Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320853934> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4320853934 abstract "Intelligent fault diagnosis has made extraordinary advancements currently. Nonetheless, few works tackle class-incremental learning for fault diagnosis under limited fault data, i.e., imbalanced and long-tailed fault diagnosis, which brings about various notable challenges. Initially, it is difficult to extract discriminative features from limited fault data. Moreover, a well-trained model must be retrained from scratch to classify the samples from new classes, thus causing a high computational burden and time consumption. Furthermore, the model may suffer from catastrophic forgetting when trained incrementally. Finally, the model decision is biased toward the new classes due to the class imbalance. The problems can consequently lead to performance degradation of fault diagnosis models. Accordingly, we introduce a supervised contrastive knowledge distillation for incremental fault diagnosis under limited fault data (SCLIFD) framework to address these issues, which extends the classical incremental classifier and representation learning (iCaRL) framework from three perspectives. Primarily, we adopt supervised contrastive knowledge distillation (KD) to enhance its representation learning capability under limited fault data. Moreover, we propose a novel prioritized exemplar selection method adaptive herding (AdaHerding) to restrict the increase of the computational burden, which is also combined with KD to alleviate catastrophic forgetting. Additionally, we adopt the cosine classifier to mitigate the adverse impact of class imbalance. We conduct extensive experiments on simulated and real-world industrial processes under different imbalance ratios. Experimental results show that our SCLIFD outperforms the existing methods by a large margin." @default.
- W4320853934 created "2023-02-16" @default.
- W4320853934 creator A5016553493 @default.
- W4320853934 creator A5016671118 @default.
- W4320853934 creator A5021412121 @default.
- W4320853934 creator A5024200175 @default.
- W4320853934 creator A5061332222 @default.
- W4320853934 creator A5062049138 @default.
- W4320853934 date "2023-02-12" @default.
- W4320853934 modified "2023-09-29" @default.
- W4320853934 title "SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data" @default.
- W4320853934 doi "https://doi.org/10.48550/arxiv.2302.05929" @default.
- W4320853934 hasPublicationYear "2023" @default.
- W4320853934 type Work @default.
- W4320853934 citedByCount "0" @default.
- W4320853934 crossrefType "posted-content" @default.
- W4320853934 hasAuthorship W4320853934A5016553493 @default.
- W4320853934 hasAuthorship W4320853934A5016671118 @default.
- W4320853934 hasAuthorship W4320853934A5021412121 @default.
- W4320853934 hasAuthorship W4320853934A5024200175 @default.
- W4320853934 hasAuthorship W4320853934A5061332222 @default.
- W4320853934 hasAuthorship W4320853934A5062049138 @default.
- W4320853934 hasBestOaLocation W43208539341 @default.
- W4320853934 hasConcept C119857082 @default.
- W4320853934 hasConcept C127313418 @default.
- W4320853934 hasConcept C138885662 @default.
- W4320853934 hasConcept C154945302 @default.
- W4320853934 hasConcept C165205528 @default.
- W4320853934 hasConcept C175551986 @default.
- W4320853934 hasConcept C41008148 @default.
- W4320853934 hasConcept C41895202 @default.
- W4320853934 hasConcept C7149132 @default.
- W4320853934 hasConcept C95623464 @default.
- W4320853934 hasConcept C97931131 @default.
- W4320853934 hasConceptScore W4320853934C119857082 @default.
- W4320853934 hasConceptScore W4320853934C127313418 @default.
- W4320853934 hasConceptScore W4320853934C138885662 @default.
- W4320853934 hasConceptScore W4320853934C154945302 @default.
- W4320853934 hasConceptScore W4320853934C165205528 @default.
- W4320853934 hasConceptScore W4320853934C175551986 @default.
- W4320853934 hasConceptScore W4320853934C41008148 @default.
- W4320853934 hasConceptScore W4320853934C41895202 @default.
- W4320853934 hasConceptScore W4320853934C7149132 @default.
- W4320853934 hasConceptScore W4320853934C95623464 @default.
- W4320853934 hasConceptScore W4320853934C97931131 @default.
- W4320853934 hasLocation W43208539341 @default.
- W4320853934 hasOpenAccess W4320853934 @default.
- W4320853934 hasPrimaryLocation W43208539341 @default.
- W4320853934 hasRelatedWork W2112343299 @default.
- W4320853934 hasRelatedWork W2476179843 @default.
- W4320853934 hasRelatedWork W2623427976 @default.
- W4320853934 hasRelatedWork W2905846897 @default.
- W4320853934 hasRelatedWork W2936891942 @default.
- W4320853934 hasRelatedWork W2961085424 @default.
- W4320853934 hasRelatedWork W3174101157 @default.
- W4320853934 hasRelatedWork W3177958285 @default.
- W4320853934 hasRelatedWork W4226339960 @default.
- W4320853934 hasRelatedWork W4287755010 @default.
- W4320853934 isParatext "false" @default.
- W4320853934 isRetracted "false" @default.
- W4320853934 workType "article" @default.