CN102437816A - Adaptive motor motion control apparatus based on neural network - Google Patents
Adaptive motor motion control apparatus based on neural network Download PDFInfo
- Publication number
- CN102437816A CN102437816A CN2011103277385A CN201110327738A CN102437816A CN 102437816 A CN102437816 A CN 102437816A CN 2011103277385 A CN2011103277385 A CN 2011103277385A CN 201110327738 A CN201110327738 A CN 201110327738A CN 102437816 A CN102437816 A CN 102437816A
- Authority
- CN
- China
- Prior art keywords
- velocity
- adaptive
- motor
- ann
- connects
- 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
Images
Abstract
The invention discloses an adaptive motor motion control apparatus based on a neural network. The apparatus is characterized in that: a standard signal generator is respectively connected with a position controller and a velocity feedforward module; the velocity feedforward module is connected with a velocity controller that is connected with an acceleration and load feedforward module; the acceleration and load feedforward module is connected with a torque controller that is connected with a phase transformer; the phase transformer is connected with a pulse width modulator that is connected with a motor; the motor is connected with an ANN adaptive velocity identifier; the ANN adaptive velocity identifier is respectively connected with the position controller, the velocity controller and a flux guide; the flux guide is connected with the phase transformer; and the position controller is respectively connected with the standard signal generator and the velocity feedforward module. According to the invention, an artificial neural network (ANN) is employed as a core of adaptive velocity control; a full hardware neural network control system having self-learning capability can be realized; a motor speed can be rapidly and accurately estimated; interfaces are diversified; and the apparatus has a wide application range.
Description
Technical field
The present invention relates to a kind of adaptive electric machine motion control device based on neural net.
Background technology
Along with industrialized fast development, satisfy the growing demand of people, require enterprise that higher production efficiency is arranged, do not enhance productivity by the increase amount of labour that passes through the earliest, increase machine quantity finally and reach the purpose of enhancing productivity.After getting into 21 century, enterprise begins to distribute rationally, reduces cost, and raises the efficiency; Mostly adopt the production model of automation, with machine handing machine, intelligent management; In carrying out intelligent management, the control of motor is particularly important, because most machine run all needs motor that the power support is not provided; It is accurate, timely, flexible to need during the control motor, and the Electric Machine Control pattern is more single at present, and a controller can only be controlled one type motor sometimes; But need usually conversion motor in the actual production,, cause the motor service efficiency low to satisfy the needs of different workpieces.
The mid-80 Germany Rule M.D epenbrock of university professor and Japanese professor I.Takahashi have successively proposed direct torque control theory, the flexibility that has improved the Electric Machine Control pattern greatly.Yet direct torque control is as a kind of new technology, and the defective that exists on the perfect inadequately and structure in theory makes and himself have many weak points that torque pulsation is serious during low speed; Switching frequency is unstable; The inaccuracy of magnetic flux observation model; The stator current that the variation of low regime stator resistance causes and the distortion of magnetic linkage etc.These problems hamper further developing of direct torque control technology always.Because the Speedless sensor direct torque control can improve the combination property of system; Therefore it is just becoming AC speed regulating hot research fields and development trend; But because some characteristics that direct torque control self exists; The combining of Speedless sensor technology and direct torque control also is faced with some problems, and especially the stability of the precision of Speed identification and system is difficult to be guaranteed under low speed.
Based Intelligent Control is a new branch of science in the automation field, and neural net is key technology wherein, has memory and processing capacity to information, is good at and from inputoutput data, learns useful knowledge; Anthropomorphic dummy's intelligent behavior does not need precise math model, can solve many complicacies, uncertain, nonlinear problem, improves the robustness and the learning adaptive property of control system.
Summary of the invention
The object of the present invention is to provide a kind of adaptive electric machine motion control device, can realize that motor speed is estimated fast and accurately, rich interface, applied range based on neural net.
