An investigation on swarm intelligence methods for the optimization of complex part programs in CNC turning
- 202 Downloads
Automation of engineering procedures for the development of new manufacturing processes is of great importance in modern competitive conditions. For example, metalworking companies would greatly benefit from the development of methods for automatic generation, testing and optimization of part programs for machining operations. Indeed, the generation of part programs—even by using CAM software—does still require strong human intervention and it is basically a best guess approach with minimum optimization. Moreover, further refinement and correction of the part program on the machine tool is often necessary. Machining operations are generally based on a large number of parameters and therefore optimization strategies should be able to deal with high-dimensional spaces and disjoint domains. In this paper, two swarm intelligence optimization algorithms—particle swarm optimization (PSO) and artificial bee colony (ABC)—have been applied for optimizating the part program of a complex turning part. The optimizers were implemented in a framework for automatic part program generation, realistic simulation, and feasibility analysis. The results evidenced that both approaches were capable of optimizing efficiently the part program, and that the optimization time of the PSO approach on modern computers may be suitable for application in production.
KeywordsTurning Optimization Swarm intelligence Part program Simulation
Unable to display preview. Download preview PDF.
- 2.Altintas Y (2012) Manufacturing automation: metal cutting mechanics, machine tool vibrations and CNC Design. Cambridge University PressGoogle Scholar
- 3.Altintas Y, Kersting P, Biermann D, Budak E, Denkena B, Lazoglu I (2014) Virtual process systems for part machining operations. CIRP Annals - Manuf Technol. doi: 10.1016/j.cirp.2014.05.007
- 6.Sortino M, Totis G, Kuljanić E, Cukor G (2009) Simulation of cutting forces and cutting conditions in complex turning operations. In: Proceedings of the 12th international scientific conference on production engineering - CIM2009, pp 201–207Google Scholar
- 7.Sortino M, Belfio S, Totis G (2014) An innovative approach for automatic generation, verification and optimization of part programs in turning. J Manuf Syst. doi: 10.1016/j.jmsy.2014.03.002
- 23.Kennedy J, Eberhart R (1995) Particle swarm optimization. In: IEEE international conference on neural networks, 1995. Proceedings, vol 4, pp 1942–1948. doi: 10.1109/ICNN.1995.488968
- 24.Kennedy J, Kennedy J, Eberhart R, Shi Y (2001) Swarm intelligence. Evolutionary computation series. Morgan Kaufmann PublishersGoogle Scholar
- 25.Karaboga D (2005) An idea based on honey bee swarm for numerical optimization. Tech. Rep. TR06. Erciyes UniversityGoogle Scholar
- 26.Karaboga D, Akay B, Ozturk C (2007) In: Torra V, Narukawa Y, Yoshida Y (eds) Modeling decisions for artificial intelligence, lecture notes in computer science, vol 4617. Springer Berlin Heidelberg, pp 318–329. doi: 10.1007/978-3-540-73729-2_30
- 27.Childs T, Maekawa K Metal machining: theory and applications. Referex Engineering (Arnold, 2000)Google Scholar
- 29.Van Den Bergh F (2002) An analysis of particle swarm optimizers. Ph.D. thesis, University of Pretoria, Pretoria, South Africa. AAI0804353Google Scholar