FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210080612> ?p ?o ?g. }

• W3210080612 endingPage "597" @default.
• W3210080612 startingPage "581" @default.
• W3210080612 abstract "Industrial processes are becoming increasingly large and complex, thus introducing potential safety risks and requiring an effective approach to maintain safe production. Intelligent process monitoring is critical to prevent losses and avoid casualties in modern industry. As the digitalization of process industry deepens, data-driven methods offer an exciting avenue to address the demands for monitoring complex systems. Nevertheless, many of these methods still suffer from low accuracy and slow response. Besides, most black-box models based on deep learning can only predict the existence of faults, but cannot provide further interpretable analysis, which greatly confines their usage in decision-critical scenarios. In this paper, we propose a novel orthogonal self-attentive variational autoencoder (OSAVA) model for process monitoring, consisting of two components, orthogonal attention (OA) and variational self-attentive autoencoder (VSAE). Specifically, OA is utilized to extract the correlations between different variables and the temporal dependency among different timesteps; VSAE is trained to detect faults through a reconstruction-based method, which employs self-attention mechanisms to comprehensively consider information from all timesteps and enhance detection performance. By jointly leveraging these two models, the OSAVA model can effectively perform fault detection and identification tasks simultaneously and deliver interpretable results. Finally, extensive evaluation on the Tennessee Eastman process (TEP) demonstrates that the proposed OSAVA-based fault detection and identification method shows promising fault detection rate as well as low detection delay and can provide interpretable identification of the abnormal variables, compared with representative statistical methods and state-of-the-art deep learning methods." @default.
• W3210080612 created "2021-11-08" @default.
• W3210080612 creator A5050240108 @default.
• W3210080612 creator A5056055815 @default.
• W3210080612 date "2021-12-01" @default.
• W3210080612 modified "2023-10-14" @default.
• W3210080612 title "A novel orthogonal self-attentive variational autoencoder method for interpretable chemical process fault detection and identification" @default.
• W3210080612 cites W1837982956 @default.
• W3210080612 cites W1966863755 @default.
• W3210080612 cites W1969158915 @default.
• W3210080612 cites W1979357005 @default.
• W3210080612 cites W1985888716 @default.
• W3210080612 cites W1990283595 @default.
• W3210080612 cites W2004977422 @default.
• W3210080612 cites W2012714569 @default.
• W3210080612 cites W2026430219 @default.
• W3210080612 cites W2029747079 @default.
• W3210080612 cites W2036887017 @default.
• W3210080612 cites W2077791644 @default.
• W3210080612 cites W2099741732 @default.
• W3210080612 cites W2100495367 @default.
• W3210080612 cites W2120480077 @default.
• W3210080612 cites W2135663228 @default.
• W3210080612 cites W2143288231 @default.
• W3210080612 cites W2157331557 @default.
• W3210080612 cites W2169347809 @default.
• W3210080612 cites W2258764094 @default.
• W3210080612 cites W2322097696 @default.
• W3210080612 cites W2340289503 @default.
• W3210080612 cites W2470142083 @default.
• W3210080612 cites W2493697924 @default.
• W3210080612 cites W2523110291 @default.
• W3210080612 cites W2563202971 @default.
• W3210080612 cites W2583392637 @default.
• W3210080612 cites W2589808763 @default.
• W3210080612 cites W2739349903 @default.
• W3210080612 cites W2743138268 @default.
• W3210080612 cites W2757109865 @default.
• W3210080612 cites W2796942168 @default.
• W3210080612 cites W2804880936 @default.
• W3210080612 cites W2890474333 @default.
• W3210080612 cites W2896880393 @default.
• W3210080612 cites W2912345712 @default.
• W3210080612 cites W2914418209 @default.
• W3210080612 cites W2916182456 @default.
• W3210080612 cites W2924334974 @default.
• W3210080612 cites W2945532623 @default.
• W3210080612 cites W2950522612 @default.
• W3210080612 cites W2954948446 @default.
• W3210080612 cites W2963166639 @default.
• W3210080612 cites W2963357083 @default.
• W3210080612 cites W2963374347 @default.
• W3210080612 cites W2964245140 @default.
• W3210080612 cites W2989818023 @default.
• W3210080612 cites W3000665539 @default.
• W3210080612 cites W3001599259 @default.
• W3210080612 cites W3004121077 @default.
• W3210080612 cites W3008638899 @default.
• W3210080612 cites W3015937655 @default.
• W3210080612 cites W3015959599 @default.
• W3210080612 cites W3026997795 @default.
• W3210080612 cites W3031080090 @default.
• W3210080612 cites W3082718164 @default.
• W3210080612 cites W3090586341 @default.
• W3210080612 cites W3110939572 @default.
• W3210080612 cites W3119756647 @default.
• W3210080612 cites W3156528735 @default.
• W3210080612 cites W3156618009 @default.
• W3210080612 cites W3157456168 @default.
• W3210080612 cites W3163905744 @default.
• W3210080612 doi "https://doi.org/10.1016/j.psep.2021.10.036" @default.
• W3210080612 hasPublicationYear "2021" @default.
• W3210080612 type Work @default.
• W3210080612 sameAs 3210080612 @default.
• W3210080612 citedByCount "41" @default.
• W3210080612 countsByYear W32100806122022 @default.
• W3210080612 countsByYear W32100806122023 @default.
• W3210080612 crossrefType "journal-article" @default.
• W3210080612 hasAuthorship W3210080612A5050240108 @default.
• W3210080612 hasAuthorship W3210080612A5056055815 @default.
• W3210080612 hasConcept C101738243 @default.
• W3210080612 hasConcept C108583219 @default.
• W3210080612 hasConcept C111919701 @default.
• W3210080612 hasConcept C116834253 @default.
• W3210080612 hasConcept C119857082 @default.
• W3210080612 hasConcept C124101348 @default.
• W3210080612 hasConcept C127313418 @default.
• W3210080612 hasConcept C152745839 @default.
• W3210080612 hasConcept C153180895 @default.
• W3210080612 hasConcept C154945302 @default.
• W3210080612 hasConcept C165205528 @default.
• W3210080612 hasConcept C172707124 @default.
• W3210080612 hasConcept C175551986 @default.
• W3210080612 hasConcept C41008148 @default.
• W3210080612 hasConcept C59822182 @default.
• W3210080612 hasConcept C86803240 @default.
• W3210080612 hasConcept C94966114 @default.
• W3210080612 hasConcept C98045186 @default.

• next