CN102437816B - Adaptive motor motion control apparatus based on neural network - Google Patents
Adaptive motor motion control apparatus based on neural network Download PDFInfo
- Publication number
- CN102437816B CN102437816B CN201110327738.5A CN201110327738A CN102437816B CN 102437816 B CN102437816 B CN 102437816B CN 201110327738 A CN201110327738 A CN 201110327738A CN 102437816 B CN102437816 B CN 102437816B
- Authority
- CN
- China
- Prior art keywords
- velocity
- adaptive
- motor
- controller
- ann
- 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.)
- Expired - Fee Related
Links
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, meet the growing demand of people, require enterprise to have higher production efficiency, by the increase amount of labour that passes through the earliest, do not enhanced productivity, increase finally machine quantity and reach the object of enhancing productivity.Enter after 21 century, enterprise starts to distribute rationally, reduce costs, raise the efficiency, mostly adopt the production model of automation, with machine handing machine, intelligent management, carrying out in intelligent management, the control of motor is particularly important, because most machine run all needs motor that power support is not provided, while controlling motor, need accurately, in time, flexibly, Electric Machine Control pattern is more single at present, a controller can only be controlled the motor of a type sometimes, but in actual production, need usually to convert motor, to meet the needs of different workpieces, cause motor service efficiency low.
The mid-80 Germany Rule M.D epenbrock of university professor has successively proposed direct torque control theory with Japanese professor I.Takahashi, has greatly improved the flexibility of Electric Machine Control pattern.But Direct torque is made as a kind of new technology, the defect existing in perfect not and structure in theory makes himself to have many weak points, and during low speed, torque pulsation is serious; 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 Study on direct torque control technology always.Because Speedless sensor direct torque control can improve the combination property of system, therefore it is just becoming study hotspot and the development trend in AC speed regulating field, but due to the Some features of direct torque control self existence, the combination of Speedless sensor technology and direct torque control is also faced with some problems, and the precision of Speed identification and the stability of system are difficult to be guaranteed especially under the low speed.
Based Intelligent Control is a new branch of science in automation field, and neural net is a key technology wherein, has memory and processing capacity to information, is good at the knowledge useful from inputoutput data learning; Simulation people's intelligent behavior, does not need accurate Mathematical Modeling, can solve many complexity, uncertain, nonlinear problem, improves robustness and the learning adaptive 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 based on neural net, can realize motor speed fast and accurately and estimate, rich interface, applied range.
The present invention is achieved like this, and it comprises standard signal generator 1, positioner 2, velocity feed forward 3, speed control 4, ANN adaptive speed identifier 5, acceleration and load feedforward 6, torque controller 7, flux guide 8, phase convertor 9, pulse width modulator 10, motor 11.
Standard signal generator 1 link position controller 2 and velocity feed forward module 3 respectively, velocity feed forward module 3 connection speed controllers 4, speed control 4 connects acceleration and load feedforward module 6, accelerate to be connected torque controller 7 with load feedforward module 6, torque controller 7 connects phase convertor 9, phase convertor 9 connects pulse width modulator 10, pulse width modulator connects motor 11, motor 11 connects ANN adaptive speed identifier 5, ANN adaptive speed identifier 5 link position controller 2 respectively, speed control 4 and flux guide 8, flux guide 8 connects phase convertor 9, positioner 2 connection standard signal generator 1 and velocity feed forward module 3 respectively.
Advantage of the present invention is: 1, can the control of implementation model reference adaptive speed, open loop control, tacho generator closed-loop control, external analog amount gives the closed-loop control of fortune rotary speed, external pulse and the given Position Control of direction; 2, can control 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.
Accompanying drawing explanation
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, acceleration and load feedforward 6, torque controller 7, flux guide 8, phase convertor 9, pulse width modulator 10, motor 11.
Standard signal generator 1 link position controller 2 and velocity feed forward module 3 respectively, velocity feed forward module 3 connection speed controllers 4, speed control 4 connects acceleration and load feedforward module 6, accelerate to be connected torque controller 7 with load feedforward module 6, torque controller 7 connects phase convertor 9, phase convertor 9 connects pulse width modulator 10, pulse width modulator connects motor 11, motor 11 connects ANN adaptive speed identifier 5, ANN adaptive speed identifier 5 link position controller 2 respectively, speed control 4 and flux guide 8, flux guide 8 connects phase convertor 9, positioner 2 connection standard signal generator 1 and velocity feed forward module 3 respectively.
