Dealing with design options in the optimization of manufacturing systems: an evolutionary approach

When designing a manufacturing system, several features have often to be de termined to optimize a performance criterion. We propose an optimization si mulation method that can be applied to optimize problems taking into accoun t design options and any type of parameters. This method is based on the as sociation of an evolutionary algorithm using a specific data structure and a simulation model. New mutation and recombination operators are proposed, which are adapted to this specific data structure. This approach is impleme nted on a network of Sun workstations, each station being responsible for r unning its own simulation model and its own evolutionary algorithm. This me thod is illustrated through the problem of designing a manufacturing system .