Multiple objective crashworthiness optimization of circular tubes with functionally graded thickness via artificial neural networks and genetic algorithms


BAYKASOĞLU A., BAYKASOĞLU C.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE, vol.231, no.11, pp.2005-2016, 2017 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 231 Issue: 11
  • Publication Date: 2017
  • Doi Number: 10.1177/0954406215627181
  • Journal Name: PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.2005-2016
  • Keywords: Thin-walled tubes, functionally graded thickness, crashworthiness optimization, genetic algorithms, artificial neural networks, THIN-WALLED STRUCTURES, ENERGY-ABSORPTION CHARACTERISTICS, STATIC AXIAL-COMPRESSION, MULTIOBJECTIVE OPTIMIZATION, DESIGN OPTIMIZATION, SQUARE TUBES, ALUMINUM TUBES, STEEL, SIMULATION, COLLAPSE
  • Dokuz Eylül University Affiliated: Yes

Abstract

The objective of this paper is to develop a multiple objective optimization procedure for crashworthiness optimization of circular tubes having functionally graded thickness. The proposed optimization approach is based on finite element analyses for construction of sample design space and verification; artificial neural networks for predicting objective functions values (peak crash force and specific energy absorption) for design parameters; and genetic algorithms for generating design parameters alternatives and determining optimal combination of them. The proposed approach seaminglesly integrates artificial neural networks and genetic algorithms. Artificial neural network acts as an objective function evaluator within the multiple objective genetic algorithms. We have shown that the proposed approach is able to generate Pareto optimal designs which are in a very good agreement with the finite element results.