CN106130431B - A kind of linear motor RBF neural generalized inverse internal model control method - Google Patents
A kind of linear motor RBF neural generalized inverse internal model control method Download PDFInfo
- Publication number
- CN106130431B CN106130431B CN201610577364.5A CN201610577364A CN106130431B CN 106130431 B CN106130431 B CN 106130431B CN 201610577364 A CN201610577364 A CN 201610577364A CN 106130431 B CN106130431 B CN 106130431B
- Authority
- CN
- China
- Prior art keywords
- linear motor
- generalized inverse
- module
- rbf neural
- rbf
- 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
- 230000001537 neural effect Effects 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 11
- 230000009466 transformation Effects 0.000 claims description 5
- 230000006698 induction Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 210000004218 nerve net Anatomy 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 abstract description 4
- 230000004044 response Effects 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000004088 simulation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P25/00—Arrangements or methods for the control of AC motors characterised by the kind of AC motor or by structural details
- H02P25/02—Arrangements or methods for the control of AC motors characterised by the kind of AC motor or by structural details characterised by the kind of motor
- H02P25/06—Linear motors
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
- H02P21/0003—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
- H02P21/0014—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Control Of Ac Motors In General (AREA)
- Control Of Multiple Motors (AREA)
Abstract
The invention discloses a kind of linear motor RBF neural generalized inverse internal model control methods, by approaching the permanent-magnetism linear motor Generalized Inverse System without mathematical models by RBF neural, and it is concatenated with permanent-magnetism linear motor system, to realize the linearisation and decoupling of permanent-magnetism linear motor control system, pseudo-linear system after decoupling keeps the key performances such as permanent-magnetism linear motor control system control accuracy, dynamic response capability, robustness more superior by the amendment of internal model control.
Description
Technical field
The present invention relates to a kind of linear motor RBF neural generalized inverse internal model control methods, belong to Electric Drive technology
Field.
Background technology
Electric energy can be converted into the mechanical energy of linear motion by linear motor, not only eliminate intermediate transmission mechanism, and
And system loss is reduced, permanent-magnet linear motor has the features such as power density is high, and controllability is good, therefore is passed in current electric power
Using increasingly extensive in dynamic and servo-control system.
Permanent-magnetism linear motor simultaneously there is also with operating status change parameter mutation, non-linear close coupling the features such as, the control
System processed has multiple-input and multiple-output and is unable to get accurate mathematical model, therefore Traditional control theory cannot be satisfied the modern times
The demand for control of high-performance linear motor.
Neural network generalized inverse system has taken into account the characteristics of Linearized Decoupling of inverse system and neural network to nonlinear system
System approximation capability；Modeling error needs existing for the pseudo-linear system be made of Neural Network Inverse System concatenation permanent-magnetism linear motor
Closed loop controller is introduced to eliminate, the access of internal mode controller will ensure to ensure the realization of this performance；Therefore, neural network
Generalized inverse internal model control system has stronger adaptive ability and robustness to the system control of non-linear close coupling.
Invention content：
The features such as permanent-magnet linear motor poor anti jamming capability, the present invention provide a kind of linear motor RBF nerve nets
Network generalized inverse internal model control method, can the effectively influence of disturbance cancelling signal and uncertain environment to control system, improve permanent magnetism
Linear motor dynamic response capability and robustness.
To achieve the above object, the present invention provides the following technical solutions：
A kind of linear motor RBF neural generalized inverse internal model control method, including：Generalized Inverse System, linear motor system
System, pi regulator, PD adjusters, internal mode controller, coordinate transformation module；Wherein Generalized Inverse System includes：RBF neural is wide
Justice inverse module, electric current loop First-order Integral module, der Geschwindigkeitkreis Second Order Integral module；Linear induction motor system includes：SVPWM modulates mould
Block, inverter, linear motor module, are as follows：
Step 1：Linear motor output end is by optical rotary encoder and for detecting the transformer measurement of phase current simultaneously
Rotational speed omega is calculatedr, electrical angle θ, phase current ia、ib、ic 。
Step 2：Phase current and electrical angle two rotational coordinates electric current i of gained after changes in coordinatesd、iq, wherein idIt is defeated
Go out and is connected with RBF neural generalized inverse module, iqWith input current signal iq *It is connected；Linear motor exports rotational speed omegar
With input speed signal ωr *It is connected；Linear motor output electrical angle θ is connected with SVPWM modulation modules.
