Structure-based neural net model establishing and optimizing method

A technology of neural network modeling and optimization method, which is applied in the field of modeling complex nonlinear systems and optimizing structural parameters to achieve the effects of improving learning efficiency, reducing complexity, and reducing learning time.

Inactive Publication Date: 2002-05-15
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to aim at the above-mentioned deficiency of prior art, provide a kind of new structure-based neural network modeling and optimization method, to solve some difficult problems existing in complex nonlinear sy

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
  • Structure-based neural net model establishing and optimizing method
  • Structure-based neural net model establishing and optimizing method
  • Structure-based neural net model establishing and optimizing method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0059] For a better understanding of the technical scheme of the present invention, below Y 2 -Hc10 type pilot overflow valve is an embodiment, and its modeling and optimization are carried out.

[0060] figure 1 for Y 2 -Schematic diagram of the structure of Hc10 type pilot relief valve.

[0061] Such as figure 1 As shown, the pilot relief valve is composed of a pilot valve and a main valve. In the figure, 1 is the valve body, 2 is the main valve core seat, 3 is the main valve core, 4 is the valve sleeve, 5 is the main valve spring, 6 is the pilot valve body, 7 is the cone valve seat, 8 is the cone valve (pilot valve), 9 is the pilot valve spring (pressure regulating spring), 10 is the pressure regulating screw, and 11 is the pressure regulating pistol. P port, T port and X port are oil inlet port, oil overflow port and external control port respectively.

[0062] Modeling and optimization are performed in the following steps:

[0063] 1. Subsystem division of pilot re...

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 relates to a method for modeling and optimizing nerve net based on structure. Depending on the structure of system and constituent features, the complex non-linear system is decomposed to several relative simpler subsystems. The models of the sub system are built by using single artificial funciton chain neural element. The input/output is determined based on structural parameters, stimulus and response as well as historic signals. Jointing inherent action relation between each subsystem forms a model of neural net based on structure. Using said model optimizes the structural parameters. The invention provides modeling and optimizing dual functions. The advantages are structurization of model, determinate number of neural elements and fast speed of convergence.

Description

Technical field: [0001] The invention relates to a structure-based neural network modeling and optimization method, which is a method for modeling complex nonlinear systems and optimizing structure parameters. Background technique: [0002] There are two main types of system modeling methods, namely, mechanism modeling method and identification modeling method, or a hybrid modeling method combining the two. The mechanism modeling method is the most basic system modeling method. However, some practical systems, especially for large-scale, severely nonlinear complex systems, may have very complicated mechanism processes, and the mechanism processes of some systems are not very clear to people. At this time, the use of mechanism modeling methods is often difficult to work. Therefore, in recent years, the identification modeling methods have been greatly developed, especially the neural network modeling methods are developing very rapidly, but they also have many problems. ...

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): G06N3/06
Inventor 詹永麒施光林乔俊伟
Owner SHANGHAI JIAO TONG UNIV
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