CN1845449A - Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller - Google Patents
Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller Download PDFInfo
- Publication number
- CN1845449A CN1845449A CNA2006100387113A CN200610038711A CN1845449A CN 1845449 A CN1845449 A CN 1845449A CN A2006100387113 A CNA2006100387113 A CN A2006100387113A CN 200610038711 A CN200610038711 A CN 200610038711A CN 1845449 A CN1845449 A CN 1845449A
- Authority
- CN
- China
- Prior art keywords
- bearing
- less
- asynchronous motor
- rotor
- magnetic linkage
- 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
Landscapes
- Magnetic Bearings And Hydrostatic Bearings (AREA)
- Control Of Ac Motors In General (AREA)
Abstract
The control method for a NN reverse decoupling controller of bearingless ac asynchronous motor comprises: composing the controlled target with two Clark inverse transforms, two current track inverters, the said motor and its load; according to corresponding inverse system, making up the NN inverse by a static NN and an integrator with learning algorithm to series connect between composite targets and form the pseudolinear system; designing linear close-loop controller as the method on linear system; finally, connecting the controller and NN inverse to form the objective controller with former transforms and inverters. This invention has well control performance.
Description
Technical field
The present invention is a kind of control method of bearing-less AC asynchronous motor neural network inverse decoupling controller of multivariable nonlinearity, is applicable to the high performance control of bearing-less AC asynchronous motor.Bearing-less AC asynchronous motor inherited the magnetic bearing supporting motor unlubricated, do not have characteristics such as wearing and tearing, no mechanical noise, have the prospect of using widely at special electric transmission fields such as electrical spindle for machine tool, turbomolecular pump, centrifuge, compressor, dynamo-electric energy storage, Aero-Space, belong to the technical field of Electric Drive control appliance.
Background technology
Bearing-less AC asynchronous motor is the controlled device of a class multivariable, non-linear, close coupling, and its radial position, rotating speed are difficult to control exactly by the signal that adds.If will realize rotor stable suspersion and operation, must carry out dynamic Decoupling Control of Load Torque to motor torque power and suspending power.
The control strategy of dynamic Decoupling Control of Load Torque is the difficult point that realizes the bearing-less AC asynchronous motor steady operation.Vector control is from Theory of Electrical Moto ﹠ Electromagnetic Fields, utilizes coordinate transform, the equivalence of bearing-less AC asynchronous motor model is converted into the model that is similar to direct current machine controls.Yet theory analysis shows that because the parameter of electric machine changes, vector control can only realize torque and suspending power Static Decoupling Control, and its dynamic response performance can't be satisfactory.For improving the dynamic property of bearing-less AC asynchronous motor control, the Differential Geometry control method also is used to the control of bearing-less AC asynchronous motor, but the linearizing realization of its decoupling zero, requirement obtains the mathematical models of object.And as the non-linear object of a complexity, the bearing-less AC asynchronous motor rotor parameter is fairly obvious with the variation of operating mode, there are some unpredictalbe interference and dynamic effects in addition, make Differential Geometry method and parsing method of inverse be difficult to real in practice application.
For further improving the dynamic duty performance of bearing-less AC asynchronous motor, need to consider the dynamic decoupling and the bearing-free motor multivariable coordination control of bearing-less AC asynchronous motor.The bearing-less AC asynchronous motor decoupling controller of development compact conformation, function admirable.
Domestic existing related application: 1) number of patent application CN200510038099.5, name is called: reluctance motor with magnistor radial neural network reversed decoupling controller and building method, and this patent of invention designs radial neural network reversed decoupling controller at reluctance motor with magnistor; 2) number of patent application CN200510040065.X, based on neural net inverse control system for permanent-magnet synchronous motor with five degrees of freedom without bearing and control method, the control method that this patent of invention designs at permanent-magnet synchronous motor with five degrees of freedom without bearing.More than the thought and this patent of the used nerve network reverse controller control motor of two patents of invention certain correlation is arranged, but the structure of various motors, Mathematical Modeling, there are essential distinction in control method, control difficulty and requirement, to the rotor flux observation of no bearing asynchronous machine and the design of controller, there are not relevant patent and documents and materials at present.
