CN109245631A - Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines - Google Patents

Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines Download PDF

Info

Publication number
CN109245631A
CN109245631A CN201811180667.9A CN201811180667A CN109245631A CN 109245631 A CN109245631 A CN 109245631A CN 201811180667 A CN201811180667 A CN 201811180667A CN 109245631 A CN109245631 A CN 109245631A
Authority
CN
China
Prior art keywords
support vector
svm
rotor
vector machines
motor
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.)
Withdrawn
Application number
CN201811180667.9A
Other languages
Chinese (zh)
Inventor
秦斌
王欣
秦羽新
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN201811180667.9A priority Critical patent/CN109245631A/en
Publication of CN109245631A publication Critical patent/CN109245631A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
    • H02P21/14—Estimation or adaptation of machine parameters, e.g. flux, current or voltage
    • H02P21/18—Estimation of position or speed
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P6/00—Arrangements for controlling synchronous motors or other dynamo-electric motors using electronic commutation dependent on the rotor position; Electronic commutators therefor
    • H02P6/14—Electronic commutators
    • H02P6/16—Circuit arrangements for detecting position
    • H02P6/18—Circuit arrangements for detecting position without separate position detecting elements
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P2203/00—Indexing scheme relating to controlling arrangements characterised by the means for detecting the position of the rotor
    • H02P2203/03—Determination of the rotor position, e.g. initial rotor position, during standstill or low speed operation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P2203/00—Indexing scheme relating to controlling arrangements characterised by the means for detecting the position of the rotor
    • H02P2203/09—Motor speed determination based on the current and/or voltage without using a tachogenerator or a physical encoder

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Control Of Motors That Do Not Use Commutators (AREA)

Abstract

The present invention is directed to brushless DC motor rotor position detection problem, proposes a kind of based on support vector machines (SVM) polytypic Brushless DC Motor Position method for sensing.It is mainly characterized by using brushless DC motor stator voltage and current as the input of SVM, rotor position information is as output, DC motor rotor location is divided into 6 regions, rotor-position is indicated with region serial number 1-6, each SVM classifier exports a corresponding region, it is combined into 15 bis- classifiers of SVM, SVM optimized parameter is determined to SVM network training by grid optimization method, trained network model is applied in motor operation again, acquire the input of motor stator voltage and electric current as SVM, output is then rotor position information, final position result is determined using ballot method, logic commutation signal is calculated by rotor-position, determine that each region corresponds to the on-off of respective switch pipe, that is phase change logic signal.

