Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149607345> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3149607345 endingPage "480" @default.
- W3149607345 startingPage "467" @default.
- W3149607345 abstract "Convolutional kernels have significant affections on feature learning of convolutional neural network (CNN). However, it is still a challenging problem to determine appropriate kernel width. Moreover, some features learned by convolutional layers are still redundant and noisy. Thus, adaptive selection of kernel width and feature selection of feature maps are key techniques to improve feature learning performance of CNNs. In this paper, a new deep neural network (DNN) model, adaptive kernel sparse network (AKSNet) is proposed to extract multi-scale fault features from one-dimensional (1-D) vibration signals. Firstly, an adaptive kernel selection method is developed, where multiple branches with different kernels are used to extract multi-scale features from vibration signals. Channel-wise attention is developed to fuse features generated by these kernels to obtain different informative scales. Secondly, a spatial attention is used for dynamic receptive field to focus on salient region of feature maps. Thirdly, a sparse regularization layer is embedded in the deep network to further filter noise and highlight impaction of the feature maps. Finally, two cases are adopted to verify effectiveness of AKSNet-based feature learning for bearing fault diagnosis. Experimental results show that AKSNet can effectively extract features from multi-channel vibration signals and then improves fault diagnosis performance of the classifier significantly. AKSNet shows better recognition performance in comparison with that of shallow neural networks and other typical DNNs." @default.
- W3149607345 created "2021-04-13" @default.
- W3149607345 creator A5041454124 @default.
- W3149607345 creator A5057830509 @default.
- W3149607345 date "2021-04-01" @default.
- W3149607345 modified "2023-10-17" @default.
- W3149607345 title "AKSNet: A novel convolutional neural network with adaptive kernel width and sparse regularization for machinery fault diagnosis" @default.
- W3149607345 cites W2057577134 @default.
- W3149607345 cites W2404692435 @default.
- W3149607345 cites W2461729787 @default.
- W3149607345 cites W2556345765 @default.
- W3149607345 cites W2595657631 @default.
- W3149607345 cites W2608571722 @default.
- W3149607345 cites W2612554669 @default.
- W3149607345 cites W2745816215 @default.
- W3149607345 cites W2768753204 @default.
- W3149607345 cites W2791139105 @default.
- W3149607345 cites W2791694051 @default.
- W3149607345 cites W2808496542 @default.
- W3149607345 cites W2904460913 @default.
- W3149607345 cites W2906256948 @default.
- W3149607345 cites W2907007702 @default.
- W3149607345 cites W2917014261 @default.
- W3149607345 cites W2919710279 @default.
- W3149607345 cites W2943389092 @default.
- W3149607345 cites W2944411166 @default.
- W3149607345 cites W2947583263 @default.
- W3149607345 cites W2966507006 @default.
- W3149607345 cites W2997417149 @default.
- W3149607345 cites W3011928337 @default.
- W3149607345 cites W3015801892 @default.
- W3149607345 cites W3018957240 @default.
- W3149607345 cites W3025585096 @default.
- W3149607345 cites W3025926773 @default.
- W3149607345 cites W3041218800 @default.
- W3149607345 cites W3043419586 @default.
- W3149607345 cites W3113371083 @default.
- W3149607345 doi "https://doi.org/10.1016/j.jmsy.2021.03.022" @default.
- W3149607345 hasPublicationYear "2021" @default.
- W3149607345 type Work @default.
- W3149607345 sameAs 3149607345 @default.
- W3149607345 citedByCount "27" @default.
- W3149607345 countsByYear W31496073452021 @default.
- W3149607345 countsByYear W31496073452022 @default.
- W3149607345 countsByYear W31496073452023 @default.
- W3149607345 crossrefType "journal-article" @default.
- W3149607345 hasAuthorship W3149607345A5041454124 @default.
- W3149607345 hasAuthorship W3149607345A5057830509 @default.
- W3149607345 hasConcept C114614502 @default.
- W3149607345 hasConcept C138885662 @default.
- W3149607345 hasConcept C148483581 @default.
- W3149607345 hasConcept C153180895 @default.
- W3149607345 hasConcept C154945302 @default.
- W3149607345 hasConcept C2776401178 @default.
- W3149607345 hasConcept C33923547 @default.
- W3149607345 hasConcept C41008148 @default.
- W3149607345 hasConcept C41895202 @default.
- W3149607345 hasConcept C74193536 @default.
- W3149607345 hasConcept C81363708 @default.
- W3149607345 hasConcept C95623464 @default.
- W3149607345 hasConceptScore W3149607345C114614502 @default.
- W3149607345 hasConceptScore W3149607345C138885662 @default.
- W3149607345 hasConceptScore W3149607345C148483581 @default.
- W3149607345 hasConceptScore W3149607345C153180895 @default.
- W3149607345 hasConceptScore W3149607345C154945302 @default.
- W3149607345 hasConceptScore W3149607345C2776401178 @default.
- W3149607345 hasConceptScore W3149607345C33923547 @default.
- W3149607345 hasConceptScore W3149607345C41008148 @default.
- W3149607345 hasConceptScore W3149607345C41895202 @default.
- W3149607345 hasConceptScore W3149607345C74193536 @default.
- W3149607345 hasConceptScore W3149607345C81363708 @default.
- W3149607345 hasConceptScore W3149607345C95623464 @default.
- W3149607345 hasFunder F4320321001 @default.
- W3149607345 hasFunder F4320335787 @default.
- W3149607345 hasFunder F4320336652 @default.
- W3149607345 hasLocation W31496073451 @default.
- W3149607345 hasOpenAccess W3149607345 @default.
- W3149607345 hasPrimaryLocation W31496073451 @default.
- W3149607345 hasRelatedWork W2175746458 @default.
- W3149607345 hasRelatedWork W2732542196 @default.
- W3149607345 hasRelatedWork W2738221750 @default.
- W3149607345 hasRelatedWork W2760085659 @default.
- W3149607345 hasRelatedWork W2883200793 @default.
- W3149607345 hasRelatedWork W2995914718 @default.
- W3149607345 hasRelatedWork W3093612317 @default.
- W3149607345 hasRelatedWork W4225852842 @default.
- W3149607345 hasRelatedWork W4307883119 @default.
- W3149607345 hasRelatedWork W564581980 @default.
- W3149607345 hasVolume "59" @default.
- W3149607345 isParatext "false" @default.
- W3149607345 isRetracted "false" @default.
- W3149607345 magId "3149607345" @default.
- W3149607345 workType "article" @default.