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

Back analysis identification method for parameters of dynamic re-crystallizing model

A technology of model parameters and identification methods, applied in biological neural network models, electrical digital data processing, special data processing applications, etc., can solve problems such as unbalanced learning samples, instabilities in the reverse analysis and solution process, and large amount of calculations. Achieve the effect of solving instability, overcoming arbitrariness, and accurately solving

Inactive Publication Date: 2012-02-01
SHENZHEN UNIV +1
View PDF1 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is based on orthogonal experiment, genetic algorithm, BP neural network and finite element numerical simulation technology to optimize and calculate the model parameters of dynamic recrystallization cellular automata of materials, and can effectively solve the instability, strong Solve problems such as nonlinearity, large amount of calculation, and unbalanced learning samples, and realize the fast and accurate solution of dynamic recrystallization model parameters

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
  • Back analysis identification method for parameters of dynamic re-crystallizing model
  • Back analysis identification method for parameters of dynamic re-crystallizing model
  • Back analysis identification method for parameters of dynamic re-crystallizing model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described below in combination with specific embodiments and with reference to the accompanying drawings.

[0036] a kind of like Figure 1~2 The shown dynamic recrystallization model parameter back analysis identification method based on the genetic neural network cellular automaton is used for back analysis and identification of the specific dynamic recrystallization model parameters when the cylinder of the AZ31 magnesium alloy sample (hereinafter referred to as the sample) is thermally compressed and deformed. Proceed as follows:

[0037] 1) Determine the value range of the parameters, design and construct the experimental plan

[0038] According to the actual problem, the value range of the model parameters of dynamic recrystallization cellular automata of the sample material is determined. There are 4 model parameters, and the value range is:

[0039] Initial dislocation density ρ cr ∈{1.2809×10 14 , 1.4976×10 14}m -2 ;

[0040...

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 back analysis identification method for parameters of a dynamic re-crystallizing model. Based on a genetic neural network cellular automatic machine, the method is characterized in that the method comprises the following steps of: 1) confirming a value range of parameters and designing and establishing a test scheme; 2) performing analog computation and establishing a learning sample library; 3) establishing a BP (Back Propagation) neural network; 4) training the BP neural network and establishing a nonlinear mapping relation; 5) randomly selecting at least one set of parameters and forecasting a flow stress; 6) comparing a precast value with a really measured value till an error meets a design demand; and 7) storing an optimum parameter value with the error meeting the design demand. Haphazardry of a dynamic re-crystallizing parameter value is overcome; the dynamic re-crystallizing parameter value is calculated by utilizing an orthogonal test, a genetic algorithm, a neural network and numerical simulation optimization; the problems of instability, strong nonlinearity, large calculating quantity and uneven learning sample during a back analysis optimizingcalculation are solved; and the accuracy and the rapidity of re-crystallizing parameter value are obviously promoted.

Description

technical field [0001] The invention relates to a parameter back-analysis identification technology for material dynamic recrystallization microscopic simulation, in particular to a dynamic recrystallization model parameter back-analysis identification method based on genetic neural network cellular automata. Background technique [0002] Dynamic recrystallization behavior is an important mechanism to improve the microstructure and properties of materials during thermal deformation. Quantitatively studying the physical metallurgical principles of the dynamic recrystallization process and forming a numerical method for predicting the dynamic recrystallization process are of great significance for controlling the microstructure evolution of materials and obtaining good mechanical properties. However, the current method of using cellular automata to simulate the dynamic recrystallization process is to randomly select the parameters of the cellular automata model, and only by re...

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): G06F17/50G06N3/02
Inventor 娄燕李落星彭怀伟吴文华
Owner SHENZHEN 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