Integrated optimal topology design and shape optimization using neural networks


Yildiz A. R., Ozturk N., Kaya N., Ozturk F.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, cilt.25, sa.4, ss.251-260, 2003 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 25 Sayı: 4
  • Basım Tarihi: 2003
  • Doi Numarası: 10.1007/s00158-003-0300-0
  • Dergi Adı: STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.251-260
  • Anahtar Kelimeler: topology optimization, shape optimization, neural networks, feature recognition, HOMOGENIZATION METHOD, DISCRIMINANT-ANALYSIS, CONTINUUM STRUCTURES, STRUCTURAL TOPOLOGY, COMPONENTS, GEOMETRY, FEATURES, CAD
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

In this paper, neural network- and feature-based approaches are introduced to overcome current shortcomings in the automated integration of topology design and shape optimization. The topology optimization results are reconstructed in terms of features, which consist of attributes required for automation and integration in subsequent applications. Features are defined as cost-efficient simple shapes for manufacturing. A neural network-based image-processing technique is presented to match the arbitrarily shaped holes inside the structure with predefined features. The effectiveness of the proposed approach in integrating topology design and shape optimization is demonstrated with several experimental examples.