The present invention realizes that like this it comprises standard signal generator 1, positioner 2, velocity feed forward 3, speed control 4, ANN adaptive speed identifier 5, feedforward 6, torque controller 7, flux guide 8, phase convertor 9, pulse width modulator 10, motor 11 quicken and load.
Standard signal generator 1 is link position controller 2 and velocity feed forward module 3 respectively, and velocity feed forward module 3 connection speed controllers 4, speed control 4 connect acceleration and load feed-forward module 6; Quicken to be connected torque controller 7 with load feed-forward module 6; Torque controller 7 connects phase convertor 9, and phase convertor 9 connects pulse width modulator 10, and pulse width modulator connects motor 11; Motor 11 connects ANN adaptive speed identifier 5; ANN adaptive speed identifier 5 is link position controller 2, speed control 4 and flux guide 8 respectively, and flux guide 8 connects phase convertor 9, and positioner 2 connects standard signal generator 1 and velocity feed forward module 3 respectively.
Advantage of the present invention is: but 1 implementation model reference adaptive speed control, open loop control, tacho generator closed-loop control, external analog amount are to the closed-loop control of running degree of hastening, external pulse and the given Position Control of direction; 2, may command AC servo motor, brushless servo motor, DC servo motor, two phase and three-phase step-servo motor and linear electric motors, rich interface, control ability is strong.
Description of drawings
Fig. 1 is adaptive electric machine motion control chip overall structure figure of the present invention.
Embodiment
As shown in Figure 1, it comprises standard signal generator 1, positioner 2, velocity feed forward 3, speed control 4, ANN adaptive speed identifier 5, feedforward 6, torque controller 7, flux guide 8, phase convertor 9, pulse width modulator 10, motor 11 quicken and load.
Standard signal generator 1 is link position controller 2 and velocity feed forward module 3 respectively, and velocity feed forward module 3 connection speed controllers 4, speed control 4 connect acceleration and load feed-forward module 6; Quicken to be connected torque controller 7 with load feed-forward module 6; Torque controller 7 connects phase convertor 9, and phase convertor 9 connects pulse width modulator 10, and pulse width modulator connects motor 11; Motor 11 connects ANN adaptive speed identifier 5; ANN adaptive speed identifier 5 is link position controller 2, speed control 4 and flux guide 8 respectively, and flux guide 8 connects phase convertor 9, and positioner 2 connects standard signal generator 1 and velocity feed forward module 3 respectively.
On-line study adjustment ANN weights carry out through the mode of error adjustment study, and for given stator voltage and stator current, if the spinner velocity that ANN estimates is identical with actual rotor speed, then the rotor flux error should be zero.When estimating that rotating speed and actual value do not wait, error is non-vanishing, utilizes them to revise the weights of ANN.
The present invention adopts has the core of the artificial neural net (ANN) of learning adaptive property as the model reference adaptive speed control; The feedback circuit that network training is required and weights storage, calculating and correction circuit all have been integrated in a chip; Thereby can realize nerve network control system devices at full hardware, that have self-learning capability; Utilize the motor working voltage current signal of artificial neural net ANN adaptive speed identifier analysis input; The high-speed parallel of realizing through chip hardware calculates on-line study adjustment artificial neural net weights, realizes velocity estimation value fast and accurately, for motor speed control provides foundation.Can control AC servo motor, brushless servo motor, DC servo motor, two phase and three-phase step-servo motor and linear electric motors etc.
