CN102097986A - Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor - Google Patents
Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor Download PDFInfo
- Publication number
- CN102097986A CN102097986A CN2011100218629A CN201110021862A CN102097986A CN 102097986 A CN102097986 A CN 102097986A CN 2011100218629 A CN2011100218629 A CN 2011100218629A CN 201110021862 A CN201110021862 A CN 201110021862A CN 102097986 A CN102097986 A CN 102097986A
- Authority
- CN
- China
- Prior art keywords
- neural network
- generalized inverse
- reluctance motor
- inverse
- synchronous reluctance
- 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.)
- Pending
Links
Images
Landscapes
- Control Of Electric Motors In General (AREA)
- Magnetic Bearings And Hydrostatic Bearings (AREA)
Abstract
The invention discloses a construction method for a neural network generalized inverse decoupling controller of a bearing-free synchronous reluctance motor, which comprises the steps: taking two Park inverse converting type inverters, two Clark inverse converting type inverters and two direct current tracking type inverters as a wholly-formed composite controlled object after the two Park inverse converting type inverters, the two Clark inverse converting type inverters and the two direct current tracking type inverters are respectively and sequentially connected with one another in series and before the two Park inverse converting type inverters, the two Clark inverse converting type inverters and the two direct current tracking type inverters are connected with the bearing-free synchronous reluctance motor; forming a generalized imitative linear system before a constructed neural network generalized inverse is connected with the composite controlled object in series, and forming a linear closed loop controller by two position controllers and a speed controller; and jointly forming the neural network generalized inverse decoupling controller by the means that the linear closed loop controller, the neural network generalized inverse, the two Park inverse converting type inverters, the two Clark inverse converting type inverters and the two direct current tracking type inverters are respectively and sequentially connected with one another in series. The independent decoupling control between the electromagnetic torque and the radial levitation force and the independent decoupling control of the radial levitation force between two components on the vertical direction are realized according to the closed ring control and the PID (proportion integration differentiation) parameter adjustment, and the control performance of the bearing-free synchronous reluctance motor is obviously improved.
Description
Technical field
The present invention relates to bearingless synchronous reluctance motor neural net generalized inverse decoupling controller, be used for the high performance control of bearingless synchronous reluctance motor, belong to the technical field of Electric Drive control appliance.
Background technology
Bearingless synchronous reluctance motor has satisfied modern industry to high rotating speed, unlubricated, the requirement of not having the high-performance drive motors of friction, freedom from repairs, it is a kind of magnetic bearing premium properties that both had, the New-type electric machine that has both the synchronous magnetic resistance motor characteristics again is with a wide range of applications at special electric transmission fields such as electrical spindle for machine tool, turbomolecular pump, centrifuge, compressor, dynamo-electric energy storage, Aero-Space.Bearingless synchronous reluctance motor is the multi-input multi-output system of non-linear a, close coupling, if will realize rotor stable suspersion and operation, must realize between electromagnetic torque and the radial suspension force and radial suspension force from the dynamic Decoupling Control of Load Torque between the component on two vertical direction.
The particularity of bearingless synchronous reluctance motor control determines that it can't be as no bearing asynchronous machine and bearing-free permanent magnet synchronous motor, controls based on field orientation and carries out the correlation formula conversion and can realize full decoupled between each variable.In the decoupling control method that motor is used always, Differential Geometry control method and method of inverse also can be used for the control of bearingless synchronous reluctance motor, but the realization of its linearisation decoupling zero requires to obtain the mathematical models of controlled device.Bearingless synchronous reluctance motor is non-linear as one, the multi-input multi-output system of close coupling, its rotor parameter is very remarkable with the variation of operating mode, the variation of suspending power when adding rotor eccentricity, the existence of load disturbance and magnetic saturation etc. not modeling influence dynamically, make Differential Geometry control method and method of inverse be difficult to really use in practice.The Neural network inverse control method can remedy the deficiency of above-mentioned control method, and the realization of its controlled system linearisation decoupling zero does not rely on precise math model, and can not bring departure because of the instability of system parameters.And neural net generalized inverse control method is except that the various advantages that possess the Neural network inverse control method, can also make its subsystem have open-loop stable linear transitive relation by the limit that disposes pseudo-linear hybrid system, the neural net generalized inverse directly can be used as a non-linear open-cycle controller, but simply the neural net generalized inverse is used as controller, enforcement open loop control, it controls poor effect.