Summary of the invention
The objective of the invention is at no bearing asynchronous machine non-linear, the close coupling complication system, to suspending power, torque force and rotor flux adopt nerve network reverse controller to carry out Nonlinear Dynamic decoupling zero control, provide a kind of bearing-less AC asynchronous motor that both can make to have good moving, static control performance, anti-parameter of electric machine variation and anti-load disturbance ability are strong, can improve every control performance index of bearing-less AC asynchronous motor again effectively, as dynamic responding speed, the control method of the bearing-less AC asynchronous motor neural network inverse decoupling controller of steady-state tracking precision and parameter robustness.
The neural net inverse system control method, use neural net directly to substitute the corresponding inverse system model that has now in the decoupling control method, thereby the system that brings of unstable institute that has remedied based on bearing-less AC asynchronous motor parameter in the methods such as vector control method, Differential Geometry control controls the deficiency that error is arranged, this method has realized the dynamic decoupling between torque force and the radial suspension force better, makes the bearing-less AC asynchronous motor governing system have stronger anti-interference and robustness simultaneously.
The control method of the neural network inverse decoupling controller of bearing-less AC asynchronous motor is: at first adopt a flux observer of electric current, voltage, speed, flux observation model and Park conversion commonly used and Clark conversion composition, obtain the required bearing-free motor rotor flux information of magnetic linkage closed-loop control.Based on nerve network reverse bearing-less AC asynchronous motor control system by two Clark inverse transformations and two current track inverters, and the bearing-less AC asynchronous motor load module makes as a whole composition composite controlled object together, and the controlled volume of composite controlled object is the displacement of bearing-less AC asynchronous motor rotor radial, rotating speed and magnetic linkage; Then adopt static neural network to add integrator s
-1Construct the nerve network reverse of composite controlled object, and make nerve network reverse realize the inverse system function of composite controlled object by the weight coefficient of adjusting static neural network; Next nerve network reverse is placed before the composite controlled object, nerve network reverse and composite controlled object are formed pseudo-linear system, the pseudo-linear system equivalence becomes the integral linearity subsystem of four decoupling zeros, be respectively the linear subsystem of the linear subsystem of two position second order integral forms, a speed single order integral form and a magnetic linkage single order integral form, thereby not only realized the dynamic decoupling between revolving force, the radial suspension force, but also realized the dynamic decoupling of bearing-less AC asynchronous motor between location subsystem; On this basis, adopt PID design of Regulator method to come the integration subsystem of comprehensive four decoupling zeros, design two rotor-position controllers, a speed control and a magnetic linkage control device respectively, and two rotor-position controllers, speed control and magnetic linkage control devices constitute the linear closed-loop controller thus; At last linear closed-loop controller, nerve network reverse, two Clark inverse transformations, two current track inverters are constituted the independent control that nerve network reverse controller is realized bearing-less AC asynchronous motor torque force, radial suspension force jointly, realize rotor stable suspersion and operation.
Wherein above-mentioned flux observer is made up of two coordinate transforms, stator flux observer model and rotor flux identification model; One of them coordinate transform is bearing-less AC asynchronous motor stator winding phase current i
1a, i
1b, i
1cGather the torque winding current i of no bearing asynchronous machine by Clark conversion and Park conversion
1d, i
1qAnother coordinate transform is bearing-less AC asynchronous motor stator winding phase current i
1a, i
1b, i
1cWith phase voltage u
1a, u
1b, u
1cGather the torque winding current i of no bearing asynchronous machine by Clark conversion and Park conversion
1d, i
1qWith voltage u
1d, u
1qObtain required magnetic linkage value by corresponding magnetic linkage recognition module then.
Principle of the present invention is to change the strategy that traditional bearing-less AC asynchronous motor adopts rotor field or air gap decoupling zero control, has designed a kind of employing neural net inverse system controller bearing-less AC asynchronous motor has been carried out Nonlinear Dynamic decoupling zero control.
