FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102735978> ?p ?o ?g. }

• W3102735978 endingPage "107174" @default.
• W3102735978 startingPage "107174" @default.
• W3102735978 abstract "Scenario-based model predictive control (MPC) methods introduce recourse into optimal control and can thus reduce the conservativeness inherent to open-loop robust MPC. However, the uncertainty scenarios are often generated offline using worst-case uncertainty bounds quantified a priori , limiting the potential gains in control performance. This paper presents a learning-based multistage MPC (msMPC) for systems with hard-to-model dynamics and time-varying plant-model mismatch. Gaussian Processes (GP) are used to learn state- and input-dependent plant-model mismatch in real-time and accordingly adapt the scenario tree online. Due to the increased computational complexity associated with incorporating the GP predictions into the optimal control problem, the learning-based msMPC (LB-msMPC) law is approximated by a deep neural network (DNN) that is cheap-to-evaluate online and has a small memory footprint, which makes it suitable for embedded applications. In addition, we present a novel algorithm for training the DNN-based controller that uses a GP description of the plant-model mismatch to generate closed-loop simulation data, which ensures the LB-msMPC law is evaluated in regions of the state space most relevant to closed-loop operation. The proposed LB-msMPC strategy is demonstrated on a cold atmospheric plasma jet with applications in (bio)materials processing. The simulation results indicate the promise of the approximate LB-msMPC strategy for control of hard-to-model systems with fast dynamics on millisecond timescales." @default.
• W3102735978 created "2020-11-23" @default.
• W3102735978 creator A5023086966 @default.
• W3102735978 creator A5025132089 @default.
• W3102735978 creator A5042465949 @default.
• W3102735978 creator A5073125136 @default.
• W3102735978 date "2021-02-01" @default.
• W3102735978 modified "2023-10-12" @default.
• W3102735978 title "Fast approximate learning-based multistage nonlinear model predictive control using Gaussian processes and deep neural networks" @default.
• W3102735978 cites W1970476229 @default.
• W3102735978 cites W1983916623 @default.
• W3102735978 cites W2006859604 @default.
• W3102735978 cites W2028332090 @default.
• W3102735978 cites W2034013221 @default.
• W3102735978 cites W2041806131 @default.
• W3102735978 cites W2045776966 @default.
• W3102735978 cites W2061757541 @default.
• W3102735978 cites W2067716288 @default.
• W3102735978 cites W2077365766 @default.
• W3102735978 cites W2095886698 @default.
• W3102735978 cites W2123871098 @default.
• W3102735978 cites W2136267489 @default.
• W3102735978 cites W2144884795 @default.
• W3102735978 cites W2151084831 @default.
• W3102735978 cites W2155482699 @default.
• W3102735978 cites W2162269500 @default.
• W3102735978 cites W2192203593 @default.
• W3102735978 cites W2273961865 @default.
• W3102735978 cites W2320868965 @default.
• W3102735978 cites W2413393233 @default.
• W3102735978 cites W2557055507 @default.
• W3102735978 cites W2724171116 @default.
• W3102735978 cites W2765557211 @default.
• W3102735978 cites W2769617651 @default.
• W3102735978 cites W2792380552 @default.
• W3102735978 cites W2842089854 @default.
• W3102735978 cites W2900806034 @default.
• W3102735978 cites W2901507551 @default.
• W3102735978 cites W2913907761 @default.
• W3102735978 cites W2951097493 @default.
• W3102735978 cites W2955319624 @default.
• W3102735978 cites W2955440934 @default.
• W3102735978 cites W3012550246 @default.
• W3102735978 cites W3101479673 @default.
• W3102735978 cites W3105252106 @default.
• W3102735978 cites W4211147054 @default.
• W3102735978 cites W2966383620 @default.
• W3102735978 doi "https://doi.org/10.1016/j.compchemeng.2020.107174" @default.
• W3102735978 hasPublicationYear "2021" @default.
• W3102735978 type Work @default.
• W3102735978 sameAs 3102735978 @default.
• W3102735978 citedByCount "30" @default.
• W3102735978 countsByYear W31027359782021 @default.
• W3102735978 countsByYear W31027359782022 @default.
• W3102735978 countsByYear W31027359782023 @default.
• W3102735978 crossrefType "journal-article" @default.
• W3102735978 hasAuthorship W3102735978A5023086966 @default.
• W3102735978 hasAuthorship W3102735978A5025132089 @default.
• W3102735978 hasAuthorship W3102735978A5042465949 @default.
• W3102735978 hasAuthorship W3102735978A5073125136 @default.
• W3102735978 hasBestOaLocation W31027359781 @default.
• W3102735978 hasConcept C108583219 @default.
• W3102735978 hasConcept C119857082 @default.
• W3102735978 hasConcept C121332964 @default.
• W3102735978 hasConcept C147597530 @default.
• W3102735978 hasConcept C154945302 @default.
• W3102735978 hasConcept C158622935 @default.
• W3102735978 hasConcept C163716315 @default.
• W3102735978 hasConcept C172205157 @default.
• W3102735978 hasConcept C185592680 @default.
• W3102735978 hasConcept C2775924081 @default.
• W3102735978 hasConcept C2984755018 @default.
• W3102735978 hasConcept C2984842247 @default.
• W3102735978 hasConcept C41008148 @default.
• W3102735978 hasConcept C47446073 @default.
• W3102735978 hasConcept C50644808 @default.
• W3102735978 hasConcept C61326573 @default.
• W3102735978 hasConcept C62520636 @default.
• W3102735978 hasConceptScore W3102735978C108583219 @default.
• W3102735978 hasConceptScore W3102735978C119857082 @default.
• W3102735978 hasConceptScore W3102735978C121332964 @default.
• W3102735978 hasConceptScore W3102735978C147597530 @default.
• W3102735978 hasConceptScore W3102735978C154945302 @default.
• W3102735978 hasConceptScore W3102735978C158622935 @default.
• W3102735978 hasConceptScore W3102735978C163716315 @default.
• W3102735978 hasConceptScore W3102735978C172205157 @default.
• W3102735978 hasConceptScore W3102735978C185592680 @default.
• W3102735978 hasConceptScore W3102735978C2775924081 @default.
• W3102735978 hasConceptScore W3102735978C2984755018 @default.
• W3102735978 hasConceptScore W3102735978C2984842247 @default.
• W3102735978 hasConceptScore W3102735978C41008148 @default.
• W3102735978 hasConceptScore W3102735978C47446073 @default.
• W3102735978 hasConceptScore W3102735978C50644808 @default.
• W3102735978 hasConceptScore W3102735978C61326573 @default.
• W3102735978 hasConceptScore W3102735978C62520636 @default.
• W3102735978 hasFunder F4320306076 @default.
• W3102735978 hasLocation W31027359781 @default.
• W3102735978 hasOpenAccess W3102735978 @default.

• next