A Neural Network Model for Predicting Two Observable Parameters of the Welded Cross Section in Case of Robotic Gas Tungsten Arc Welding Process

Gabriel Gorghiu; Paul Ciprian Patic; Dorin Cârstoiu

doi:10.4028/www.scientific.net/AMM.162.531

Paper Titles

Fabric Defect Detection Using Wavelet-Enhanced Single-Point Photoelectric Sensing System
p.497

Rollover Prevention System Dedicated to ATVs on Natural Ground
p.505

A Linear Electrostatic Induction Motor with Coils Mounted on its Slider for Voltage Boosting
p.515

Robot Vision Application for Bearings Identification and Sorting
p.523

A Neural Network Model for Predicting Two Observable Parameters of the Welded Cross Section in Case of Robotic Gas Tungsten Arc Welding Process
p.531

EOG-Based Interface for Manipulation Tasks
p.537

Compliant Structures in Book Handling Applications
p.543

Elements of Synthesis and Experiment for Parallel Robots
p.549

Mechatronical Approach of Analyzing One DOF Leg Mechanism in Order to Construct a Walking Robot System
p.559

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 162A Neural Network Model for Predicting Two...

A Neural Network Model for Predicting Two Observable Parameters of the Welded Cross Section in Case of Robotic Gas Tungsten Arc Welding Process

Abstract:

The paper presents a model of using the artificial neural networks when determining the relations of dependency between the observable parameters and the controllable ones in the case of Robotic Gas Tungsten Arc Welding. The proposed model is based on the direct observation of welded joints, emphasizing on the process variables which have been arranged in the nodes of a neural network. The design of the network intended to achieve an architecture that contains four nodes in the input layer (all of them being controllable parameters) and two nodes in the output layer (one for each observable parameter).

You might also be interested in these eBooks

Mechanisms, Mechanical Transmissions and Robotics

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 162)

Pages:

531-536

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.162.531

Citation:

Cite this paper

Online since:

March 2012

Authors:

Gabriel Gorghiu, Paul Ciprian Patic, Dorin Cârstoiu

Keywords:

Artificial Neural Network (ANN), Controllable Parameters, Observable Parameters, Robotic Welding

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] G. Gorghiu, Gh. Măzăreanu, Computer Aided Welding – A new modern concept in control and leading of the robotic welding processes. The Annals of the Valahia University of Targoviste, Macarie Publishing House, Targoviste (2003) 270-273.

DOI: 10.18662/lumproc.rsacvp2017.27

Google Scholar

[2] M. Brooks: Robotic GTAW, Practical Welding Today (September 2008).

Google Scholar

[3] A. A. Shirali, K. C. Mills, The Effect of Welding Parameters on Penetration in GTA Welds, Welding Journal, 72(7) (1993) 347-353.

Google Scholar

[4] K. Andersen, G. E. Cook, G. Karsai, K. Ramaswamy, Artificial neural networks applied to arc welding process modeling and control, IEEE Transactions on Industry Applications 26(5) (1990) 824-830.

DOI: 10.1109/28.60056

Google Scholar

[5] R. Hecht-Nielsen, Neurocomputing, Addison Wesley, San Diego, (1990).

Google Scholar

[6] B. J. A. Krose, P. P. Van der Smagt, An Introduction to Neural Networks, fifth ed., University of Amsterdam, (1993).

Google Scholar

[7] M. T. Hagan, M. Menhaj, Training Feedforward Networks with the Marquardt Algorithm, IEEE Transactions on Neural Networks, V(6) (1994) 989.

DOI: 10.1109/72.329697

Google Scholar