The invention has the advantages that:
Bearing-less AC asynchronous motor have than the motor of magnetic bearing supporting more reasonable, Shi Yong structure more.1) system configuration compactness, rotor axial length shortens greatly, and motor speed, power can be further enhanced, and can realize the high speed and ultrahigh speed operation; 2) power amplification circuit adopts the three phase power inverter circuit in the radial suspension Force control system, make that the control method of neural net reversed decoupling control bearing-less AC asynchronous motor is simple, compact conformation, low in energy consumption, cost descends, and has broken away from the bearing-less AC asynchronous motor complex structure of traditional magnetic suspension bearing supporting, critical whirling speed is low, the control system complexity, power amplifier cost height, defective such as volume is big.
2. contrary by constructing neural network, with this multivariable of bearing-less AC asynchronous motor, close coupling, the control of nonlinear and time-varying system is converted into two rotor-position second order integral linearity subsystems, the control of a speed single order integral linearity subsystem and a magnetic linkage single order integral linearity subsystem, utilize PID design of Regulator method to design linear closed loop controller, thereby realized the dynamic decoupling between torque force and the radial suspension force, thereby can realize respectively independently position system bearing-less AC asynchronous motor, the rotating speed of rotor, and the control of magnetic linkage.And further adopt methods for designing such as PID, POLE PLACEMENT USING, linear optimal quadratic form adjuster or robust servo-operated regulator to design linear closed loop controller, can obtain the high performance control of bearing-less AC asynchronous motor and the runnability of anti-load disturbance.
3. add the inverse system that integrator is realized composite controlled object with static neural network, the constructing neural network inverse controller is realized the control to bearing-less AC asynchronous motor, be completely free of the dependence of traditional Differential Geometry control method to Mathematical Modeling, remedied based on the system that brings of unstable institute of strict and system parameters controls the deficiency that error is arranged to the Mathematical Modeling of bearing-less AC asynchronous motor in the Differential Geometry control method, can realize the decoupling zero between torque force and the radial suspension force better, reduce parameter of electric machine variation and load disturbance effectively to the bearing-less AC asynchronous motor Effect on Performance, improved the performance index of bearing-less AC asynchronous motor significantly.
The present invention is based on the bearing-less AC asynchronous motor neural network inverse controller of nerve network reverse structure, improved the bearing-less AC asynchronous motor control performance, and be fit to other bearing-free motor control system, and various types of electric machine control systems of suitable magnetic bearing supporting.This bearing-less AC asynchronous motor application prospect with the control of Neural network inverse control method is very wide, and this bearing-less AC asynchronous motor neural network inverse controller based on the nerve network reverse structure also has boundless using value in the bearing-free motor of other type.
Description of drawings
The schematic diagram of the bearing-less AC asynchronous motor rotor flux observer 10 that Fig. 1 is made up of coordinate transform 11, coordinate transform 12, stator flux observer model 13 and rotor flux identification model 14.
Fig. 2 follows the tracks of the composite controlled object 26 that inverter (23,24) and bearing-less AC asynchronous motor and load module 25 thereof are formed by two Clark inverse transformations (21,22), two current modes.
Fig. 3 is a nerve network reverse 32, and it has 3 layers of static neural network 31 of 10 input nodes, 4 output nodes to add 6 integrator s
-1Constitute.
Fig. 4 is the schematic diagram and the isoboles thereof of the pseudo-linear system 41 of nerve network reverse 32 and composite controlled object 26 compound formations.
The structure chart of the closed-loop control system that Fig. 5 is made up of linear closed-loop controller 51 and pseudo-linear system 41.Wherein pseudo-linear system 41 comprises two location subsystem, a speed subsystem and a magnetic linkage subsystem; The linear closed-loop controller comprises two positioners (52,53), a speed control 54 and a magnetic linkage control device 55.
Fig. 6, Fig. 7 are based on the theory diagram of nerve network reverse bearing-less AC asynchronous motor control system.