Number of patent application 200710190554.2, name is called: the neural net generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing, be at bearing-free permanent magnet synchronous motor design neural net generalized inverse decoupling controller, the mechanical structure of its rotor and operation mechanism, Mathematical Modeling, performance requirement are different with bearingless synchronous reluctance motor, bearingless synchronous reluctance motor has utilized the field spider d-axis and has handed over the axle inductance not wait and produced reluctance torque, and then drags load.In addition, its decoupling control method is that the neural net generalized inverse is directly used as a non-linear open-cycle controller, the control poor effect.
Summary of the invention
The objective of the invention is for overcoming above-mentioned the deficiencies in the prior art, a kind of bearingless synchronous reluctance motor neural net generalized inverse decoupling controller building method is provided, both can realize between bearingless synchronous reluctance motor electromagnetic torque and the radial suspension force and the radial suspension force control of the decoupling zero between the component on two vertical direction certainly, can obtain good every control performance index again; After adopting the neural net generalized inverse, design linear closed loop controller again with controlled system linearisation decoupling zero, thus the robustness of enhanced system.
Technical scheme of the present invention is to adopt following steps: 1) with first, second Park inverse transformation, make as a whole composition composite controlled object before being connected in bearingless synchronous reluctance motor after first, second Clark inverse transformation, first, second current track inverter are connected in series respectively successively; 2) set up the Mathematical Modeling of bearingless synchronous reluctance motor, obtain the Mathematical Modeling of composite controlled object through coordinate transform and linear amplification, on the basis of the Mathematical Modeling of composite controlled object, adopt static neural network to add 5 linear elements and come the constructing neural network generalized inverse; 3) the neural net generalized inverse is serially connected with composite controlled object and forms the broad sense pseudo-linear system before, composite controlled object is with the position of rotor
x,
yAnd rotating speed
ωBe output, with four current signals of neural net generalized inverse output
,
,
,
Input controlled quentity controlled variable as composite controlled object; The broad sense pseudo-linear system comprises two location subsystem and these three single output subsystems of single input of a speed subsystem; 4) generalized inverse is trained to neural net, by training each weight coefficient of determining static neural network, makes the neural net generalized inverse approach the generalized inverse system of composite controlled object; 5) respectively to two positioners, the speed control of two location subsystem, a speed subsystem design correspondence in the broad sense pseudo-linear system after the linearisation decoupling zero, with these three linear closed loop controllers of controller mutual group; 6) linear closed-loop controller, neural net generalized inverse, first, second Park inverse transformation, first, second Clark inverse transformation, first, second current track inverter are constituted bearingless synchronous reluctance motor neural net generalized inverse decoupling controller after the serial connection respectively successively jointly.
The invention has the beneficial effects as follows:
1, bearingless synchronous reluctance motor compare with the synchronous magnetic resistance motor of simple use magnetic bearing supporting have more reasonable, Shi Yong structure more: the one, the bearingless synchronous reluctance motor compact mechanical structure, rotor axial length reduces, motor speed, power can be further enhanced, and can realize the high speed and ultrahigh speed operation; The 2nd, power amplification circuit adopts the three phase power inverter circuit in the radial suspension Force control system, makes that the control method of bearingless synchronous reluctance motor is simple, and compact conformation is low in energy consumption, and cost descends.Broken away from the synchronous magnetic resistance motor complex structure of traditional magnetic bearing supporting, critical whirling speed is low, control system complexity, power amplifier cost height, defective such as volume is big.
