The Aluminum Brazing Pieces of Mechanical Performance Based on GRNN Neural Network

Xing Hua Liang; Lin Shi; Yu Si Liu; Xiao Ming Hua

doi:10.4028/www.scientific.net/AMM.455.154

Paper Titles

Research on Cu-Cr Alloy Produced by Equal Channel Angular Pressing
p.131

Multi-band Terahertz Chiral Metamaterials Based on Complementary Cross-wire Structure
p.137

Experimental Study on Abrasion Resistance of Grinding Rolls with Stripes Surface
p.142

Structural, Magnetic and Electrical Transport Properties of Ternary Compound LaCo₂Ge₂
p.148

The Aluminum Brazing Pieces of Mechanical Performance Based on GRNN Neural Network
p.154

Serrated Flow in 316LN Austenitic Stainless Steel
p.159

The Numerical Simulation of Transverse Tensile of High Temperature on Ti-6Al-4V Laser Butt Weld Joint
p.163

Design and Simulation of a Polarization-Independent Active Metamaterial Terahertz Modulator
p.167

Forming Performance of 800MPa Grade Advanced High Strength Steels
p.173

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 455The Aluminum Brazing Pieces of Mechanical...

The Aluminum Brazing Pieces of Mechanical Performance Based on GRNN Neural Network

Abstract:

Aluminum and aluminum alloy were widely used in various industrial fields,the key to application is the reliable welding. In this thesis,LF21 aluminum alloy brazing materials were designed and prepared by Orthogonal experiment,and mechanical properties of the brazing specimen was tested. Based on the GRNN(Generalized Regression Neural Network),Nonlinear relationship modle of brazing material preparation parameters and mechanical properties of the weldment was established.The results show that the model has better stability.When smooth factor value is 0.1,the network approximation error and prediction error absolute value is 0.01%.It can be realized that an nonliner mapping between the aluminum alloy brazing preparation parameters and solder joint tensil strenth based on the Orthogonal test and can do better prediction of the weld mechanical properties,according to brazing material preparation parameters.

You might also be interested in these eBooks

Mechanical Materials and Manufacturing Engineering III

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 455)

Pages:

154-158

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.455.154

Citation:

Cite this paper

Online since:

November 2013

Authors:

Xing Hua Liang, Lin Shi, Yu Si Liu, Xiao Ming Hua

Keywords:

Aluminum Brazing Pieces, GRNN Neural Network, Mechanical Performance, Orthogonal Experiment

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Wang Zhu Tong, Tian Rongzhang editor, aluminum and processing manual [M]. Changsha: Central South University Press, 1989: 901-903.

Google Scholar

[2] Liu Bing, Peng Maria, WANG Ri elementary, large aircraft Aluminum Alloy Research Situation and Prospect [J]. Chinese Journal of Nonferrous Metals, 2010, 20 (9) : 38-42.

Google Scholar

[3] Jinxia, Hulan Wei, Xu Baisheng etc. fluoroaluminate aluminum brazing flux research status and development trend [J]. Electronic technology, 2012, 33, (3) : 140-145.

Google Scholar

[4] Qian light Xing, Cui Dongwen, RBF and GRNN Neural Network Model in Urban Water Demand Forecasting [J]. Water Resources and Water Engineering, 2012, 23 (5) : 89-92.

Google Scholar

[5] Fei Sike Technology R & D Center. Neural network theory and realize MATLAB7 [M]. Beijing: Electronic Industry Press, 2005. : 30-45.

Google Scholar