Embodiment
Embodiments of the present invention are: at first based on bearing-less AC asynchronous motor model machine body, make the as a whole composite controlled object of forming by two Clark inverse transformations, two current track inverters and bearing-less AC asynchronous motor load then, this composite controlled object equivalence is 6 rank Differential Equation Models under the rest frame, the relative rank of system's vector are { 2,2,1,1}.Adopt the static neural network (3 layer network) of 10 input nodes, 4 output nodes to add 6 integrator s
-1Constitute the nerve network reverse of composite controlled object with 10 input nodes, 4 output nodes.And make nerve network reverse realize the inverse system function of composite controlled object by each weights of adjusting static neural network.Nerve network reverse is serially connected in before the composite controlled object again, it is two location subsystem, a speed subsystem and a magnetic linkage subsystem that nerve network reverse and composite controlled object synthesize by two second order integration subsystems and two single order integration subsystems, thereby the multivariable of a complexity, controlling object non-linear, close coupling is converted into the control of two second order integration subsystems and two single order integration subsystems.Two second order integration subsystems and two single order integration subsystems for decoupling zero, adopt a kind of linear system integration method, as PID, POLE PLACEMENT USING, linear optimal quadratic form adjuster or robust servo-operated regulator method for designing etc., design two positioners, a speed control and a magnetic linkage control device respectively, by positioner, speed control and the linear closed loop controller of magnetic linkage control device mutual group.Finally constitute, come bearing-less AC asynchronous motor is carried out dynamic Decoupling Control of Load Torque by linear closed-loop controller, nerve network reverse, two Clark inverse transformations, two ANN (Artificial Neural Network) inverse system method controllers that the current tracking inverter is formed.
Concrete enforcement divides following 7 steps:
1. to bearing-less AC asynchronous motor structure rotor flux observer, as shown in Figure 1.Flux observer is made up of coordinate transform, stator flux observer model and rotor flux identification model.Flux observer be input as bearing-less AC asynchronous motor stator winding phase current i
1a, i
1b, i
1c, phase voltage u
1a, u
1b, u
1cAnd speed omega
r, be output as rotor flux ψ
Dr, ψ
QrCan obtain i respectively according to coordinate transform
1d, i
1q, u
1d, u
1q, can obtain ψ by stator flux observer
1q, ψ
1d, ignore the influence in radial load winding magnetic field, then respectively with speed omega
rAnd time constant T
rThe product that multiplies each other, and i
1d, i
1qRespectively with L
M1rThe product that multiplies each other, can obtain rotor flux respectively by the rotor flux identification model is ψ
Dr, ψ
QrFlux observer provides necessary magnetic linkage information for whole nerve network reverse controller.
2. make the as a whole composite controlled object of forming by two Clark inverse transformations, two current tracking inverters and bearing-less AC asynchronous motor load module, as shown in Figure 2.This composite controlled object is with { i
2 α, i
2 β, i
1 α, i
1 βFour current signals are as input, with position, rotating speed and the magnetic linkage of rotor as output.
By analyze, equivalence and derivation, for the structure of nerve network reverse and learning training provide basis on the method.At first set up the Mathematical Modeling of composite controlled object, based on the bearing-less AC asynchronous motor operation principle, set up the bearing-less AC asynchronous motor Mathematical Modeling, through Clark conversion and linear amplification, obtain the Mathematical Modeling of composite controlled object, i.e. the 6 rank differential equations under the rest frame, its vector rank relatively is { 2,2,1,1}.Can prove that through deriving this 6 rank differential equation is reversible, be that inverse system exists, and can determine that four of its inverse system are input as the first derivative of the second dervative of two position coordinateses, a speed and the first derivative of a magnetic linkage, four outputs are respectively four inputs of compound controlled system.Thereby can construct nerve network reverse, as shown in Figure 3.For learning training provides the basis on the method.
