Optimization of genetic algorithm parameters for multi-channel manufacturing systems by Taguchi method

Anagun A., ÖZÇELİK F.

AI 2005: ADVANCES IN ARTIFICIAL INTELLIGENCE, cilt.3809, ss.1021-1024, 2005 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 3809
  • Basım Tarihi: 2005
  • Dergi Adı: AI 2005: ADVANCES IN ARTIFICIAL INTELLIGENCE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED)
  • Sayfa Sayıları: ss.1021-1024
  • Eskişehir Osmangazi Üniversitesi Adresli: Evet

Özet

An important issue in multi-channel manufacturing (MCM) design is the channel formation process. In this study, the control parameters that affect the performance of genetic algorithms (GAs) developed to solve channel formation problem, are examined and the optimum values of such parameters are explored using Taguchi method. Two types of problems were taken into account in terms of machines, parts, and channels. Experimental results show that the performance of a GA significantly dependent on the levels of the design factors for the problem being solved. The results also show that Taguchi method is a powerful approach for identifying design factors suitable for the GA comparing to time consuming and possibly impractical trial-error tests.