FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904698032> ?p ?o ?g. }

• W2904698032 abstract "Early and accurately detecting faults in rotating machineries is crucial for operation safety of modern manufacturing system. In this paper, we proposed a novel deep CNN method based on knowledge-transferring from shallow models for rotating machinery fault diagnosis with scarce labeled samples. It is based on the idea that shallow models trained with different hand-crafted features can reveal the latent prior knowledge or diagnostic expertise and have good generalization ability even with scarce labeled samples. First, The raw vibration signal is transformed into time-frequency domain by applying the short-time Fourier transform (STFT) to extract integral features accordingly. Then, we train the SVM model with scarce labeled samples and make predictions on unlabeled samples. The predicted labels can be regarded as the data format of expert knowledge learned by the SVM model, which are combined together with the scarce fine labeled samples. Finally, they are used to train a deep CNN model of better discriminative ability. Experimental results demonstrate the effectiveness the proposed method that it achieves better performance than SVM model and original deep CNN model trained with only scarce labeled samples. Moreover, it is computational efficient and is promising for real-time rotating machinery fault diagnosis." @default.
• W2904698032 created "2018-12-22" @default.
• W2904698032 creator A5015599512 @default.
• W2904698032 creator A5028166500 @default.
• W2904698032 creator A5039794398 @default.
• W2904698032 creator A5041096372 @default.
• W2904698032 creator A5078691114 @default.
• W2904698032 creator A5086718724 @default.
• W2904698032 date "2018-10-01" @default.
• W2904698032 modified "2023-09-24" @default.
• W2904698032 title "Fault Diagnosis for Rotating Machinery with Scarce Labeled Samples: A Deep CNN Method Based on Knowledge-Transferring from Shallow Models" @default.
• W2904698032 cites W1538131130 @default.
• W2904698032 cites W1967352108 @default.
• W2904698032 cites W1984541135 @default.
• W2904698032 cites W1988790447 @default.
• W2904698032 cites W1991941961 @default.
• W2904698032 cites W2008056655 @default.
• W2904698032 cites W2019928639 @default.
• W2904698032 cites W2039951318 @default.
• W2904698032 cites W2062227835 @default.
• W2904698032 cites W2083520984 @default.
• W2904698032 cites W2107074288 @default.
• W2904698032 cites W2111072639 @default.
• W2904698032 cites W2115954437 @default.
• W2904698032 cites W2126584714 @default.
• W2904698032 cites W2136922672 @default.
• W2904698032 cites W2144187919 @default.
• W2904698032 cites W2155893237 @default.
• W2904698032 cites W2163605009 @default.
• W2904698032 cites W2168013545 @default.
• W2904698032 cites W2184192902 @default.
• W2904698032 cites W2187089797 @default.
• W2904698032 cites W2219903032 @default.
• W2904698032 cites W2258884143 @default.
• W2904698032 cites W2321143615 @default.
• W2904698032 cites W2324044936 @default.
• W2904698032 cites W2542700981 @default.
• W2904698032 cites W2587192379 @default.
• W2904698032 cites W2613718673 @default.
• W2904698032 cites W2734669076 @default.
• W2904698032 doi "https://doi.org/10.1109/iccais.2018.8570515" @default.
• W2904698032 hasPublicationYear "2018" @default.
• W2904698032 type Work @default.
• W2904698032 sameAs 2904698032 @default.
• W2904698032 citedByCount "3" @default.
• W2904698032 countsByYear W29046980322019 @default.
• W2904698032 countsByYear W29046980322020 @default.
• W2904698032 countsByYear W29046980322021 @default.
• W2904698032 crossrefType "proceedings-article" @default.
• W2904698032 hasAuthorship W2904698032A5015599512 @default.
• W2904698032 hasAuthorship W2904698032A5028166500 @default.
• W2904698032 hasAuthorship W2904698032A5039794398 @default.
• W2904698032 hasAuthorship W2904698032A5041096372 @default.
• W2904698032 hasAuthorship W2904698032A5078691114 @default.
• W2904698032 hasAuthorship W2904698032A5086718724 @default.
• W2904698032 hasConcept C102519508 @default.
• W2904698032 hasConcept C108583219 @default.
• W2904698032 hasConcept C119857082 @default.
• W2904698032 hasConcept C12267149 @default.
• W2904698032 hasConcept C127313418 @default.
• W2904698032 hasConcept C134306372 @default.
• W2904698032 hasConcept C153180895 @default.
• W2904698032 hasConcept C154945302 @default.
• W2904698032 hasConcept C165205528 @default.
• W2904698032 hasConcept C166386157 @default.
• W2904698032 hasConcept C175551986 @default.
• W2904698032 hasConcept C177148314 @default.
• W2904698032 hasConcept C203024314 @default.
• W2904698032 hasConcept C207685749 @default.
• W2904698032 hasConcept C33923547 @default.
• W2904698032 hasConcept C41008148 @default.
• W2904698032 hasConcept C97931131 @default.
• W2904698032 hasConceptScore W2904698032C102519508 @default.
• W2904698032 hasConceptScore W2904698032C108583219 @default.
• W2904698032 hasConceptScore W2904698032C119857082 @default.
• W2904698032 hasConceptScore W2904698032C12267149 @default.
• W2904698032 hasConceptScore W2904698032C127313418 @default.
• W2904698032 hasConceptScore W2904698032C134306372 @default.
• W2904698032 hasConceptScore W2904698032C153180895 @default.
• W2904698032 hasConceptScore W2904698032C154945302 @default.
• W2904698032 hasConceptScore W2904698032C165205528 @default.
• W2904698032 hasConceptScore W2904698032C166386157 @default.
• W2904698032 hasConceptScore W2904698032C175551986 @default.
• W2904698032 hasConceptScore W2904698032C177148314 @default.
• W2904698032 hasConceptScore W2904698032C203024314 @default.
• W2904698032 hasConceptScore W2904698032C207685749 @default.
• W2904698032 hasConceptScore W2904698032C33923547 @default.
• W2904698032 hasConceptScore W2904698032C41008148 @default.
• W2904698032 hasConceptScore W2904698032C97931131 @default.
• W2904698032 hasLocation W29046980321 @default.
• W2904698032 hasOpenAccess W2904698032 @default.
• W2904698032 hasPrimaryLocation W29046980321 @default.
• W2904698032 hasRelatedWork W1906421653 @default.
• W2904698032 hasRelatedWork W2555500570 @default.
• W2904698032 hasRelatedWork W2743258233 @default.
• W2904698032 hasRelatedWork W3014676278 @default.
• W2904698032 hasRelatedWork W3112948183 @default.
• W2904698032 hasRelatedWork W3136979370 @default.
• W2904698032 hasRelatedWork W3140675663 @default.
• W2904698032 hasRelatedWork W3157993706 @default.

• next