Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Position Sensorless Control Method of Brushless DC Motor Based on Extreme Learning Machine Classification

A technology of extreme learning machine and brushed DC motor, which is applied in the direction of electronic commutator, adaptive control, general control system, etc. It can solve the problems of low precision and difficult to use motor operation requirements, etc., and achieve fast learning rate and dynamic The effect of good performance and improved accuracy

Active Publication Date: 2020-08-11
HUNAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Technical problem: A variety of position sensorless rotor signal detection methods have their limitations, and the accuracy is not very high, so it is difficult to apply to occasions that require relatively high motor operation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Position Sensorless Control Method of Brushless DC Motor Based on Extreme Learning Machine Classification
  • A Position Sensorless Control Method of Brushless DC Motor Based on Extreme Learning Machine Classification
  • A Position Sensorless Control Method of Brushless DC Motor Based on Extreme Learning Machine Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The brushless DC motor position sensorless control method based on the extreme learning machine classification proposed by the present invention is described in detail as follows in combination with the control system structure diagram:

[0028] The first part: the extreme learning machine classification processing part, composed of figure 1 It can be seen that the number of neurons in the input layer of the ELM network is 6, and the number of neurons in the output layer is 6. Its training steps are as follows:

[0029] The training data and test data are obtained by simulating the position sensor brushless DC motor through MATLAB, and the measured 5000 sets of training data and 2500 sets of test data are normalized;

[0030] Step2: Determine the number of neurons in the hidden layer, write a for loop program with an M file, embed the ELM program inside the loop, and initialize the number of hidden layer nodes, so that the number of hidden layer nodes continues to incr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a brushless DC motor sensor-less control method based on extreme learning machine (ELM) classification, and aims at the problem of brushless DC motor rotor position detection. According to the sensor-less control based on the extreme learning machine, the brushless DC motor stator voltage and current act as the input of the extreme learning machine network, the rotor position information acts as the output, the DC motor rotor position is divided into six areas and each area is corresponding to conduction of the corresponding switching tube, i.e. the switching logic signal. The network parameters are determined through training of the ELM network and then the trained network model is applied to motor operation so that the rotor position information can be solved by using the motor stator voltage and current. The sensor-less control method has the advantages of great dynamic performance and high robustness, and the accuracy of the controller can be enhanced throughapplication of the extreme learning machine so that the learning rate of the algorithm is fast and the reaction speed of the controller can be enhanced.

Description

technical field [0001] The invention relates to a control method in the field of brushless direct current motors, specifically a method for controlling a brushless direct current motor without a position sensor based on extreme learning machine classification. Background technique [0002] Since the brushless DC motor has no brushes, it needs an electronic commutation circuit for current commutation, and a position signal is necessary to realize electronic commutation. The electronic commutation circuit is controlled by the rotor position signal so that the windings of the stator armature are continuously commutated and energized, so that the stator magnetic field changes continuously with the position of the rotor, so that the stator magnetic field and the rotor permanent magnetic field always maintain a left and right space Angle, generate torque to drive the rotor to rotate. [0003] Because the electronic commutation circuit needs the rotor position signal control, it i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H02P6/18G05B13/04
CPCG05B13/042H02P6/18
Inventor 王欣梁辉秦斌
Owner HUNAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com