Hybrid search for faster production and safer process conditions in friction stir welding

Authors:
Cem Celal Tutum;Kalyanmoy Deb;Jesper Hattel
Affiliations:
Technical University of Denmark, Department of Mechanical Engineering, Kgs. Lyngby, Denmark;Kanpur Genetic Algorithms Laboratory, Indian Institute of Technology Kanpur, Kanpur, India;Technical University of Denmark, Department of Mechanical Engineering, Kgs. Lyngby, Denmark
Venue:
SEAL'10 Proceedings of the 8th international conference on Simulated evolution and learning
Year:
2010

Citing 5
Cited 2

Multi-Objective Optimization Using Evolutionary Algorithms

Multi-Objective Optimization Using Evolutionary Algorithms
Innovization: innovating design principles through optimization

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Hybrid Evolutionary Algorithms

Hybrid Evolutionary Algorithms
Multi-objective optimization of process parameters in friction stir welding

Proceedings of the 12th annual conference on Genetic and evolutionary computation
A fast and elitist multiobjective genetic algorithm: NSGA-II

IEEE Transactions on Evolutionary Computation

Design knowledge extraction in multi-objective optimization problems

Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
An integrated approach to automated innovization for discovering useful design principles: Case studies from engineering

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The objective of this paper is to investigate optimum process parameters and tool geometries in Friction Stir Welding (FSW) to minimize temperature difference between the leading edge of the tool probe and the work piece material in front of the tool shoulder, and simultaneously maximize traverse welding speed, which conflicts with the former objective. An evolutionary multi-objective optimization algorithm (i.e. NSGA-II), is applied to find multiple trade-off solutions followed by a gradient-based local search (i.e. SQP) to improve the convergence of the obtained Pareto-optimal front. In order to reduce the number of function evaluations in the local search procedure, the obtained nondominated solutions are clustered in the objective space and consequently, a postoptimality study is manually performed to find out some common design principles among those solutions. Finally, two reasonable design choices have been offered based on several process specific performance and cost related criteria.