20.500.12556/RUL-121028 Multi-objective adjustment of remaining useful life predictions based on reinforcement learning Effective tracking of degradation in machine tools or vehicle, ship, and aircraft engines is key to ensure their high utilization, effective maintenance, and safety. Data from the built-in sensors can be used to build models that accurately predict the remaining useful life (RUL) of the observed system. However, existing approaches often lack the ability to incorporate domain-specific knowledge in form of degradation models. This paper proposes a reinforcement-learning based approach for encoding the degradation model used for multi-objective adjustment of RUL predictions. The approach is demonstrated with a case of RUL prediction for aircraft engines. predictive maintainance remaining useful life reinforcement learning napovedno vzdrževanje preostala uporabna doba vzpodbujevalno učenje true false true Angleški jezik Slovenski jezik Članek v reviji 2020-09-29 09:16:54 2020-09-29 09:16:57 2025-02-04 11:08:58 0000-00-00 00:00:00 2020 0 0 Str. 425-430 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 658.5(045) 2212-8271 10.1016/j.procir.2020.03.051 30188803 30177283 RAZ_Kozjek_Dominik_2020.pdf RAZ_Kozjek_Dominik_2020.pdf 1 85FF7E4570D24157710B03BA698C4EA0 d22d7e8672c6e851f052523dfe19ffa0e14e9799c407bb64d485bd5fa463a078 35143d53-a1ba-11eb-a523-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=135873 https://www.sciencedirect.com/science/article/pii/S2212827120306582 1 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=135871 Fakulteta za strojništvo 0 0 0