Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384472178> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4384472178 endingPage "106651" @default.
- W4384472178 startingPage "106651" @default.
- W4384472178 abstract "Detecting series arcing faults in the electrical networks of aircraft can help mitigate dramatic consequences such as fires. Non-Artificial Intelligence algorithms often fail to generalise due to arc fault signals diversity. Most methods in the detection literature use multiple pre-processing (descriptors) associated to a machine learning model (or deep learning). These approaches require to handcraft the descriptors. We propose a deep learning approach without descriptors. We adapted a sequence-based model called a Transformer Neural Network (TNN) model to this time series problem. We repurposed the encoder of the transformer as a sequence-to-sequence model. The model takes as an input a window of electric current, with at least one period of the signals (800 Hz). The output is the label of each point in the input window. This required to propose an original manner of labelling the signals, for which we designed an automated algorithm, increasing the training supervision. Contrary to existing models on aircraft signals, our TNN model has been verified using a public experimental database of electrical-arc signals that simulates aircraft signals (230 V AC at 400−800 Hz, arcs in series with resistive loads). Our model obtained an identification accuracy of 96.3% at a 2% false positive rate. One of the significant performance of our model is that it has the lowest parameter number (2266) that can be found in scientific literature by quite some margin. TNNs are therefore an appropriate candidate for the purpose of arc fault detection, and our labelling method provides a very high temporal resolution of the output." @default.
- W4384472178 created "2023-07-17" @default.
- W4384472178 creator A5031657878 @default.
- W4384472178 creator A5039436711 @default.
- W4384472178 creator A5052908434 @default.
- W4384472178 creator A5056431886 @default.
- W4384472178 creator A5064328258 @default.
- W4384472178 date "2023-10-01" @default.
- W4384472178 modified "2023-10-06" @default.
- W4384472178 title "A Transformer Neural Network For AC series arc-fault detection" @default.
- W4384472178 cites W1977209575 @default.
- W4384472178 cites W2050386590 @default.
- W4384472178 cites W2557908743 @default.
- W4384472178 cites W2607235040 @default.
- W4384472178 cites W2616665904 @default.
- W4384472178 cites W2792870038 @default.
- W4384472178 cites W2800598202 @default.
- W4384472178 cites W2903738303 @default.
- W4384472178 cites W2947617058 @default.
- W4384472178 cites W2998423323 @default.
- W4384472178 cites W3004668108 @default.
- W4384472178 cites W3011528740 @default.
- W4384472178 cites W3082299565 @default.
- W4384472178 cites W3090166999 @default.
- W4384472178 cites W3115118039 @default.
- W4384472178 cites W3144184193 @default.
- W4384472178 cites W3170516065 @default.
- W4384472178 cites W3177367985 @default.
- W4384472178 cites W3209387760 @default.
- W4384472178 cites W4205819167 @default.
- W4384472178 cites W4220821900 @default.
- W4384472178 cites W4296473538 @default.
- W4384472178 cites W4296640344 @default.
- W4384472178 doi "https://doi.org/10.1016/j.engappai.2023.106651" @default.
- W4384472178 hasPublicationYear "2023" @default.
- W4384472178 type Work @default.
- W4384472178 citedByCount "0" @default.
- W4384472178 crossrefType "journal-article" @default.
- W4384472178 hasAuthorship W4384472178A5031657878 @default.
- W4384472178 hasAuthorship W4384472178A5039436711 @default.
- W4384472178 hasAuthorship W4384472178A5052908434 @default.
- W4384472178 hasAuthorship W4384472178A5056431886 @default.
- W4384472178 hasAuthorship W4384472178A5064328258 @default.
- W4384472178 hasConcept C111919701 @default.
- W4384472178 hasConcept C118505674 @default.
- W4384472178 hasConcept C119599485 @default.
- W4384472178 hasConcept C119857082 @default.
- W4384472178 hasConcept C127413603 @default.
- W4384472178 hasConcept C153180895 @default.
- W4384472178 hasConcept C154945302 @default.
- W4384472178 hasConcept C165801399 @default.
- W4384472178 hasConcept C41008148 @default.
- W4384472178 hasConcept C50644808 @default.
- W4384472178 hasConcept C66322947 @default.
- W4384472178 hasConcept C774472 @default.
- W4384472178 hasConceptScore W4384472178C111919701 @default.
- W4384472178 hasConceptScore W4384472178C118505674 @default.
- W4384472178 hasConceptScore W4384472178C119599485 @default.
- W4384472178 hasConceptScore W4384472178C119857082 @default.
- W4384472178 hasConceptScore W4384472178C127413603 @default.
- W4384472178 hasConceptScore W4384472178C153180895 @default.
- W4384472178 hasConceptScore W4384472178C154945302 @default.
- W4384472178 hasConceptScore W4384472178C165801399 @default.
- W4384472178 hasConceptScore W4384472178C41008148 @default.
- W4384472178 hasConceptScore W4384472178C50644808 @default.
- W4384472178 hasConceptScore W4384472178C66322947 @default.
- W4384472178 hasConceptScore W4384472178C774472 @default.
- W4384472178 hasFunder F4320332999 @default.
- W4384472178 hasFunder F4320335254 @default.
- W4384472178 hasLocation W43844721781 @default.
- W4384472178 hasOpenAccess W4384472178 @default.
- W4384472178 hasPrimaryLocation W43844721781 @default.
- W4384472178 hasRelatedWork W2275988210 @default.
- W4384472178 hasRelatedWork W2385621972 @default.
- W4384472178 hasRelatedWork W2961085424 @default.
- W4384472178 hasRelatedWork W3046775127 @default.
- W4384472178 hasRelatedWork W3161911362 @default.
- W4384472178 hasRelatedWork W4285260836 @default.
- W4384472178 hasRelatedWork W4286629047 @default.
- W4384472178 hasRelatedWork W4306321456 @default.
- W4384472178 hasRelatedWork W4306674287 @default.
- W4384472178 hasRelatedWork W4224009465 @default.
- W4384472178 hasVolume "125" @default.
- W4384472178 isParatext "false" @default.
- W4384472178 isRetracted "false" @default.
- W4384472178 workType "article" @default.