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

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

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.

• Language: English
• Keywords: predictive maintainance, remaining useful life, reinforcement learning
• Work type: Article
• Typology: 1.08 - Published Scientific Conference Contribution
• Organization: FS - Faculty of Mechanical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2020
• Number of pages: Str. 425-430
• PID: 20.500.12556/RUL-121028
• UDC: 658.5(045)
• ISSN on article: 2212-8271
• DOI: 10.1016/j.procir.2020.03.051
• COBISS.SI-ID: 30188803
• Publication date in RUL: 29.09.2020

Record is a part of a proceedings

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

Record is a part of a journal

• Title: Procedia CIRP
• Publisher: Elsevier
• ISSN: 2212-8271
• COBISS.SI-ID: 12981019

Secondary language

• Language: Slovenian
• Keywords: napovedno vzdrževanje, preostala uporabna doba, vzpodbujevalno učenje

Projects

• Funder: ARRS - Slovenian Research Agency
• Project number: P2-0270
• Name: Proizvodni sistemi, laserske tehnologije in spajanje materialov