CN102055390B - Construction method for neural network Alpha-order inverse controller of bearing-free brushless DC motor - Google Patents
Construction method for neural network Alpha-order inverse controller of bearing-free brushless DC motor Download PDFInfo
- Publication number
- CN102055390B CN102055390B CN2011100038058A CN201110003805A CN102055390B CN 102055390 B CN102055390 B CN 102055390B CN 2011100038058 A CN2011100038058 A CN 2011100038058A CN 201110003805 A CN201110003805 A CN 201110003805A CN 102055390 B CN102055390 B CN 102055390B
- Authority
- CN
- China
- Prior art keywords
- neural network
- input
- motor
- output
- bearing
- 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
Images
Abstract
The invention discloses a construction method for a neural network Alpha-order inverse controller of a bearing-free brushless DC motor. Firstly, two PWM (Pulse-Width Modulation) inverters and the bearing-free brushless DC motor serve as a whole to form a compounded to-be-controlled target; an adopted static neural network and six integrators construct the neural network inverse of the compounded to-be-controlled target; then the neural network inverse is placed in front of the compounded to-be-controlled target and is connected with the compounded to-be-controlled target in series to form a pseudo linear system, and two designed position controllers and a speed controller form a linear close-loop controller; and finally, the linear close-loop controller, the neural network inverse and thetwo PWM inverters are connected in series in sequence to form the neural network Alpha-order inverse controller of the bearing-free brushless DC motor. The construction method realizes the independent control of the radial displacement and the rotational speed of the bearing-free brushless DC motor rotor, ensures the steady suspension and operation of the motor rotor, and enables the bearing-freebrushless DC motor to obtain favorable dynamic and static performance and load disturbance resistance.
Description
Technical field
The present invention relates to a kind of no bearing brushless DC motor neural net α rank inverse controller, be applicable to the high performance control of no bearing brushless DC motor, belong to Electric Drive control appliance technical field.
Background technology
Brshless DC motor has combined the characteristics of direct current machine and alternating current machine, have good speed adjustment features, starting easily, can the load-carrying starting, advantage such as the life-span is long, and easy to maintenance, noise is little, do not have a series of problems that cause because of brush.No bearing brushless DC motor utilizes the magnetic field force effect to realize the suspension of rotor; The advantage that had both possessed brshless DC motor; Possess again the magnetic bearing motor no friction, do not have wear and tear, need lubricate and seal, high-speed, high accuracy, long characteristics of life-span, have potential very greatly practical applications value.
Modern industry is increasingly high to the electric machine control system performance demands in using, and in order to improve motor properties, not only will study the motor body structure, also will adopt advanced control strategy that motor is controlled.Research to no bearing brushless DC motor mainly concentrates on aspects such as motor body, controller hardware circuit and position-sensor-frees; Research to modern control strategy application facet is less, and normal PID control only can obtain good performance in the described control system of the Mathematical Modeling of LTI.When having the dynamic amount of unknown or variation in the system; This control mode just can not obtain good effect; When particularly will not have bearing technology and be applied in the middle of the brshless DC motor, whole system will become the non-linear strongly coupled system of a complicacy, when the parameter time varying of system is excessive; System even meeting are unstable, are difficult to realize not having the operate as normal of bearing brushless DC motor.
In order to improve the dynamic property of no bearing brushless DC motor control system; Can adopt Differential Geometry or inverse system control method; But these methods require the Mathematical Modeling of controlled systems accurately known, must obtain the analytical expression of FEEDBACK CONTROL, and require system parameters constant or the parameter Changing Pattern is known; And as the non-linear controlled device of a complicacy; No bearing brushless DC motor rotor parameter is fairly obvious with the variation of operating mode, has some unpredictalbe interference and dynamic effects in addition, makes Differential Geometry method and parsing method of inverse be difficult in reality, really use.