2, the present invention realizes high-accuracy control by closed-loop control and adjustment pid parameter, finally make system obtain satisfied every performance, as the dynamic and static regulating characteristics in rotor radial position and torque, speed regulation performance, make bearingless synchronous reluctance motor have very high using value, be used widely at a high speed or in numerous special electric transmission fields such as ultrahigh speed Digit Control Machine Tool, canned pump, semi-conductor industry, Aero-Space, chemical engineering industry, life science and bioengineering.
3, the method that adopts static neural network to add linear link realizes the generalized inverse system of composite controlled object, and then structure nerve net generalized inverse decoupling controller is realized the control to bearingless synchronous reluctance motor, be completely free of traditional Differential Geometry control method and method of inverse dependence to mathematical models, do not exist owing to the unstable system's departure brought of system parameters, realize the independent control of the rotating speed of bearingless synchronous reluctance motor position system, rotor well, improved the control performance of bearingless synchronous reluctance motor significantly.
4. the present invention adopts a static neural network and 5 linear elements to constitute the neural net generalized inverse, and approach the generalized inverse system with the neural net generalized inverse, this is non-linear with bearingless synchronous reluctance motor, the multi-input multi-output system linearisation of close coupling and decoupling zero are two second-order linearity location subsystem and a first-order linear speed subsystem, make location subsystem after the decoupling zero and limit reasonable disposition in complex plane of speed subsystem by the parameter of reasonably regulating the generalized inverse system, thereby obtain open-loop stable subsystem, and respectively to two location subsystem and two positioners of a speed subsystem design and a speed control, realized between electromagnetic torque and the radial suspension force and the radial suspension force control of the decoupling zero between the component on two vertical direction certainly, thereby realized the open loop LINEARIZED CONTROL of non linear system.
5, because neural net has the ability of Function approximation capabilities and the variation of adaptive system parameter, thereby the present invention can not need to know the mathematical models of controlled system, but also need not measure the just limit of the pseudo-linear hybrid system of reasonable disposition of controlled system internal state, the linearisation on a large scale of realization system, decoupling zero and depression of order, improved the robustness of system greatly to parameter variation and load disturbance, 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 and decoupling zero control provide an effective way.
Description of drawings
Fig. 1 is the composite controlled object of being made up of 22,32, two current track inverters 23,33 of 21,31, two Clark inverse transformations of two Park inverse transformations and bearingless synchronous reluctance motor 15;
Fig. 2 is the structural representation of the neural net generalized inverse 6 that is made of static neural network 61 and 5 linear element;
The schematic diagram and the isoboles thereof of Fig. 3 broad sense pseudo-linear system 8 that to be neural net generalized inverse 61 be composed in series with composite controlled object 5;
The closed-loop control system structure chart that Fig. 4 is made up of linear closed-loop controller 4 and pseudo-linear hybrid system 8;
Fig. 5 is a bearingless synchronous reluctance motor neural net generalized inverse decoupling controller theory diagram;
Among the figure: 1. bearingless synchronous reluctance motor; 4. linear closed-loop controller; 5. composite controlled object; 6. neural net generalized inverse; 7. bearingless synchronous reluctance motor neural net broad sense decoupling zero inverse controller; 8. broad sense pseudo-linear system; 21,31.Park inverse transformation, 22,32.Clark inverse transformation; 23,33. current track inverters; 41,42. positioners; 43. speed control; 61. static neural network; 81,82. location subsystem; 83. speed subsystem.
Embodiment
The present invention specifically implements following 6 steps of branch:
1, as shown in Figure 1, form composite controlled object 5.The present invention is connected in before the bearingless synchronous reluctance motor 1 after 22,32, two current track inverters 23,33 of 21,31, two Clark inverse transformations of two Park inverse transformations are connected in series respectively successively, makes as a whole composition composite controlled object 5.A Park inverse transformation 21 soon, a Clark inverse transformation 22, first current track inverter 23 are connected in before the bearingless synchronous reluctance motor 1 after being connected in series successively, do as a wholely after being connected in before the bearingless synchronous reluctance motor 1 after the 2nd Park inverse transformation 31, the 2nd Clark inverse transformation 32, second current track inverter 33 be connected in series successively, equivalence is a composite controlled object 5.Composite controlled object 5 is with the position of rotor
x,
yAnd rotating speed
ωAs output, and with four current signals of neural net generalized inverse 6 output
,
,
,
Input controlled quentity controlled variable as composite controlled object 5.
