FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362633747> ?p ?o ?g. }

• W4362633747 endingPage "121071" @default.
• W4362633747 startingPage "121071" @default.
• W4362633747 abstract "With more and more data being collected, data-driven modeling methods have been gaining in popularity in recent years. While physically sound, classical gray-box models are often cumbersome to identify and scale, and their accuracy might be hindered by their limited expressiveness. On the other hand, classical black-box methods, typically relying on Neural Networks (NNs) nowadays, often achieve impressive performance, even at scale, by deriving statistical patterns from data. However, they remain completely oblivious to the underlying physical laws, which may lead to potentially catastrophic failures if decisions for real-world physical systems are based on them. Physically Consistent Neural Networks (PCNNs) were recently developed to address these aforementioned issues, ensuring physical consistency while still leveraging NNs to attain state-of-the-art accuracy, and applied to zone temperature modeling. In this work, we scale PCNNs to model the temperature dynamics of buildings with several connected thermal zones and propose a thorough comparison with classical gray-box and black-box methods. More precisely, we design three distinct PCNN extensions with different levels of information sharing between the modeled zones, thereby exemplifying the modularity and flexibility of the architecture, and formally prove their physical consistency. In the presented case study, PCNNs are shown to achieve state-of-the-art accuracy, even outperforming classical NN-based models despite their constrained structure. Our investigations furthermore provide a clear illustration of NNs achieving seemingly good performance while remaining completely physics-agnostic, which can be misleading in practice. While this performance comes at the cost of computational complexity, PCNNs on the other hand show accuracy improvements of 17–35% compared to all other physically consistent methods, paving the way for scalable physically consistent models with state-of-the-art performance." @default.
• W4362633747 created "2023-04-07" @default.
• W4362633747 creator A5005151144 @default.
• W4362633747 creator A5056840318 @default.
• W4362633747 creator A5069545422 @default.
• W4362633747 creator A5085117832 @default.
• W4362633747 date "2023-06-01" @default.
• W4362633747 modified "2023-09-30" @default.
• W4362633747 title "Towards scalable physically consistent neural networks: An application to data-driven multi-zone thermal building models" @default.
• W4362633747 cites W1965345917 @default.
• W4362633747 cites W1997334587 @default.
• W4362633747 cites W2064860826 @default.
• W4362633747 cites W2108152153 @default.
• W4362633747 cites W2116341502 @default.
• W4362633747 cites W2164861471 @default.
• W4362633747 cites W2181523240 @default.
• W4362633747 cites W2291639396 @default.
• W4362633747 cites W2548560601 @default.
• W4362633747 cites W2592453717 @default.
• W4362633747 cites W2811374795 @default.
• W4362633747 cites W2899283552 @default.
• W4362633747 cites W2936343203 @default.
• W4362633747 cites W2947489409 @default.
• W4362633747 cites W2957897705 @default.
• W4362633747 cites W2964522134 @default.
• W4362633747 cites W2989354373 @default.
• W4362633747 cites W3000984364 @default.
• W4362633747 cites W3016970897 @default.
• W4362633747 cites W3033217105 @default.
• W4362633747 cites W3090789943 @default.
• W4362633747 cites W3106507514 @default.
• W4362633747 cites W3119095567 @default.
• W4362633747 cites W3148568426 @default.
• W4362633747 cites W3152331843 @default.
• W4362633747 cites W3156755729 @default.
• W4362633747 cites W3158049794 @default.
• W4362633747 cites W3163993681 @default.
• W4362633747 cites W3172213065 @default.
• W4362633747 cites W3205884499 @default.
• W4362633747 cites W3212810272 @default.
• W4362633747 cites W3217738881 @default.
• W4362633747 cites W4289767041 @default.
• W4362633747 cites W4292023839 @default.
• W4362633747 cites W4292551110 @default.
• W4362633747 cites W4292824450 @default.
• W4362633747 cites W4322766057 @default.
• W4362633747 doi "https://doi.org/10.1016/j.apenergy.2023.121071" @default.
• W4362633747 hasPublicationYear "2023" @default.
• W4362633747 type Work @default.
• W4362633747 citedByCount "0" @default.
• W4362633747 crossrefType "journal-article" @default.
• W4362633747 hasAuthorship W4362633747A5005151144 @default.
• W4362633747 hasAuthorship W4362633747A5056840318 @default.
• W4362633747 hasAuthorship W4362633747A5069545422 @default.
• W4362633747 hasAuthorship W4362633747A5085117832 @default.
• W4362633747 hasBestOaLocation W43626337471 @default.
• W4362633747 hasConcept C105795698 @default.
• W4362633747 hasConcept C119857082 @default.
• W4362633747 hasConcept C120314980 @default.
• W4362633747 hasConcept C121332964 @default.
• W4362633747 hasConcept C124101348 @default.
• W4362633747 hasConcept C154945302 @default.
• W4362633747 hasConcept C2776436953 @default.
• W4362633747 hasConcept C2778755073 @default.
• W4362633747 hasConcept C2779478453 @default.
• W4362633747 hasConcept C2780598303 @default.
• W4362633747 hasConcept C2984842247 @default.
• W4362633747 hasConcept C33923547 @default.
• W4362633747 hasConcept C41008148 @default.
• W4362633747 hasConcept C48044578 @default.
• W4362633747 hasConcept C50644808 @default.
• W4362633747 hasConcept C54355233 @default.
• W4362633747 hasConcept C62520636 @default.
• W4362633747 hasConcept C77088390 @default.
• W4362633747 hasConcept C86803240 @default.
• W4362633747 hasConcept C94966114 @default.
• W4362633747 hasConceptScore W4362633747C105795698 @default.
• W4362633747 hasConceptScore W4362633747C119857082 @default.
• W4362633747 hasConceptScore W4362633747C120314980 @default.
• W4362633747 hasConceptScore W4362633747C121332964 @default.
• W4362633747 hasConceptScore W4362633747C124101348 @default.
• W4362633747 hasConceptScore W4362633747C154945302 @default.
• W4362633747 hasConceptScore W4362633747C2776436953 @default.
• W4362633747 hasConceptScore W4362633747C2778755073 @default.
• W4362633747 hasConceptScore W4362633747C2779478453 @default.
• W4362633747 hasConceptScore W4362633747C2780598303 @default.
• W4362633747 hasConceptScore W4362633747C2984842247 @default.
• W4362633747 hasConceptScore W4362633747C33923547 @default.
• W4362633747 hasConceptScore W4362633747C41008148 @default.
• W4362633747 hasConceptScore W4362633747C48044578 @default.
• W4362633747 hasConceptScore W4362633747C50644808 @default.
• W4362633747 hasConceptScore W4362633747C54355233 @default.
• W4362633747 hasConceptScore W4362633747C62520636 @default.
• W4362633747 hasConceptScore W4362633747C77088390 @default.
• W4362633747 hasConceptScore W4362633747C86803240 @default.
• W4362633747 hasConceptScore W4362633747C94966114 @default.
• W4362633747 hasLocation W43626337471 @default.
• W4362633747 hasLocation W43626337472 @default.

• next