Robot joint synovial membrane control method and system based on neural network observer

A robot joint and neural network technology is applied in the field of robot joint synovial control based on a neural network observer, which can solve the problems that the robot joint system model is difficult to determine and the system state is difficult to measure.

Active Publication Date: 2020-11-20
UNIV OF SCI & TECH BEIJING
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a robot joint synovium control method and system based on a neural network observer to solve the technical problems that the robot joint system model is difficult to determine and the system state is difficult to measure

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
  • Robot joint synovial membrane control method and system based on neural network observer
  • Robot joint synovial membrane control method and system based on neural network observer
  • Robot joint synovial membrane control method and system based on neural network observer

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0065] This embodiment provides a method for controlling the synovial membrane of a robot joint based on a neural network observer. The method can be implemented by an electronic device, and the electronic device can be a terminal or a server.

[0066] The method of this embodiment can track the ideal target of the system very well. Compared with the method of combining neural network and modern control, it also has a good control effect, and solves the problems that the robot system model is difficult to determine and the system state is difficult to measure. Many parameters of the robot joint system will change in actual work. The coupling relationship between subsystems and the existence of modeling errors, such as: inertia matrix, centrifugal force and Coriolis force items, and coupling of cross-linking items, lead to The model of the system is difficult to determine, so a synovial membrane control method based on neural network observer is designed. The RBF neural network...

no. 2 example

[0118] The present embodiment provides a robot joint synovium control system based on a neural network observer, and the robot joint synovium control system based on a neural network observer includes the following modules:

[0119] The joint subsystem model building module is used to establish a dynamic model of the robot joint system to be controlled, and separate local variables from the dynamic model to obtain the joint subsystem model corresponding to each joint in the robot joint system ;

[0120] The neural network observer building module is used to establish a neural network observer for the joint subsystem model constructed by the joint subsystem model building module under the constraint of limited cross-linking items, so as to monitor the state of the robot joint system performing online estimation; wherein the state of the system estimated by the neural network observer converges to the actual state of the robot joint system within a limited time;

[0121] The sy...

no. 3 example

[0125] This embodiment provides an electronic device, which includes a processor and a memory; at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor, so as to implement the method of the first embodiment.

[0126] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) and one or more memories, wherein at least one instruction is stored in the memory, so The above instructions are loaded by the processor and perform the following steps:

[0127] S101, establishing a dynamic model of the robot joint system to be controlled, and separating local variables from the dynamic model, to obtain a joint subsystem model corresponding to each joint in the robot joint system;

[0128] S102, under the constraints of limited cross-linking items, establish a neural network observer for the joint subsystem model to ...

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 robot joint synovial membrane control method and system based on a neural network observer, and the method comprises the steps: building a kinetic model for a to-be-controlled robot joint system, and obtaining a joint subsystem model through the separation of a local variable; establishing a neural network observer for the joint subsystem model under the constraint condition of limited cross-linking items so as to perform online estimation on the state of the robot joint system; wherein the system state estimated by the neural network observer converges to the actualstate of the robot joint system within limited time; designing a sliding mode controller according to the control thought of a sliding mode variable structure, and obtaining the control input of the system under the condition of ensuring the stability of the system. The method can achieve the control of the robot joint system under the condition that the system state and model of the robot joint system are unknown, and can guarantee the control precision and stability of the robot joint system.

Description

technical field [0001] The invention relates to the technical field of robot control, in particular to a method and system for controlling the synovium of a robot joint based on a neural network observer. Background technique [0002] Robotic joint systems are widely used in a series of environments such as aerospace, high-risk operations, medical treatment, service, production and processing. The robot joint system is a multivariable, nonlinear, and strongly coupled system. The traditional torque control and PID control methods have been difficult to meet the high precision and high stability requirements of the system. [0003] In the face of the problems that the model of the robot joint system is difficult to determine and the state is difficult to measure, the approximation ability of the neural network can be used to estimate and approximate the system model. Most of the existing neural network and modern control methods are used to design controllers, such as: neural...

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 潘月斗蔡国庆
Owner UNIV OF SCI & TECH BEIJING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap