Prediction model of bead geometry shaped by rapid prototyping based on pulsed PAW

Fujia Xu; Yaohui Lü; Yuxin Liu; Binshi Xu; Peng He

Prediction model of bead geometry shaped by rapid prototyping based on pulsed PAW

Fujia Xu^*
, Yaohui Lü
, Yuxin Liu
, Binshi Xu
, Peng He

^*Corresponding author for this work

School of Materials Science and Engineering

Harbin Institute of Technology
Academy of Armored Force Engineering China

Research output: Contribution to journal › Article › peer-review

10 Scopus citations

Abstract

In this paper, rapid prototyping based on pulsed PAW technology is introduced. The Taguchi method is applied to design single bead forming experiments properly and then multi-group experimental data of weld width and height are obtained. The prediction model of bead geometry is developed by applying BP neural network based on genetic algorithm. It turns out that the model holds high prediction accuracy and generalization ability verified by error analysis and linear regression, which can predict single and multiple beads geometry accurately.

Original language	English
Pages (from-to)	49-52
Number of pages	4
Journal	Hanjie Xuebao/Transactions of the China Welding Institution
Volume	33
Issue number	1
State	Published - Jan 2012

Keywords

BP neural network
Genetic algorithm
Pulsed PAW
Rapid prototyping
Taguchi method

Cite this

@article{32727befc72c47249f79da7f5a3d8449,

title = "Prediction model of bead geometry shaped by rapid prototyping based on pulsed PAW",

abstract = "In this paper, rapid prototyping based on pulsed PAW technology is introduced. The Taguchi method is applied to design single bead forming experiments properly and then multi-group experimental data of weld width and height are obtained. The prediction model of bead geometry is developed by applying BP neural network based on genetic algorithm. It turns out that the model holds high prediction accuracy and generalization ability verified by error analysis and linear regression, which can predict single and multiple beads geometry accurately.",

keywords = "BP neural network, Genetic algorithm, Pulsed PAW, Rapid prototyping, Taguchi method",

author = "Fujia Xu and Yaohui L{\"u} and Yuxin Liu and Binshi Xu and Peng He",

year = "2012",

month = jan,

language = "英语",

volume = "33",

pages = "49--52",

journal = "Hanjie Xuebao/Transactions of the China Welding Institution",

issn = "0253-360X",

publisher = "Harbin Research Institute of Welding",

number = "1",

}

TY - JOUR

T1 - Prediction model of bead geometry shaped by rapid prototyping based on pulsed PAW

AU - Xu, Fujia

AU - Lü, Yaohui

AU - Liu, Yuxin

AU - Xu, Binshi

AU - He, Peng

PY - 2012/1

Y1 - 2012/1

N2 - In this paper, rapid prototyping based on pulsed PAW technology is introduced. The Taguchi method is applied to design single bead forming experiments properly and then multi-group experimental data of weld width and height are obtained. The prediction model of bead geometry is developed by applying BP neural network based on genetic algorithm. It turns out that the model holds high prediction accuracy and generalization ability verified by error analysis and linear regression, which can predict single and multiple beads geometry accurately.

AB - In this paper, rapid prototyping based on pulsed PAW technology is introduced. The Taguchi method is applied to design single bead forming experiments properly and then multi-group experimental data of weld width and height are obtained. The prediction model of bead geometry is developed by applying BP neural network based on genetic algorithm. It turns out that the model holds high prediction accuracy and generalization ability verified by error analysis and linear regression, which can predict single and multiple beads geometry accurately.

KW - BP neural network

KW - Genetic algorithm

KW - Pulsed PAW

KW - Rapid prototyping

KW - Taguchi method

UR - https://www.scopus.com/pages/publications/84863130891

M3 - 文章

AN - SCOPUS:84863130891

SN - 0253-360X

VL - 33

SP - 49

EP - 52

JO - Hanjie Xuebao/Transactions of the China Welding Institution

JF - Hanjie Xuebao/Transactions of the China Welding Institution

IS - 1

ER -

Prediction model of bead geometry shaped by rapid prototyping based on pulsed PAW

Abstract

Keywords

Other files and links

Fingerprint

Cite this