2, as shown in Figure 2, determine the structure of neural net generalized inverse 6, neural net generalized inverse 6 is serially connected with before the composite controlled object 5.Set up the Mathematical Modeling of bearingless synchronous reluctance motor 1 according to the principle of bearingless synchronous reluctance motor 1, through coordinate transform and linear amplification, obtain the Mathematical Modeling of composite controlled object 5, be the 5 rank differential equations under the rotating coordinate system, the relative rank of vector of obtaining system on this basis are { 2,2,1}, then the generalized inverse system of composite controlled object 5 exists.Adopt static neural network 61 to add 5 linear elements and come constructing neural network generalized inverse 6, thereby can construct neural net generalized inverse 6.3 of neural net generalized inverse 6 are input as
,
With
, 4 outputs are respectively 4 inputs of composite controlled object, promptly
,
,
With
Static neural network 61 adopts three layers of feedforward network structure, has 8 input nodes, 4 output nodes, 18 implicit nodes, and the hidden neuron activation primitive uses the S type function
, the neuron of output layer adopts pure linear function
,
Be neuronic input.First input of neural net generalized inverse 6
As first input of static neural network 61, it is through second-order system
Be output as
, be second input of static neural network 61, again through an integrator
s -1For
, be the 3rd input of static neural network 61; Second input of neural net generalized inverse 6
As the 4th input of static neural network 61, it is through second-order system
Be output as
, be the 5th input of static neural network 61, again through an integrator
s -1For
, be the 6th input of static neural network 61; The 3rd input of neural net generalized inverse 6
As the 7th input of static neural network 61, it is through an integrator
s -1For
, be the 8th input of static neural network.The output of static neural network 61 is exactly four output currents of neural net generalized inverse 6
,
,
With
3, as shown in Figure 3, form broad sense pseudo-linear system 8.Neural net generalized inverse 6 is placed before the composite controlled object 5, neural net generalized inverse 6 is composed in series broad sense pseudo-linear system 8 with composite controlled object 5, broad sense pseudo-linear system 8 comprises three single output subsystems of single input, be respectively 81,82 and speed subsystems 83 of two location subsystem, the transfer function of location subsystem 81 is
, the transfer function of location subsystem 82 is
, the transfer function of speed subsystem 83 is
By reasonably regulating the generalized inverse system parameters
a 10,
a 11,
a 12,
a 20,
a 21,
a 22,
a 30,
a 31, reasonable disposition location subsystem 81,82 and the limit of speed subsystem 83 in complex plane make location subsystem 81,82 after the decoupling zero and limit reasonable disposition in complex plane of speed subsystem 83; Make system obtain comparatively desirable open loop frequency characteristic.
4, neural net generalized inverse 6 is trained.In the working region of bearingless synchronous reluctance motor 1, with four electric currents
,
,
With
All get the step excitation signal, be added to the input of composite controlled object 5, gather the rotor radial displacement of bearing-free permanent magnet synchronous motor
x,
yRotating speed with rotor
w, obtain 10000 groups of primary data sample
,
,
,
,
x,
y,
w; Adopt high-order numerical differentiation method with two rotor displacements
x,
yOff-line is asked its single order, second dervative respectively, and then goes out
With
, rotating speed
wAsk its first derivative, and then obtain
, and signal done standardization processing, form neural net training sample set
,
,
,
,
,
,
,
,
,
,
,
, and training sample set done normalized; Choose 7000 groups of data the training sample after normalization, utilize variable step to add the BP algorithm off-line training static neural network 61 of momentum term, make neural net output mean square error less than 0.001, thereby determine each weight coefficient of static neural network 61.Weight coefficient by training acquisition static neural network 61 makes neural net generalized inverse 6 approach the generalized inverse system of composite controlled object 5.
