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

Nonlinear control method of neural network based on imitated operant conditioned reflex

A non-linear control and conditioned reflex technology, applied in the directions of adaptive control, general control system, control/regulation system, etc., can solve the problems of short time and imperfect theoretical system of type III controller, and reduce manual parameter adjustment work. , improve the effectiveness, the effect of a wide range of system operating conditions

Inactive Publication Date: 2017-10-20
青岛格莱瑞智能控制技术有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the type III controller has appeared for a relatively short time, and its theoretical system is not perfect, and there are many unforeseen problems worthy of in-depth discussion.

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
  • Nonlinear control method of neural network based on imitated operant conditioned reflex
  • Nonlinear control method of neural network based on imitated operant conditioned reflex
  • Nonlinear control method of neural network based on imitated operant conditioned reflex

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0051] The present embodiment imitates the neural network nonlinear control method of operant conditioning, and comprises the following steps:

[0052] Step 1. Establish an operant conditioning bionic model:

[0053] In the nervous system of higher organisms, neuron inclusions gather in the central nervous system to form neural nuclei, and neuron nuclei with similar functions gather to form neural nuclei. Inspired by this principle, the present invention classifies neurons in the network according to different neural activities, so that neurons with the same neural activity form a neural adaptive unit, and the overall network is composed of M neural units, then the i-th Neural activity of neurons:

[0054]

[0055] Among them, μ i ∈ R q , σ i ∈R is the parameter of the i-th neuron cluster, z=[z 1 ,z 2 ,...,z q ] T input to the neural network...

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 nonlinear control method of a neural network based on imitated operant conditioned reflex. The method comprises: step one, an operational conditional reflex bionic model is established; step two, a class of non-affine system based on the operational conditional reflex bionic model is established; step three, a controller u is designed by using an OCBM bionic network; and step four, the controller u is applied to the non-affine system, so that an output y(t) tracks an expected track xd (t) based on a given precision beta0 and a system tracking error e(t) is ensured to have a boundary in a range of being larger than or equal to 0 by t. According to the invention, on the basis of the biological principle of the operational conditional reflection, a bionic-inspired artificial neural network is constructed and the network is applied to deal with an unknown nonlinear term of a complicated uncertain system; and a control strategy based on an operational conditional reflection model is designed for one class of uncertain non-affine system, so that the effectiveness, flexibility and adaptability of neural network control are improved.

Description

technical field [0001] The invention relates to the fields of nonlinear system control and neural network control, in particular to a method for dealing with unknown nonlinear items of complex uncertain systems. Background technique [0002] Artificial Neural Network (ANN) is often used as a popular mathematical tool in the field of nonlinear system control because of its ability to approximate nonlinear functions on arbitrary norms. Among many achievements, neural network controllers can be divided into three types: Type I controllers for off-line training weights, Type II controllers for online weight learning based on fixed network structures, and online weight learning with adjustable network structures Type III controller. [0003] Up to now, the vast majority of research work has focused on the design and development of Type I and Type II controllers. However, the Type I controller lacks the adaptive ability of the offline weight training network, and the Type II con...

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 宋永端方觅贾梓筠张东赖俊峰
Owner 青岛格莱瑞智能控制技术有限公司
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