Domestic existing related application is disclosed to be had: 1) number of patent application is CN200510038099.5; Name is called: reluctance motor with magnistor radial neural network reversed decoupling controller and building method, to reluctance motor with magnistor design radial neural network reversed decoupling controller; 2) number of patent application is CN200510040065.X, the name be called: based on neural net inverse control system for permanent-magnet synchronous motor with five degrees of freedom without bearing and control method, to be the permanent-magnet synchronous motor with five degrees of freedom without bearing design control method.3) number of patent application is CN200610038711.3, and name is called: bearing-less AC asynchronous motor neural network inverse decoupling controller and building method, to be bearing-less AC asynchronous motor design neural network inverse decoupling controller.And also do not see at present anyly have document to disclose to no bearing brushless DC motor design neural network inverse decoupling controller; Its torque system and suspension system Mathematical Modeling because the particularity of no bearing brushless DC motor structure, necessary segmentation are derived, and its invertibity of piecewise analysis, its corresponding nerve network reverse system configuration is also different with other bearing-free motor.
Summary of the invention
The purpose of this invention is to provide a kind of building method that does not have bearing brushless DC motor neural net α rank inverse controller; Neural net α rank inverse system principle is introduced no bearing brushless DC motor; To no bearing brushless DC motor constructing neural network α rank inverse controller; Both can make no bearing brushless DC motor have the good anti-parameter of electric machine and change and anti-load disturbance ability, and can improve each item control performance index of no bearing brushless DC motor again effectively.
Technical scheme of the present invention is to adopt following steps successively: 1) by two PWM inverters and do not have bearing brushless DC motor and make the as a whole composite controlled object of forming; 2) set up the Mathematical Modeling of composite controlled object, adopt static neural network to add the nerve network reverse that 6 integrators are constructed composite controlled object; 3) each weight coefficient of adjustment and definite static neural network; Place composite controlled object to be composed in series pseudo-linear system before nerve network reverse, the pseudo-linear system equivalence is two rotor-position second order integral linearity subsystems and a speed second order integral linearity subsystem; 4) constitute the linear closed-loop controller respectively to two rotor-position second order integral linearity subsystems and two positioners of speed second order integral linearity subsystem design and a speed control, and by two positioners and a speed control; 5) linear closed-loop controller, nerve network reverse and two PWM inverters are connected in series common formation successively and do not have bearing brushless DC motor neural net α rank inverse controller.
The invention has the beneficial effects as follows:
1. do not have bearing brushless DC motor have than the motor of magnetic bearing supporting more reasonable; Practical more structure, system configuration is compact, and rotor axial length shortens greatly; Motor speed, power can be further enhanced, and can realize high speed and ultrahigh speed operation.
2. contrary through constructing neural network; The control of this non-linear close coupling time-varying system of no bearing brushless DC motor is converted into the control to two rotor-position second order integral linearity subsystems and a speed second order integral linearity subsystem; Can adopt methods such as PID, POLE PLACEMENT USING, linear optimal quadratic form adjuster or robust servo-operated regulator to design linear closed loop controller easily; Make no bearing brushless DC motor obtain good dynamic and static state performance and anti-load disturbance ability; Improve each item control performance index of no bearing brushless DC motor effectively; Like dynamic responding speed, steady-state tracking precision and parameter robustness; Solve the high performance control problem of no bearing brushless DC motor well, realized the independent control between the displacement of no bearing brushless DC motor rotor radial, the rotating speed, guaranteed rotor stable suspersion and operation; Greatly promoted the practicability paces of brushless DC motor, and be other bearing-free motor control system, and the non linear system linearisation of various types of Electric Machine Control of suitable magnetic bearing supporting is controlled with decoupling zero an effective way is provided.
3. adopt static neural network to add the inverse system that integrator is realized composite controlled object; And constructing neural network α rank inverse controller is realized the control to no bearing brushless DC motor; The contrary control method in neural net α rank does not rely on the mathematical models of controlled system; Only need priori seldom, thereby be applicable to conventional non linear system, decoupling zero linearisation that can fine realization controlled system.Be completely free of the dependence of traditional Differential Geometry control method to Mathematical Modeling; Remedied based on defective strict in the Differential Geometry control method the Mathematical Modeling of no bearing brushless DC motor; Avoided because the unstable system's departure that is caused of system parameters; Can reduce parameter of electric machine variation and load disturbance effectively to no bearing brushless DC motor Effect on Performance, improve the performance index of no bearing brushless DC motor significantly.
