Artificial neural network approach for estimating weld bead width and depth of penetration from infrared thermal image of weld pool

被引：61

作者：

Ghanty, P. ^{[1
]}

Vasudevan, M. ^{[2
]}

Mukherjee, D. P. ^{[1
]}

Pal, N. R. ^{[1
]}

Chandrasekhar, N. ^{[2
]}

Maduraimuthu, V. ^{[2
]}

Bhaduri, A. K. ^{[2
]}

Barat, P. ^{[3
]}

Raj, B. ^{[2
]}

机构：

[1] Indian Stat Inst, Elect & Commun Sci Unit, Kolkata 700108, W Bengal, India

[2] Indira Gandhi Ctr Atom Res, Kalpakkam 603102, Tamil Nadu, India

[3] Ctr Variable Energy Cyclotron, Kolkata 700064, W Bengal, India

来源：

SCIENCE AND TECHNOLOGY OF WELDING AND JOINING | 2008年 / 13卷 / 04期

关键词：

infrared thermal image; weld bead geometry; artificial neural network; multilayer perceptron; radial basis function; online feature selection;

D O I：

10.1179/174329308X300118

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

In this article an artificial neural network based system to predict weld bead geometry using features derived from the infrared thermal video of a welding process is proposed. The multilayer perceptron and radial basis function networks are used in the prediction model and an online feature selection technique prioritises the features used in the prediction model. The efficacy of the system is demonstrated with a number of welding experiments and using the leave one out cross-validation experiments.

引用

页码：395 / 401

页数：7

共 24 条

[1] Infrared sensing for on-line weld geometry monitoring and control [J].

Banerjee, P. ;

Govardhan, S. ;

Wikle, H.C. ;

Liu, J.Y. ;

Chin, B.A. .

Journal of engineering for industry, 1995, 117 (03) :323-330

[2]

Bingül Z, 2000, IEEE T IND APPL, V36, P1523, DOI 10.1109/28.887202

[3]

Chen SB, 2004, LECT NOTES CONTR INF, V299, P25

[4]

CHEN W, 1990, WELD RES S, pS181

[5]

Devijver P., 1982, PATTERN RECOGN

[6] Extracting weld penetration information in tungsten-inert gas welding [J].

Gao, J ;

Wu, C .

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE, 2002, 216 (02) :207-214

[7] Modelling weld bead geometry using neural networks for GTAW of austenitic stainless steel [J].

Ghanty, P. ;

Paul, S. ;

Mukherjee, P. ;

Vasudevan, M. ;

Pal, N. R. ;

Bhaduri, A. K. .

SCIENCE AND TECHNOLOGY OF WELDING AND JOINING, 2007, 12 (07) :649-658

[8]

GHANTY P, SCI TECHNOL IN PRESS

[9]

Haykin S., 1999, Neural networks: a comprehensive foundation, V2nd ed.

[10] A prediction of welding process parameters by prediction of back-bead geometry [J].

Lee, JI ;

Um, KW .

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2000, 108 (01) :106-113

← 1 2 3 →