Reduction of Product Driven System emulation models based on neural network: impact of discrete data

Philippe Thomas (1) , André Thomas (1) , Marie-Christine Suhner (1)

1 CRAN - Centre de Recherche en Automatique de Nancy

Product Driven Systems (PDS) architecture needs emulation systems [13]. Discrete events simulation is then often used to build this emulation tool, but emulation model design is not a trivial task. Also, the goal of this paper is the study of the design of a simulation model by reducing its complexity. According to theory of constraints, we want to build reduced models composed exclusively by bottlenecks and a neural network. Particularly a multilayer perceptron, is used. The structure of the network is determined by using a pruning procedure. This work focuses on the impact of discrete data on the results. This approach is applied to sawmill internal supply chain.

Mots clés: multilayer perceptron; reduced model; simulation; neural network; re-scheduling; supply chain

Domaines: Modélisation et simulation; Automatique

Philippe Thomas, André Thomas, Marie-Christine Suhner. Reduction of Product Driven System emulation models based on neural network: impact of discrete data. International Conference on Industrial Engineering and Systems Management, IESM' 2009, May 2009, Montréal, Canada. pp.CD. ⟨hal-00388829⟩