Description

Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines
Technical field
It is specifically exactly a kind of based on supporting vector the present invention relates to a kind of control method in brshless DC motor field The polytypic Brushless DC Motor Position method for sensing of machine (SVM).
Background technique
Brshless DC motor, which controls electronics commutation circuit by rotor-position signal, keeps each winding of stator armature continuous Commutation is powered, so that stator field and rotor permanent magnet magnetic field be made to remain 90 or so Space Angle, generates torque drive rotor Operating.
The rotor position information of conventional brushless DC motor is measured by position sensor, and installation site is needed to detect Device, but there is the brshless DC motor of position detecting device to have the disadvantage in that increase motor volume, it is small-sized to be unfavorable for motor Change；Position sensor is mounted in space very limited inside motor, it is difficult to installation and maintenance difficult；It is difficult to adapt to badly Environment；Sensor wire is complicated, is readily incorporated interference.Therefore the heat that brushless DC motor without position sensor is studied at people Point.
The position measurement technique of rotor position-sensor-free device mainly has Based on Back-EMF Method, electric current testing, intelligence at present Algorithm.Back-emf is directly proportional to speed, therefore cannot be obtained zero by detection back-emf in revolving speed very low even zero Signal；And the realization of current method depends on the precision of current sensor, under normal circumstances, sensor can be obtained preferably The signal of size of current, and the minor variations of current phase and waveform are then difficult to detect.Therefore Based on Back-EMF Method and current method list Solely using has its limitation.
Summary of the invention
Technical problem: the gyrator channel detection method of position sensor and a variety of position-sensor-free devices has its office It is sex-limited, therefore more difficult apply to requires motor operation relatively high occasion.
Technical solution: to solve the above-mentioned problems, the classification of support vector machines (SVM) two is used in rotor-position detection It goes, motor steady running as requested is enabled by rate of current control.For brshless DC motor, rotor-position is believed Mapping model number between electric moter voltage, electric current is set up, and realizes this mapping using support vector machines Decision Classfication.It will The input of electric moter voltage and electric current as support vector machines, rotor position information is as output, to realize motor rotor position Judgement.
The present invention be based on SVM on the basis of rotor-position detection system, by winding known to brushless motor working principle A, the induction magnetic linkage of B, C phase winding is the function of electrical angle θ, and the induction magnetic linkage and three phase terminals voltage of winding A, B, C phase winding There are certain relationships with electric current, therefore electrical angle θ, i.e. rotor-position signal can be predicted by three phase terminals voltage and current.
SVM is a kind of two disaggregated models, its purpose is to find a hyperplane to be split to sample, the original of segmentation It is then margin maximization, is eventually converted into a convex quadratic programming problem to solve.It is general to describe nonlinear multivariable disaggregated model Form are as follows: yi=sgn (g (xi)) whereinI=1,2 ..., N indicate the input quantity of support vector cassification prediction model, Yi indicates simulated target output quantity.Mapping functionThe sample of original input space is mapped using kernel function Into high-dimensional feature space Ω, linear classification is carried out to sample data using mapping function in feature space.
Svm classifier may be expressed as: g (x)=(w Φ (x))+b (1)
Wherein vector w ∈ Rn, bias b ∈ R.SVM minimizes the structure wind of model while minimizing sample error Danger, it may be assumed that
Constraint condition: yi[(wxi)+b]≤1-ξi, ξi>=0i=1 ..., N
Here ξiFor slack variable, equation (2) passes through the Lagrange multinomial of dual form, final classification is calculated Function are as follows:
Classification results are determined according to the symbol of g (x), in formula: optimal Lagrange multiplier αi；B is bias term.G(xi, x) be Kernel function, common part kernel function have radial basis function, global kernel function Polynomial kernel function.
Brushless DC Motor Position method for sensing proposed by the present invention based on support vector machines (SVM) Decision Classfication, A, B Phase voltage ua(k),ub(k) electric current ia(k),ib(k),ia(k-1),ib(k-1) as the input of support vector machines, S (K) is rotor Position signal, as the output of support vector machines, the corresponding SVM one kind output in each region, Gj(xi, x) and it is core letter Number, j=1,2 ..., L are respectively L classifier, i=1,2 ..., m.M is supporting vector number, certainly by algorithm of support vector machine Dynamic to generate, k is time series, KiFor rotor-position.Svm classifier exports corresponding two rotor-position regions, and 6 position outputs can Combination of two is exported at 15 two classification.
It is proposed by the present invention it is a kind of be based on the polytypic detection algorithm of SVM, using two taxonomic structure of support vector machines, Final classification output is determined by voting, and mainly includes support vector cassification modeling and model running part.
1) support vector cassification modeled segments mainly realize that steps are as follows:
