Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133445669> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3133445669 endingPage "287" @default.
- W3133445669 startingPage "275" @default.
- W3133445669 abstract "Machine learning modeling of chemical processes using noisy data is a practically challenging task due to the occurrence of overfitting during learning. In this work, we propose a dropout method and a co-teaching learning algorithm that develop long short-term memory (LSTM) neural networks to capture the ground truth (i.e., underlying process dynamics) from noisy data. To evaluate the performance and robustness of the proposed modeling approaches, we consider an industrial chemical reactor example and use a large-scale process simulator, Aspen Plus Dynamics that does not employ assumptions on reactor properties typically made in the derivation of first-principles models, to generate process operational data that are corrupted by sensor noise which is determined using industrial data. The dropout method is first utilized to reduce the overfitting of LSTM models to noisy data. Then, another approach termed co-teaching method is used to train LSTM models with additional noise-free data generated from simulations of the reactor first-principles model that employs several standard modeling assumptions not made in the Aspen model. Through open-loop and closed-loop simulations, we demonstrate the improvement of model prediction accuracy and of the open- and closed-loop performances under model predictive controllers using dropout and co-teaching LSTM neural network models compared to the LSTM model developed from the standard training process from the noisy data." @default.
- W3133445669 created "2021-03-01" @default.
- W3133445669 creator A5002367171 @default.
- W3133445669 creator A5013295212 @default.
- W3133445669 creator A5015091824 @default.
- W3133445669 creator A5065092309 @default.
- W3133445669 date "2021-04-01" @default.
- W3133445669 modified "2023-10-15" @default.
- W3133445669 title "Machine learning-based predictive control using noisy data: evaluating performance and robustness via a large-scale process simulator" @default.
- W3133445669 cites W1967511636 @default.
- W3133445669 cites W2000580046 @default.
- W3133445669 cites W2010348927 @default.
- W3133445669 cites W2061200912 @default.
- W3133445669 cites W2072425076 @default.
- W3133445669 cites W2097322982 @default.
- W3133445669 cites W2123871098 @default.
- W3133445669 cites W2144600834 @default.
- W3133445669 cites W2157153875 @default.
- W3133445669 cites W2326768527 @default.
- W3133445669 cites W2792397017 @default.
- W3133445669 cites W2948963925 @default.
- W3133445669 cites W2969424518 @default.
- W3133445669 cites W2996988779 @default.
- W3133445669 cites W3009955490 @default.
- W3133445669 cites W3022837682 @default.
- W3133445669 cites W3034202893 @default.
- W3133445669 cites W3043087654 @default.
- W3133445669 cites W3048643786 @default.
- W3133445669 doi "https://doi.org/10.1016/j.cherd.2021.02.011" @default.
- W3133445669 hasPublicationYear "2021" @default.
- W3133445669 type Work @default.
- W3133445669 sameAs 3133445669 @default.
- W3133445669 citedByCount "18" @default.
- W3133445669 countsByYear W31334456692021 @default.
- W3133445669 countsByYear W31334456692022 @default.
- W3133445669 countsByYear W31334456692023 @default.
- W3133445669 crossrefType "journal-article" @default.
- W3133445669 hasAuthorship W3133445669A5002367171 @default.
- W3133445669 hasAuthorship W3133445669A5013295212 @default.
- W3133445669 hasAuthorship W3133445669A5015091824 @default.
- W3133445669 hasAuthorship W3133445669A5065092309 @default.
- W3133445669 hasBestOaLocation W31334456691 @default.
- W3133445669 hasConcept C104317684 @default.
- W3133445669 hasConcept C111919701 @default.
- W3133445669 hasConcept C115961682 @default.
- W3133445669 hasConcept C119857082 @default.
- W3133445669 hasConcept C154945302 @default.
- W3133445669 hasConcept C185592680 @default.
- W3133445669 hasConcept C22019652 @default.
- W3133445669 hasConcept C2776145597 @default.
- W3133445669 hasConcept C2781170535 @default.
- W3133445669 hasConcept C41008148 @default.
- W3133445669 hasConcept C50644808 @default.
- W3133445669 hasConcept C55493867 @default.
- W3133445669 hasConcept C63479239 @default.
- W3133445669 hasConcept C67186912 @default.
- W3133445669 hasConcept C77088390 @default.
- W3133445669 hasConcept C98045186 @default.
- W3133445669 hasConcept C99498987 @default.
- W3133445669 hasConceptScore W3133445669C104317684 @default.
- W3133445669 hasConceptScore W3133445669C111919701 @default.
- W3133445669 hasConceptScore W3133445669C115961682 @default.
- W3133445669 hasConceptScore W3133445669C119857082 @default.
- W3133445669 hasConceptScore W3133445669C154945302 @default.
- W3133445669 hasConceptScore W3133445669C185592680 @default.
- W3133445669 hasConceptScore W3133445669C22019652 @default.
- W3133445669 hasConceptScore W3133445669C2776145597 @default.
- W3133445669 hasConceptScore W3133445669C2781170535 @default.
- W3133445669 hasConceptScore W3133445669C41008148 @default.
- W3133445669 hasConceptScore W3133445669C50644808 @default.
- W3133445669 hasConceptScore W3133445669C55493867 @default.
- W3133445669 hasConceptScore W3133445669C63479239 @default.
- W3133445669 hasConceptScore W3133445669C67186912 @default.
- W3133445669 hasConceptScore W3133445669C77088390 @default.
- W3133445669 hasConceptScore W3133445669C98045186 @default.
- W3133445669 hasConceptScore W3133445669C99498987 @default.
- W3133445669 hasFunder F4320306076 @default.
- W3133445669 hasFunder F4320306084 @default.
- W3133445669 hasLocation W31334456691 @default.
- W3133445669 hasLocation W31334456692 @default.
- W3133445669 hasOpenAccess W3133445669 @default.
- W3133445669 hasPrimaryLocation W31334456691 @default.
- W3133445669 hasRelatedWork W2781855238 @default.
- W3133445669 hasRelatedWork W2792147139 @default.
- W3133445669 hasRelatedWork W2897443685 @default.
- W3133445669 hasRelatedWork W2951100320 @default.
- W3133445669 hasRelatedWork W2998675825 @default.
- W3133445669 hasRelatedWork W3110700750 @default.
- W3133445669 hasRelatedWork W3128220493 @default.
- W3133445669 hasRelatedWork W4226354336 @default.
- W3133445669 hasRelatedWork W4298017035 @default.
- W3133445669 hasRelatedWork W4307654087 @default.
- W3133445669 hasVolume "168" @default.
- W3133445669 isParatext "false" @default.
- W3133445669 isRetracted "false" @default.
- W3133445669 magId "3133445669" @default.
- W3133445669 workType "article" @default.