On-line study adjustment ANN weights are undertaken by the mode of error regularized learning algorithm, and for given stator voltage and stator current, if the spinner velocity that ANN estimates is identical with actual rotor speed, rotor flux error should be zero.When estimating that rotating speed and actual value are not etc., error is non-vanishing, utilizes them to revise the weights of ANN.
The present invention adopts has the artificial neural net (ANN) of learning adaptive as the core of model reference adaptive speed control, by feedback circuit required network training and weight storage, calculating and correction circuit have all been integrated in a chip, thereby can realize devices at full hardware, there is the nerve network control system of 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 by chip hardware calculates on-line study and adjusts artificial neural net weights, realize 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 module (3), speed control (4), ANN adaptive speed identifier (5), acceleration 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, velocity feed forward module (3) connection speed controller (4), speed control (4) connects acceleration and load feedforward module (6), accelerate to be connected torque controller (7) with load feedforward module (6), torque controller (7) connects phase convertor (9), phase convertor (9) connects pulse width modulator (10), pulse width modulator connects motor (11), motor (11) connects ANN adaptive speed identifier (5), ANN adaptive speed identifier (5) is link position controller (2) respectively, speed control (4) and flux guide (8), flux guide (8) connects phase convertor (9), positioner (2) is connection 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 CN102437816A (en) | 2012-05-02 |
| CN102437816B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105305895B (en) * | 2015-11-17 | 2017-09-05 | 吉林大学 | A kind of brushless motor control method based on torque feedback and switch compensation |
| JP6604198B2 (en) * | 2015-12-25 | 2019-11-13 | 株式会社ジェイテクト | Motor control device |
| 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 |
| FR3062762B1 (en) * | 2017-02-08 | 2020-08-07 | Valeo Siemens Eautomotive France Sas | METHOD FOR ESTIMATING THE ANGULAR POSITION OF A ROTOR OF AN ELECTRICAL DRIVE SYSTEM |
| CN106952782B (en) * | 2017-04-19 | 2019-02-22 | 福州大学 | Contactor velocity close-loop control method neural network based |
| CN110460285B (en) * | 2019-08-09 | 2021-07-09 | 瑞声科技(新加坡)有限公司 | 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 |
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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102437816A (en) | 2012-05-02 |
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 | |
| Uddin et al. | Online loss-minimization-based adaptive flux observer for direct torque and flux control of PMSM drive | |
| CN102497156A (en) | Neural-network self-correcting control method of permanent magnet synchronous motor speed loop | |
| CN105871282A (en) | Controller PI parameter tuning method based on rotational inertia of motor | |
| CN102497153B (en) | Constant-power-angle self-adaptive control method of permanent magnet synchronous motor | |
| CN102624315A (en) | High-precision permanent magnetic servo motor three-closed-loop control system and method | |
| Xiaojuan et al. | A novel sliding mode control for BLDC motor network control system | |
| CN105262393A (en) | Speed control method applying novel transition process for fault-tolerant permanent magnet motor | |
| CN107834919A (en) | The single-phase simulator of current-responsive type permagnetic synchronous motor and its drive system | |
| Liu et al. | Second-order ESO-based current sensor fault-tolerant strategy for sensorless control of PMSM with B-phase current | |
| CN104022701B (en) | Mould method for control speed in a kind of permanent magnetic linear synchronous motor Newton method | |
| Ananthamoorthy et al. | Simulation of PMSM based on current hysteresis PWM and Fed PI controller | |
| CN107395080A (en) | Speedless sensor moment controlling system and method based on cascade non-singular terminal sliding mode observer | |
| CN106602945B (en) | A kind of discrete control of brush direct current motor revolving speed and explicit forecast Control Algorithm | |
| Kamel et al. | Speed control of permanent magnet synchronous motor using fuzzy logic controller | |
| Engel et al. | Energy-saving technology of vector controlled induction motor based on the adaptive neuro-controller | |
| Hu et al. | Research on injection molding machine drive system based on model predictive control | |
| Chen et al. | The simulation research of PMSM control based on MPC | |
| Tech et al. | Indirect vector control of induction motor using Pi speed controller and neural networks | |
| Parida | A sliding mode controller for induction motor drives | |
| Ranjan et al. | Analysis of the performance of an hcc based pmsm drive using adaptive neuro fuzzy inference | |
| Lin et al. | A linear synchronous motor drive using robust fuzzy neural network control | |
| Douiri et al. | Neural computation based vector controlled asynchronous motor fed by three levels NPC |
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 |