5, as shown in Figure 4, respectively to 81,82, speed subsystems of two location subsystem after the linearisation decoupling zero, 83 design attitude controller 41,42 and speed controls 43, form linear closed-loop controller 4.Linear closed-loop controller 4 can adopt PID control, 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, two position controls have all been selected proportion differential PD controller for use, and rotational speed governor has been selected the proportional integral pi regulator for use, and selects and adjust regulator parameter according to the bearingless synchronous reluctance motor parameter.
6, as shown in Figure 5, constitute bearingless synchronous reluctance motor neural net broad sense decoupling zero inverse controller 7.With linear closed-loop controller 4, neural net generalized inverse 6, first, second Park inverse transformation 21,31, first, second Clark inverse transformation 22,32, first, second current track inverter 23,33 are connected in series respectively successively, constitute bearingless synchronous reluctance motor neural net generalized inverse decoupling controller 7 jointly.According to different control requirements, can select different hardware and softwares to realize.
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 in the case of without departing from the spirit and scope of protection of the present invention still are included within the protection range of the present invention.
Claims (3)
1. bearingless synchronous reluctance motor neural net generalized inverse decoupling controller building method is characterized in that adopting following steps:
1) with first, second Park inverse transformation (21,31), be connected in bearingless synchronous reluctance motor (1) after first, second Clark inverse transformation (22,32), first, second current track inverter (23,33) are connected in series respectively successively and make as a whole composition composite controlled object (5) before;
2) set up the Mathematical Modeling of bearingless synchronous reluctance motor (1), obtain the Mathematical Modeling of composite controlled object (5) through coordinate transform and linear amplification, on the basis of the Mathematical Modeling of composite controlled object (5), adopt static neural network (61) to add 5 linear elements and come constructing neural network generalized inverse (6);
3) neural net generalized inverse (6) is serially connected with composite controlled object (5) and forms broad sense pseudo-linear system (8) before, composite controlled object (5) is with the position of rotor
x,
yAnd rotating speed
ωBe output, with four current signals of neural net generalized inverse (6) output
,
,
,
Input controlled quentity controlled variable as composite controlled object (5); Broad sense pseudo-linear system (8) comprises two location subsystem (81,82) and these three single output subsystems of single input of a speed subsystem (83);
4) neural net generalized inverse (6) is trained,, made neural net generalized inverse (6) approach the generalized inverse system of composite controlled object (5) by training each weight coefficient of definite static neural network (61);
5) respectively to two location subsystem (81,82), corresponding two positioners (41,42), the speed control (43) of a speed subsystem (83) design in the broad sense pseudo-linear system (8) after the linearisation decoupling zero, with these three linear closed loop controllers of controller mutual group (4);
6) linear closed-loop controller (4), neural net generalized inverse (6), first, second Park inverse transformation (21,31), first, second Clark inverse transformation (22,32), first, second current track inverter (23,33) are constituted bearingless synchronous reluctance motor neural net generalized inverse decoupling controller (7) after the serial connection respectively successively jointly.
2. bearingless synchronous reluctance motor neural net generalized inverse decoupling controller building method according to claim 1, it is characterized in that: step 2) three layers of feedforward network structure of middle static neural network (61) employing, have 8 input nodes, 4 output nodes, 18 implicit nodes; Will
As first input of static neural network (61),
Through second-order system
The output that obtains is as second input of static neural network (61),
Through second-order system
And integrator
s -1The output that obtains is as the 3rd input of static neural network (61); Will
As the 4th input of static neural network (61),
Through second-order system
The output that obtains is as the 5th input of static neural network (61),
Through second-order system
And integrator
s -1The output that obtains is as the 6th input of static neural network (61); Will
As the 7th input of static neural network (61),
Through first-order system
The output that obtains is as the 8th input of static neural network (61).
