Fuzzy rule based approach for predicting weld bead geometry in gas tungsten arc welding
Authors:
- P. GhantyPGP. Ghanty
- S. PaulSPS. Paul
- A. RoyARA. Roy
- D. P. MukherjeeDMD. P. Mukherjee
- N. R. PalNPN. R. Pal
- M. VasudevanMVM. Vasudevan
- H. KumarHKH. Kumar
- A. K. BhaduriABA. K. Bhaduri
- 1 February 2008
- journal article
- research article
- Published by SAGE Publications in Science and Technology of Welding and Joining
- Vol. 13 (2) , 167-175
Abstract
The use of fuzzy rule based systems to model the relationship between weld control parameters and the weld bead geometry features is explored in this paper. The Takagi–Sugeno model with linear functions of the inputs is used as the rule consequents. Given some training data, the authors use exploratory data analysis to find an initial rule base. The system parameters, e.g. consequent parameters, are estimated using a mixture of least square error (LSE) method and gradient search. The system is tested on three datasets and the performance is found to be satisfactory compared to the multilayer perceptron (MLP) and radial basis function (RBF) neural networks based systems.Keywords
This publication has 33 references indexed in Scilit:
- A Fuzzy-Logic Based Optical Sensor for Online Weld Defect-DetectionIEEE Transactions on Industrial Informatics, 2005
- Classification of welding flaw types with fuzzy expert systemsExpert Systems with Applications, 2003
- A new scheme for fuzzy rule-based system identification and its application to self-tuning fuzzy controllersIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2002
- Fuzzy logic approaches to structure preserving dimensionality reductionIEEE Transactions on Fuzzy Systems, 2002
- Application of fuzzy logic to spatial thermal control in fusion weldingIEEE Transactions on Industry Applications, 2000
- A comparison between the back-propagation and counter-propagation networks in the modeling of the TIG welding processJournal of Materials Processing Technology, 1998
- A fuzzy clustering-based rapid prototyping for fuzzy rule-based modelingIEEE Transactions on Fuzzy Systems, 1997
- Neurofuzzy model-based weld fusion state estimationIEEE Control Systems, 1997
- Control of weldpool width and cooling time in TIG welding using a neural network modelWelding International, 1996
- Artificial neural networks applied to arc welding process modeling and controlIEEE Transactions on Industry Applications, 1990