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

Multilayer neural network-based motor position servo system friction compensation control method

A multi-layer neural network and servo system technology, applied in the field of friction compensation control of motor position servo system based on multi-layer neural network, can solve the problems of self-excited limit cycle oscillation, inaccurate compensation, and many friction model parameters, and achieve smooth Effects of motion, high tracking accuracy

Active Publication Date: 2018-01-09
NANJING UNIV OF SCI & TECH
View PDF5 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In previous studies, the simplified friction model may cause the controller designed based on it to deteriorate the control performance of the system due to inaccurate compensation, cause self-excited limit cycle oscillation, and even lead to system instability.
For a dynamic model that can describe the friction phenomenon more comprehensively, this kind of friction model has many parameters and complex structure, and it is difficult to design a high-performance controller.

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
  • Multilayer neural network-based motor position servo system friction compensation control method
  • Multilayer neural network-based motor position servo system friction compensation control method
  • Multilayer neural network-based motor position servo system friction compensation control method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0100] The simulation parameters are: J=0.9kgm 2 , T L =2Nm, f=0.002x 1 x 2 ,σ 0 =12Nm / rad,σ 1 =2.5Nms / rad,σ 2 =0.2Nms / rad,F s =0.34Nm,F c =0.28Nm,

[0101] The value of the motor position servo system friction compensation control method (ARCNN) based on the multilayer neural network proposed by the present embodiment is as follows: k 1 =150,k 2 =50,k=10,ε s =0.05,Γ 1 =diag{120,120,120,120,120},Γ 2 =diag{80,80},Γ 3 =diag{0.0005,0.003,0.005}

[0102] When the position reference tracking signal is a ramp signal x 1d =0.0001t, as shown in Figure 3(a), Figure 3(b), Figure 4(a), and Figure 4(b). Figure 3(a) , 3(b) It is the curve diagram of reference command signal and tracking signal under two kinds of controllers. Figure 4(a) and Figure 4(b) are the position tracking errors of the two controllers under the slope reference signal. It can be seen from the figure that a slight crawling phenomenon and a relatively large tracking error will appear at the beginnin...

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 discloses a multilayer neural network-based motor position servo system friction compensation control method and belongs to the electromechanical servo control field. According to the friction compensation control method, a neural network and the idea of adaptive robust control are combined, so that a multilayer neural network observer-based adaptive robust controller is designed; and a multilayer neural network is adopted to compensate complex uncertain items in nonlinear friction, and at the same time, an adaptive robust controller is designed to estimate uncertain parameters in a system and compensate external disturbances and the approximation errors of the neural network. With the control method designed by the invention adopted, the nonlinear friction problem ofa motor servo system can be solved, and the excellent tracking performance of the motor servo system can be ensured.

Description

technical field [0001] The invention relates to a friction compensation control method, in particular to a friction compensation control method for a motor position servo system based on a multilayer neural network. Background technique [0002] With the rapid development of modern technology, equipment such as robots, CNC machine tools and launch platforms have higher and higher performance requirements for servo control systems. But it is not easy to design a high-performance controller, because the uncertainty of parameters, friction nonlinearity, external disturbance and other uncertain nonlinearities always exist in the servo system, which seriously affects the performance of the servo system. Among the many factors affecting low-speed performance, friction nonlinearity is the most important, which makes the system prone to waveform distortion and crawling. Therefore, how to achieve high-precision tracking control and reduce the impact of friction on the servo system h...

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 Applications(China)
IPC IPC(8): G05B13/04
Inventor 胡健王元刚
Owner NANJING UNIV OF SCI & 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