FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313293844> ?p ?o ?g. }

• W4313293844 endingPage "115771" @default.
• W4313293844 startingPage "115771" @default.
• W4313293844 abstract "Repeatedly solving nonlinear partial differential equations with varying parameters is often an essential requirement to characterise the parametric dependences of dynamical systems. Reduced-order modelling (ROM) provides an economical way to construct low-dimensional parametric surrogates for rapid predictions of high-dimensional physical fields. This paper presents a physics-data combined machine learning (PDCML) method for non-intrusive parametric ROM in small-data regimes. Proper orthogonal decomposition (POD) is adopted for dimension reduction by deriving basis functions from a limited number of high-fidelity snapshots, and parametric ROM is thus transformed into establishing reliable mappings between the system parameters and the POD coefficients. To overcome labelled data scarcity, a physics-data combined ROM framework is developed to jointly integrate the physical principle and the small labelled data into feedforward neural networks (FNN) via a step-by-step training scheme. Specifically, a preliminary FNN model is firstly fitted via data-driven training, and then the governing physical rules are embedded into the loss function to improve the model interpolation and extrapolation performances through physics-guided training constrained by the labelled data. During the constrained optimisation procedure, dynamic weighting factors are used to adjust the physics-data proportion of the loss functions, aiming at continuously highlighting the physics loss as the primary optimisation objective and keeping the data loss as the constraint. This new PDCML method is tested on a series of nonlinear problems with different numbers of physical variables, and it is also compared with the data-driven ROM, the physics-guided ROM and the traditional projection-based ROM methods. The results demonstrate that the proposed method provides a cost-effective way for non-intrusive parametric ROM via machine learning, and it possesses good characteristics of high prediction accuracy, strong generalisation capability and small data requirement." @default.
• W4313293844 created "2023-01-06" @default.
• W4313293844 creator A5011102677 @default.
• W4313293844 creator A5052285573 @default.
• W4313293844 creator A5055950364 @default.
• W4313293844 creator A5072175564 @default.
• W4313293844 creator A5082362303 @default.
• W4313293844 creator A5085852399 @default.
• W4313293844 creator A5088565152 @default.
• W4313293844 date "2023-02-01" @default.
• W4313293844 modified "2023-09-25" @default.
• W4313293844 title "Physics-data combined machine learning for parametric reduced-order modelling of nonlinear dynamical systems in small-data regimes" @default.
• W4313293844 cites W1512642921 @default.
• W4313293844 cites W1562562553 @default.
• W4313293844 cites W1981554056 @default.
• W4313293844 cites W1987166016 @default.
• W4313293844 cites W2009000341 @default.
• W4313293844 cites W2027355161 @default.
• W4313293844 cites W2049753327 @default.
• W4313293844 cites W2066074607 @default.
• W4313293844 cites W2144538403 @default.
• W4313293844 cites W2145107531 @default.
• W4313293844 cites W2151549067 @default.
• W4313293844 cites W2152896489 @default.
• W4313293844 cites W2533529223 @default.
• W4313293844 cites W2552979726 @default.
• W4313293844 cites W2578000937 @default.
• W4313293844 cites W2746440938 @default.
• W4313293844 cites W2885397520 @default.
• W4313293844 cites W2899283552 @default.
• W4313293844 cites W2900769969 @default.
• W4313293844 cites W2901661213 @default.
• W4313293844 cites W2914208769 @default.
• W4313293844 cites W2948230027 @default.
• W4313293844 cites W2954760057 @default.
• W4313293844 cites W2987245967 @default.
• W4313293844 cites W2989594843 @default.
• W4313293844 cites W2998104826 @default.
• W4313293844 cites W3003922491 @default.
• W4313293844 cites W3013558159 @default.
• W4313293844 cites W3093605970 @default.
• W4313293844 cites W3095248049 @default.
• W4313293844 cites W3098680501 @default.
• W4313293844 cites W3100989476 @default.
• W4313293844 cites W3108700187 @default.
• W4313293844 cites W3137611682 @default.
• W4313293844 cites W3163993681 @default.
• W4313293844 cites W3176843930 @default.
• W4313293844 cites W3194202055 @default.
• W4313293844 cites W3209503845 @default.
• W4313293844 cites W4376453679 @default.
• W4313293844 doi "https://doi.org/10.1016/j.cma.2022.115771" @default.
• W4313293844 hasPublicationYear "2023" @default.
• W4313293844 type Work @default.
• W4313293844 citedByCount "6" @default.
• W4313293844 countsByYear W43132938442023 @default.
• W4313293844 crossrefType "journal-article" @default.
• W4313293844 hasAuthorship W4313293844A5011102677 @default.
• W4313293844 hasAuthorship W4313293844A5052285573 @default.
• W4313293844 hasAuthorship W4313293844A5055950364 @default.
• W4313293844 hasAuthorship W4313293844A5072175564 @default.
• W4313293844 hasAuthorship W4313293844A5082362303 @default.
• W4313293844 hasAuthorship W4313293844A5085852399 @default.
• W4313293844 hasAuthorship W4313293844A5088565152 @default.
• W4313293844 hasConcept C104114177 @default.
• W4313293844 hasConcept C105795698 @default.
• W4313293844 hasConcept C11413529 @default.
• W4313293844 hasConcept C116672817 @default.
• W4313293844 hasConcept C117251300 @default.
• W4313293844 hasConcept C119857082 @default.
• W4313293844 hasConcept C121332964 @default.
• W4313293844 hasConcept C132459708 @default.
• W4313293844 hasConcept C134306372 @default.
• W4313293844 hasConcept C137800194 @default.
• W4313293844 hasConcept C154945302 @default.
• W4313293844 hasConcept C158622935 @default.
• W4313293844 hasConcept C183115368 @default.
• W4313293844 hasConcept C202444582 @default.
• W4313293844 hasConcept C24890656 @default.
• W4313293844 hasConcept C33676613 @default.
• W4313293844 hasConcept C33923547 @default.
• W4313293844 hasConcept C41008148 @default.
• W4313293844 hasConcept C50644808 @default.
• W4313293844 hasConcept C62520636 @default.
• W4313293844 hasConcept C70518039 @default.
• W4313293844 hasConceptScore W4313293844C104114177 @default.
• W4313293844 hasConceptScore W4313293844C105795698 @default.
• W4313293844 hasConceptScore W4313293844C11413529 @default.
• W4313293844 hasConceptScore W4313293844C116672817 @default.
• W4313293844 hasConceptScore W4313293844C117251300 @default.
• W4313293844 hasConceptScore W4313293844C119857082 @default.
• W4313293844 hasConceptScore W4313293844C121332964 @default.
• W4313293844 hasConceptScore W4313293844C132459708 @default.
• W4313293844 hasConceptScore W4313293844C134306372 @default.
• W4313293844 hasConceptScore W4313293844C137800194 @default.
• W4313293844 hasConceptScore W4313293844C154945302 @default.
• W4313293844 hasConceptScore W4313293844C158622935 @default.
• W4313293844 hasConceptScore W4313293844C183115368 @default.

• next