3. bearingless synchronous reluctance motor neural net generalized inverse decoupling controller building method according to claim 1, it is characterized in that: each weight coefficient of the static neural network described in the step 4) (61) determines that method is: earlier in the working region of bearingless synchronous reluctance motor (1) with four current signals
,
,
With
All use the step excitation signal to be added to the input of composite controlled object (5), and gather the rotor radial displacement of bearing-free permanent magnet synchronous motor (1)
x,
yRotating speed with rotor
w, obtain primary data sample
,
,
,
,
x,
y,
w; Adopt high-order numerical differentiation method with two rotor displacements again
x,
yOff-line is asked its single order, second dervative respectively, and then goes out
With
, rotating speed
wAsk its first derivative, and then obtain
, and signal done standardization processing, form neural net training sample set
,
,
,
,
,
,
,
,
,
,
,
, training sample set is done normalized; The BP algorithm off-line training static neural network (61) that utilizes variable step to add momentum term is at last determined each weight coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100218629A CN102097986A (en) | 2011-01-20 | 2011-01-20 | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100218629A CN102097986A (en) | 2011-01-20 | 2011-01-20 | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102097986A true CN102097986A (en) | 2011-06-15 |
Family
ID=44130887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100218629A Pending CN102097986A (en) | 2011-01-20 | 2011-01-20 | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102097986A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629843A (en) * | 2012-04-06 | 2012-08-08 | 江苏大学 | Method for constructing neutral network generalized inverse adaptive controller of three-motor driving system |
| CN102647130A (en) * | 2012-04-20 | 2012-08-22 | 上海电机学院 | Permanent magnet synchronous linear motor control method |
| CN102790583A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Constructing method for internal model controller of radial generalized inverter of bearingless permanent magnet synchronous motor |
| CN103633911A (en) * | 2013-11-18 | 2014-03-12 | 江苏大学 | Construction method for differential geometry decoupling controller of bearing-free synchronous reluctance machine |
| CN103888037A (en) * | 2014-02-25 | 2014-06-25 | 江苏大学 | Construction method for inverse decoupling controller of extreme learning machine |
| CN104953913A (en) * | 2015-07-03 | 2015-09-30 | 兰州交通大学 | Networked AC (alternating current) motor LS-SVM (least squares support vector machine) generalized inverse decoupling control method based on active-disturbance rejection |
| CN110262244A (en) * | 2019-07-02 | 2019-09-20 | 武汉科技大学 | A kind of self adaptation straightening method for improving FSRBFD |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1845449A (en) * | 2006-03-08 | 2006-10-11 | 江苏大学 | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller |
| KR20070080249A (en) * | 2007-07-02 | 2007-08-09 | 순천대학교 산학협력단 | Efficiency optimization system of ipmsm using neural-network |
| CN101227160A (en) * | 2007-11-30 | 2008-07-23 | 江苏大学 | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing |
| CN101814892A (en) * | 2010-03-04 | 2010-08-25 | 江苏大学 | Support vector machine inverse system composite controller based on bearingless synchronous reluctance motor |
-
2011
- 2011-01-20 CN CN2011100218629A patent/CN102097986A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1845449A (en) * | 2006-03-08 | 2006-10-11 | 江苏大学 | Method for controlling bearing-less AC asynchronous motor neural network inverse decoupling controller |
| KR20070080249A (en) * | 2007-07-02 | 2007-08-09 | 순천대학교 산학협력단 | Efficiency optimization system of ipmsm using neural-network |
| CN101227160A (en) * | 2007-11-30 | 2008-07-23 | 江苏大学 | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing |
| CN101814892A (en) * | 2010-03-04 | 2010-08-25 | 江苏大学 | Support vector machine inverse system composite controller based on bearingless synchronous reluctance motor |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629843A (en) * | 2012-04-06 | 2012-08-08 | 江苏大学 | Method for constructing neutral network generalized inverse adaptive controller of three-motor driving system |
