Parametric Modeling of SAW Process using Genetic Algorithms Based Technique
P Sahithi1, V Srujana2, S Khaleed Saifulla3, D Kondayya4
1P Sahithi*, Department of Mechanical engineering, Sreenidhi Institute of Science and Technology, Hyderabad, India.
2V Srujama, Department of Mechanical engineering, Sreenidhi Institute of Science and Technology, Hyderabad, India.
3S Khaleed Saifulla, Department of Mechanical engineering, Sreenidhi Institute of Science and Technology, Hyderabad, India.
4D Kondayya, Department of Mechanical engineering, Sreenidhi Institute of Science and Technology, Hyderabad, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 782-787 | Volume-8 Issue-5, January 2020. | Retrieval Number: E5762018520/2020©BEIESP | DOI: 10.35940/ijrte.E5762.018520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The main aim of the present work paper is to apply a novel and efficient evolutionary technique in modeling welding responses which is very essential in subsequent optimization of the welding process. Submerged arc welding (SAW) being a highly efficient welding process owing to deep penetrant weld and smooth finish is used for the process modeling in the present research study. An empirical relationship is established between the significant input welding parameters and bead geometrical parameters (responses) by using a potential modeling tool namely, gene expression programming (GEP). Thus GEP gives the optimized model expressions to relate the responses to selected inputs. The various input parameters selected are Voltage, electrode wire feed, carriage speed and tube-end to work distance. These are altered to predict the responses namely, reinforcement, penetration and width of the bead. The models obtained have high correlation coefficients thus indicating the effectiveness of the GEP algorithm.
Keywords: Weld Bead Geometry, Welding Parameters, Empirical Modeling, Genetic Algorithms.
Scope of the Article: Parallel and Distributed Algorithms.