FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387204729> ?p ?o ?g. }

• W4387204729 endingPage "308" @default.
• W4387204729 startingPage "298" @default.
• W4387204729 abstract "Physics-informed neural networks (PINNs) have demonstrated effectiveness in solving partial differential equations (PDEs) associated with manufacturing scenarios, due to their physically interpretable training logic. One limitation has been that PINNs often exhibit heterogenous error maps and high-error “hot spots” throughout the solution domain, which reduce not only the solutions’ accuracy but also their overall consistency with the physical laws. This study addresses this limitation by presenting an efficient and error-aware PINN ensembling technique for error homogenization in solving manufacturing problems. Specifically, a PINN is first established by constraining its training process through a manufacturing specific PDE and corresponding boundary conditions to ensure physical consistency. Next, the loss landscape in the neighborhood of three PINNs trained with varying network parameter initialization is sampled to generate a PINN ensemble. Finally, the outputs of the ensemble members are combined through an inverse error-weighted average to yield the prediction of the PDE solution. Evaluation using the Allen-Cahn PDE, which describes phase separation in the solidification of metallic alloys, shows that the developed method reduces the average prediction error by 63% and error standard deviation by 30% across the solution space, demonstrating its effectiveness for PINN error reduction and homogenization. Additionally, the method has also demonstrated 96% reduction in the computational time as compared to conventional ensembling methods." @default.
• W4387204729 created "2023-09-30" @default.
• W4387204729 creator A5060566070 @default.
• W4387204729 creator A5075712660 @default.
• W4387204729 creator A5085982115 @default.
• W4387204729 date "2023-12-01" @default.
• W4387204729 modified "2023-10-14" @default.
• W4387204729 title "Error homogenization in physics-informed neural networks for modeling in manufacturing" @default.
• W4387204729 cites W1535833146 @default.
• W4387204729 cites W1965573563 @default.
• W4387204729 cites W1997841560 @default.
• W4387204729 cites W2007355286 @default.
• W4387204729 cites W2078236179 @default.
• W4387204729 cites W2782812883 @default.
• W4387204729 cites W2898606386 @default.
• W4387204729 cites W2899283552 @default.
• W4387204729 cites W2919115771 @default.
• W4387204729 cites W2995351224 @default.
• W4387204729 cites W2998366519 @default.
• W4387204729 cites W3014009018 @default.
• W4387204729 cites W3043941844 @default.
• W4387204729 cites W3086959365 @default.
• W4387204729 cites W3100714140 @default.
• W4387204729 cites W3137611682 @default.
• W4387204729 cites W3163993681 @default.
• W4387204729 cites W3164356889 @default.
• W4387204729 cites W3171849353 @default.
• W4387204729 cites W3191904496 @default.
• W4387204729 cites W3205172848 @default.
• W4387204729 cites W3216959350 @default.
• W4387204729 cites W4206716233 @default.
• W4387204729 cites W4210725851 @default.
• W4387204729 cites W4212883601 @default.
• W4387204729 cites W4247680473 @default.
• W4387204729 cites W4283814536 @default.
• W4387204729 cites W4309809248 @default.
• W4387204729 cites W4313551293 @default.
• W4387204729 cites W4315782922 @default.
• W4387204729 cites W4319869073 @default.
• W4387204729 cites W4321251611 @default.
• W4387204729 cites W4322743280 @default.
• W4387204729 doi "https://doi.org/10.1016/j.jmsy.2023.09.013" @default.
• W4387204729 hasPublicationYear "2023" @default.
• W4387204729 type Work @default.
• W4387204729 citedByCount "0" @default.
• W4387204729 crossrefType "journal-article" @default.
• W4387204729 hasAuthorship W4387204729A5060566070 @default.
• W4387204729 hasAuthorship W4387204729A5075712660 @default.
• W4387204729 hasAuthorship W4387204729A5085982115 @default.
• W4387204729 hasConcept C111335779 @default.
• W4387204729 hasConcept C11413529 @default.
• W4387204729 hasConcept C114466953 @default.
• W4387204729 hasConcept C126255220 @default.
• W4387204729 hasConcept C130217890 @default.
• W4387204729 hasConcept C134306372 @default.
• W4387204729 hasConcept C154945302 @default.
• W4387204729 hasConcept C182310444 @default.
• W4387204729 hasConcept C18903297 @default.
• W4387204729 hasConcept C199360897 @default.
• W4387204729 hasConcept C207467116 @default.
• W4387204729 hasConcept C2524010 @default.
• W4387204729 hasConcept C2778722038 @default.
• W4387204729 hasConcept C28826006 @default.
• W4387204729 hasConcept C33923547 @default.
• W4387204729 hasConcept C41008148 @default.
• W4387204729 hasConcept C50644808 @default.
• W4387204729 hasConcept C86803240 @default.
• W4387204729 hasConceptScore W4387204729C111335779 @default.
• W4387204729 hasConceptScore W4387204729C11413529 @default.
• W4387204729 hasConceptScore W4387204729C114466953 @default.
• W4387204729 hasConceptScore W4387204729C126255220 @default.
• W4387204729 hasConceptScore W4387204729C130217890 @default.
• W4387204729 hasConceptScore W4387204729C134306372 @default.
• W4387204729 hasConceptScore W4387204729C154945302 @default.
• W4387204729 hasConceptScore W4387204729C182310444 @default.
• W4387204729 hasConceptScore W4387204729C18903297 @default.
• W4387204729 hasConceptScore W4387204729C199360897 @default.
• W4387204729 hasConceptScore W4387204729C207467116 @default.
• W4387204729 hasConceptScore W4387204729C2524010 @default.
• W4387204729 hasConceptScore W4387204729C2778722038 @default.
• W4387204729 hasConceptScore W4387204729C28826006 @default.
• W4387204729 hasConceptScore W4387204729C33923547 @default.
• W4387204729 hasConceptScore W4387204729C41008148 @default.
• W4387204729 hasConceptScore W4387204729C50644808 @default.
• W4387204729 hasConceptScore W4387204729C86803240 @default.
• W4387204729 hasLocation W43872047291 @default.
• W4387204729 hasOpenAccess W4387204729 @default.
• W4387204729 hasPrimaryLocation W43872047291 @default.
• W4387204729 hasRelatedWork W2298446516 @default.
• W4387204729 hasRelatedWork W2352590024 @default.
• W4387204729 hasRelatedWork W2356364244 @default.
• W4387204729 hasRelatedWork W2368205053 @default.
• W4387204729 hasRelatedWork W2368370270 @default.
• W4387204729 hasRelatedWork W2374442885 @default.
• W4387204729 hasRelatedWork W2374512474 @default.
• W4387204729 hasRelatedWork W2386387936 @default.
• W4387204729 hasRelatedWork W4294079398 @default.
• W4387204729 hasRelatedWork W4316511403 @default.

• next