Multi-objective adjustment of remaining useful life predictions based on reinforcement learning

Kozjek, Dominik (avtor), Malus, Andreja (avtor), Vrabič, Rok (avtor)

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.

• Jezik: Angleški jezik
• Ključne besede: predictive maintainance, remaining useful life, reinforcement learning
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.08 - Objavljeni znanstveni prispevek na konferenci
• Organizacija: FS - Fakulteta za strojništvo
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2020
• Št. strani: Str. 425-430
• PID: 20.500.12556/RUL-121028
• UDK: 658.5(045)
• ISSN pri članku: 2212-8271
• DOI: 10.1016/j.procir.2020.03.051
• COBISS.SI-ID: 30188803
• Datum objave v RUL: 29.09.2020

Gradivo je del zbornika

• Naslov: 53rd CIRP Conference on Manufacturing Systems 2020
• COBISS.SI-ID: 30177283

Gradivo je del revije

• Naslov: Procedia CIRP
• Založnik: Elsevier
• ISSN: 2212-8271
• COBISS.SI-ID: 12981019

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: napovedno vzdrževanje, preostala uporabna doba, vzpodbujevalno učenje

Projekti

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
• Številka projekta: P2-0270
• Naslov: Proizvodni sistemi, laserske tehnologije in spajanje materialov