Title: Optimisation of welding process for modified 9Cr-1Mo steel using genetic algorithm

Authors: L. Subashini; P. Madhumitha; M. Vasudevan

Addresses: Department of Metallurgical Engineering, PSG College of Technology, Coimbatore – 641004, Tamil Nadu, India. ' Department of Computer Science and Engineering, College of Engineering, Guindy, Chennai – 600036, Tamil Nadu, India. ' Advanced Welding Processes, Monitoring and Modelling Programme, Materials Technology Division, Indira Gandhi Centre for Atomic Research, Kalpakkam – 603102, India

Abstract: Modified 9Cr-1Mo steel is used as the structural material for steam generator components of power plants. Activated tungsten inert gas (A-TIG) welding is increasingly used for fabricating these components. With the aim to achieve maximum depth of penetration (DOP) and minimum heat affected zone (HAZ) width, computational methodologies were adopted for optimisation of A-TIG welding process. Genetic algorithm (GA)-based model has been developed to determine the optimum process parameters. In this methodology, independent artificial neural network (ANN) models correlating DOP and HAZ width with process parameters (current, torch speed and arc voltage) respectively were developed. Then GA code was developed whose objective function was evaluated using the artificial neural network (ANN) models. The developed GA produced multiple outputs of the process parameters for the same target DOP and HAZ width. Thus, a methodology using GA has been developed for optimising the A-TIG process parameters for modified 9Cr-1Mo steel.

Keywords: modified 9Cr-1Mo steel; A-TIG welding; welding optimisation; artificial neural networks; ANNs; genetic algorithms; GAs; steam generators; power plants; activated TIG welding; tungsten inert gas; depth of penetration; DOP; heat affected zone; HAZ; process parameters.

DOI: 10.1504/IJCMSSE.2012.049050

International Journal of Computational Materials Science and Surface Engineering, 2012 Vol.5 No.1, pp.1 - 15

Received: 28 Jun 2011
Accepted: 28 Oct 2011

Published online: 23 Aug 2014 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article