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

NNs-MRAS-based speed sensorless doubly-fed induction generator LQR control method

A speed sensorless, doubly-fed motor technology, used in motor generator control, electronically commutated motor control, control systems, etc., can solve the problems of ignoring transient characteristics and slow dynamic response, and achieve good control performance and sine degree. Good results

Inactive Publication Date: 2018-05-01
CHAJNA MAJNING DRAJVS EHND AUTOMEHJSHN KO
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At the same time, in the doubly-fed motor control system, the double-closed-loop structure based on vector control is mostly used, and the inner-loop controller that determines the control effect of the system is mostly the traditional PI controller, and the PI controller only considers the system in a certain The steady-state model near the operating state ignores its transient characteristics and its dynamic response is slow

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
  • NNs-MRAS-based speed sensorless doubly-fed induction generator LQR control method
  • NNs-MRAS-based speed sensorless doubly-fed induction generator LQR control method
  • NNs-MRAS-based speed sensorless doubly-fed induction generator LQR control method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to deepen the understanding of the present invention, the present embodiment will be described in detail below with reference to the accompanying drawings.

[0030] Neural Network-Model Reference Adaptive (NNs-MRAS) velocity observation models such as figure 1 In the figure, u is the input of the NNs-MRAS velocity observation model, X and is the state quantity with the same physical meaning, and ε is the deviation value of the state quantity. The NNs-MRAS speed observation method is derived from the MRAS speed estimation method. The mathematical equation without speed information is used as the reference model of the MRAS, while the adjustable model is the neural network (NNs) model. The output of the reference model and the NNs model has the same output. Physical meaning, the deviation information obtained based on the output of the two models is output by the back-propagation algorithm. The intrinsic parameters of the motor are calculated by the neural net...

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 relates to an NNs-MRAS-based speed sensorless doubly-fed induction generator LQR control method. A differential algorithm is adopted to design a neural network (NNs) model, the neural network model is trained by a deviation backpropagation algorithm, and thus, a good rotation speed observation ability is achieved. A controller based on a linear quadratic (LQR) optimal control algorithm for stator current under a two-phase synchronous rotating reference frame is designed, the gains are controlled through state feedback, optimal control on the current closed loop parameters is realized, and the dynamic and static performance of the system is improved.

Description

technical field [0001] The invention relates to a LQR control method of a doubly-fed motor, in particular to a LQR control method of a doubly-fed motor without a speed sensor based on NNs-MRAS. Background technique [0002] The high dynamic and steady-state performance of the DFIG speed control system needs to install a speed sensor to obtain accurate motor speed for closed-loop control. However, high-precision speed sensors are expensive and difficult to install and maintain. At the same time, the speed signal is easily connected to interference noise during the transmission of the signal line, which reduces the accuracy of speed observation. If the observed speed information is lost, it will directly lead to incomplete decoupling of the flux linkage and torque of the doubly-fed motor, affecting the performance of the control system, and even causing the motor's starting current to have an excessive impact, which will directly damage the inverter and the motor. [0003] In...

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): H02P21/00H02P21/12H02P21/22H02P21/18
CPCH02P21/0014H02P21/0017H02P21/12
Inventor 谭国俊李浩刘毅刘战杨波
Owner CHAJNA MAJNING DRAJVS EHND AUTOMEHJSHN KO
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