| CN102647130A (en) * | 2012-04-20 | 2012-08-22 | 上海电机学院 | Permanent magnet synchronous linear motor control method |
| CN102790583A (en) * | 2012-08-06 | 2012-11-21 | 江苏大学 | Constructing method for internal model controller of radial generalized inverter of bearingless permanent magnet synchronous motor |
| CN102790583B (en) * | 2012-08-06 | 2015-08-05 | 江苏大学 | The building method of the radial generalized inverse internal mode controller of bearing-free permanent magnet synchronous motor |
| CN103633911A (en) * | 2013-11-18 | 2014-03-12 | 江苏大学 | Construction method for differential geometry decoupling controller of bearing-free synchronous reluctance machine |
| CN103633911B (en) * | 2013-11-18 | 2016-04-06 | 江苏大学 | The building method of bearingless synchronous reluctance motor differential geometrical decoupled control device |
| CN103888037A (en) * | 2014-02-25 | 2014-06-25 | 江苏大学 | Construction method for inverse decoupling controller of extreme learning machine |
| CN104953913A (en) * | 2015-07-03 | 2015-09-30 | 兰州交通大学 | Networked AC (alternating current) motor LS-SVM (least squares support vector machine) generalized inverse decoupling control method based on active-disturbance rejection |
| CN104953913B (en) * | 2015-07-03 | 2018-08-07 | 兰州交通大学 | Networking alternating current generator LS-SVM generalized inverse decoupling control methods based on active disturbance rejection |
| CN110262244A (en) * | 2019-07-02 | 2019-09-20 | 武汉科技大学 | A kind of self adaptation straightening method for improving FSRBFD |
| CN110262244B (en) * | 2019-07-02 | 2022-04-01 | 武汉科技大学 | Self-adaptive decoupling control method for improving FSRBFD |
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 | |
| CN102097986A (en) | Construction method for neural network generalized inverse decoupling controller of bearing-free synchronous reluctance motor | |
| CN100536311C (en) | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing | |
| CN102136822B (en) | Five-DOF (freedom of degree) bearingless synchronous reluctance motor decoupling controller and construction method thereof | |
| CN101958685B (en) | Nonlinear inverse decoupling controller for bearingless synchronous reluctance motor and construction method thereof | |
| CN202043069U (en) | Decoupling controller of five-degree-freedom bearingless synchronous reluctance motor | |
| CN201928221U (en) | Neural net generalized inverse decoupling controller for bearingless synchronous reluctance motor | |
| CN102790580B (en) | The building method of induction-type bearingless motor SVMs inverse decoupling controller | |
| 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 | |
| CN103414428A (en) | Bearingless synchronous reluctance motor rotor eccentric displacement controller and construction method thereof | |
| CN102013870B (en) | Inverse system decoupling controller of five-degree-of-freedom bearingless synchronous reluctance motor | |
| CN102790578B (en) | Manufacturing method of bearingless asynchronous motor neural network generalized inverse decoupling controller | |
| CN102790583B (en) | The building method of the radial generalized inverse internal mode controller of bearing-free permanent magnet synchronous motor | |
| CN202004708U (en) | Bearingless brushless direct current motor neural network alpha-order inverse controller | |
| CN110048657B (en) | Decoupling control method for neural network inverse system of bearingless asynchronous motor | |
| CN102790576B (en) | A kind of building method of bearing-free permanent magnet synchronous motor decoupling controller | |
| CN115085609B (en) | Control method for sliding mode system of single-winding magnetic suspension motor | |
| Daoud et al. | A design example of an 8-pole radial AMB for flywheel energy storage | |
| CN102790579B (en) | Constructing method for decoupling controller of bearingless permanent magnet synchronous motor with five degrees of freedom | |
| Zhao et al. | Robust adaptive speed control of disturbed brushless direct current motor | |
| Bu et al. | A control method of bearingless induction motor based on neural network | |
| Barbaraci et al. | Experimental investigations of minimum power consumption optimal control for variable speed AMB rotor | |
| CN102801382B (en) | Method for constructing five-freedom bearingless asynchronous motor support vector machine inverse 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 | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110615 |