Genetic Algorithm-Based Optimization of Friction Stir Welding Process Parameters on Aa7108
Maulikkumar B. Patel1, Komal G. Dave2
1Maulikkumar B. Patel*, Research Scholar, Department of Mechanical Engineering, Gujarat Technological University, Ahmedabad (Gujarat), India.
2Dr. Komal G. Dave, Professor, Department of Mechanical Engineering, Lalbhai Dalpatbhai College of Engineering, Ahmedabad (Gujarat), India.
Manuscript received on June 10, 2021. | Revised Manuscript received on June 17, 2021. | Manuscript published on June 30, 2021. | PP: 47-53 | Volume-10, Issue-8, June 2021 | Retrieval Number: 100.1/ijitee.H92230610821 | DOI: 10.35940/ijitee.H9223.0610821
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: This research paper deals with the characterization of friction stir welding aluminium 7108 with twin stir technology. The coupons of the above metal were friction stir welded using a cylindrical pin with counter-rotating twin stir technology using at constant speed 900, 1200, 1500,1800 with four different feed rates of 30,50,70,90 mm/min. Microstructure examination showed the variation of each zone and their influence on the mechanical properties. Also, tensile strength and hardness measurements were done as a part of the mechanical characterization and correlation between mechanical and metallurgical properties and deduced at the speed of 1500 rpm. Friction stir welding process parameters such as tool rotational speed (rpm), tool feed (mm/min) were considered to find their influence on the tensile strength (MPa) and hardness (HRB). A genetic algorithm (GA) was employed by taking the fitness function as a combined objective function to optimize the friction welding process parameters to predict the maximum value of the tensile strength and hardness. The confirmation test also revealed good closeness to the genetic algorithm predicted results and the optimized value of process parameters for different weights of the tensile and hardness have been predicted in the model.
Keywords: Friction Stir Welding, Design Of Experiment, Optimization, Ultimate Tensile Strength, Hardness, Genetic Algorithm.