Step1: signal: A, B phase is detected with model brshless DC motor acquisition system input and output to position sensor Voltage ua(k),ub(k) electric current ia(k),ib(k),ia(k-1),ib(k-1) as the input of support vector machines, S (K) is rotor position As the output of support vector machines Decision Classfication 15 2 classifiers of support vector machines are arranged, first just in confidence number altogether The sample of classification 1 is set to positive sample (+1)), 2 are set to negative sample (- 1), so go down, and 6 position output samples are respectively combined It is exported at 15 two classifiers, the training data data and test data that measure is normalized；
Step2: kernel function G is determinedj, kernel function can choose functions, the sig functions such as multinomial, radial base etc..Using Vapnik algorithm is trained, and by grid optimization method, to different model parameters, (penalty coefficient C, slack variable ξ and kernel function are joined Number) study and validation test are carried out to SVM, obtain 15 two disaggregated models of best support vector machines.
2) the more sort run parts of support vector machines mainly realize that steps are as follows:
Step1: relevant voltage and current input signal is acquired in real time and is normalized；
Step2: relevant voltage and current input signal input two classifier of established 15 support vector machines is obtained Corresponding classification results count classification results using ballot method, and who gets the most votes's classification is rotor region Ki points Class result；When belong to 1,2 ..., 6 classes there are two and result above it is identical when keep last time classification results constant, when belong to 1, 2, holding last time classification results are constant when ..., 6 classes are completely without result.
Step3 carries out real-time control according to the rotor-position that classification obtains.Logic commutation signal is calculated by rotor-position, Determine that each region corresponds to the on-off of respective switch pipe, i.e. phase change logic signal, rotor position information and phase change logic signal Transformation relation is as shown in table 1, wherein 1 indicates open-minded, 0 indicates shutdown.
The transformation relation table of 1 rotor position information of table and phase change logic signal
The utility model has the advantages that method for controlling position-less sensor of the invention has many advantages, such as that dynamic property is good, robustness is high.It calculates The operating rate of method is fast, improves controller response speed.
Detailed description of the invention
Fig. 1 is the Brushless DC Motor Position sensing network structure chart individually classified based on support vector machines two.System by 15 two classification position sensing networks are constituted,
Specific embodiment:
It is proposed by the present invention based on a pair of polytypic Brushless DC Motor Position method for sensing of support vector machines, in conjunction with being Details are as follows for its specific embodiment of structure chart of uniting:
First part: support vector cassification modeling processing part, the input number of the SVM network is 6 as shown in Figure 1, The classifier 2 corresponding positions of output.6 output position groups amount to 15 two classification devices, as shown in table 2；
2 support vector machines region of table exports assembled classifier
Its training step is as follows:
Step1: training data and test data are measured by position sensor brshless DC motor, by direct current 360 degree of electrical angles of the rotor rotation of motor are divided into 6 regions, and rotor-position is indicated with region serial number 1-6.By what is measured 5000 groups of training data data and 2500 groups of test datas are normalized；
Step2: determine that excitation function be G is radial basis function
Wherein x is input data, xiFor radial base center, σiFor radial base radius, i=1,2 ... m, m are center vector Number.J be corresponding classifier serial number, j=1,2 ..., 15.
Step3: choosing the training sample of respective class according to classifier output respectively, and positive sample is+1, and negative sample is -1, adopts 15 support vector machines are trained with Vapnik algorithm, using gridding method and cross validation test are stayed to obtain optimal models Parameter penalty coefficient C, slack variable ξ and radial base radius sigmai, obtain 15 optimal two classifiers of support vector machines.Parametric grid It is chosen by index variation as follows:
Penalty coefficient C:107-101；Slack variable ξ: 10-5-10-1, radial base radius sigmai: 10-5-10-1
Second part: mainly realize that steps are as follows in support vector cassification model running part:
Step1: relevant voltage and current input signal and normalized are acquired in real time；
Step2: input signal after the normalization of relevant voltage and current is inputted into established 15 support vector machines two and is divided Class device obtains corresponding classification results, is counted using ballot method to classification results, and who gets the most votes's classification is rotor place Region Ki classification results；When belong to 1,2 ..., 6 classes there are two and the above voting results it is identical when holding last time classification results not Become, when belong to 1,2 ..., 6 classes completely without result when keep last time classification results constant.
Step3 is according to rotor-position region KiBoth S (K) carried out real-time control.Calculate that logic is changed by rotor-position Phase signals determine that each region corresponds to the on-off of respective switch pipe, i.e. phase change logic signal.
Above-mentioned specific implementation is preferable realization of the invention, and certainly, the invention may also have other embodiments, Without deviating from the spirit and substance of the present invention, those skilled in the art make various in accordance with the present invention Corresponding changes and modifications, but these corresponding changes and modifications all should belong to scope of protection of the claims of the invention.