Description of drawings
Below in conjunction with accompanying drawing and embodiment the present invention is done further explain:
Fig. 1 is by two PWM inverters 2,3 and do not have the composite controlled object 4 that bearing brushless DC motor 1 is formed;
Fig. 2 is the structural representation of the nerve network reverse 6 that is made up of static neural network 5 and 6 integral element;
Fig. 3 is the sketch map and the isoboles thereof of the pseudo-linear system 7 of nerve network reverse 6 and composite controlled object 4 formations;
The closed-loop control system structure chart that Fig. 4 is made up of linear closed-loop controller 8 and pseudo-linear system 7;
Fig. 5 is no bearing brushless DC motor neural net α rank inverse controller 9 theory diagrams;
Among the figure: 1. do not have bearing brushless DC motor; 2,3.PWM inverter; 4. composite controlled object; 5. static neural network; 6. nerve network reverse; 7. pseudo-linear system; 8. linear closed-loop controller; 9. there is not bearing brushless DC motor neural net α rank inverse controller; 81,82. positioners; 83. speed control.
Embodiment
Referring to Fig. 1-5, the present invention is at first with two PWM inverters 2,3 and do not have bearing brushless DC motor 1 and make as a whole composition composite controlled object 4, and then adopts static neural network 5 to add integrator
s -1Construct the nerve network reverse 6 of composite controlled object 4; And make nerve network reverse 6 realize the inverse system function of composite controlled object 4 through the weight coefficient of adjustment neural net; Then nerve network reverse 6 is placed before the composite controlled object 4; Nerve network reverse 6 is formed pseudo-linear system 7 with composite controlled object 4; Pseudo-linear system 7 equivalences are the linear subsystem of two position second order integral forms and the linear subsystem of a speed second order integral form, on this basis, and respectively to 81,82 and speed controls 83 of two positioners of three integration subsystem design; And constitute linear closed-loop controller 8 by 81,82 and speed controls 83 of above-mentioned two positioners; With linear closed-loop controller 8, nerve network reverse 6 and two the no bearing brushless DC motor neural net α of PWM inverter 2,3 common formations rank inverse controllers 9, realize the independent control between the displacement of no bearing brushless DC motor rotor radial, the rotating speed at last, guarantee rotor stable suspersion and operation.According to the requirement of no bearing brushless DC motor Different control, can select different hardware and softwares to realize.The present invention introduces no bearing brushless DC motor 1 with neural net α rank inverse system principle; Adopt static neural network 5 and linear element to constitute nerve network reverse 6; And approach the inverse system of composite controlled object 4 with nerve network reverse 6, the contrary control method in neural net α rank does not rely on the mathematical models of controlled system, only needs priori seldom; Decoupling zero linearisation that can fine realization controlled system, and can improve greatly that system changes parameter and the robustness of load disturbance.Concrete steps are following:
1. referring to Fig. 1, form composite controlled object 4.By two PWM inverters 2,3 and do not have bearing brushless DC motor 1 and make the as a whole composite controlled object 4 of forming; The desired output of composite controlled object 4 does
, wherein export signal
ωBe motor speed, the output signal
x,
yBe respectively the displacement of rotor on X, Y direction; Being input as of composite controlled object 4
, input signal wherein
ρ* be the input duty cycle of PWM inverter 2, input signal
,
Be respectively the given electric current of U phase suspending windings su1, su2, input signal
,
Be respectively the given electric current of V phase suspending windings sv1, sv2, input signal
,
Be respectively the given electric current of W phase suspending windings sw1, sw2.
