Distributed Manufacturing is considered as one of the modern pervasive production paradigm spreading as a response to demand for green and customized products with low cost and fast delivery time. Mini factory seems to effectively overcome challenges posed by the modern business environment (Reichwald et al. The Practical Real-Time Enterprise, Springer, Berlin, pp. 403-434,2005, [1]). However, design of the Mini factory network has to consider several inner and external variables to reach high performances. Then, in this paper authors analyze how products demand volume impact on the size and the configuration, i.e. typologies of Mini-factory, of the Mini factory network. To do that, an EFUNN adapted for this application has been implemented. Results show an accuracy of over 90% for running with 3 different MFs used (Triangular, Trapezoidal, Gaussian), with a constraints of 2 possible configuration number of mini-factories range. In conclusion, this model seems to be an accurate tool to predict the best network architecture, given market demand. to be satisfied.

A production scheduling algorithm for a distributed mini factories network model

SEREGNI, MARCO;ZANETTI, CRISTIANO;TAISCH, MARCO
2016-01-01

Abstract

Distributed Manufacturing is considered as one of the modern pervasive production paradigm spreading as a response to demand for green and customized products with low cost and fast delivery time. Mini factory seems to effectively overcome challenges posed by the modern business environment (Reichwald et al. The Practical Real-Time Enterprise, Springer, Berlin, pp. 403-434,2005, [1]). However, design of the Mini factory network has to consider several inner and external variables to reach high performances. Then, in this paper authors analyze how products demand volume impact on the size and the configuration, i.e. typologies of Mini-factory, of the Mini factory network. To do that, an EFUNN adapted for this application has been implemented. Results show an accuracy of over 90% for running with 3 different MFs used (Triangular, Trapezoidal, Gaussian), with a constraints of 2 possible configuration number of mini-factories range. In conclusion, this model seems to be an accurate tool to predict the best network architecture, given market demand. to be satisfied.
2016
Advances in Neural Networks Computational Intelligence for ICT
978-3-319-33747-0
Distributed manufacturing systems, Mini factory, Production scheduling, Neural networks
File in questo prodotto:
File Dimensione Formato  
Seregni et al..pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 206.06 kB
Formato Adobe PDF
206.06 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1019475
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact