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

A Diagonal Recurrent Neural Network Control Method Based on q-Learning Algorithm

A recursive neural network and learning algorithm technology, applied in the field of brushless DC motor control, can solve the problem of PID neural network initialization for a long time, and achieve the effects of enhanced robustness, enhanced anti-interference ability, and good control effect.

Active Publication Date: 2022-05-10
CHANGCHUN UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it takes a long time for PSO to initialize the PID neural network.

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 Diagonal Recurrent Neural Network Control Method Based on q-Learning Algorithm
  • A Diagonal Recurrent Neural Network Control Method Based on q-Learning Algorithm
  • A Diagonal Recurrent Neural Network Control Method Based on q-Learning Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings. It should be noted that the technical features and combinations of technical features described in the following embodiments should not be regarded as isolated, and they can be combined with each other to achieve better technical effects.

[0049] Such as figure 1 As shown, a kind of diagonal recursive neural network control method based on the Q learning algorithm proposed by the present invention, the specific framework includes a Q learning algorithm optimized DRNN module, a brushless DC motor, and the specific control method is as follows: sampling obtains the brushless DC motor input Speed ​​Y d (k) and the output speed y(k), calculate the speed error e(k)=Y d (k)-y(k), according to the speed error e(k), for e(k), e(k)-e(k-1), e(k)-2e(k-1)+e(k -2) Perform normalization processing as the input x of Q-DRNN 1 ,x 2 ,x 3 . At this time, th...

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 present invention designs a diagonal recursive neural network (DRNN) control method (Q‑DRNN) based on a Q learning algorithm. Q‑DRNN combines the strong search ability of Q learning with the self-contained recursive loop structure and dynamic mapping ability of DRNN and The advantages of adapting to time variation are organically combined to improve the working stability of the brushless DC motor (BLDCM). In Q‑DRNN, DRNN iterates the output variables through a unique recursive loop in the hidden layer, and optimizes its key weights to speed up iteration. At the same time, the improved Q learning is introduced to modify the weight and momentum factor of DRNN, so that DRNN has the ability of self-learning and online correction, which enhances the anti-interference ability and robustness of the system, so that the brushless DC motor achieves better control effect.

Description

technical field [0001] The invention belongs to the field of brushless DC motor control methods, and in particular relates to a diagonal recursive neural network control method based on a Q learning algorithm. Background technique [0002] Due to its simple structure, large output and high efficiency, brushless DC motors have been widely used in the fields of national defense, aerospace, robotics, industrial process control, precision machine tools, automotive electronics, household appliances and office automation. The brushless DC motor plays an important role in the modern motor speed control system. Therefore, it is of great practical significance and application prospect to study the speed control method of the brushless DC motor with fast response speed, strong adjustment ability and high control precision. [0003] PID control is one of the earliest linear control methods and has a long history. It remains the most commonly used control algorithm in industrial contro...

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): G05B13/04
CPCG05B13/04
Inventor 王宏志王婷婷胡黄水韩优佳
Owner CHANGCHUN 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