2. referring to Fig. 2, make up the structure of nerve network reverse 6.Set up the Mathematical Modeling of composite controlled object 4 according to the principle of no bearing brushless DC motor 1, the vector of obtaining system on this basis relatively rank for 2,2,2}, then composite controlled object 4 segmentations are reversible.Adopt static neural network 5 to add 6 integrators and come constructing neural network contrary 6; With the input as nerve network reverse 6 of the α order derivative
of the desired output
of composite controlled object 4, nerve network reverse 6 is output as
.Static neural network 5 adopts three layers of feedforward network structure; It has 9 input nodes, 7 output nodes; 24 implicit nodes; The hidden neuron activation primitive uses S type function
, and the neuron of output layer adopts pure linear function
.First input of nerve network reverse 6
As first input of static neural network 5, it is through first integrator
s -1Output as second input of static neural network 5, again through second integrator
s -1Output as the 3rd input of static neural network 5; Second input of nerve network reverse 6
As the 4th input of static neural network 5, it is through the 3rd integrator
s -1Output as the 5th input of static neural network 5, again through the 4th integrator
s -1Output as the 6th input of static neural network 5; The 3rd input of nerve network reverse 6
As the 7th input of static neural network 5, it is through the 5th integrator
s -1Output as the 8th input of static neural network 5; Again through the 6th integrator
s -1Output as the 9th input of static neural network 5; The output of static neural network 5 is exactly the output of nerve network reverse 6.
3. referring to Fig. 3, static neural network 5 weight coefficients are confirmed.In the working region of no bearing brushless DC motor 1, will
ρ*,
,
,
,
,
,
These 7 for square-wave signal at random puts on the input of composite controlled object 4 as the step excitation signal, and to this input signal
And output response
Gather, obtain 10000 groups of primary data sample
u 1,
u 2,
u 3,
u 4,
u 5,
u 6,
u 7,
y 1,
y 2,
y 3; Adopt high-order numerical differentiation method calculated off-line
y All-order derivative
,
,
,
,
,
, thereby obtain the training sample set of nerve network reverse 6, wherein import sample set be taken as
,
,
,
,
,
, the output sample collection be taken as
u 1,
u 2,
u 3,
u 4,
u 5,
u 6,
u 7, and training sample set is done normalization handle; Choose 7000 groups of data the training sample after normalization, utilize variable step to add the BP algorithm off-line training static neural network 5 of momentum term, make neural net output mean square error less than 0.001, thereby confirm each weight coefficient of static neural network 5.
4. referring to Fig. 3, form pseudo-linear system 7.Nerve network reverse 6 is placed before the composite controlled object 4; Nerve network reverse 6 is composed in series pseudo-linear system 7 with composite controlled object 4; Pseudo-linear system 7 comprises three single output subsystems of single input, is respectively two rotor-position second order integral linearity subsystems and a speed second order integral linearity subsystem.
5. referring to Fig. 4, design linear closed loop controller 8.Respectively to two rotor-position second order integral linearity subsystems and 81,82 and speed controls 83 of two positioners of a speed second order integral linearity subsystem design; And constitute linear closed-loop controller 8 by 81,82 and speed controls 83 of above-mentioned two positioners, as shown in Figure 4.Wherein linear closed-loop controller 8 can adopt methods such as PID control in the lineary system theory, POLE PLACEMENT USING, linear optimal quadratic form adjuster, robust servo-operated regulator to design.Wherein linear quadratic type optimal controller not only can overcome the measurement noise; And can dealing with nonlinear disturb; It is a kind of important tool of reponse system design; In the embodiment that the present invention provides, 81,82 and speed controls 83 of two positioners are all selected the design of linear quadratic type optimal control theory for use, and the parameter of controller need be adjusted according to the working control object.
6. referring to Fig. 5, constitute no bearing brushless DC motor neural net α rank inverse controller 9.Linear closed-loop controller 8, nerve network reverse 6 and two PWM inverters 2,3 are connected in series the common no bearing brushless DC motor neural net α of formation rank inverse controller 9 successively.
According to the above, just can realize the present invention.The variation and the modification of other that those skilled in the art is made under the situation that does not deviate from spirit of the present invention and protection range still are included within the protection range of the present invention.
