Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199293824> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3199293824 abstract "The rapid and accurate prediction of residual stresses in metal additive manufacturing (3D printing) processes is crucial to ensuring defect-free fabrication of parts used in critical industrial applications. This paper presents promising outcomes from applying attention-based neural architectures for predicting such 3D stress phenomena accurately, efficiently, and reliably. This capability is critical to drastically reducing the design maturation time for additively manufactured parts. High fidelity, physics-based numerical models of the additive melting process exist that can simulate the thermal gradients and consequent stresses produced during manufacturing, which can then be used to synthesize a 3D crack index field for the entire part volume, capturing the likelihood that a region in a part will crack upon heat treatment. However, these models are expensive and time-consuming to run. In response, a Deep Convolutional Neural Network (DCNN) model is explored as a surrogate for the physics-based model, so that it can be used to time-efficiently estimate the crack index for a given part-design. This requires careful design of the training regime and dataset for a given design problem. Using the U-Net architecture as the baseline, we expand the standard 2D application of this architecture for segmentation to the estimation of the full 3D, continuous valued, stress field. We illustrate the primary challenge faced by the standard U-Net architecture with L2-loss arising from sparsity in critical values of the crack index and show how augmenting the architecture with attention mechanisms helps address the issue as well as improve the overall accuracy of estimation." @default.
- W3199293824 created "2021-09-27" @default.
- W3199293824 creator A5010965630 @default.
- W3199293824 creator A5048817987 @default.
- W3199293824 creator A5049635458 @default.
- W3199293824 creator A5058857045 @default.
- W3199293824 creator A5084889876 @default.
- W3199293824 date "2021-01-01" @default.
- W3199293824 modified "2023-09-24" @default.
- W3199293824 title "Attention-Based 3D Neural Architectures for Predicting Cracks in Designs" @default.
- W3199293824 cites W1901129140 @default.
- W3199293824 cites W2098459033 @default.
- W3199293824 cites W2279780730 @default.
- W3199293824 cites W2464708700 @default.
- W3199293824 cites W2762367303 @default.
- W3199293824 cites W2785071288 @default.
- W3199293824 cites W2790662084 @default.
- W3199293824 cites W2888358068 @default.
- W3199293824 cites W2914830398 @default.
- W3199293824 cites W2956046114 @default.
- W3199293824 cites W2962914239 @default.
- W3199293824 cites W2963351448 @default.
- W3199293824 cites W2972429586 @default.
- W3199293824 cites W3127451557 @default.
- W3199293824 doi "https://doi.org/10.1007/978-3-030-86362-3_15" @default.
- W3199293824 hasPublicationYear "2021" @default.
- W3199293824 type Work @default.
- W3199293824 sameAs 3199293824 @default.
- W3199293824 citedByCount "0" @default.
- W3199293824 crossrefType "book-chapter" @default.
- W3199293824 hasAuthorship W3199293824A5010965630 @default.
- W3199293824 hasAuthorship W3199293824A5048817987 @default.
- W3199293824 hasAuthorship W3199293824A5049635458 @default.
- W3199293824 hasAuthorship W3199293824A5058857045 @default.
- W3199293824 hasAuthorship W3199293824A5084889876 @default.
- W3199293824 hasConcept C111919701 @default.
- W3199293824 hasConcept C113775141 @default.
- W3199293824 hasConcept C123657996 @default.
- W3199293824 hasConcept C142362112 @default.
- W3199293824 hasConcept C153349607 @default.
- W3199293824 hasConcept C154945302 @default.
- W3199293824 hasConcept C159985019 @default.
- W3199293824 hasConcept C192562407 @default.
- W3199293824 hasConcept C202444582 @default.
- W3199293824 hasConcept C33923547 @default.
- W3199293824 hasConcept C37292000 @default.
- W3199293824 hasConcept C41008148 @default.
- W3199293824 hasConcept C50644808 @default.
- W3199293824 hasConcept C81363708 @default.
- W3199293824 hasConcept C9652623 @default.
- W3199293824 hasConcept C98045186 @default.
- W3199293824 hasConceptScore W3199293824C111919701 @default.
- W3199293824 hasConceptScore W3199293824C113775141 @default.
- W3199293824 hasConceptScore W3199293824C123657996 @default.
- W3199293824 hasConceptScore W3199293824C142362112 @default.
- W3199293824 hasConceptScore W3199293824C153349607 @default.
- W3199293824 hasConceptScore W3199293824C154945302 @default.
- W3199293824 hasConceptScore W3199293824C159985019 @default.
- W3199293824 hasConceptScore W3199293824C192562407 @default.
- W3199293824 hasConceptScore W3199293824C202444582 @default.
- W3199293824 hasConceptScore W3199293824C33923547 @default.
- W3199293824 hasConceptScore W3199293824C37292000 @default.
- W3199293824 hasConceptScore W3199293824C41008148 @default.
- W3199293824 hasConceptScore W3199293824C50644808 @default.
- W3199293824 hasConceptScore W3199293824C81363708 @default.
- W3199293824 hasConceptScore W3199293824C9652623 @default.
- W3199293824 hasConceptScore W3199293824C98045186 @default.
- W3199293824 hasLocation W31992938241 @default.
- W3199293824 hasOpenAccess W3199293824 @default.
- W3199293824 hasPrimaryLocation W31992938241 @default.
- W3199293824 hasRelatedWork W115308 @default.
- W3199293824 hasRelatedWork W11853729 @default.
- W3199293824 hasRelatedWork W1678066 @default.
- W3199293824 hasRelatedWork W2235786 @default.
- W3199293824 hasRelatedWork W4235637 @default.
- W3199293824 hasRelatedWork W5053695 @default.
- W3199293824 hasRelatedWork W8261117 @default.
- W3199293824 hasRelatedWork W8821115 @default.
- W3199293824 hasRelatedWork W9190101 @default.
- W3199293824 hasRelatedWork W9321062 @default.
- W3199293824 isParatext "false" @default.
- W3199293824 isRetracted "false" @default.
- W3199293824 magId "3199293824" @default.
- W3199293824 workType "book-chapter" @default.