Prediction of EVA Plastic's Expansion Ratio Based on BP Neural Network

Lai Fa Zhu; Bin Liu; Jian Wen Xu

doi:10.4028/www.scientific.net/AMM.364.529

Paper Titles

Testing Study on Surface Grinding of Post-High-Temperature Granite
p.509

A Hybrid Approach Based on the Fuzzy AHP and Benefit Cost Analysis to Evaluating Cutting Blade Alternatives
p.513

Research on Stretching Efficiency of Heavy Forged Shaft Based on Orthogonal Experimental Design
p.519

Optimal Design of Heating and Ventilation for Drying Room Based on Transient CFD Simulation
p.524

Prediction of EVA Plastic's Expansion Ratio Based on BP Neural Network
p.529

Study of Martensitic Transformation Temperatures of Ferromagnetic Shape Memory NiMnGa Alloys
p.537

Experimental and Simulation Research on Stamping Formability of Hot-Dip Galvanized Sheet
p.542

Numerical Analysis of Irradiation Effects on Metal Materials of Fusion Reactor
p.547

Properties of Porous FeAl Manufactured from Ball Milled Fe/Al Elemental Powders by Two-Step Sintering
p.553

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 364Prediction of EVA Plastic's Expansion Ratio Based...

Prediction of EVA Plastic's Expansion Ratio Based on BP Neural Network

Abstract:

Combined with Taguchi method of experimental design and BP neural network technology, select process parameters including molding temperature, molding time and injection pressure, Taguchi experiments are respectively arranged for different diameters of sphere and cylinder, different side lengths of tri-prism and quadrangular prism, different thicknesses of thin sheet without hole and with hole etc. molds, then these experiment results are used as neural network sample data, and expansion ratio of EVA plastic can be predicted more accurately after neural network is trained.

You might also be interested in these eBooks

Mechanical Automation and Materials Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 364)

Pages:

529-533

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.364.529

Citation:

Cite this paper

Online since:

August 2013

Authors:

Lai Fa Zhu, Bin Liu, Jian Wen Xu

Keywords:

BP Neural Network (BPNN), EVA Plastic, Expansion Ratio, Prediction, Taguchi Method of Experimental Design

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] R.D. Allen, S.T. Newman, S.R. Mitchell, R.I. Temple, C.L. Jones, C.R. Boer and S. Dulio. Design of experiments for the qualification of EVA expansion characteristics. Robotics and Computer-Integrated Manufacturing. Vol. 21 (2005), p.412–420.

DOI: 10.1016/j.rcim.2004.11.018

Google Scholar

[2] R. Verdejo, N.J. Mills. Heel–shoe interactions and the durability of EVA foam running-shoe midsoles. Journal of Biomechanics. Vol. 37 (2004) , p.1379–1386.

DOI: 10.1016/j.jbiomech.2003.12.022

Google Scholar

[3] LIN Gao-yong, CHEN Xing-ke, JIANG Jie, WANG Fang, PENG Da-shu. Application of BP Artificial Neural Network and Genetic Algorithm to the Parameters Optimization of Profile Extrusion Die. Natural Science Journal of Xiangtan University. Vol. 28(2006).

Google Scholar

[4] ZHANG Shu-juan, HE Yong, FANG Hui. Application of Artificial Neutral Network on Relationship Analysis of Crop Yield and Soil Space Distributing Information. Systems Engineering-theory & Practice. (2003), pp.121-127, 132.

Google Scholar

[5] FEICIT Sci-Tec Product Research & Development center: Neural Network Theory and MATLAB 7 realization (Publishing House of Electronic Industry, Beijing 2005. ).

Google Scholar

[6] Chen Gui-ming, Qi Hong-yu, Pan Wei: MATLAB Mathematical Statistics (6. x) (Science and Technology Publishing House, Beijing 2002).

Google Scholar