Deep learning representation pre-training for industry 4.0
Deep learning (DL) approaches have several advantages that have been explored in many fields. However, this is not the case for prognostic and health management (PHM) applications, since the lack of relevant industrial data stands as barrier to achieving a more reliable and sustainable industry.
While PHM of equipments has theoretically proven to be an approach to maximize profit and provide more safety for workers, its application to real-world data still remains a pressing question. This fact actually limits the research in this area, even though these types of applications have a strong impact on the industrial world.
As AI-PROFICIENT partners Alaaeddine Chaoub, Christophe Cerisara, Alexandre Voisin and Benoıt Iung from University de Lorraine mention in their paper ‘Deep learning representation pre-training for industry 4.0.’, to introduce ‘the benefits of DL in this area, we should be able to develop models even when we have small data sets, to verify whether or not this is possible, in this thesis we explore the research direction of few shot learning in the context of equipment PHM’