Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384157063> ?p ?o ?g. }
- W4384157063 endingPage "126551" @default.
- W4384157063 startingPage "126551" @default.
- W4384157063 abstract "Considering the changing working conditions of rotating machinery in operation, it is often difficult to collect data accurately in some severe fault states, and the lack of data can lead to poor performance of deep learning-based fault diagnosis models. In the few-shot scenario, traditional meta-learning methods yield superior predictions by identifying ideal initialization parameters. When the update gradients of tasks are in different directions, meta-learning modifies the weights of samples in the current tasks to average them out, which may lead to negative transfer between tasks and poor generalization of biases. Based on the above problems, we propose a meta-learning network with anti-interference (AIML) for few-shot fault diagnosis, which is obtained by combining a dynamic fine-tuning technique to increase the gradient agreement of the tasks. AIML consists of two functions: the feature encoding network (FEN) and the base network. AIML uses the property of shared parameters about transfer learning to learn shared feature representations of different tasks, while FEN dynamically adjusts the loss weights of conflicting tasks due to meta-learning with two-level optimization techniques. First, in the internal loop, AIML updates the gradient of the base network while the network parameters of FEN are fixed. Instead of immediately computing the gradient of the optimal parameters for the new task, the FEN is then integrated in the outer loop to learn the meta-representation, and the weights obtained for the various tasks relate to the gradient for meta-optimization. Only during the outer loop stage of the meta-training is the FEN updated. Three publicly available datasets are used to assess the performance of AIML, and the results show that it is more effective at resolving problems involving few-shot fault diagnosis." @default.
- W4384157063 created "2023-07-14" @default.
- W4384157063 creator A5008618885 @default.
- W4384157063 creator A5035124841 @default.
- W4384157063 creator A5040143854 @default.
- W4384157063 creator A5040504491 @default.
- W4384157063 creator A5063251428 @default.
- W4384157063 creator A5085790205 @default.
- W4384157063 creator A5086219789 @default.
- W4384157063 date "2023-10-01" @default.
- W4384157063 modified "2023-10-14" @default.
- W4384157063 title "A meta-learning network with anti-interference for few-shot fault diagnosis" @default.
- W4384157063 cites W243674440 @default.
- W4384157063 cites W2791694051 @default.
- W4384157063 cites W2887782657 @default.
- W4384157063 cites W2898760173 @default.
- W4384157063 cites W2912744143 @default.
- W4384157063 cites W2915423430 @default.
- W4384157063 cites W2940256401 @default.
- W4384157063 cites W2953680418 @default.
- W4384157063 cites W2981982720 @default.
- W4384157063 cites W3025981493 @default.
- W4384157063 cites W3034354010 @default.
- W4384157063 cites W3039216919 @default.
- W4384157063 cites W3080996465 @default.
- W4384157063 cites W3095270930 @default.
- W4384157063 cites W3100777112 @default.
- W4384157063 cites W3115552943 @default.
- W4384157063 cites W3126446664 @default.
- W4384157063 cites W3127617278 @default.
- W4384157063 cites W3128553897 @default.
- W4384157063 cites W3131860561 @default.
- W4384157063 cites W3134397144 @default.
- W4384157063 cites W3139302692 @default.
- W4384157063 cites W3163936961 @default.
- W4384157063 cites W3164543983 @default.
- W4384157063 cites W3174485934 @default.
- W4384157063 cites W3200647619 @default.
- W4384157063 cites W3209207186 @default.
- W4384157063 cites W3209453546 @default.
- W4384157063 cites W3209651137 @default.
- W4384157063 cites W4211058054 @default.
- W4384157063 cites W4213075002 @default.
- W4384157063 cites W4224219490 @default.
- W4384157063 cites W4229063675 @default.
- W4384157063 cites W4281685334 @default.
- W4384157063 cites W4286383144 @default.
- W4384157063 cites W4286435434 @default.
- W4384157063 cites W4312737473 @default.
- W4384157063 doi "https://doi.org/10.1016/j.neucom.2023.126551" @default.
- W4384157063 hasPublicationYear "2023" @default.
- W4384157063 type Work @default.
- W4384157063 citedByCount "0" @default.
- W4384157063 crossrefType "journal-article" @default.
- W4384157063 hasAuthorship W4384157063A5008618885 @default.
- W4384157063 hasAuthorship W4384157063A5035124841 @default.
- W4384157063 hasAuthorship W4384157063A5040143854 @default.
- W4384157063 hasAuthorship W4384157063A5040504491 @default.
- W4384157063 hasAuthorship W4384157063A5063251428 @default.
- W4384157063 hasAuthorship W4384157063A5085790205 @default.
- W4384157063 hasAuthorship W4384157063A5086219789 @default.
- W4384157063 hasConcept C111472728 @default.
- W4384157063 hasConcept C114466953 @default.
- W4384157063 hasConcept C119857082 @default.
- W4384157063 hasConcept C127162648 @default.
- W4384157063 hasConcept C127313418 @default.
- W4384157063 hasConcept C138885662 @default.
- W4384157063 hasConcept C150899416 @default.
- W4384157063 hasConcept C153180895 @default.
- W4384157063 hasConcept C154945302 @default.
- W4384157063 hasConcept C162324750 @default.
- W4384157063 hasConcept C165205528 @default.
- W4384157063 hasConcept C175551986 @default.
- W4384157063 hasConcept C17744445 @default.
- W4384157063 hasConcept C187736073 @default.
- W4384157063 hasConcept C189950617 @default.
- W4384157063 hasConcept C199360897 @default.
- W4384157063 hasConcept C199539241 @default.
- W4384157063 hasConcept C2776359362 @default.
- W4384157063 hasConcept C2776401178 @default.
- W4384157063 hasConcept C2780451532 @default.
- W4384157063 hasConcept C2781002164 @default.
- W4384157063 hasConcept C31258907 @default.
- W4384157063 hasConcept C32022120 @default.
- W4384157063 hasConcept C41008148 @default.
- W4384157063 hasConcept C41895202 @default.
- W4384157063 hasConcept C59404180 @default.
- W4384157063 hasConcept C94625758 @default.
- W4384157063 hasConceptScore W4384157063C111472728 @default.
- W4384157063 hasConceptScore W4384157063C114466953 @default.
- W4384157063 hasConceptScore W4384157063C119857082 @default.
- W4384157063 hasConceptScore W4384157063C127162648 @default.
- W4384157063 hasConceptScore W4384157063C127313418 @default.
- W4384157063 hasConceptScore W4384157063C138885662 @default.
- W4384157063 hasConceptScore W4384157063C150899416 @default.
- W4384157063 hasConceptScore W4384157063C153180895 @default.
- W4384157063 hasConceptScore W4384157063C154945302 @default.
- W4384157063 hasConceptScore W4384157063C162324750 @default.