FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4364352458> ?p ?o ?g. }

• W4364352458 abstract "Abstract We introduce a reinforcement learning (RL) environment to design and benchmark control strategies aimed at reducing drag in turbulent fluid flows enclosed in a channel. The environment provides a framework for computationally efficient, parallelized, high-fidelity fluid simulations, ready to interface with established RL agent programming interfaces. This allows for both testing existing deep reinforcement learning (DRL) algorithms against a challenging task, and advancing our knowledge of a complex, turbulent physical system that has been a major topic of research for over two centuries, and remains, even today, the subject of many unanswered questions. The control is applied in the form of blowing and suction at the wall, while the observable state is configurable, allowing to choose different variables such as velocity and pressure, in different locations of the domain. Given the complex nonlinear nature of turbulent flows, the control strategies proposed so far in the literature are physically grounded, but too simple. DRL, by contrast, enables leveraging the high-dimensional data that can be sampled from flow simulations to design advanced control strategies. In an effort to establish a benchmark for testing data-driven control strategies, we compare opposition control, a state-of-the-art turbulence-control strategy from the literature, and a commonly used DRL algorithm, deep deterministic policy gradient. Our results show that DRL leads to 43% and 30% drag reduction in a minimal and a larger channel (at a friction Reynolds number of 180), respectively, outperforming the classical opposition control by around 20 and 10 percentage points, respectively." @default.
• W4364352458 created "2023-04-12" @default.
• W4364352458 creator A5001997189 @default.
• W4364352458 creator A5011614712 @default.
• W4364352458 creator A5049616413 @default.
• W4364352458 creator A5063892805 @default.
• W4364352458 creator A5071284506 @default.
• W4364352458 date "2023-04-01" @default.
• W4364352458 modified "2023-10-16" @default.
• W4364352458 title "Deep reinforcement learning for turbulent drag reduction in channel flows" @default.
• W4364352458 cites W1570245886 @default.
• W4364352458 cites W1954793758 @default.
• W4364352458 cites W1964321515 @default.
• W4364352458 cites W1973445304 @default.
• W4364352458 cites W2003331893 @default.
• W4364352458 cites W2006653321 @default.
• W4364352458 cites W2038889042 @default.
• W4364352458 cites W2042457194 @default.
• W4364352458 cites W2051729320 @default.
• W4364352458 cites W2060687937 @default.
• W4364352458 cites W2070003964 @default.
• W4364352458 cites W2091931764 @default.
• W4364352458 cites W2100239359 @default.
• W4364352458 cites W2111828743 @default.
• W4364352458 cites W2171731011 @default.
• W4364352458 cites W2546700740 @default.
• W4364352458 cites W2888317899 @default.
• W4364352458 cites W2902480423 @default.
• W4364352458 cites W2963604378 @default.
• W4364352458 cites W2964027982 @default.
• W4364352458 cites W2967095864 @default.
• W4364352458 cites W2995200295 @default.
• W4364352458 cites W3009818618 @default.
• W4364352458 cites W3021135564 @default.
• W4364352458 cites W3022840352 @default.
• W4364352458 cites W3035733053 @default.
• W4364352458 cites W3045905724 @default.
• W4364352458 cites W3090502885 @default.
• W4364352458 cites W3100363258 @default.
• W4364352458 cites W3102566396 @default.
• W4364352458 cites W3105438996 @default.
• W4364352458 cites W3118391542 @default.
• W4364352458 cites W3120515765 @default.
• W4364352458 cites W3135144629 @default.
• W4364352458 cites W3137253052 @default.
• W4364352458 cites W3158115046 @default.
• W4364352458 cites W3161200675 @default.
• W4364352458 cites W3164727289 @default.
• W4364352458 cites W3172576596 @default.
• W4364352458 cites W3173085845 @default.
• W4364352458 cites W3185689115 @default.
• W4364352458 cites W3197659304 @default.
• W4364352458 cites W3201717768 @default.
• W4364352458 cites W3206302539 @default.
• W4364352458 cites W3208290324 @default.
• W4364352458 cites W4213377513 @default.
• W4364352458 cites W4221143781 @default.
• W4364352458 cites W4225377386 @default.
• W4364352458 cites W4225471971 @default.
• W4364352458 cites W4281890315 @default.
• W4364352458 cites W4286909924 @default.
• W4364352458 cites W4308733186 @default.
• W4364352458 cites W4311528211 @default.
• W4364352458 cites W4364380586 @default.
• W4364352458 cites W4381704851 @default.
• W4364352458 cites W764422886 @default.
• W4364352458 doi "https://doi.org/10.1140/epje/s10189-023-00285-8" @default.
• W4364352458 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37039923" @default.
• W4364352458 hasPublicationYear "2023" @default.
• W4364352458 type Work @default.
• W4364352458 citedByCount "9" @default.
• W4364352458 countsByYear W43643524582022 @default.
• W4364352458 countsByYear W43643524582023 @default.
• W4364352458 crossrefType "journal-article" @default.
• W4364352458 hasAuthorship W4364352458A5001997189 @default.
• W4364352458 hasAuthorship W4364352458A5011614712 @default.
• W4364352458 hasAuthorship W4364352458A5049616413 @default.
• W4364352458 hasAuthorship W4364352458A5063892805 @default.
• W4364352458 hasAuthorship W4364352458A5071284506 @default.
• W4364352458 hasBestOaLocation W43643524581 @default.
• W4364352458 hasConcept C121332964 @default.
• W4364352458 hasConcept C13280743 @default.
• W4364352458 hasConcept C154945302 @default.
• W4364352458 hasConcept C182748727 @default.
• W4364352458 hasConcept C185798385 @default.
• W4364352458 hasConcept C186766456 @default.
• W4364352458 hasConcept C196558001 @default.
• W4364352458 hasConcept C205649164 @default.
• W4364352458 hasConcept C2775924081 @default.
• W4364352458 hasConcept C31258907 @default.
• W4364352458 hasConcept C41008148 @default.
• W4364352458 hasConcept C47446073 @default.
• W4364352458 hasConcept C57879066 @default.
• W4364352458 hasConcept C72921944 @default.
• W4364352458 hasConcept C97541855 @default.
• W4364352458 hasConceptScore W4364352458C121332964 @default.
• W4364352458 hasConceptScore W4364352458C13280743 @default.
• W4364352458 hasConceptScore W4364352458C154945302 @default.
• W4364352458 hasConceptScore W4364352458C182748727 @default.
• W4364352458 hasConceptScore W4364352458C185798385 @default.

• next