Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210573603> ?p ?o ?g. }
- W4210573603 endingPage "117467" @default.
- W4210573603 startingPage "117467" @default.
- W4210573603 abstract "Deep learning is attracting widespread attention in the field of chemical process fault diagnosis recently. However, most deep learning methods are based on supervised learning and heavily rely on labeled data, with massive unlabeled data underutilized. Moreover, these supervised deep learning methods are uninterpretable and cannot facilitate fault localization, which is necessary for supervising the process back to normal. In this study, long short-term memory (LSTM) is used to extract temporal features and ladder autoencoder (LAE) is adopted for semi-supervised learning. Combining LSTM and LAE, LSTM-LAE is innovatively proposed to effectively utilize unlabeled data, with fault diagnosis performance largely improved. Moreover, LSTM-LAE achieves the interpretability to extract fault-relevant process variables with its elaborately designed internal features. When applied on a continuous stirred tank heater and the benchmark Tennessee Eastman process, LSTM-LAE exhibited a state-of-the-art fault diagnosis performance and localized faults to their relevant variables correctly." @default.
- W4210573603 created "2022-02-08" @default.
- W4210573603 creator A5048761975 @default.
- W4210573603 creator A5056293693 @default.
- W4210573603 date "2022-04-01" @default.
- W4210573603 modified "2023-10-14" @default.
- W4210573603 title "Semi-supervised LSTM ladder autoencoder for chemical process fault diagnosis and localization" @default.
- W4210573603 cites W1955857676 @default.
- W4210573603 cites W1970537494 @default.
- W4210573603 cites W1991519797 @default.
- W4210573603 cites W2019928639 @default.
- W4210573603 cites W2025768430 @default.
- W4210573603 cites W2062274641 @default.
- W4210573603 cites W2064675550 @default.
- W4210573603 cites W2084327162 @default.
- W4210573603 cites W2093598546 @default.
- W4210573603 cites W2145114096 @default.
- W4210573603 cites W2303531378 @default.
- W4210573603 cites W2336795703 @default.
- W4210573603 cites W2516800775 @default.
- W4210573603 cites W2767346351 @default.
- W4210573603 cites W2794081072 @default.
- W4210573603 cites W2796942168 @default.
- W4210573603 cites W2889351375 @default.
- W4210573603 cites W2896266079 @default.
- W4210573603 cites W2905523020 @default.
- W4210573603 cites W2915656323 @default.
- W4210573603 cites W2919115771 @default.
- W4210573603 cites W2972206279 @default.
- W4210573603 cites W2995524811 @default.
- W4210573603 cites W2997718270 @default.
- W4210573603 cites W3001599259 @default.
- W4210573603 cites W3017785036 @default.
- W4210573603 cites W3042633774 @default.
- W4210573603 cites W3047165957 @default.
- W4210573603 doi "https://doi.org/10.1016/j.ces.2022.117467" @default.
- W4210573603 hasPublicationYear "2022" @default.
- W4210573603 type Work @default.
- W4210573603 citedByCount "20" @default.
- W4210573603 countsByYear W42105736032022 @default.
- W4210573603 countsByYear W42105736032023 @default.
- W4210573603 crossrefType "journal-article" @default.
- W4210573603 hasAuthorship W4210573603A5048761975 @default.
- W4210573603 hasAuthorship W4210573603A5056293693 @default.
- W4210573603 hasConcept C101738243 @default.
- W4210573603 hasConcept C108583219 @default.
- W4210573603 hasConcept C111919701 @default.
- W4210573603 hasConcept C119857082 @default.
- W4210573603 hasConcept C127313418 @default.
- W4210573603 hasConcept C13280743 @default.
- W4210573603 hasConcept C136389625 @default.
- W4210573603 hasConcept C152745839 @default.
- W4210573603 hasConcept C153180895 @default.
- W4210573603 hasConcept C154945302 @default.
- W4210573603 hasConcept C165205528 @default.
- W4210573603 hasConcept C172707124 @default.
- W4210573603 hasConcept C175551986 @default.
- W4210573603 hasConcept C185798385 @default.
- W4210573603 hasConcept C202444582 @default.
- W4210573603 hasConcept C205649164 @default.
- W4210573603 hasConcept C2781067378 @default.
- W4210573603 hasConcept C33923547 @default.
- W4210573603 hasConcept C41008148 @default.
- W4210573603 hasConcept C50644808 @default.
- W4210573603 hasConcept C9652623 @default.
- W4210573603 hasConcept C98045186 @default.
- W4210573603 hasConceptScore W4210573603C101738243 @default.
- W4210573603 hasConceptScore W4210573603C108583219 @default.
- W4210573603 hasConceptScore W4210573603C111919701 @default.
- W4210573603 hasConceptScore W4210573603C119857082 @default.
- W4210573603 hasConceptScore W4210573603C127313418 @default.
- W4210573603 hasConceptScore W4210573603C13280743 @default.
- W4210573603 hasConceptScore W4210573603C136389625 @default.
- W4210573603 hasConceptScore W4210573603C152745839 @default.
- W4210573603 hasConceptScore W4210573603C153180895 @default.
- W4210573603 hasConceptScore W4210573603C154945302 @default.
- W4210573603 hasConceptScore W4210573603C165205528 @default.
- W4210573603 hasConceptScore W4210573603C172707124 @default.
- W4210573603 hasConceptScore W4210573603C175551986 @default.
- W4210573603 hasConceptScore W4210573603C185798385 @default.
- W4210573603 hasConceptScore W4210573603C202444582 @default.
- W4210573603 hasConceptScore W4210573603C205649164 @default.
- W4210573603 hasConceptScore W4210573603C2781067378 @default.
- W4210573603 hasConceptScore W4210573603C33923547 @default.
- W4210573603 hasConceptScore W4210573603C41008148 @default.
- W4210573603 hasConceptScore W4210573603C50644808 @default.
- W4210573603 hasConceptScore W4210573603C9652623 @default.
- W4210573603 hasConceptScore W4210573603C98045186 @default.
- W4210573603 hasFunder F4320321001 @default.
- W4210573603 hasFunder F4320321540 @default.
- W4210573603 hasLocation W42105736031 @default.
- W4210573603 hasOpenAccess W4210573603 @default.
- W4210573603 hasPrimaryLocation W42105736031 @default.
- W4210573603 hasRelatedWork W2605281151 @default.
- W4210573603 hasRelatedWork W3006943036 @default.
- W4210573603 hasRelatedWork W3191046242 @default.
- W4210573603 hasRelatedWork W3208423683 @default.
- W4210573603 hasRelatedWork W4206493799 @default.