Claims (1)

1. one kind is based on support vector machines (SVM) polytypic Brushless DC Motor Position method for sensing, it is characterised in that pass through SVM multi-categorizer obtains the position signal of brushless DC motor rotor, reduce motor because position sensor there are due to bring Error and reduction motor volume.It mainly include the more classification model constructions of support vector machines based on the polytypic detection algorithm of SVM It is proposed by the present invention a kind of based on the polytypic detection algorithm of SVM with model running part, divided using support vector machines two Class formation determines final classification output by voting, mainly includes support vector cassification modeling and model running part:
1) support vector cassification modeled segments mainly realize that steps are as follows:
Step1: signal: A, B phase voltage u is detected with model brshless DC motor acquisition system input and output to position sensora (k),ub(k) electric current ia(k),ib(k),ia(k-1),ib(k-1) as the input of support vector machines, S (K) is rotor-position letter Number, as the output of support vector machines Decision Classfication, 15 2 classifiers of support vector machines are set altogether, and first just class Other 1 sample is set to positive sample (+1)), 2 are set to negative sample (- 1), so go down, and 6 position output samples are respectively combined into 15 A two classifiers output, pretreatment is normalized in training and test data to acquisition.
Step2: kernel function G is determinedj, kernel function can choose functions, the sig functions such as multinomial, radial base etc..It is calculated using Vapnik Method is trained, by grid optimization method to different model parameters (penalty coefficient C, slack variable ξ and kernel functional parameter) to SVM Study and cross validation test are carried out, 15 two disaggregated models of best support vector machines are obtained.
2) the more sort run parts of support vector machines mainly realize that steps are as follows:
Step1: relevant voltage and current input signal is acquired in real time and is normalized；
Step2: relevant voltage and current input signal input two classifier of established 15 support vector machines is obtained accordingly Classification results, classification results are counted using ballot method, who gets the most votes's classification be rotor region Ki classification knot Fruit；When belong to 1,2 ..., 6 classes there are two and result above it is identical when keep last time classification results constant, when belong to 1,2 ..., 6 Keep last time classification results constant when class is completely without result.
Step3 carries out real-time control according to the rotor-position that classification obtains.Logic commutation signal is calculated by rotor-position, is determined Each region corresponds to the on-off of respective switch pipe, i.e. phase change logic signal.
CN201811180667.9A 2018-10-09 2018-10-09 Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines Withdrawn CN109245631A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811180667.9A CN109245631A (en) 2018-10-09 2018-10-09 Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811180667.9A CN109245631A (en) 2018-10-09 2018-10-09 Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines

Publications (1)

Publication Number Publication Date
CN109245631A true CN109245631A (en) 2019-01-18

Family

ID=65052534

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811180667.9A Withdrawn CN109245631A (en) 2018-10-09 2018-10-09 Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines

Country Status (1)

Country Link
CN (1) CN109245631A (en)

Similar Documents

Publication Publication Date Title
Soualhi et al. Detection and diagnosis of faults in induction motor using an improved artificial ant clustering technique
Vazquez-Sanchez et al. A new method for sensorless estimation of the speed and position in brushed DC motors using support vector machines
Ebrahimi et al. Diagnosis and performance analysis of three-phase permanent magnet synchronous motors with static, dynamic and mixed eccentricity
CN109167545A (en) Magneto alternator magnetic linkage on-line identification method and system
CN105119549A (en) Motor stator resistor recognition method
CN102662323B (en) Adoptive sliding mode control method and adoptive sliding mode control system of wind power generation variable-pitch actuator
Sediki et al. ADALINE approach for induction motor mechanical parameters identification
US6922025B2 (en) Zero ripple linear motor system
Kumar et al. Accurate fault diagnosis and classification scheme based on non-parametric, statistical-frequency features and neural networks
CN102522948A (en) Hybrid intelligent adjusting method of torque hysteresis width in DTC (Direct Torque Control) system
CN109245631A (en) Based on the polytypic Brushless DC Motor Position method for sensing of support vector machines
Ilten et al. Design of induction motor speed observer based on long short-term memory
Rai et al. A comparative performance analysis for loss minimization of induction motor drive based on soft computing techniques
CN109194227A (en) Brushless DC Motor Position method for sensing based on support vector machines Decision Classfication
CN109217744A (en) Brushless DC Motor Position method for sensing based on support vector machines hierarchical classification
CN109150027A (en) Based on a pair of polytypic Brushless DC Motor Position method for sensing of support vector machines
Cipin et al. Measurement and evaluation of DC motor starting torque
CN109245651A (en) Based on the polytypic Brushless DC Motor Position method for sensing of LSSVM
CN107947650A (en) A kind of brushless direct current motor sensorless control method based on extreme learning machine classification
Oner et al. Neural networks detect inter-turn short circuit faults using inverter switching statistics for a closed-loop controlled motor drive
El Idrissi et al. Bearing Ball Fault Diagnosis of an Induction Machine by Using the Hilbert Transform and the Performance of Intelligent Control
CN109120191A (en) Brushless DC Motor Position method for sensing based on LSSVM hierarchical classification
CN109120192A (en) Based on a pair of polytypic Brushless DC Motor Position method for sensing of LSSVM
CN109150054A (en) Brushless DC Motor Position method for sensing based on LSSVM Decision Classfication
Banerjee et al. Hybrid intelligent predictive control system for high speed BLDC motor in aerospace application

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication

Application publication date: 20190118

WW01 Invention patent application withdrawn after publication