IPro-GA: an integrated prognostic based GA for scheduling jobs and predictive maintenance in a single multifunctional machine

Abstract

In highly competitive environment, manufacturing system availability has become a critical issue. For this reason, predictive maintenance must be properly integrated in the production scheduling in order to take into account the wear and tear of the equipment to prevent it from the failure risk. In this context, we investigate the problem of a single multifunctional machine subjected to predictive maintenance based on Prognostic Health Management (PHM). We propose a new interpretation of PHM outputs to define the machine degradation corresponding to the processing of every task. We design a genetic algorithm that we called IPro-GA with the objective of minimizing the total interventions cost. Computational results show the efficiency of our scheme with an average deviation of about 0.1% over a lower bound.