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

Sliding mode controller design method based on multi-parameter self-adaptive neural network

A neural network and design method technology, applied in the directions of adaptive control, general control system, control/regulation system, etc., can solve the problem that the tracking performance needs to be improved, and achieve the goal of avoiding singularity problems, simplifying control design, and improving convergence speed. Effect

Pending Publication Date: 2021-11-02
NANCHANG UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although they can effectively weaken the chattering phenomenon, the tracking performance of the manipulator that requires high precision still needs to be improved.

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
  • Sliding mode controller design method based on multi-parameter self-adaptive neural network
  • Sliding mode controller design method based on multi-parameter self-adaptive neural network
  • Sliding mode controller design method based on multi-parameter self-adaptive neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] Below in conjunction with specific embodiment, further illustrate the present invention, in order to illustrate the present invention better, adopt matlab numerical simulation to verify the proposed controller, the result is as follows Figures 1 to 7 shown. Specific steps are as follows:

[0059] Step 1, establish the dynamic model of the rigid manipulator with n-DOF rotating joints. The specific steps are as follows:

[0060]

[0061] In the formula, represent the position, velocity and acceleration of the joints of the manipulator, respectively;

[0062] M(q)=M 0 (q)+ΔM(q) is a positive definite inertia matrix, is the matrix of centrifugal force and Coriolis force, G(q)=G 0 (q)+ΔG(q) is the gravity vector, is the nominal value of the system parameter, Indicates the uncertain part of the system, τ is the control input, τ d For disturbance input, is the friction torque.

[0063] Step 2, first define the error signal as follows:

[0064]

[0065] ...

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 sliding mode controller design method based on a multi-parameter self-adaptive neural network. The sliding mode controller design method comprises the steps: 1, establishing an n-degree-of-freedom rotary joint rigid mechanical arm dynamic model; 2, converting the model system in the step 1 into a second-order state equation based on a joint position, and designing a fast terminal sliding mode surface for the second-order state equation; 3, approaching unknown dynamic parameters of the system by using an RBF neural network; and 4, designing a self-adaptive nonsingular fast terminal sliding mode controller, and realizing model-free control of a mechanical arm based on the dynamic parameter approximation result in the step 3. The method is suitable for trajectory tracking control of the mechanical arm influenced by model uncertainty and external interference, the number of self-adaptive design parameters given in a control design program is reduced, and an unknown nonlinear function of robot dynamics is approximated on the basis of RBFNN; and in addition, the convergence speed and tracking precision of errors are improved, and global asymptotic stability based on the lyapunov theorem is achieved.

Description

technical field [0001] The invention belongs to the technical field of automatic control, in particular to a design method of a sliding mode controller based on a multi-parameter self-adaptive neural network for trajectory tracking control of a manipulator. Background technique [0002] Trajectory tracking control of robots has attracted great attention in recent years due to the increasing demand for fast response and high-precision tracking in real-world applications. In order to solve the tracking problem, many scholars have proposed various control schemes, including backstepping control, adaptive control, sliding mode control (SMC), and intelligent control. [0003] As we all know, the sliding mode control scheme is a main control method, which has the advantages of well-established, good transient performance and robustness to unknown system dynamics. The basic principle of sliding mode control is to land the system on a designed sliding surface. In general, robust s...

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 徐正宏张文杰杨晓辉张伟刘康张柳芳杨爽冷正旸宋曜任陈伟张亮
Owner NANCHANG 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

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