Lagging characteristics modeling method based on nerve network

A neural network model and neural network technology, applied in the direction of instruments, adaptive control, control/regulation systems, etc., can solve the problems that the neural network is incompetent, achieve good flexibility and adaptability, simple structure, and convenient real-time control Effect

Inactive Publication Date: 2006-06-28
桂林电子工业学院
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the neural network can only be used in one-to-one mapping occasions. For the hys

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
  • Lagging characteristics modeling method based on nerve network
  • Lagging characteristics modeling method based on nerve network
  • Lagging characteristics modeling method based on nerve network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Modeling Method of Hysteresis Characteristics Based on Neural Network for Piezoelectric Actuators

[0045] Piezoelectric actuators generate a certain displacement for positioning control when the input voltage is different. However, due to the hysteresis characteristics of piezoelectric actuators, the displacements generated when the input voltage is the same at different times are different. In order to grasp its hysteresis characteristics, a hysteresis factor was introduced to establish a hysteresis nonlinear model based on neural network for precise on-line control.

[0046] Under the input voltage of 0-100v, the piezoelectric actuator has a rated displacement of 0-25μm and a sampling frequency of 1000Hz. After the measured data are filtered, 1200 sets of data are used to divide these data intervals into two equal parts. The first 600 sets are used to approximate the hysteresis curve, and the second 600 sets are used to check the generality of the neural network mod...

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

A method for establishing model of retardation property based on neural network includes leading retardation factor f (x) in, applying different property of retardation factor f (x) at different time T1 and T2 to transform multiple mapping relation in retardation system to be one by one mapping relation in retardation system. The method can be use in real time control on retardation property of mechanical gap system, magnetic material and piezoceramic component.

Description

(1) Technical field [0001] The invention relates to the application of neural network in the field of automatic control, in particular to a hysteresis characteristic modeling method based on neural network. (2) Technical background [0002] Smart materials such as memory alloys, piezoelectric wafers and piezoelectric ceramics have been widely used in precision positioning systems as sensors and actuators. However, the hysteresis characteristics parasitic in these components will not only reduce the control accuracy of the system, but even cause the system to be unstable. The hysteresis characteristic is an unconventional non-smooth nonlinearity. The complexity of the hysteresis characteristic first manifests as multi-mapping. Due to the influence of the hysteresis characteristic, the dynamic system can have different outputs under the same input value, or at the same There can be different inputs under the output. The second is its memory. The output of the hysteresis char...

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): G05B13/00G05B13/04
Inventor 谭永红赵新龙陈辉
Owner 桂林电子工业学院
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