224A1 (en) * | 2016-05-07 | 2017-11-09 | 1026 Labs, Inc. | Apparatus for hardware accelerated machine learning |
| CN107561935A (en) * | 2017-08-26 | 2018-01-09 | 南京理工大学 | Motor position servo system friciton compensation control method based on multilayer neural network |
| CN108133282A (en) * | 2017-12-07 | 2018-06-08 | 浙江大学城市学院 | A kind of Growth of Dendrobium candidum environmental forecasting method |
| KR20180085422A (en) * | 2017-01-18 | 2018-07-27 | 한국전자통신연구원 | Sigmoid function circuit used in an artificial neural network |
| US20180225564A1 (en) * | 2017-01-23 | 2018-08-09 | Dsp Group Ltd. | Neural cell and a neural network |
| CN108445766A (en) * | 2018-05-15 | 2018-08-24 | 山东大学 | Model-free quadrotor drone contrail tracker and method based on RPD-SMC and RISE |
-
2018
- 2018-08-28 CN CN201810990916.4A patent/CN109324503B/en active Active
Patent Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101725468A (en) * | 2008-10-28 | 2010-06-09 | 西门子公司 | Wind turbine arrangement and method for aligning a wind turbine with the wind direction |
| CN101917150A (en) * | 2010-06-24 | 2010-12-15 | 江苏大学 | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof |
| US20130024409A1 (en) * | 2011-07-21 | 2013-01-24 | Qualcomm Incorporated | Method and apparatus of robust neural temporal coding, learning and cell recruitments for memory using oscillation |
| CN102361429A (en) * | 2011-09-13 | 2012-02-22 | 江苏大学 | Bearing-free asynchronous motor control method based on neural network inverse system theory |
| CN102710214A (en) * | 2012-06-11 | 2012-10-03 | 桂林电子科技大学 | Nonlinear interference control method and control system for permanent magnet linear synchronous motor |
| WO2014096507A1 (en) * | 2012-12-21 | 2014-06-26 | Metso Automation Oy | Controller and method for controlling a property of an object |
| CN103197562A (en) * | 2013-04-11 | 2013-07-10 | 浙江工业大学 | Rotary-table servo system neural network control method |
| EP2999940A2 (en) * | 2013-05-22 | 2016-03-30 | Neurala Inc. | Methods and apparatus for early sensory integration and robust acquisition of real world knowledge |
| KR20150118456A (en) * | 2014-04-14 | 2015-10-22 | 엘에스산전 주식회사 | Method for partial discharge diagnosis of monitoring apparatus |
| CN104333280A (en) * | 2014-09-17 | 2015-02-04 | 南京理工大学 | Robustness adaptive control (RAC) method of direct driving motor system |
| CN104270053A (en) * | 2014-10-21 | 2015-01-07 | 南京理工大学 | Output feedback control method of motor position servo system based on state estimation |
| CN104460321A (en) * | 2014-12-15 | 2015-03-25 | 南京理工大学 | Hydraulic motor preset performance tracking control method with hysteresis compensating |
| CN104570733A (en) * | 2014-12-15 | 2015-04-29 | 南京理工大学 | Method for tracking control of preset performance in magnetic hysteresis compensation-containing motor servo system |
| CN105700348A (en) * | 2014-12-15 | 2016-06-22 | 南京理工大学 | Electric turntable position tracking control method based on disturbance upper bound estimation |
| CN104656442A (en) * | 2014-12-30 | 2015-05-27 | 河海大学常州校区 | Dynamic PID global sliding mode control method of micro gyroscope neural network |
| EP3070649A2 (en) * | 2015-03-18 | 2016-09-21 | International Business Machines Corporation | Implementing a neural network algorithm on a neurosynaptic substrate based on criteria related to the neurosynaptic substrate |
| CN105278331A (en) * | 2015-05-26 | 2016-01-27 | 河海大学常州校区 | Robust-adaptive neural network H-infinity control method of MEMS gyroscope |
| CN105223808A (en) * | 2015-06-24 | 2016-01-06 | 浙江工业大学 | Based on the mechanical arm system saturation compensation control method that neural network dynamic face sliding formwork controls |
| CN106470005A (en) * | 2015-08-11 | 2017-03-01 | 南京理工大学 | There is the implementation method of the motor servo system robust position controller of input constraint |
| CN105186958A (en) * | 2015-09-08 | 2015-12-23 | 江苏大学 | Neural network inverse system-based internal model control method for five-phase fault-tolerant permanent magnet motor |
| CN105629734A (en) * | 2016-02-14 | 2016-06-01 | 济南大学 | Trajectory tracking control method for NSV (Near Space Vehicle) |
| US20170323224A1 (en) * | 2016-05-07 | 2017-11-09 | 1026 Labs, Inc. | Apparatus for hardware accelerated machine learning |
| CN106059418A (en) * | 2016-06-17 | 2016-10-26 | 清华大学 | Neural network adaptive trajectory tracking control method for permanent magnet synchronous linear motor |
| CN106354022A (en) * | 2016-12-02 | 2017-01-25 | 湖南大学 | Brushless direct current motor and control method and system thereof |
| KR20180085422A (en) * | 2017-01-18 | 2018-07-27 | 한국전자통신연구원 | Sigmoid function circuit used in an artificial neural network |
| US20180225564A1 (en) * | 2017-01-23 | 2018-08-09 | Dsp Group Ltd. | Neural cell and a neural network |
