Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209020960> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3209020960 endingPage "43" @default.
- W3209020960 startingPage "38" @default.
- W3209020960 abstract "Fault-tolerant industrial systems need effective fault detection, which we can treat as a classification problem based on the observable system properties. Artificial neural networks (ANN) are provenly strong contenders in this field, capable of supervised learning from experience. They operate with large amounts of data, which we need to prepare and use carefully. This paper explores how different temporal data quantities provided to a long short-term memory network affect its performance and fault detection delay. The case study for this research was the Tennessee Eastman Process data. Test results indicate that networks detect faults best when given the full-length time series data, regardless of the data shape during training. On the downside, the longer the time series, the more delayed the recognition of a possible fault. The systematic approach in feeding the ANN with specific amounts of data revealed a potential overfitting problem of an otherwise perfect classifier." @default.
- W3209020960 created "2021-11-08" @default.
- W3209020960 creator A5018415753 @default.
- W3209020960 creator A5040866728 @default.
- W3209020960 creator A5048108516 @default.
- W3209020960 date "2021-01-01" @default.
- W3209020960 modified "2023-10-14" @default.
- W3209020960 title "On Data Windows for Fault Detection with Neural Networks" @default.
- W3209020960 cites W1988301066 @default.
- W3209020960 cites W2004186751 @default.
- W3209020960 cites W2008616192 @default.
- W3209020960 cites W2076063813 @default.
- W3209020960 cites W2122538988 @default.
- W3209020960 cites W2897745724 @default.
- W3209020960 cites W2953560522 @default.
- W3209020960 cites W2981386789 @default.
- W3209020960 cites W2985882047 @default.
- W3209020960 doi "https://doi.org/10.1016/j.ifacol.2021.10.007" @default.
- W3209020960 hasPublicationYear "2021" @default.
- W3209020960 type Work @default.
- W3209020960 sameAs 3209020960 @default.
- W3209020960 citedByCount "0" @default.
- W3209020960 crossrefType "journal-article" @default.
- W3209020960 hasAuthorship W3209020960A5018415753 @default.
- W3209020960 hasAuthorship W3209020960A5040866728 @default.
- W3209020960 hasAuthorship W3209020960A5048108516 @default.
- W3209020960 hasBestOaLocation W32090209601 @default.
- W3209020960 hasConcept C119857082 @default.
- W3209020960 hasConcept C124101348 @default.
- W3209020960 hasConcept C127313418 @default.
- W3209020960 hasConcept C152745839 @default.
- W3209020960 hasConcept C153180895 @default.
- W3209020960 hasConcept C154945302 @default.
- W3209020960 hasConcept C165205528 @default.
- W3209020960 hasConcept C172707124 @default.
- W3209020960 hasConcept C175551986 @default.
- W3209020960 hasConcept C22019652 @default.
- W3209020960 hasConcept C41008148 @default.
- W3209020960 hasConcept C50644808 @default.
- W3209020960 hasConcept C95623464 @default.
- W3209020960 hasConceptScore W3209020960C119857082 @default.
- W3209020960 hasConceptScore W3209020960C124101348 @default.
- W3209020960 hasConceptScore W3209020960C127313418 @default.
- W3209020960 hasConceptScore W3209020960C152745839 @default.
- W3209020960 hasConceptScore W3209020960C153180895 @default.
- W3209020960 hasConceptScore W3209020960C154945302 @default.
- W3209020960 hasConceptScore W3209020960C165205528 @default.
- W3209020960 hasConceptScore W3209020960C172707124 @default.
- W3209020960 hasConceptScore W3209020960C175551986 @default.
- W3209020960 hasConceptScore W3209020960C22019652 @default.
- W3209020960 hasConceptScore W3209020960C41008148 @default.
- W3209020960 hasConceptScore W3209020960C50644808 @default.
- W3209020960 hasConceptScore W3209020960C95623464 @default.
- W3209020960 hasIssue "4" @default.
- W3209020960 hasLocation W32090209601 @default.
- W3209020960 hasOpenAccess W3209020960 @default.
- W3209020960 hasPrimaryLocation W32090209601 @default.
- W3209020960 hasRelatedWork W1996541855 @default.
- W3209020960 hasRelatedWork W2961085424 @default.
- W3209020960 hasRelatedWork W2985459377 @default.
- W3209020960 hasRelatedWork W2989932438 @default.
- W3209020960 hasRelatedWork W3099765033 @default.
- W3209020960 hasRelatedWork W3128220493 @default.
- W3209020960 hasRelatedWork W3175189414 @default.
- W3209020960 hasRelatedWork W3206592002 @default.
- W3209020960 hasRelatedWork W4210794429 @default.
- W3209020960 hasRelatedWork W4317528991 @default.
- W3209020960 hasVolume "54" @default.
- W3209020960 isParatext "false" @default.
- W3209020960 isRetracted "false" @default.
- W3209020960 magId "3209020960" @default.
- W3209020960 workType "article" @default.