Open AccessOptimization of Friction Stir Welded Aluminium Plates by the New Modified Particle Swarm Optimization
Author(s) -
Rasha Mohammed Hussien,
Mohsin Abdullah Al-Shammari
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1094/1/012156
Subject(s) - particle swarm optimization , friction stir welding , welding , swarm behaviour , artificial neural network , aluminium , work (physics) , multi swarm optimization , computer science , process (computing) , mathematical optimization , materials science , algorithm , mathematics , engineering , mechanical engineering , composite material , artificial intelligence , operating system
Friction stir welding (FSW) is a complex process that needs and trial to reach the optimal properties. In This work deals theoretical consideration done by two ways; first way is conventional Particle Swarm Optimization (PSO) and the second method is new modified Particle Swarm Optimization. The Friction stir welding data were taken from recent studies. The input to the program are nine experiments for different cases and the output is the ultimate stress for each experiment. The artificial neural network is used to relate the relation between input and output to form a cost function. The results show that the modified PSO gives the more accurate optimum result than conventional PSO when compared with other researches with maximum discrepancy 23.5%.