| CN107561935A (en) * | 2017-08-26 | 2018-01-09 | 南京理工大学 | Motor position servo system friciton compensation control method based on multilayer neural network |
| CN108133282A (en) * | 2017-12-07 | 2018-06-08 | 浙江大学城市学院 | A kind of Growth of Dendrobium candidum environmental forecasting method |
| CN108445766A (en) * | 2018-05-15 | 2018-08-24 | 山东大学 | Model-free quadrotor drone contrail tracker and method based on RPD-SMC and RISE |
Non-Patent Citations (8)
| Title |
|---|
| F.L. LEWIS: "NONLINEAR NETWORK STRUCTURES FOR FEEDBACK CONTROL", 《ASIAN JOURNAL OF CONTROL》 * |
| JIANYONG YAO等: "RISE-Based Precision Motion Control of DC Motors With Continuous Friction Compensation", 《IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS》 * |
| LU, CHUN-HAO等: "Design of a heart rate controller for treadmill exercise using a recurrent fuzzy neural network", 《COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE》 * |
| PREMKUMAR, K等: "Antlion Algorithm Optimized Fuzzy PID Supervised On-line Recurrent Fuzzy Neural Network Based Controller for Brushless DC Motor", 《ELECTRIC POWER COMPONENTS AND SYSTEMS》 * |
| 岳欣等: "基于积分鲁棒的电液负载模拟器渐近跟踪控制", 《航空学报》 * |
| 岳欣等: "基于自适应的电液负载模拟器积分鲁棒控制", 《液压与气动》 * |
| 董振乐等: "含磁滞非线性的电动机伺服系统预设性能跟踪控制", 《上海交通大学学报》 * |
| 陈丽君等: "基于连续可微摩擦模型的直流电机扰动补偿自适应控制", 《计算机测量与控制》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110703609A (en) * | 2019-11-18 | 2020-01-17 | 南京工业大学 | Intelligent motion control method for motor servo system |
| CN113359440A (en) * | 2021-05-24 | 2021-09-07 | 华南理工大学 | Multi-rotor unmanned aerial vehicle controller design method based on multilayer integral neurodynamics |
| CN113359440B (en) * | 2021-05-24 | 2023-06-20 | 华南理工大学 | Multi-rotor unmanned aerial vehicle controller design method based on multilayer integral neural dynamics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109324503B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107561935B (en) | Motor position servo system friction compensation control method based on multilayer neural network | |
| CN104333280B (en) | Robustness adaptive control (RAC) method of direct driving motor system | |
| CN104345639B (en) | A kind of electro-hydraulic position servo system Robust Adaptive Control method | |
| Huang et al. | Intelligent friction modeling and compensation using neural network approximations | |
| Lin et al. | Decoupled torque control of series elastic actuator with adaptive robust compensation of time-varying load-side dynamics | |
| De Bruin et al. | Control of mechanical motion systems with non-collocation of actuation and friction: A Popov criterion approach for input-to-state stability and set-valued nonlinearities | |
| CN107121932B (en) | Motor servo system error symbol integral robust self-adaptive control method | |
| CN108228975B (en) | Motor servo system parameter identification method and backlash elimination control method | |
| CN108303885A (en) | A kind of motor position servo system self-adaptation control method based on interference observer | |
| CN104238572A (en) | Motor servo system jitter-free sliding mode position control method based on disturbance compensation | |
| CN105171758B (en) | Self-adaptive finite time convergence sliding-mode control method of robot | |
| Ali et al. | Adaptive FIT-SMC approach for an anthropomorphic manipulator with robust exact differentiator and neural network-based friction compensation | |
| Wang et al. | Adaptive robust torque control of electric load simulator with strong position coupling disturbance | |
| CN112286139B (en) | Motion system contour control method and system based on neural network and disturbance observation | |
| Wang et al. | Output torque tracking control of direct-drive rotary torque motor with dynamic friction compensation | |
| CN113110048A (en) | Nonlinear system output feedback adaptive control system and method adopting HOSM observer | |
| CN109324503A (en) | Multilayer neural network electric system control method based on robust integral | |
| Zhao et al. | Manipulator trajectory tracking based on adaptive sliding mode control | |
| Wang et al. | Hybrid active–passive robust control framework of a flexure-joint dual-drive gantry robot for high-precision contouring tasks | |
| Moghadam et al. | Hierarchical optimal contour control of motion systems | |
| Sun | Robust finite time tracking control for robotic manipulators based on nonsingular fast terminal sliding mode | |
| Hu et al. | Impedance with Finite‐Time Control Scheme for Robot‐Environment Interaction | |
| Ji et al. | Precise tracking control of piezoelectric actuators based on a hysteresis observer | |
| Rozali et al. | Asymptotic tracking position control for nonlinear systems using backsteppingtechnique | |
| Lu et al. | Gpc‐based self‐tuning PI controller for speed servo system of PMSLM |
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 |