Claims (2)
1. building method that does not have bearing brushless DC motor neural net α rank inverse controller is characterized in that adopting successively following steps:
1) by two PWM inverter (2,3) and do not have bearing brushless DC motor (1) and make the as a whole composite controlled object (4) of forming;
2) set up the Mathematical Modeling of composite controlled object (4), adopt static neural network (5) to add the nerve network reverse (6) that 6 integrators are constructed composite controlled object (4); Desired output with composite controlled object (4)
The α order derivative
As the input of nerve network reverse (6), nerve network reverse (6) is output as
ωBe motor speed output signal,
x,
yBe respectively the output signal of displacement of rotor on X, Y direction;
ρ* be PWM inverter (2) input duty cycle signal,
,
Be respectively the given current input signal of U phase suspending windings su1, su2,
,
Be respectively the given current input signal of V phase suspending windings sv1, sv2,
,
Be respectively the given current input signal of W phase suspending windings sw1, sw2;
Static neural network (5) has 9 input nodes, 7 output nodes, 24 implicit nodes; With first input of nerve network reverse (6) as first input of static neural network (5); It is through the output of first integrator second input as static neural network (5), again through the output of second integrator the 3rd input as static neural network (5); With second input of nerve network reverse (6) the 4th input as static neural network (5); The output of the 3rd integrator of its warp is as the 5th input of static neural network (5), and the output of the 4th integrator of warp is as the 6th input of static neural network (5) again; With the 3rd input of nerve network reverse (6) the 7th input as static neural network (5), it is through the output of the 5th integrator the 8th input as static neural network (5); The output of the 6th integrator of warp is as the 9th input of static neural network (5) again; The output of static neural network (5) is the output of nerve network reverse (6);
3) each weight coefficient of adjustment and definite static neural network (5); Place composite controlled object (4) to be composed in series pseudo-linear system (7) before nerve network reverse (6), pseudo-linear system (7) equivalence is two rotor-position second order integral linearity subsystems and a speed second order integral linearity subsystem;
4) constitute linear closed-loop controller (8) respectively to two rotor-position second order integral linearity subsystems and two positioners of speed second order integral linearity subsystem design (81,82) and a speed control (83), and by two positioners (81,82) and a speed control (83);
5) linear closed-loop controller (8), nerve network reverse (6) and two PWM inverters (2,3) are connected in series the common no bearing brushless DC motor neural net α rank inverse controllers (9) that constitute successively.
2. the building method of no bearing brushless DC motor neural net α according to claim 1 rank inverse controller is characterized in that: step 2) in, will
ρ*,
,
,
,
,
,
These 7 signals put on the input of composite controlled object (4) as the step excitation signal, and to input signal
u And output response
y Collect primary data sample; Adopt high-order numerical differentiation method calculated off-line
y All-order derivative obtain the training sample set of nerve network reverse (6); Training sample set is done the BP algorithm off-line training static neural network (5) that utilizes variable step to add momentum term after normalization is handled, make neural net output mean square error less than 0.001 each weight coefficient with definite static neural network (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100038058A CN102055390B (en) | 2011-01-10 | 2011-01-10 | Construction method for neural network Alpha-order inverse controller of bearing-free brushless DC motor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100038058A CN102055390B (en) | 2011-01-10 | 2011-01-10 | Construction method for neural network Alpha-order inverse controller of bearing-free brushless DC motor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102055390A CN102055390A (en) | 2011-05-11 |
| CN102055390B true CN102055390B (en) | 2012-11-07 |
Family
ID=43959407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100038058A Expired - Fee Related CN102055390B (en) | 2011-01-10 | 2011-01-10 | Construction method for neural network Alpha-order inverse controller of bearing-free brushless DC motor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102055390B (en) |
Citations (4)
| 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 |
| CN1431768A (en) * | 2003-02-20 | 2003-07-23 | 东南大学 | Method for structuring neural network reversal composite controller of variable frequency speed control system with constant ratio of voltage and frequency |
