Using Genetic Algorithms to Design an Overall Control Strategy of an Industrial Process

Abstract In this paper a methodology is presented to design a control strategy to optimise a complex production process using a neural network combined with genetic algorithms. The method is applied to the case study of a spinning (fibre - yarn) production process. The neural network is used to model the process, with input the machine setpoints and raw fibre quality parameters and with output the yam tenacity and elongation. Genetic algorithms are used twofold: • to optimise the architecture and the underlying paralneters of the neural network in order to achieve the most effective model of the production process; • to obtain setpoint values and raw material characteristics for an optimal tenacity and elongation of the spinned yarns.