4. it is contrary to adopt static neural network to add 6 integrator constructing neural networks.Wherein static neural network adopts 3 layers of MLN network, and input number of nodes is 10, and implicit node number is 17, and output layer node number is 4, and the hidden neuron activation primitive uses the S type function
, the neuron of output layer adopts pure linear function f (x)=x, and x is neuronic input, and the weight coefficient of static neural network will be determined in next step off-line learning.Then adopt static neural network to add 6 integrator s with 10 input nodes, 4 output nodes
-1Constitute, wherein: first of static neural network is input as first input of nerve network reverse, and it is through first integrator s
-1Being output as second input of static neural network, is the 3rd input of static neural network again through second integrator; The 4th second input that is input as nerve network reverse of static neural network, it is through the 3rd integrator s
-1Being output as the 5th input of static neural network, is the 6th input of static neural network again through the 4th integrator; The 7th the 3rd input that is input as nerve network reverse of static neural network, it is through the 5th integrator s
-1Be output as the 8th input of static neural network; The 9th the 4th input that is input as nerve network reverse of static neural network, it is through the 6th integrator s
-1Be output as the tenth input of static neural network.Static neural network is formed nerve network reverse with six integrators, and the output of static neural network is exactly the output of nerve network reverse.
Adjust the weight coefficient of static neural network: 1) with step excitation signal { i
2 α, i
2 β, i
1 α, i
1 βBe added to the input of composite controlled object, gather rotor displacement x, the y of bearing-less AC asynchronous motor; The rotational speed omega of rotor
rAnd magnetic linkage ψ
r2) two displacement x, the y off-line of rotor are asked its single order and second dervative, rotational speed omega respectively
rAsk its first derivative, magnetic linkage ψ
rAsk its first derivative, and signal is done standardization processing, form the training sample set of neural net
。3) adopt the error anti-pass BP algorithm that drives quantifier and learning rate changing that static neural network is trained, through about 500 times training, neural net output mean square error meets the demands less than 0.001, thereby has determined each weight coefficient of static neural network.
5. form two location subsystem, a speed subsystem and a magnetic linkage subsystem.Constitute nerve network reverse by static neural network and 6 integrators of determining each weight coefficient, nerve network reverse and composite controlled object polyphone are formed pseudo-linear system, and this pseudo-linear system is by the linear subsystem of the linear subsystem of two position second order integral forms, a speed single order integral form and the linear subsystem of a magnetic linkage single order integral form.Thereby reached between torque force and the radial suspension force, the dynamic decoupling between each location subsystem, Complex Nonlinear System control has been converted into the control of simple four single argument linear systems, as shown in Figure 4.
6. design linear closed loop controller.Two location subsystem, a speed subsystem and a magnetic linkage subsystem are designed closed loop controller respectively, as shown in Figure 5.The linear closed-loop controller adopts proportion integration differentiation PID, POLE PLACEMENT USING, linear optimal quadratic form adjuster or the robust servo-operated regulator method for designing in the lineary system theory to design.In the invention process process, select and adjust regulator parameter according to the bearing-less AC asynchronous motor parameter, two positioners have all been selected proportion integration differentiation PID controller for use, and rotational speed governor and magnetic linkage control device have all been selected proportion differential PD controller for use.As latter two positioner transfer function of adjusting is:
, rotational speed governor and magnetic linkage control device transfer function are G (S)=23324.81+41.23S, the transfer function of the closed-loop system of rotational speed governor can be written as:
, τ=0.1 wherein.The whole control system such as Fig. 6, shown in Figure 7.
7. formation nerve network reverse controller.Linear closed-loop controller, nerve network reverse, two Clark inverse transformations, two current tracking inverters are formed nerve network reverse controller (Fig. 7) jointly.
According to the above, just can realize the present invention.