| CN1484372A (en) * | 2003-07-28 | 2004-03-24 | 东南大学 | Method for structuring mervo network inverse synchronous controller of tow-frequenct changing speed regulating motor system |
| CN101630936A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Neural network inverse controller of brushless DC motor and construction method thereof |
-
2011
- 2011-01-10 CN CN2011100038058A patent/CN102055390B/en not_active Expired - Fee Related
Patent Citations (4)
| 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 |
| CN1431768A (en) * | 2003-02-20 | 2003-07-23 | 东南大学 | Method for structuring neural network reversal composite controller of variable frequency speed control system with constant ratio of voltage and frequency |
| CN1484372A (en) * | 2003-07-28 | 2004-03-24 | 东南大学 | Method for structuring mervo network inverse synchronous controller of tow-frequenct changing speed regulating motor system |
| CN101630936A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Neural network inverse controller of brushless DC motor and construction method thereof |
Non-Patent Citations (8)
| Title |
|---|
| 付丽辉.基于改进型BP神经网络的无刷直流电机调速系统的应用研究.《大庆师范学院学报》.2010,第30卷(第06期),29-32. * |
| 卢健康等.磁悬浮无轴承电机的解耦控制.《微电机》.2006,第39卷(第06期), * |
| 张钰玲.无刷直流电动机的神经网络PID控制器研究.《制造业自动化》.2009,第31卷(第04期),129-132. * |
| 戈素贞.新型无轴承无刷直流电动机结构与模型研究.《农业工程学报》.2008,第24卷(第02期), * |
| 戴先中等.恒压频比变频调速系统的神经网络逆控制.《中国电机工程学报》.2005,第25卷(第07期),20050430. * |
| 戴崇.GA-BP神经网络PID控制器在无刷直流电动机调速系统中的应用.《水利水电技术》.2010,第41卷(第11期),59-62. * |
| 王群京等.基于神经网络的无刷直流电机预测控制的仿真研究.《系统仿真学报》.2005,(第06期),149-1493. * |
| 黄守道等.基于神经网络的无轴承电机悬浮子系统仿真研究.《微电机》.2006,第39卷(第08期), * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102055390A (en) | 2011-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101814892B (en) | Support vector machine inverse system composite controller based on bearingless synchronous reluctance motor | |
| CN100433537C (en) | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller | |
| CN102136822B (en) | Five-DOF (freedom of degree) bearingless synchronous reluctance motor decoupling controller and construction method thereof | |
| Yang et al. | An improved dynamic model for bearingless induction motor considering rotor eccentricity and load change | |
| CN104660141A (en) | Stator-flux oriented inverse decoupling control system of bearing-free asynchronous motor | |
| CN102790581B (en) | Constructing method for robust controller for radial position of bearingless asynchronous motor | |
| CN103414428B (en) | Bearingless synchronous reluctance motor rotor eccentric displacement controller and building method thereof | |
| CN102097986A (en) | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor | |
| CN102790580B (en) | The building method of induction-type bearingless motor SVMs inverse decoupling controller | |
| CN202043069U (en) | Decoupling controller of five-degree-freedom bearingless synchronous reluctance motor | |
| CN202004708U (en) | Bearingless brushless direct current motor neural network alpha-order inverse controller | |
| CN105071730A (en) | Bearing-free asynchronous motor stator orientated reverse closed-loop control system taking current dynamics into consideration | |
| CN102790577B (en) | Constructing method for suspended subsystem controller of bearingless permanent magnet synchronous motor | |
| CN102510253A (en) | Sensorless controller of bearingless synchronous reluctance motor and method for controlling sensorless controller | |
| CN101958685B (en) | Nonlinear inverse decoupling controller for bearingless synchronous reluctance motor and construction method thereof | |
| CN102130647B (en) | Speed-sensor-less construction method for detecting rotating speed of bearing-less asynchronous motor | |
| CN102013870B (en) | Inverse system decoupling controller of five-degree-of-freedom bearingless synchronous reluctance motor | |
| CN201928221U (en) | Neural net generalized inverse decoupling controller for bearingless synchronous reluctance motor | |
| Sun et al. | Artificial neural networks inverse control of 5 degrees of freedom bearingless induction motor | |
| CN102790576B (en) | A kind of building method of bearing-free permanent magnet synchronous motor decoupling controller | |
| CN110504884A (en) | A kind of induction-type bearingless motor radial force suspension control system based on differential geometrical decoupled control | |
| CN102055390B (en) | Construction method for neural network Alpha-order inverse controller of bearing-free brushless DC motor | |
| CN110048657B (en) | Decoupling control method for neural network inverse system of bearingless asynchronous motor | |
| Bu et al. | A control method of bearingless induction motor based on neural network | |
| Sahraoui et al. | Performance enhancement of sensorless speed control of DSIM using MRAS and EKF optimized by genetic algorithm |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121107 Termination date: 20180110 |