Step 3：By feedback current iqAnd rotational speed omegarWith input current signal iq *And tach signal ωr *Done deviation feedback
To internal mode controller, it is separately input to pi regulator after internal mode controller is corrected and PD adjusters are adjusted.Pi regulator
And PD adjusters output quantity is connected with First-order Integral device and second-order integrator respectively.
Step 4：Electric current First-order Integral device, rotating speed second-order integrator export and by the i obtained by coordinate transformdWith RBF god
It is connected through network generalized inverse module input, to constitute linear motor Generalized Inverse System；RBF neural generalized inverse module
Output quantity ud、uqAnd feedback end electrical angle θ is respectively connected to SVPWM modulation modules, it is wide to constitute linear motor RBF neural
The inverse internal model control model of justice.
The beneficial effects of the present invention are compared with prior art, the present invention is by designing a kind of linear motor RBF nerves
Network generalized inverse internal model control method, by approaching the permanent-magnet linear electricity without mathematical models by RBF neural
Machine Generalized Inverse System, and it is concatenated with permanent-magnetism linear motor system, to realize the linear of permanent-magnetism linear motor control system
Change and decoupling, the pseudo-linear system after decoupling make permanent-magnetism linear motor control system control essence by the amendment of internal model control
The key performances such as degree, dynamic response capability, robustness are more superior.
Description of the drawings
Fig. 1 is the linear motor RBF neural generalized inverse internal model control method structure diagram of the embodiment of the present invention.
Fig. 2 is that RBF neural broad sense reversed decoupling is pseudo-linear system schematic diagram.
Specific implementation mode
In conjunction with attached drawing, elaborate to present example.
As shown in Figure 1, linear motor RBF neural generalized inverse internal model control method, including：Generalized Inverse System, straight line
Electric system, pi regulator, PD adjusters, internal mode controller, coordinate transformation module.Wherein Generalized Inverse System includes：RBF god
Through network generalized inverse module, electric current loop First-order Integral module, der Geschwindigkeitkreis Second Order Integral module；Linear induction motor system includes：SVPWM
Modulation module, inverter, linear motor module.
Transformer measurement of the linear motor output end by optical rotary encoder and for detecting phase current simultaneously calculates
To rotational speed omegar, electrical angle θ, phase current ia、ib、ic .Phase current and electrical angle two rotational coordinates of gained after changes in coordinates
Electric current id、iq, wherein idOutput is connected with RBF neural generalized inverse module, iqWith input current signal iq *It is connected；Directly
Line motor output speeds ωrWith input speed signal ωr *It is connected；Linear motor exports electrical angle θ and SVPWM modulation module phases
Connection.
By feedback current iqAnd rotational speed omegarWith input current signal iq *And tach signal ωr *Done deviation feeds back to internal model
Controller, is separately input to pi regulator after internal mode controller is corrected and PD adjusters are adjusted.Pi regulator and PD tune
Section device output quantity is connected with First-order Integral device and second-order integrator respectively.
Electric current First-order Integral device, rotating speed second-order integrator export and by the i obtained by coordinate transformation moduledWith RBF nerves
Network generalized inverse module input is connected, to constitute linear motor Generalized Inverse System；RBF neural generalized inverse module is defeated
Output ud、uqAnd feedback end electrical angle θ is respectively connected to SVPWM modulation modules, to complete decoupling and the linearisation such as Fig. 2 of system
It is shown.
The pseudo-linear system access internal mode controller for completing decoupling carries out the adjustment of modeling parameters, and then constitutes linear motor
RBF neural generalized inverse internal model control model.
In the implementation case, using MATLAB/Simulink for dSPACE is combined driving permanent-magnetism linear motor,
The implementation for the control method that the present invention will be described in detail：
Step 1：Data sampling is carried out to the structure of RBF neural generalized inverse module in MATLAB/Simulink, it is first
First determine the sampled signal, [i in neural metwork trainingd,id´,ωr,ωr´,ωr' '] forms the input of neural network, [ud,
uq] output of neural network is formed, so only needing to acquire idAnd ωrAs sample.
Step 2：After sampling enough training datas, the number of plies and number of nodes of selected RBF neural are determined, in RBF
Neural network module is front and back to be added normalization and renormalization module, and trained iterations and the suitable training letter of selection is arranged
Number, Training RBF Neural Network select Approximation effect by error between reality output and expectation.
Step 3：The good RBF neural generalized inverse module of Approximation effect is selected, it, will in the simulation model built
RBF neural generalized inverse module input is connected to constitute broad sense with First-order Integral subsystem, Second Order Integral subsystem
Inverse system.