Claims (3)
1, based on the control method of nerve network reverse bearing-less AC asynchronous motor decoupling controller, it is characterized in that at first adopting a flux observer (10) of electric current commonly used, voltage, speed, flux observation model and Park conversion and Clark conversion composition, obtain the required bearing-free motor rotor flux information of magnetic linkage closed-loop control; Flux observer (10) is made up of coordinate transform (11), coordinate transform (12), stator flux observer model (13) and rotor flux identification model (14); Then two Clark inverse transformations (21,22), two current track inverters (23,24) and bearing-less AC asynchronous motor and load module (25) thereof are made as a whole composition composite controlled object (26); And then adopt static neural network (31) to add integrator s
-1Construct the nerve network reverse (32) of composite controlled object, and make nerve network reverse (32) realize the inverse system function of composite controlled object (26) by the weight coefficient of adjusting neural net; Then nerve network reverse (32) is placed composite controlled object (26) before, nerve network reverse (32) is formed pseudo-linear system (41) with composite controlled object (26); Pseudo-linear system (41) equivalence is the integral linearity subsystem of four decoupling zeros, is respectively the linear subsystem of the linear subsystem of two position second order integral forms, a speed single order integral form and the linear subsystem of a magnetic linkage single order integral form; On this basis, adopt PID design of Regulator method that the integration subsystem of four decoupling zeros is designed two rotor-position controllers (52,53), a speed control (54) and a magnetic linkage control device (55) respectively; And constitute linear closed-loop controller (51) by above-mentioned two rotor-position controllers, a speed control and a magnetic linkage control device; At last linear closed-loop controller (51), nerve network reverse (32) and two Clark inverse transformations (21,22), two current track inverters (23,24) are constituted nerve network reverse bearing-less AC asynchronous motor controller (71) jointly.
2, the control method based on nerve network reverse bearing-less AC asynchronous motor controller according to claim 1 is characterized in that described flux observer (10) is made up of coordinate transform (11), coordinate transform (12), stator flux observer model (13) and rotor flux identification model (14); Coordinate transform (11) is bearing-less AC asynchronous motor stator winding phase current i
1a, i
1b, i
1cGather the torque winding current i of no bearing asynchronous machine by Clark conversion and Park conversion
1d, i
1qCoordinate transform (12) is bearing-less AC asynchronous motor stator winding phase current i
1a, i
1b, i
1cWith phase voltage u
1a, u
1b, u
1cGather the torque winding current i of no bearing asynchronous machine by Clark conversion and Park conversion
1d, i
1qWith voltage u
1d, u
1qObtain required magnetic linkage value by corresponding magnetic linkage recognition module then.
3, the control method based on nerve network reverse bearing-less AC asynchronous motor controller according to claim 1 is characterized in that each weight coefficient of described static neural network (31) is determined method: with step excitation signal { i
2 α, i
2 β, i
1 α, i
1 βBe added to the input of composite controlled object (26); Gather the rotational speed omega of rotor radial displacement x, y and the rotor of bearing-less AC asynchronous motor
rAnd magnetic linkage ψ
r, two rotor displacement x, y off-line are asked its second dervative, rotational speed omega respectively
rAsk its first derivative, magnetic linkage ψ
rAsk its first derivative, and signal is done standardization processing, the training sample set of composition neural net
X,
Y,
ω
r,
ψ
r, i
2 α, i
2 β, i
1 α, i
1 β, static neural network (31) is trained, thus each weight coefficient of definite static neural network (31).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2006100387113A CN100433537C (en) | 2006-03-08 | 2006-03-08 | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2006100387113A CN100433537C (en) | 2006-03-08 | 2006-03-08 | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1845449A true CN1845449A (en) | 2006-10-11 |
CN100433537C CN100433537C (en) | 2008-11-12 |
Family
ID=37064369
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2006100387113A Expired - Fee Related CN100433537C (en) | 2006-03-08 | 2006-03-08 | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100433537C (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100536311C (en) * | 2007-11-30 | 2009-09-02 | 江苏大学 | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing |
