A simulation based multi-criteria scheduling approach of dual-resource constrained manufacturing systems with neural networks

Araz O.

AI 2005: ADVANCES IN ARTIFICIAL INTELLIGENCE, cilt.3809, ss.1047-1052, 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.1047-1052
  • Dokuz Eylül Üniversitesi Adresli: Hayır

Özet

This paper presents a multicriteria DRC scheduler in order to select appropriate dispatching rules. This scheduler integrates several tools, namely; a simulation model, a backpropagation neural network (BPNN) and a Multicriteria decision aid (MCDA) method. Simulation is used to collect predefined performance measures corresponding to decision rule set and system state variables. Because of the time consuming nature of simulation, BPNN is used to obtain the performance measures for each alternative schedule. In order to compare the system performance between all alternatives, the evaluation of each alternative is performed by PROMETHEE, which is a well-known MCDA method. By means of a realistic numerical example, the proposed methodology is proved to be an effective method in a DRC manufacturing system.