Claims (1)
1. the adaptive electric machine motion control device based on neural net comprises standard signal generator 1, positioner 2, velocity feed forward 3, speed control 4, ANN adaptive speed identifier 5, quickens and load feedforward 6, torque controller 7, flux guide 8, phase convertor 9, pulse width modulator 10 and motor 11;
Standard signal generator 1 is link position controller 2 and velocity feed forward module 3 respectively, and velocity feed forward module 3 connection speed controllers 4, speed control 4 connect acceleration and load feed-forward module 6; Quicken to be connected torque controller 7 with load feed-forward module 6; Torque controller 7 connects phase convertor 9, and phase convertor 9 connects pulse width modulator 10, and pulse width modulator connects motor 11; Motor 11 connects ANN adaptive speed identifier 5; ANN adaptive speed identifier 5 is link position controller 2, speed control 4 and flux guide 8 respectively, and flux guide 8 connects phase convertor 9, and positioner 2 connects standard signal generator 1 and velocity feed forward module 3 respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110327738.5A CN102437816B (en) | 2011-10-25 | 2011-10-25 | Adaptive motor motion control apparatus based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110327738.5A CN102437816B (en) | 2011-10-25 | 2011-10-25 | Adaptive motor motion control apparatus based on neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102437816A true CN102437816A (en) | 2012-05-02 |
CN102437816B CN102437816B (en) | 2014-05-07 |
Family
ID=45985723
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110327738.5A Expired - Fee Related CN102437816B (en) | 2011-10-25 | 2011-10-25 | Adaptive motor motion control apparatus based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102437816B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105305895A (en) * | 2015-11-17 | 2016-02-03 | 吉林大学 | Torque feedback and commutation compensation-based brushless motor control method |
CN106200383A (en) * | 2016-08-08 | 2016-12-07 | 北京宇鹰科技有限公司 | A kind of three axle Inertially-stabilizeplatform platform control method based on model reference adaptive neutral net |
CN106919147A (en) * | 2015-12-25 | 2017-07-04 | 株式会社捷太格特 | Motor control apparatus |
CN106952782A (en) * | 2017-04-19 | 2017-07-14 | 福州大学 | Contactor velocity close-loop control method based on neutral net |
CN108400740A (en) * | 2017-02-08 | 2018-08-14 | 维洛西门子新能源汽车法国简式股份公司 | Evaluation method, Torque Control method, control device, dynamical system, vehicle |
CN110673468A (en) * | 2019-12-04 | 2020-01-10 | 中航金城无人系统有限公司 | Unmanned aerial vehicle online real-time flight state identification and parameter adjustment method |
WO2021026769A1 (en) * | 2019-08-09 | 2021-02-18 | 瑞声声学科技(深圳)有限公司 | Self-adaptive motor control method, apparatus and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1431769A (en) * | 2003-02-20 | 2003-07-23 | 东南大学 | Neural network reversal control frequency converter of induction motor and structure method |
CN101299581A (en) * | 2008-03-10 | 2008-11-05 | 江苏大学 | Neural network generalized inverse coordination control frequency transformer for two induction machines and construction method thereof |
CN101719732A (en) * | 2009-12-07 | 2010-06-02 | 江南大学 | five-level svpwm controller |
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 |
CN101938246A (en) * | 2010-09-29 | 2011-01-05 | 重庆交通大学 | Fuzzy fusion identification method of rotating speed of sensorless motor |
-
2011
- 2011-10-25 CN CN201110327738.5A patent/CN102437816B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1431769A (en) * | 2003-02-20 | 2003-07-23 | 东南大学 | Neural network reversal control frequency converter of induction motor and structure method |
CN101299581A (en) * | 2008-03-10 | 2008-11-05 | 江苏大学 | Neural network generalized inverse coordination control frequency transformer for two induction machines and construction method thereof |
CN101719732A (en) * | 2009-12-07 | 2010-06-02 | 江南大学 | five-level svpwm controller |
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 |
CN101938246A (en) * | 2010-09-29 | 2011-01-05 | 重庆交通大学 | Fuzzy fusion identification method of rotating speed of sensorless motor |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105305895A (en) * | 2015-11-17 | 2016-02-03 | 吉林大学 | Torque feedback and commutation compensation-based brushless motor control method |
