C Conferentia Proceedings
CILAMCE2015-0181 COMPUTATIONAL INTELLIGENCE TECHNIQUES FOR OPTIMIZATION AND DATA MODELING

Optimization under Uncertainty in Mechanical Systems

Arinan Dourado Guerra Silva1; Aldemir Ap Cavalini Jr.1; Valder Steffen Jr1

1 Federal University of Uberlândia

doi:10.20906/CPS/CILAMCE2015-0181

Resumo

Recently the search for robust mechanical systems has increased significantly. To develop robust systems, the inherent uncertainties must be taken into account and to do so generally an optimization problem with uncertain quantities is formulated. Thus, a reliable methodology that can perform the optimization of a system with uncertain quantities is very important. The current work aims at evaluating the use of fuzzy optimization techniques in the robust design of mechanical systems. The proposed fuzzy robust optimization strategy uses a dual evaluation of the unconstrained cost function by means of the pessimistic and optimistic values of the fuzzy inputs. Thus, by generating the fuzzy response the robust values are obtained from the defuzzification process. To evaluate the performance of procedure proposed, examples from the literature are used to test the methodology conveyed, as follows: the design of a welded cantilever beam and the design of a tension/compression spring were performed considering uncertainties both in the cost functions and in the constraints.

Palavras-chave: fuzzy optimization; uncertainties; robust optimization

Como citar

Arinan Dourado Guerra Silva; Aldemir Ap Cavalini Jr.; Valder Steffen Jr. “Optimization under Uncertainty in Mechanical Systems”. XXXVI Ibero-Latin American Congress on Computational Methods in Engineering. CILAMCE2015. 2015. DOI: 10.20906/CPS/CILAMCE2015-0181