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

Magnetic levitation switch reluctance motor radial neural network reversed decoupling controller and method for constructing same

A neural network inverse and decoupling controller technology, applied in the field of electric drive control equipment, can solve problems such as increased rotor frictional resistance, uneven motor air gap, and poor motor dynamic characteristics, achieving broad application prospects and getting rid of dependence. , the effect of high application value

Inactive Publication Date: 2005-08-17
JIANGSU UNIV
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] A prominent problem of high-speed and ultra-high-speed motors is the wear of mechanical bearings. Mechanical friction not only increases the frictional resistance of the rotor, but also causes heating of the components. Reduce the efficiency of the motor and shorten the service life of the motor and equipment

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
  • Magnetic levitation switch reluctance motor radial neural network reversed decoupling controller and method for constructing same
  • Magnetic levitation switch reluctance motor radial neural network reversed decoupling controller and method for constructing same
  • Magnetic levitation switch reluctance motor radial neural network reversed decoupling controller and method for constructing same

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The implementation of the present invention is: firstly, the current hysteresis control voltage source inverter and Clark transformation jointly form an extended current control inverter, and this extended current control inverter will serve as the entire neural network inverse decoupling controller A part of. Secondly, the extended flow control inverter and the magnetic levitation switched reluctance motor suspension position control are taken as a composite controlled object, which is equivalent to a fourth-order differential equation model in a two-phase coordinate system, and the relative order of the vector of the system Is {2, 2}. A static neural network with 6 input nodes and 2 output nodes (static neural network is a multi-layer network MLN) plus 4 integrators (s -1 ) To construct the neural network inverse of the compound controlled object. And by adjusting each weight coefficient of the static neural network, the neural network inversely realizes the inverse syste...

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

This invention relates to a simultaneous control applied in magnetic suspension switch magnetic resistance motor, which comprises the following steps: adopting extensive flow control inverter, wherein the controlled magnetic suspension switch magnetism motor forms compound controlled subject; forming neural net athwart by static neural net and integral device through formula study; connecting neutral net with the compound controlled subject then compounding into two radius direction position sub system to forming anti-linear system; making the linear loop controller to the false linear system according to the linear system design; finally connecting the neural net with the linear loop controller and with the flow controlled inverter to form neural net decoupling controller.

Description

Technical field [0001] The invention is a radial neural network inverse decoupling controller and a construction method for a magnetic suspension switched reluctance motor, which is suitable for high-performance control of a magnetic suspension switched reluctance motor and belongs to the technical field of electric drive control equipment. Background technique [0002] A prominent problem of high-speed and ultra-high-speed motors is the problem of mechanical bearing wear. Mechanical friction not only increases the frictional resistance of the rotor, but also causes heating of the components. In severe cases, the air gap of the motor will be uneven, resulting in poor dynamic characteristics of the motor. Reduce the efficiency of the motor and shorten the service life of the motor and equipment. Magnetic levitation switched reluctance motor (also known as bearingless switched reluctance motor, BSRM for short) does not require the design of special mechanical bearings, and uses mag...

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
IPC IPC(8): G05B13/02H02N15/00H02P25/08
Inventor 刘国海孙玉坤戴先中沈跃刘贤兴朱熀秋
Owner JIANGSU UNIV
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