CN101552589B (en) * | 2009-05-14 | 2010-09-29 | 上海交通大学 | Relay feedback based AC servo system automatic setting method |
CN101355281B (en) * | 2008-03-10 | 2010-12-08 | 江苏大学 | Method for analyzing magnetic field equivalent air gap virtual winding current of non-bearings electric machine |
CN102011745A (en) * | 2010-12-31 | 2011-04-13 | 清华大学 | Neural network control system and method of magnetic suspension molecular pump |
CN102097986A (en) * | 2011-01-20 | 2011-06-15 | 江苏大学 | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor |
CN102361429A (en) * | 2011-09-13 | 2012-02-22 | 江苏大学 | Bearing-free asynchronous motor control method based on neural network inverse system theory |
CN102769424A (en) * | 2012-06-18 | 2012-11-07 | 江苏大学 | Support vector machine inverse-based bearingless asynchronous motor control system |
CN102790580A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Constructing method for decoupling controller of support vector machine inverter of bearingless asynchronous motor |
CN102790578A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Manufacturing method of bearingless asynchronous motor neural network generalized inverse decoupling controller |
CN102790576A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Construction method for bearing-less permanent-magnet synchronous motor decoupling controller |
CN103595321A (en) * | 2013-09-27 | 2014-02-19 | 江苏大学 | Method for constructing decoupling controller of five-degree-of-freedom alternating-current active magnetic bearing |
CN104483829A (en) * | 2014-12-31 | 2015-04-01 | 重庆科技学院 | Method and device for acquiring frequency domain performance of controlled object |
CN104767449A (en) * | 2015-03-02 | 2015-07-08 | 江苏大学 | Bearing-free asynchronous motor RBF neural network self-adaptive inverse decoupling control and parameter identification method |
CN105425802A (en) * | 2015-12-10 | 2016-03-23 | 长安大学 | Two-wheeled intelligent balance vehicle and control method thereof |
CN109194236A (en) * | 2018-09-26 | 2019-01-11 | 河南科技大学 | Based on the induction-type bearingless motor of LS-SVM without radial displacement transducer control system |
CN110061676A (en) * | 2019-03-04 | 2019-07-26 | 江苏大学 | A kind of bearing-free permanent magnet synchronous motor controller based on flux observer |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1212702C (en) * | 2003-02-20 | 2005-07-27 | 东南大学 | Neural network reversal control frequency converter of induction motor and structure method |
FI115806B (en) * | 2003-07-04 | 2005-07-15 | Abb Oy | Frequency converter and electric motor drive |
CN1303753C (en) * | 2005-06-07 | 2007-03-07 | 南京工业大学 | Non-speed sensor inverse controller for AC asynchronous motor |
-
2006
- 2006-03-08 CN CNB2006100387113A patent/CN100433537C/en not_active Expired - Fee Related
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100536311C (en) * | 2007-11-30 | 2009-09-02 | 江苏大学 | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing |
CN101355281B (en) * | 2008-03-10 | 2010-12-08 | 江苏大学 | Method for analyzing magnetic field equivalent air gap virtual winding current of non-bearings electric machine |
CN101552589B (en) * | 2009-05-14 | 2010-09-29 | 上海交通大学 | Relay feedback based AC servo system automatic setting method |
CN102011745B (en) * | 2010-12-31 | 2013-08-07 | 清华大学 | Neural network control system and method of magnetic suspension molecular pump |
CN102011745A (en) * | 2010-12-31 | 2011-04-13 | 清华大学 | Neural network control system and method of magnetic suspension molecular pump |
CN102097986A (en) * | 2011-01-20 | 2011-06-15 | 江苏大学 | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor |
CN102361429A (en) * | 2011-09-13 | 2012-02-22 | 江苏大学 | Bearing-free asynchronous motor control method based on neural network inverse system theory |
CN102769424A (en) * | 2012-06-18 | 2012-11-07 | 江苏大学 | Support vector machine inverse-based bearingless asynchronous motor control system |
CN102769424B (en) * | 2012-06-18 | 2016-12-21 | 江苏大学 | Based on the induction-type bearingless motor control system that support vector machine is inverse |
CN102790580B (en) * | 2012-08-06 | 2015-08-26 | 江苏大学 | The building method of induction-type bearingless motor SVMs inverse decoupling controller |
CN102790578A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Manufacturing method of bearingless asynchronous motor neural network generalized inverse decoupling controller |
CN102790576A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Construction method for bearing-less permanent-magnet synchronous motor decoupling controller |
CN102790580A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Constructing method for decoupling controller of support vector machine inverter of bearingless asynchronous motor |
CN102790578B (en) * | 2012-08-06 | 2015-06-10 | 江苏大学 | Manufacturing method of bearingless asynchronous motor neural network generalized inverse decoupling controller |
