Static properties model of magnetically controlled shape memory alloy based on neural networks

Author

Zhang, Qingxin ; Zhang, Jing ; Yang, Ming ; Qiu, Xiaoyan

Author_Institution

Sch. of Autom., Shenyang Inst. of Aeronaut. Eng., Shenyang, China

fYear

2009

fDate

17-19 June 2009

Firstpage

3239

Lastpage

3243

Abstract

Based on the experimental data obtained from static properties test of magnetically controlled shape memory alloy, using the function of approximation of BP neural networks, the forecasting modelling was established. The experimental data and the forecasting data agreed well and the error was only 0.04%, which indicates that the modelling had good accuracy. The neural networks modelling can avoid the problem to calculate the modelling parameters based on the material physical properties and solve the material inherent coupling problem between magnetic field, the force fields and temperature field. It provided a new method to research the properties of magnetically controlled shape memory alloy.

Keywords

alloys; backpropagation; forecasting theory; magnetostriction; materials science computing; neural nets; shape memory effects; BP neural networks; force fields; forecasting modelling; magnetic field; magnetically controlled shape memory alloy; material inherent coupling problem; material physical properties; neural networks modelling; static properties model; temperature field; Couplings; Magnetic fields; Magnetic materials; Magnetic properties; Neural networks; Predictive models; Shape control; Shape memory alloys; Temperature; Testing; BP Neural Network; Coupling; Magnetically Controlled Shape Memory Alloy; Static Characteristics;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference, 2009. CCDC '09. Chinese

Conference_Location

Guilin

Print_ISBN

978-1-4244-2722-2

Electronic_ISBN

978-1-4244-2723-9

Type

conf

DOI

10.1109/CCDC.2009.5192004

Filename

5192004