Multi-objective adjustment of remaining useful life predictions based on reinforcement learning. Kozjek, D., Malus, A., & Vrabič, R. Procedia CIRP, 93:425–430, January, 2020. ![Multi-objective adjustment of remaining useful life predictions based on reinforcement learning [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 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.
@article{kozjek_multi-objective_2020,
series = {53rd {CIRP} {Conference} on {Manufacturing} {Systems} 2020},
title = {Multi-objective adjustment of remaining useful life predictions based on reinforcement learning},
volume = {93},
issn = {2212-8271},
url = {http://www.sciencedirect.com/science/article/pii/S2212827120306582},
doi = {10.1016/j.procir.2020.03.051},
abstract = {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 = {en},
urldate = {2020-09-28},
journal = {Procedia CIRP},
author = {Kozjek, Dominik and Malus, Andreja and Vrabič, Rok},
month = jan,
year = {2020},
keywords = {predictive maintainance, reinforcement learning, remaining useful life},
pages = {425--430},
}
Downloads: 0
{"_id":"it69sqArbBGwSZKPA","bibbaseid":"kozjek-malus-vrabi-multiobjectiveadjustmentofremainingusefullifepredictionsbasedonreinforcementlearning-2020","author_short":["Kozjek, D.","Malus, A.","Vrabič, R."],"bibdata":{"bibtype":"article","type":"article","series":"53rd CIRP Conference on Manufacturing Systems 2020","title":"Multi-objective adjustment of remaining useful life predictions based on reinforcement learning","volume":"93","issn":"2212-8271","url":"http://www.sciencedirect.com/science/article/pii/S2212827120306582","doi":"10.1016/j.procir.2020.03.051","abstract":"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":"en","urldate":"2020-09-28","journal":"Procedia CIRP","author":[{"propositions":[],"lastnames":["Kozjek"],"firstnames":["Dominik"],"suffixes":[]},{"propositions":[],"lastnames":["Malus"],"firstnames":["Andreja"],"suffixes":[]},{"propositions":[],"lastnames":["Vrabič"],"firstnames":["Rok"],"suffixes":[]}],"month":"January","year":"2020","keywords":"predictive maintainance, reinforcement learning, remaining useful life","pages":"425–430","bibtex":"@article{kozjek_multi-objective_2020,\n\tseries = {53rd {CIRP} {Conference} on {Manufacturing} {Systems} 2020},\n\ttitle = {Multi-objective adjustment of remaining useful life predictions based on reinforcement learning},\n\tvolume = {93},\n\tissn = {2212-8271},\n\turl = {http://www.sciencedirect.com/science/article/pii/S2212827120306582},\n\tdoi = {10.1016/j.procir.2020.03.051},\n\tabstract = {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.},\n\tlanguage = {en},\n\turldate = {2020-09-28},\n\tjournal = {Procedia CIRP},\n\tauthor = {Kozjek, Dominik and Malus, Andreja and Vrabič, Rok},\n\tmonth = jan,\n\tyear = {2020},\n\tkeywords = {predictive maintainance, reinforcement learning, remaining useful life},\n\tpages = {425--430},\n}\n\n","author_short":["Kozjek, D.","Malus, A.","Vrabič, R."],"key":"kozjek_multi-objective_2020","id":"kozjek_multi-objective_2020","bibbaseid":"kozjek-malus-vrabi-multiobjectiveadjustmentofremainingusefullifepredictionsbasedonreinforcementlearning-2020","role":"author","urls":{"Paper":"http://www.sciencedirect.com/science/article/pii/S2212827120306582"},"keyword":["predictive maintainance","reinforcement learning","remaining useful life"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["yanwtMpCcFaHzRwWb","iwKepCrWBps7ojhDx"],"keywords":["predictive maintainance","reinforcement learning","remaining useful life"],"search_terms":["multi","objective","adjustment","remaining","useful","life","predictions","based","reinforcement","learning","kozjek","malus","vrabič"],"title":"Multi-objective adjustment of remaining useful life predictions based on reinforcement learning","year":2020}