S\'election de la structure d'un perceptron multicouches pour la r\'eduction dun mod\`ele de simulation d'une scierie

TL;DR

This paper explores using multilayer perceptrons and pruning algorithms to simplify simulation models of a sawmill, aiming to optimize network structure for effective complexity reduction.

Contribution

It introduces a method to select the optimal perceptron structure for reducing simulation model complexity in a sawmill context.

Findings

Pruning algorithms effectively identify optimal network structures.

Reduced model complexity maintains simulation accuracy.

Method improves modeling efficiency for industrial simulations.

Abstract

Simulation is often used to evaluate the relevance of a Directing Program of Production (PDP) or to evaluate its impact on detailed sc\'enarii of scheduling. Within this framework, we propose to reduce the complexity of a model of simulation by exploiting a multilayer perceptron. A main phase of the modeling of one system using a multilayer perceptron remains the determination of the structure of the network. We propose to compare and use various pruning algorithms in order to determine the optimal structure of the network used to reduce the complexity of the model of simulation of our case of application: a sawmill.