CN106919147A (en) * | 2015-12-25 | 2017-07-04 | 株式会社捷太格特 | Motor control apparatus |
CN106919147B (en) * | 2015-12-25 | 2021-04-27 | 株式会社捷太格特 | Motor control apparatus |
CN106200383A (en) * | 2016-08-08 | 2016-12-07 | 北京宇鹰科技有限公司 | A kind of three axle Inertially-stabilizeplatform platform control method based on model reference adaptive neutral net |
CN106200383B (en) * | 2016-08-08 | 2019-10-18 | 北京宇鹰科技有限公司 | A kind of three axis Inertially-stabilizeplatform platform control methods based on model reference adaptive neural network |
CN108400740A (en) * | 2017-02-08 | 2018-08-14 | 维洛西门子新能源汽车法国简式股份公司 | Evaluation method, Torque Control method, control device, dynamical system, vehicle |
CN106952782A (en) * | 2017-04-19 | 2017-07-14 | 福州大学 | Contactor velocity close-loop control method based on neutral net |
CN106952782B (en) * | 2017-04-19 | 2019-02-22 | 福州大学 | Contactor velocity close-loop control method neural network based |
WO2021026769A1 (en) * | 2019-08-09 | 2021-02-18 | 瑞声声学科技(深圳)有限公司 | Self-adaptive motor control method, apparatus and storage medium |
CN110673468A (en) * | 2019-12-04 | 2020-01-10 | 中航金城无人系统有限公司 | Unmanned aerial vehicle online real-time flight state identification and parameter adjustment method |
Also Published As
Publication number | Publication date |
---|---|
CN102437816B (en) | 2014-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102437816B (en) | Adaptive motor motion control apparatus based on neural network | |
Ma'arif et al. | Control of DC motor using integral state feedback and comparison with PID: simulation and arduino implementation | |
Peresada et al. | Indirect stator flux-oriented output feedback control of a doubly fed induction machine | |
CN102710188B (en) | Direct torque control method and device of brushless continuous current dynamo | |
CN103984242A (en) | Layering predictive control system and method based on model predictive control | |
CN102497153B (en) | Constant-power-angle self-adaptive control method of permanent magnet synchronous motor | |
CN102497156A (en) | Neural-network self-correcting control method of permanent magnet synchronous motor speed loop | |
CN101938246A (en) | Fuzzy fusion identification method of rotating speed of sensorless motor | |
CN102624315A (en) | High-precision permanent magnetic servo motor three-closed-loop control system and method | |
CN104378038A (en) | Permanent magnet synchronous motor parameter identification method based on artificial neural network | |
CN103208958A (en) | DC (direct control) servo drive control system | |
CN106849790A (en) | A kind of new sliding-mode control for mismatching the disturbed fault-tolerant permanent-magnetism linear motor system of cylinder | |
CN103647481B (en) | Bearing-free permanent magnet synchronous motor radial position neural Network Adaptive Inversion Control device building method | |
CN110061676A (en) | A kind of bearing-free permanent magnet synchronous motor controller based on flux observer | |
CN104022701B (en) | Mould method for control speed in a kind of permanent magnetic linear synchronous motor Newton method | |
CN101383573B (en) | Direct suspending power control method for permanent magnet type non-bearing motor | |
CN109639200A (en) | A kind of rotary inertia on-line identification method based on electric motor load torque detection | |
CN201479069U (en) | High-speed and high-precision servo motor drive | |
Khan et al. | Hybrid stepper motor and its controlling techniques a survey | |
CN108199636B (en) | A kind of motor initial angle localization method based on vector control strategy | |
CN106602945B (en) | A kind of discrete control of brush direct current motor revolving speed and explicit forecast Control Algorithm | |
CN109067273A (en) | The AC servo driver of DTC-SVPWM for industrial six-joint robot regulates and controls method | |
CN107395080A (en) | Speedless sensor moment controlling system and method based on cascade non-singular terminal sliding mode observer | |
Hu et al. | Research on injection molding machine drive system based on model predictive control | |
Mowaviq et al. | Embedded position control of permanent magnet synchronous motor using sliding mode control |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140507 Termination date: 20141025 |
|
EXPY | Termination of patent right or utility model |