Multi-objective adjustment of remaining useful life predictions based on reinforcement learning
| Autor: | Andreja Malus, Rok Vrabič, Dominik Kozjek |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
predictive maintainance reinforcement learning business.product_category Computer science remaining useful life 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences vzpodbujevalno učenje udc:658.5(045) 020901 industrial engineering & automation Encoding (memory) Reinforcement learning 0105 earth and related environmental sciences General Environmental Science business.industry preostala uporabna doba Machine tool Key (cryptography) General Earth and Planetary Sciences Artificial intelligence napovedno vzdrževanje business computer Degradation (telecommunications) |
| Zdroj: | 53rd CIRP Conference on Manufacturing Systems 2020, Procedia CIRP, pp. 425-430, 2020. |
| ISSN: | 2212-8271 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|