Prediction of the Remaining Useful Life of Engines for Remanufacturing Using a Semi-supervised Deep Learning Model Trained by the Bees Algorithm

Abstract

Smart and sustainable manufacturing is important for enterprises to handle global challenges [1]. Products, systems, and components are reused, remanufactured, and recycled instead of being disposed of in landfills, which supports a circular material flow. In the case of remanufacturing, where the idea is that components and products are returned to “like-new” or “better-than-new” conditions, it is mandatory to check their quality and health status [2]. Remaining Useful Life (RUL) prediction within the scope of predictive maintenance is a critical stage for remanufacturing decisions on complex machines to prevent unexpected degradations. Estimation of the RUL of a product is one of the most important tasks for Predictive Maintenance Systems (PMS). Instead of operating reactive or preventive maintenance, predictive maintenance reduces costs and can pinpoint problems in complex machines before failure since it can estimate the usable time of the product before the time of maintenance or replacement.