Step 4：SVPWM modulation modules, inverter module, linear motor module are built in simulation model.
Step 5：By linear motor module output electrical angle θ, phase current ia、ib、ic It is connected with coordinate transformation module, sits
It marks conversion module and exports idIt is connected with RBF neural generalized inverse module, iqWith input current signal iq *It is connected；Straight-line electric
Machine module exports rotational speed omegarWith input speed signal ωr *It is connected；Linear motor module exports electrical angle θ and SVPWM and modulates mould
Block is connected.
Step 6：Internal mode controller inner parameter is designed, by feedback current iqAnd rotational speed omegarWith input current signal iq *And
Tach signal ωr *Done deviation feeds back to internal mode controller, and pi regulator and PD are separately input to after internal mode controller is corrected
Adjuster is adjusted.
Step 7：MATLAB/Simulink is combined by RTW with the RTI of dSPACE, by each module and I/O into
Row parameter configuration converts simulation model to digital drive signals, and the mathematical model in former analogue system is converted to practical
The controlled device of physical significance designs Driven by inverter linear motor, observes and records experimental waveform and adjust RBF neural in due course
Generalized inverse linear motor control system variable parameter.
Claims (1)
1. a kind of linear motor RBF neural generalized inverse internal model control method, it is characterised in that：Including：It is Generalized Inverse System, straight
Line electric system, pi regulator, PD adjusters, internal mode controller, coordinate transformation module；Wherein Generalized Inverse System includes：RBF god
Through network generalized inverse module, electric current loop First-order Integral module, der Geschwindigkeitkreis Second Order Integral module；Linear induction motor system includes：SVPWM
Modulation module, inverter, linear motor module, are as follows：
Step 1：Linear motor output end passes through optical rotary encoder and the transformer measurement for detecting phase current and calculating
Obtain rotational speed omegar, electrical angle θ, phase current ia、ib、ic ；
Step 2：Phase current and electrical angle two rotational coordinates electric current i of gained after changes in coordinatesd、iq, wherein idOutput with
RBF neural generalized inverse module is connected, iqWith input current signal iq *It is connected；Linear motor exports rotational speed omegarWith it is defeated
Enter tach signal ωr *It is connected；Linear motor output electrical angle θ is connected with SVPWM modulation modules；
Step 3：By feedback current iqAnd rotational speed omegarWith input current signal iq *And tach signal ωr *In done deviation is fed back to
Mould controller, is separately input to pi regulator after internal mode controller is corrected and PD adjusters are adjusted；
Step 4：Pi regulator and PD adjusters output quantity are connected with First-order Integral device and second-order integrator respectively；
Step 5：Electric current First-order Integral device, rotating speed second-order integrator export and by the i obtained by coordinate transformdWith RBF nerve nets
Network generalized inverse module input is connected, to constitute linear motor Generalized Inverse System；RBF neural generalized inverse module exports
Measure ud、uqAnd feedback end electrical angle θ is respectively connected to SVPWM modulation modules, to constitute linear motor RBF neural generalized inverse
Internal model control model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610577364.5A CN106130431B (en) | 2016-07-21 | 2016-07-21 | A kind of linear motor RBF neural generalized inverse internal model control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610577364.5A CN106130431B (en) | 2016-07-21 | 2016-07-21 | A kind of linear motor RBF neural generalized inverse internal model control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106130431A CN106130431A (en) | 2016-11-16 |
| CN106130431B true CN106130431B (en) | 2018-09-28 |
Family
ID=57289124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610577364.5A Active CN106130431B (en) | 2016-07-21 | 2016-07-21 | A kind of linear motor RBF neural generalized inverse internal model control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106130431B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108365787A (en) * | 2018-03-23 | 2018-08-03 | 东南大学 | A kind of Permanent-magnet Synchronous-motor Speed Servo System and its design method based on internal model control |
| CN110244563B (en) * | 2019-06-18 | 2020-10-27 | 华北电力大学 | Neural network internal model controller model mismatch identification and online updating method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| JP2011030393A (en) * | 2009-07-29 | 2011-02-10 | Fuji Electric Systems Co Ltd | Controller of linear permanent magnet synchronous motor |
| CN102790581A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Constructing method for robust controller for radial position of bearingless asynchronous motor |
| CN104022701A (en) * | 2014-06-20 | 2014-09-03 | 福州大学 | Method for controlling internal model speed of permanent magnet synchronous linear motor through Newton method |