CN102790576B (en) * | 2012-08-06 | 2015-09-02 | 江苏大学 | A kind of building method of bearing-free permanent magnet synchronous motor decoupling controller |
CN103595321A (en) * | 2013-09-27 | 2014-02-19 | 江苏大学 | Method for constructing decoupling controller of five-degree-of-freedom alternating-current active magnetic bearing |
CN104483829A (en) * | 2014-12-31 | 2015-04-01 | 重庆科技学院 | Method and device for acquiring frequency domain performance of controlled object |
CN104483829B (en) * | 2014-12-31 | 2017-06-09 | 重庆科技学院 | The acquisition methods and device of controlled device frequency domain performance |
CN104767449A (en) * | 2015-03-02 | 2015-07-08 | 江苏大学 | Bearing-free asynchronous motor RBF neural network self-adaptive inverse decoupling control and parameter identification method |
CN104767449B (en) * | 2015-03-02 | 2018-04-24 | 江苏大学 | Self-bearings motors RBF neural adaptive inversion decoupling control and parameter identification method |
CN105425802A (en) * | 2015-12-10 | 2016-03-23 | 长安大学 | Two-wheeled intelligent balance vehicle and control method thereof |
CN109194236A (en) * | 2018-09-26 | 2019-01-11 | 河南科技大学 | Based on the induction-type bearingless motor of LS-SVM without radial displacement transducer control system |
CN110061676A (en) * | 2019-03-04 | 2019-07-26 | 江苏大学 | A kind of bearing-free permanent magnet synchronous motor controller based on flux observer |
Also Published As
Publication number | Publication date |
---|---|
CN100433537C (en) | 2008-11-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100433537C (en) | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller | |
CN100536311C (en) | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing | |
Sun et al. | Precise control of a four degree-of-freedom permanent magnet biased active magnetic bearing system in a magnetically suspended direct-driven spindle using neural network inverse scheme | |
CN1314193C (en) | Magnetic levitation switch reluctance motor radial neural network reversed decoupling controller and method for constructing same | |
CN100573370C (en) | Based on neural network inverse control system for permanent-magnet synchronous motor with five degrees of freedom without bearing and control method | |
CN101814892B (en) | Support vector machine inverse system composite controller based on bearingless synchronous reluctance motor | |
CN102136822B (en) | Five-DOF (freedom of degree) bearingless synchronous reluctance motor decoupling controller and construction method thereof | |
CN105406784B (en) | The torque of simplex winding bearing-free motor and suspending power self-operated controller and building method | |
CN101741297A (en) | Radial position fuzzy compensation inverse control method and device for bearingless synchronous reluctance motor | |
CN102790577B (en) | Constructing method for suspended subsystem controller of bearingless permanent magnet synchronous motor | |
CN102097986A (en) | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor | |
CN102510253A (en) | Sensorless controller of bearingless synchronous reluctance motor and method for controlling sensorless controller | |
CN202043069U (en) | Decoupling controller of five-degree-freedom bearingless synchronous reluctance motor | |
CN102790580B (en) | The building method of induction-type bearingless motor SVMs inverse decoupling controller | |
CN102130647B (en) | Speed-sensor-less construction method for detecting rotating speed of bearing-less asynchronous motor | |
CN101958685B (en) | Nonlinear inverse decoupling controller for bearingless synchronous reluctance motor and construction method thereof | |
CN1212702C (en) | Neural network reversal control frequency converter of induction motor and structure method | |
CN110061676B (en) | Bearingless permanent magnet synchronous motor controller based on flux linkage observer | |
CN202004708U (en) | Bearingless brushless direct current motor neural network alpha-order inverse controller | |
CN106130429A (en) | Bearing-free permanent magnet synchronous motor predictive controller and building method | |
CN102790578B (en) | Manufacturing method of bearingless asynchronous motor neural network generalized inverse decoupling controller | |
CN110048657B (en) | Decoupling control method for neural network inverse system of bearingless asynchronous motor | |
CN201928221U (en) | Neural net generalized inverse decoupling controller for bearingless synchronous reluctance motor | |
CN115085609B (en) | Control method for sliding mode system of single-winding magnetic suspension motor | |
CN102790576B (en) | A kind of building method of bearing-free permanent magnet synchronous motor decoupling controller |
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 | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20081112 Termination date: 20110308 |