Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378697051> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4378697051 endingPage "12" @default.
- W4378697051 startingPage "1" @default.
- W4378697051 abstract "Recent advance of deep learning has seen remarkable progress in compound fault diagnosis modelling for industrial robots. Nevertheless, the data scarcity of compound fault samples jeopardizes the modelling performance of deep learning algorithms. Meta learning has become an effective tool in few-shot fault diagnosis modelling. However, due to the training instability of meta learning, it is challenging to deploy advanced networks such as Transformers as the base learner due to the extremely large model size. Therefore, this study proposes a lightweight convolutional Transformers (LCT) network enhanced meta learning (Meta-LCT) method to achieve accurate compound fault diagnosis with limited compound fault samples. Specifically, the LCT is firstly designed by taking advantage of linear spatial reduction (LSR) attention and spatial pooling mechanism to achieve high computational efficiency. LCT is adopted as the base learner in the Meta-SGD algorithm, and then the meta-training is performed based on the single fault data. Subsequently, the limited compound fault samples are used in the meta testing stage to obtain a compound fault diagnosis model. An experimental study based on the real-world compound fault dataset of industrial robots is presented. The experimental results indicate that the proposed Meta-LCT can achieve the compound fault diagnosis accuracy of 81.1% when only 40 data samples in each compound fault category are available." @default.
- W4378697051 created "2023-05-30" @default.
- W4378697051 creator A5025318443 @default.
- W4378697051 creator A5032362514 @default.
- W4378697051 creator A5076490243 @default.
- W4378697051 creator A5089852781 @default.
- W4378697051 creator A5092045931 @default.
- W4378697051 date "2023-01-01" @default.
- W4378697051 modified "2023-10-16" @default.
- W4378697051 title "Lightweight Convolutional Transformers Enhanced Meta-Learning for Compound Fault Diagnosis of Industrial Robot" @default.
- W4378697051 cites W2194775991 @default.
- W4378697051 cites W2799620499 @default.
- W4378697051 cites W2990705538 @default.
- W4378697051 cites W2995279030 @default.
- W4378697051 cites W3041076719 @default.
- W4378697051 cites W3087227514 @default.
- W4378697051 cites W3100513142 @default.
- W4378697051 cites W3126446664 @default.
- W4378697051 cites W3128553897 @default.
- W4378697051 cites W3132422289 @default.
- W4378697051 cites W3138516171 @default.
- W4378697051 cites W3174485934 @default.
- W4378697051 cites W3175515048 @default.
- W4378697051 cites W3184578020 @default.
- W4378697051 cites W3200647619 @default.
- W4378697051 cites W3209564648 @default.
- W4378697051 cites W3211127597 @default.
- W4378697051 cites W3213088652 @default.
- W4378697051 cites W3215145458 @default.
- W4378697051 cites W4200591402 @default.
- W4378697051 cites W4212861124 @default.
- W4378697051 cites W4226058060 @default.
- W4378697051 cites W4226432849 @default.
- W4378697051 cites W4281721340 @default.
- W4378697051 cites W4281734162 @default.
- W4378697051 cites W4284714138 @default.
- W4378697051 cites W4285245107 @default.
- W4378697051 cites W4286383144 @default.
- W4378697051 cites W4288772854 @default.
- W4378697051 cites W4296703705 @default.
- W4378697051 cites W4307567853 @default.
- W4378697051 cites W4311918071 @default.
- W4378697051 cites W4312537998 @default.
- W4378697051 cites W4317038442 @default.
- W4378697051 doi "https://doi.org/10.1109/tim.2023.3277956" @default.
- W4378697051 hasPublicationYear "2023" @default.
- W4378697051 type Work @default.
- W4378697051 citedByCount "0" @default.
- W4378697051 crossrefType "journal-article" @default.
- W4378697051 hasAuthorship W4378697051A5025318443 @default.
- W4378697051 hasAuthorship W4378697051A5032362514 @default.
- W4378697051 hasAuthorship W4378697051A5076490243 @default.
- W4378697051 hasAuthorship W4378697051A5089852781 @default.
- W4378697051 hasAuthorship W4378697051A5092045931 @default.
- W4378697051 hasConcept C108583219 @default.
- W4378697051 hasConcept C119857082 @default.
- W4378697051 hasConcept C124101348 @default.
- W4378697051 hasConcept C127313418 @default.
- W4378697051 hasConcept C127413603 @default.
- W4378697051 hasConcept C154945302 @default.
- W4378697051 hasConcept C165205528 @default.
- W4378697051 hasConcept C175551986 @default.
- W4378697051 hasConcept C200601418 @default.
- W4378697051 hasConcept C41008148 @default.
- W4378697051 hasConcept C70437156 @default.
- W4378697051 hasConceptScore W4378697051C108583219 @default.
- W4378697051 hasConceptScore W4378697051C119857082 @default.
- W4378697051 hasConceptScore W4378697051C124101348 @default.
- W4378697051 hasConceptScore W4378697051C127313418 @default.
- W4378697051 hasConceptScore W4378697051C127413603 @default.
- W4378697051 hasConceptScore W4378697051C154945302 @default.
- W4378697051 hasConceptScore W4378697051C165205528 @default.
- W4378697051 hasConceptScore W4378697051C175551986 @default.
- W4378697051 hasConceptScore W4378697051C200601418 @default.
- W4378697051 hasConceptScore W4378697051C41008148 @default.
- W4378697051 hasConceptScore W4378697051C70437156 @default.
- W4378697051 hasFunder F4320321001 @default.
- W4378697051 hasFunder F4320321921 @default.
- W4378697051 hasLocation W43786970511 @default.
- W4378697051 hasOpenAccess W4378697051 @default.
- W4378697051 hasPrimaryLocation W43786970511 @default.
- W4378697051 hasRelatedWork W3014300295 @default.
- W4378697051 hasRelatedWork W3173326738 @default.
- W4378697051 hasRelatedWork W4223943233 @default.
- W4378697051 hasRelatedWork W4225161397 @default.
- W4378697051 hasRelatedWork W4296990061 @default.
- W4378697051 hasRelatedWork W4309045103 @default.
- W4378697051 hasRelatedWork W4312200629 @default.
- W4378697051 hasRelatedWork W4360585206 @default.
- W4378697051 hasRelatedWork W4364306694 @default.
- W4378697051 hasRelatedWork W4380086463 @default.
- W4378697051 hasVolume "72" @default.
- W4378697051 isParatext "false" @default.
- W4378697051 isRetracted "false" @default.
- W4378697051 workType "article" @default.