| CN105790661A (en) * | 2016-04-22 | 2016-07-20 | 江苏大学 | Linear permanent magnet vernier motor decoupling control method based on improved regression support vector machine generalized inverse |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4473076B2 (en) * | 2004-08-30 | 2010-06-02 | 株式会社日立産機システム | Control method and apparatus for linear synchronous motor |
-
2016
- 2016-07-21 CN CN201610577364.5A patent/CN106130431B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011030393A (en) * | 2009-07-29 | 2011-02-10 | Fuji Electric Systems Co Ltd | Controller of linear permanent magnet synchronous motor |
| 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 |
| CN102790581A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Constructing method for robust controller for radial position of bearingless asynchronous motor |
| CN104022701A (en) * | 2014-06-20 | 2014-09-03 | 福州大学 | Method for controlling internal model speed of permanent magnet synchronous linear motor through Newton method |
| CN105790661A (en) * | 2016-04-22 | 2016-07-20 | 江苏大学 | Linear permanent magnet vernier motor decoupling control method based on improved regression support vector machine generalized inverse |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106130431A (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101917150B (en) | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof | |
| CN104022524B (en) | D.C. high voltage transmission multichannel additional longitudinal forces method based on structure changes | |
| CN105811849B (en) | A kind of the switched reluctance machines method for controlling torque and system of current non-linear compensation | |
| CN106130431B (en) | A kind of linear motor RBF neural generalized inverse internal model control method | |
| CN110492820A (en) | A kind of permanent magnet synchronous motor sensorless strategy method and system | |
| CN104201963B (en) | Compensating controller for suppressing positioning disturbance of linear motor | |
| CN103303454A (en) | Electric helm gear based on speed ring reversing and control method of electric helm gear | |
| CN105610369A (en) | Sliding-mode observer based flux linkage observation method of asynchronous motor | |
| CN103516280B (en) | Improving one's methods of a kind of permagnetic synchronous motor electric current loop adjuster | |
| CN110212575A (en) | The small signal stability modal analysis method of double-fed blower one machine infinity bus system | |
| CN109617466B (en) | Nonlinear modeling method for complex power electronic system of switched reluctance motor | |
| CN103699006B (en) | A kind of based on fuzzy variable sliding-surface Nonlinear Tracking Differentiator control method | |
| CN107272409A (en) | A kind of linear servo system vibration suppressing method based on iterative learning | |
| CN110757882B (en) | Full closed-loop control system and method based on sensorless servo press | |
| CN107872182A (en) | A kind of method for controlling permanent magnet synchronous motor based on generalized model prediction | |
| CN105186958A (en) | Neural network inverse system-based internal model control method for five-phase fault-tolerant permanent magnet motor | |
| CN104022701B (en) | Mould method for control speed in a kind of permanent magnetic linear synchronous motor Newton method | |
| CN107294453A (en) | Magnetic linkage combines the method and system for suppressing switched reluctance machines torque pulsation with electric current | |
| CN101630940B (en) | Fuzzy neural network inverse robust controller of induction motor speed regulation system and construction method | |
| CN105305392A (en) | Symmetrical component method for short circuit calculation of voltage-controlled type IIDG included power distribution network | |
| CN106130425B (en) | The building method of hybrid vehicle switching magnetic-resistance BSG system intelligent controllers | |
| CN105262405B (en) | Closed loop disturbance observation compensation method for servomotor electric current loop | |
| CN104038135B (en) | A kind of torque motor structure parameter optimization method | |
| CN105186938A (en) | Sensorless tension identification method for two-motor speed regulating system | |
| CN113315122B (en) | Fault transient current analysis method considering nonlinear characteristics of inverter power supply control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231022 Address after: 230000 B-2704, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui. Patentee after: HEFEI LONGZHI ELECTROMECHANICAL TECHNOLOGY Co.,Ltd. Address before: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee before: Dragon totem Technology (Hefei) Co.,Ltd. Effective date of registration: 20231022 Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Dragon totem Technology (Hefei) Co.,Ltd. Address before: 223800 South Huanghe Road, Suqian City, Jiangsu Province, 399 Patentee before: SUQIAN College |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231114 Address after: Room 1006, Building B, Kaiping Business Center, 11666 East the Taihu Lake Avenue, the Taihu Lake New Town, East the Taihu Lake Eco tourism Resort, Wujiang District, Suzhou City, Jiangsu Province, 215000 Patentee after: Suzhou Muyuxi Environmental Technology Co.,Ltd. Address before: 230000 B-2704, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui. Patentee before: HEFEI LONGZHI ELECTROMECHANICAL TECHNOLOGY Co.,Ltd. |