Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384502023> ?p ?o ?g. }
- W4384502023 endingPage "109511" @default.
- W4384502023 startingPage "109511" @default.
- W4384502023 abstract "In recent years, deep neural networks have been widely applied in remaining useful life (RUL) prediction, and good prognostic performance has been achieved. However, existing centralized learning methods often ignore data privacy, modelling efficiency, and common feature of learning tasks. This paper presents a new RUL prediction method using global health degradation representation (GHDR) in federated learning (FL) framework named GHDR-FL, which aims to extract GHDR from distributed datasets and build personalized models for multiple clients. Specifically, GHDR is an aggregation of shallow features learned by the FL server and clients jointly. The head of each model is the unique superstructure, which is adopted to extract high-level features from the GHDR and local data on the client side. With the GHDR and unique superstructures, RUL prediction models customized for different operating conditions and fault modes can be built simultaneously in the FL. A degradation dataset of turbofan engines is used to evaluate the proposed method. The experimental results show that the GHDR-FL has high accuracy than the centralized learning methods, and the ready-made GHDR has strong versatility." @default.
- W4384502023 created "2023-07-18" @default.
- W4384502023 creator A5011148961 @default.
- W4384502023 creator A5042204348 @default.
- W4384502023 creator A5057517079 @default.
- W4384502023 creator A5083638473 @default.
- W4384502023 creator A5090366405 @default.
- W4384502023 date "2023-11-01" @default.
- W4384502023 modified "2023-09-26" @default.
- W4384502023 title "Remaining useful life prediction of turbofan engine using global health degradation representation in federated learning" @default.
- W4384502023 cites W2772084711 @default.
- W4384502023 cites W2792018332 @default.
- W4384502023 cites W2808622270 @default.
- W4384502023 cites W2943154646 @default.
- W4384502023 cites W3006585575 @default.
- W4384502023 cites W3009075394 @default.
- W4384502023 cites W3010852232 @default.
- W4384502023 cites W3014570380 @default.
- W4384502023 cites W3033580259 @default.
- W4384502023 cites W3037995823 @default.
- W4384502023 cites W3089341989 @default.
- W4384502023 cites W3092267918 @default.
- W4384502023 cites W3104795042 @default.
- W4384502023 cites W3115710758 @default.
- W4384502023 cites W3118534614 @default.
- W4384502023 cites W3123983671 @default.
- W4384502023 cites W3129318029 @default.
- W4384502023 cites W3135855722 @default.
- W4384502023 cites W3137613462 @default.
- W4384502023 cites W3150223772 @default.
- W4384502023 cites W3207642814 @default.
- W4384502023 cites W4205830141 @default.
- W4384502023 cites W4210745385 @default.
- W4384502023 cites W4224252567 @default.
- W4384502023 cites W4226461442 @default.
- W4384502023 cites W4303684738 @default.
- W4384502023 doi "https://doi.org/10.1016/j.ress.2023.109511" @default.
- W4384502023 hasPublicationYear "2023" @default.
- W4384502023 type Work @default.
- W4384502023 citedByCount "0" @default.
- W4384502023 crossrefType "journal-article" @default.
- W4384502023 hasAuthorship W4384502023A5011148961 @default.
- W4384502023 hasAuthorship W4384502023A5042204348 @default.
- W4384502023 hasAuthorship W4384502023A5057517079 @default.
- W4384502023 hasAuthorship W4384502023A5083638473 @default.
- W4384502023 hasAuthorship W4384502023A5090366405 @default.
- W4384502023 hasConcept C108583219 @default.
- W4384502023 hasConcept C110050840 @default.
- W4384502023 hasConcept C119857082 @default.
- W4384502023 hasConcept C124101348 @default.
- W4384502023 hasConcept C127413603 @default.
- W4384502023 hasConcept C129364497 @default.
- W4384502023 hasConcept C138885662 @default.
- W4384502023 hasConcept C154945302 @default.
- W4384502023 hasConcept C171146098 @default.
- W4384502023 hasConcept C17744445 @default.
- W4384502023 hasConcept C199539241 @default.
- W4384502023 hasConcept C2776359362 @default.
- W4384502023 hasConcept C2776401178 @default.
- W4384502023 hasConcept C2779679103 @default.
- W4384502023 hasConcept C2992525071 @default.
- W4384502023 hasConcept C41008148 @default.
- W4384502023 hasConcept C41895202 @default.
- W4384502023 hasConcept C50644808 @default.
- W4384502023 hasConcept C59404180 @default.
- W4384502023 hasConcept C76155785 @default.
- W4384502023 hasConcept C94625758 @default.
- W4384502023 hasConceptScore W4384502023C108583219 @default.
- W4384502023 hasConceptScore W4384502023C110050840 @default.
- W4384502023 hasConceptScore W4384502023C119857082 @default.
- W4384502023 hasConceptScore W4384502023C124101348 @default.
- W4384502023 hasConceptScore W4384502023C127413603 @default.
- W4384502023 hasConceptScore W4384502023C129364497 @default.
- W4384502023 hasConceptScore W4384502023C138885662 @default.
- W4384502023 hasConceptScore W4384502023C154945302 @default.
- W4384502023 hasConceptScore W4384502023C171146098 @default.
- W4384502023 hasConceptScore W4384502023C17744445 @default.
- W4384502023 hasConceptScore W4384502023C199539241 @default.
- W4384502023 hasConceptScore W4384502023C2776359362 @default.
- W4384502023 hasConceptScore W4384502023C2776401178 @default.
- W4384502023 hasConceptScore W4384502023C2779679103 @default.
- W4384502023 hasConceptScore W4384502023C2992525071 @default.
- W4384502023 hasConceptScore W4384502023C41008148 @default.
- W4384502023 hasConceptScore W4384502023C41895202 @default.
- W4384502023 hasConceptScore W4384502023C50644808 @default.
- W4384502023 hasConceptScore W4384502023C59404180 @default.
- W4384502023 hasConceptScore W4384502023C76155785 @default.
- W4384502023 hasConceptScore W4384502023C94625758 @default.
- W4384502023 hasFunder F4320321001 @default.
- W4384502023 hasFunder F4320335777 @default.
- W4384502023 hasLocation W43845020231 @default.
- W4384502023 hasOpenAccess W4384502023 @default.
- W4384502023 hasPrimaryLocation W43845020231 @default.
- W4384502023 hasRelatedWork W2795261237 @default.
- W4384502023 hasRelatedWork W3014300295 @default.
- W4384502023 hasRelatedWork W3164822677 @default.
- W4384502023 hasRelatedWork W4223943233 @default.
- W4384502023 hasRelatedWork W4225161397 @default.