Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386314827> ?p ?o ?g. }
- W4386314827 endingPage "109605" @default.
- W4386314827 startingPage "109605" @default.
- W4386314827 abstract "Aero-engines are core equipment in aerospace field, and their remaining useful life (RUL) prediction is a critical aspect in spacecraft monitoring and maintenance. Transformer model demonstrates remarkable performance in this domain, but its construction heavily relies on a sizeable number of parameters and the excessive model redundancy may adversely affect its prediction performance. To address this issue, a pruning-adaptive optimal lightweight Transformer (PAOLTransformer) is proposed. The method employs norm information to evaluate the contribution of each element within the model to the outputs and subsequently utilizes structured pruning to eliminate unimportant redundant elements. The pruning procedure is executed automatically by seeking out the optimal compression rate via reinforcement learning with a reward score combining the accuracy and efficiency of RUL prediction. Experimental analysis on the C-MAPSS aero-engine dataset shows that PAOLTransformer significantly improves the performance metrics, including a 7% reduction in prediction error and a 33% reduction in computational complexity compared to the standard Transformer. It follows that the proposed model can achieve an optimal equilibrium between model performance and pruning rate. Furthermore, PAOLTransformer outperforms several advanced models in predicting long and complex time series. Therefore, this study holds significant implications for the implementation of preventive maintenance strategies for aero-engines." @default.
- W4386314827 created "2023-09-01" @default.
- W4386314827 creator A5004080085 @default.
- W4386314827 creator A5010472607 @default.
- W4386314827 creator A5014310116 @default.
- W4386314827 creator A5032842898 @default.
- W4386314827 creator A5073216396 @default.
- W4386314827 creator A5082767158 @default.
- W4386314827 date "2023-12-01" @default.
- W4386314827 modified "2023-09-27" @default.
- W4386314827 title "PAOLTransformer: Pruning-adaptive optimal lightweight Transformer model for aero-engine remaining useful life prediction" @default.
- W4386314827 cites W2617137613 @default.
- W4386314827 cites W2756887047 @default.
- W4386314827 cites W2772084711 @default.
- W4386314827 cites W2902700103 @default.
- W4386314827 cites W2985380938 @default.
- W4386314827 cites W2997308049 @default.
- W4386314827 cites W3001566134 @default.
- W4386314827 cites W3011803685 @default.
- W4386314827 cites W3132028723 @default.
- W4386314827 cites W3148366207 @default.
- W4386314827 cites W3168279674 @default.
- W4386314827 cites W3172450624 @default.
- W4386314827 cites W3173924324 @default.
- W4386314827 cites W3177628906 @default.
- W4386314827 cites W3209662019 @default.
- W4386314827 cites W4200209943 @default.
- W4386314827 cites W4210562913 @default.
- W4386314827 cites W4212940123 @default.
- W4386314827 cites W4224264360 @default.
- W4386314827 cites W4281708005 @default.
- W4386314827 cites W4298325860 @default.
- W4386314827 cites W4320181720 @default.
- W4386314827 cites W4320479785 @default.
- W4386314827 cites W4321072566 @default.
- W4386314827 cites W4322505825 @default.
- W4386314827 cites W4322724151 @default.
- W4386314827 cites W4327977707 @default.
- W4386314827 cites W4362558040 @default.
- W4386314827 doi "https://doi.org/10.1016/j.ress.2023.109605" @default.
- W4386314827 hasPublicationYear "2023" @default.
- W4386314827 type Work @default.
- W4386314827 citedByCount "0" @default.
- W4386314827 crossrefType "journal-article" @default.
- W4386314827 hasAuthorship W4386314827A5004080085 @default.
- W4386314827 hasAuthorship W4386314827A5010472607 @default.
- W4386314827 hasAuthorship W4386314827A5014310116 @default.
- W4386314827 hasAuthorship W4386314827A5032842898 @default.
- W4386314827 hasAuthorship W4386314827A5073216396 @default.
- W4386314827 hasAuthorship W4386314827A5082767158 @default.
- W4386314827 hasConcept C104317684 @default.
- W4386314827 hasConcept C108010975 @default.
- W4386314827 hasConcept C111919701 @default.
- W4386314827 hasConcept C119599485 @default.
- W4386314827 hasConcept C119857082 @default.
- W4386314827 hasConcept C127413603 @default.
- W4386314827 hasConcept C146978453 @default.
- W4386314827 hasConcept C152124472 @default.
- W4386314827 hasConcept C165801399 @default.
- W4386314827 hasConcept C167740415 @default.
- W4386314827 hasConcept C185592680 @default.
- W4386314827 hasConcept C200601418 @default.
- W4386314827 hasConcept C21200559 @default.
- W4386314827 hasConcept C24326235 @default.
- W4386314827 hasConcept C2985438705 @default.
- W4386314827 hasConcept C41008148 @default.
- W4386314827 hasConcept C49740808 @default.
- W4386314827 hasConcept C55493867 @default.
- W4386314827 hasConcept C63479239 @default.
- W4386314827 hasConcept C6557445 @default.
- W4386314827 hasConcept C66322947 @default.
- W4386314827 hasConcept C78519656 @default.
- W4386314827 hasConcept C86803240 @default.
- W4386314827 hasConceptScore W4386314827C104317684 @default.
- W4386314827 hasConceptScore W4386314827C108010975 @default.
- W4386314827 hasConceptScore W4386314827C111919701 @default.
- W4386314827 hasConceptScore W4386314827C119599485 @default.
- W4386314827 hasConceptScore W4386314827C119857082 @default.
- W4386314827 hasConceptScore W4386314827C127413603 @default.
- W4386314827 hasConceptScore W4386314827C146978453 @default.
- W4386314827 hasConceptScore W4386314827C152124472 @default.
- W4386314827 hasConceptScore W4386314827C165801399 @default.
- W4386314827 hasConceptScore W4386314827C167740415 @default.
- W4386314827 hasConceptScore W4386314827C185592680 @default.
- W4386314827 hasConceptScore W4386314827C200601418 @default.
- W4386314827 hasConceptScore W4386314827C21200559 @default.
- W4386314827 hasConceptScore W4386314827C24326235 @default.
- W4386314827 hasConceptScore W4386314827C2985438705 @default.
- W4386314827 hasConceptScore W4386314827C41008148 @default.
- W4386314827 hasConceptScore W4386314827C49740808 @default.
- W4386314827 hasConceptScore W4386314827C55493867 @default.
- W4386314827 hasConceptScore W4386314827C63479239 @default.
- W4386314827 hasConceptScore W4386314827C6557445 @default.
- W4386314827 hasConceptScore W4386314827C66322947 @default.
- W4386314827 hasConceptScore W4386314827C78519656 @default.
- W4386314827 hasConceptScore W4386314827C86803240 @default.
- W4386314827 hasLocation W43863148271 @default.
- W4386314827 hasOpenAccess W4386314827 @default.