Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328125448> ?p ?o ?g. }
- W4328125448 endingPage "147592172311574" @default.
- W4328125448 startingPage "147592172311574" @default.
- W4328125448 abstract "Multisource domain adaptation (MDA) methods have been preliminarily applied in cross-domain fault diagnosis of rotating system due to its correlation ability between different but related fields. However, it still remains challenging to learn domain-invariant representations under multisource scenarios. This article proposes a multi-representation symbolic convolutional neural network (MR-SCNN) for multisource cross-domain fault diagnosis of rotating system. The novelty of our work lies in three aspects. First, the proposed method combines symbolic dynamics with CNN to obtain a coarse-grained description of vibration signals, which could eliminate the negative transfer caused by subtle changes in dynamic characteristics among different source domains. Second, considering that most MDA methods ignore the significant limitations brought by statistical properties of the specific working condition, a multi-representation Softmax (MR-Softmax) is developed to learn domain-invariant discriminative representations by allowing the diversity of the predictions of samples with the same label. In addition, an undifferentiated adversarial training strategies is proposed to narrow the domain discrepancies and reasonably assess the residual negative transfer risk of different source domains. Based on the assessment, confidence coeffients are defined and embedded into MR-Softmax to extract and utilize the useful diagnostic knowledge on each source domain. Compared with several state-of-the-art diagnostic models, the experimental results confirm the validation of the proposed MR-SCNN method." @default.
- W4328125448 created "2023-03-22" @default.
- W4328125448 creator A5012400248 @default.
- W4328125448 creator A5053781798 @default.
- W4328125448 creator A5058896326 @default.
- W4328125448 creator A5064733309 @default.
- W4328125448 date "2023-03-21" @default.
- W4328125448 modified "2023-09-27" @default.
- W4328125448 title "Multi-representation symbolic convolutional neural network: a novel multisource cross-domain fault diagnosis method for rotating system" @default.
- W4328125448 cites W1987029079 @default.
- W4328125448 cites W2164943005 @default.
- W4328125448 cites W2315868700 @default.
- W4328125448 cites W2568819930 @default.
- W4328125448 cites W2582662555 @default.
- W4328125448 cites W2798149494 @default.
- W4328125448 cites W2887782657 @default.
- W4328125448 cites W2904209271 @default.
- W4328125448 cites W2906578288 @default.
- W4328125448 cites W2939535241 @default.
- W4328125448 cites W2963506806 @default.
- W4328125448 cites W2969736276 @default.
- W4328125448 cites W2980113592 @default.
- W4328125448 cites W2997724457 @default.
- W4328125448 cites W3021632667 @default.
- W4328125448 cites W3034878846 @default.
- W4328125448 cites W3040883240 @default.
- W4328125448 cites W3082883578 @default.
- W4328125448 cites W3083358932 @default.
- W4328125448 cites W3089183752 @default.
- W4328125448 cites W3110006982 @default.
- W4328125448 cites W3137795735 @default.
- W4328125448 cites W3141070438 @default.
- W4328125448 cites W3184777843 @default.
- W4328125448 cites W4223985943 @default.
- W4328125448 cites W4252103803 @default.
- W4328125448 doi "https://doi.org/10.1177/14759217231157487" @default.
- W4328125448 hasPublicationYear "2023" @default.
- W4328125448 type Work @default.
- W4328125448 citedByCount "0" @default.
- W4328125448 crossrefType "journal-article" @default.
- W4328125448 hasAuthorship W4328125448A5012400248 @default.
- W4328125448 hasAuthorship W4328125448A5053781798 @default.
- W4328125448 hasAuthorship W4328125448A5058896326 @default.
- W4328125448 hasAuthorship W4328125448A5064733309 @default.
- W4328125448 hasConcept C119857082 @default.
- W4328125448 hasConcept C127313418 @default.
- W4328125448 hasConcept C134306372 @default.
- W4328125448 hasConcept C153180895 @default.
- W4328125448 hasConcept C154945302 @default.
- W4328125448 hasConcept C165205528 @default.
- W4328125448 hasConcept C175551986 @default.
- W4328125448 hasConcept C17744445 @default.
- W4328125448 hasConcept C188441871 @default.
- W4328125448 hasConcept C190470478 @default.
- W4328125448 hasConcept C199539241 @default.
- W4328125448 hasConcept C2776359362 @default.
- W4328125448 hasConcept C33923547 @default.
- W4328125448 hasConcept C36503486 @default.
- W4328125448 hasConcept C37914503 @default.
- W4328125448 hasConcept C41008148 @default.
- W4328125448 hasConcept C81363708 @default.
- W4328125448 hasConcept C94625758 @default.
- W4328125448 hasConcept C95623464 @default.
- W4328125448 hasConcept C97931131 @default.
- W4328125448 hasConceptScore W4328125448C119857082 @default.
- W4328125448 hasConceptScore W4328125448C127313418 @default.
- W4328125448 hasConceptScore W4328125448C134306372 @default.
- W4328125448 hasConceptScore W4328125448C153180895 @default.
- W4328125448 hasConceptScore W4328125448C154945302 @default.
- W4328125448 hasConceptScore W4328125448C165205528 @default.
- W4328125448 hasConceptScore W4328125448C175551986 @default.
- W4328125448 hasConceptScore W4328125448C17744445 @default.
- W4328125448 hasConceptScore W4328125448C188441871 @default.
- W4328125448 hasConceptScore W4328125448C190470478 @default.
- W4328125448 hasConceptScore W4328125448C199539241 @default.
- W4328125448 hasConceptScore W4328125448C2776359362 @default.
- W4328125448 hasConceptScore W4328125448C33923547 @default.
- W4328125448 hasConceptScore W4328125448C36503486 @default.
- W4328125448 hasConceptScore W4328125448C37914503 @default.
- W4328125448 hasConceptScore W4328125448C41008148 @default.
- W4328125448 hasConceptScore W4328125448C81363708 @default.
- W4328125448 hasConceptScore W4328125448C94625758 @default.
- W4328125448 hasConceptScore W4328125448C95623464 @default.
- W4328125448 hasConceptScore W4328125448C97931131 @default.
- W4328125448 hasFunder F4320321001 @default.
- W4328125448 hasLocation W43281254481 @default.
- W4328125448 hasOpenAccess W4328125448 @default.
- W4328125448 hasPrimaryLocation W43281254481 @default.
- W4328125448 hasRelatedWork W2112343299 @default.
- W4328125448 hasRelatedWork W2518599539 @default.
- W4328125448 hasRelatedWork W2549125172 @default.
- W4328125448 hasRelatedWork W2743258233 @default.
- W4328125448 hasRelatedWork W2758063741 @default.
- W4328125448 hasRelatedWork W2807311372 @default.
- W4328125448 hasRelatedWork W2905846897 @default.
- W4328125448 hasRelatedWork W2915159483 @default.
- W4328125448 hasRelatedWork W2977314777 @default.
- W4328125448 hasRelatedWork W4366723329 @default.