Intelligent modeling using genetic algorithm for optimizing a-tig welding process parameters of mod. 9Cr-1Mo steel

Muthukumaran Vasudevan¹, Krishnamoorthy Nadimuthu Gowtham², Tammana Jayakumar¹

¹Metallurgy and Materials Group Indira Gandhi Centre for Atomic Research, Kalpakkam.
²Department of Metallurgical Engineering PSG College of Technology, Coimbatore.

DOI:

https://doi.org/10.7494/cmms.2011.1.0306

Abstract:

Modified 9Cr-1Mo ferritic steel is used as structural material for stream generator components of power plants. Generally, Tungsten Inert Gas (TIG) welding is preferred for welding these steels in which the depth of penetration achievable during autogenous welding is very limited and hence productivity is less. Therefore, Activated flux Tungsten Inert Gas (A-TIG) welding, a novel welding technique has been developed in house to increase the depth of penetration. In modified 9Cr-1Mo steel joints produced by A-TIG welding process, weld bead width, depth of penetration and Heat Affected Zone (HAZ) width play an important role in determining the mechanical properties and also the performance of the weld joints during service. To obtain the desired weld bead geometry, HAZ width and make a good weld, it becomes important to set up the welding process parameters. Since the experimental optimization of these parameters is time consuming, Genetic Algorithm based computational model is developed for optimization of the welding process parameters. First Adaptive Neuro Fuzzy Inference System (ANFIS), one of the soft-computing tools is used to develop independent models correlating the welding process parameters like current, voltage and speed with weld bead shape parameters like depth of penetration, bead width and HAZ width. Then Genetic Algorithm is employed to determine the optimum A-TIG welding process parameters in order to obtain the desired weld bead shape parameters and HAZ width. Validation of the GA model is completed by carrying out experiments to compare the target values with that of the actual values of the weld bead shape parameters obtained. There is good agreement between the target values and the actual values.

Cite as:

Vasudevan, M., Gowtham, K., & Jayakumar, T. (2011). Intelligent modeling using genetic algorithm for optimizing a-tig welding process parameters of mod. 9Cr-1Mo steel. Computer Methods in Materials Science, 11(1), 16 – 22. https://doi.org/10.7494/cmms.2011.1.0306

Article (PDF):

Keywords:

ANFIS, Genetic algorithm, A-TIG welding, Welding process optimization, Mod. 9Cr-1Mo steel

References: