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

Neural network control method for backlash compensation of turntable servo system

A neural network control and servo system technology, applied in the field of electromechanical control, can solve the problems of fast response speed, good stability, low tracking accuracy and low tracking stability, and achieve overcoming the influence of backlash nonlinearity, high-precision tracking control, Good estimate of the effect of velocity information

Inactive Publication Date: 2020-10-16
XI AN JIAOTONG UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

PID control is a non-model-based control strategy with a simple structure, easy to operate and implement, but for nonlinear systems with backlash, the tracking accuracy and tracking stability of PID control are low
The advantages of sliding mode control are strong anti-interference ability and fast response speed. The disadvantage is that high-frequency chattering will occur when the tracking error is close to zero steady state
[0005] For a servo system with backlash nonlinearity, the above single control strategy is difficult to achieve control goals such as high tracking accuracy, good stability, and fast response speed. Therefore, how to design a high-performance controller to compensate for the influence of backlash is very important. of actual engineering value

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
  • Neural network control method for backlash compensation of turntable servo system
  • Neural network control method for backlash compensation of turntable servo system
  • Neural network control method for backlash compensation of turntable servo system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention.

[0048] The object of the present invention is to provide a neural network control method for backlash compensation of the turntable servo system, so as to realize the dynamic performance of high precision, fast response speed and smooth tracking. figure 1 A flow chart of a neural network control method for backlash compensation of a turntable servo system provided by the present invention, figure 2 The corresponding mathematical model control flow chart includes the following steps:

[0049] 1) Analyze the turntable servo system with backlash nonlinearity, and use the dead zone model of backlash to establish the state space equation of the turntable servo system.

[0050] The dynamic equations are respectively established for the motor shaft and the load shaft, and the establi...

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 discloses a neural network control method for backlash compensation of a turntable servo system, and aims to obtain higher tracking precision, faster response time and more stable tracking performance in allusion to the problems of driving delay and response hysteresis caused by the existence of a backlash in the turntable servo system. The method comprises the following steps of: establishing a state-space equation of an industrial robot turntable servo system, and selecting a dead zone function to describe backlash nonlinearity; directed at the problem that the speed information loaded by an industrial robot servo system is difficult to measure, a speed observer is designed to estimate the speed information; meanwhile, applying a backstepping method, introducing a virtual control quantity, selecting a Lyapunov function for backstepping recursion, and meanwhile introducing a radial basis function neural network for approximating a nonlinear part in the system, designingan RBF neural network backstepping controller, and proving the stability of the system by using the Lyapunov stability principle, ensuring the progressive stability of the system, compensating the influence of backlash nonlinearity, and improving the tracking precision.

Description

technical field [0001] The invention belongs to the technical field of electromechanical control, and specifically refers to a neural network control method for backlash compensation of a turntable servo system. Background technique [0002] Turntable servo systems are widely used in industry and military, such as precise positioning of industrial robots, precision machining on CNC equipment, precise control of radar, etc., and the requirements for performance indicators are getting higher and higher. Backlash nonlinearity is ubiquitous in the turntable servo system. Backlash is beneficial for the lubrication between gears and preventing gear teeth from being stuck, but it will cause the system output to lag, causing delay, oscillation and steady-state error. Therefore, it is necessary to apply a reasonable compensation control strategy to the backlash in the turntable servo system. [0003] The method of electric backlash elimination and control compensation is usually use...

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): G05B13/04
CPCG05B13/042
Inventor 董光能王世剑王佳伟
Owner XI AN JIAOTONG 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