MMGUNet morphs coarse graph hierarchies with feature-aligned barycentric mapping and uses masked pretraining plus frozen edge layers to improve generalisability of mesh surrogates for crashworthiness prediction under large geometric changes.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Formulates active learning sample acquisition for surrogate model-based reliability analysis as multi-objective optimization yielding a Pareto set, with adaptive selection rules that show robust performance across tested limit-state functions.
A neural surrogate trained on a clinically-derived virtual cohort enables real-time hemodynamic prediction and cardiac output estimation while rejecting non-physiological parameter sets.
Hybrid mesh GNNs with geometry-aware attention achieve 3.20 mm temporal RMSE on a 25-sample full-vehicle lateral pole-impact test set while preserving interpretable displacement fields.
citing papers explorer
-
Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation
MMGUNet morphs coarse graph hierarchies with feature-aligned barycentric mapping and uses masked pretraining plus frozen edge layers to improve generalisability of mesh surrogates for crashworthiness prediction under large geometric changes.
-
Balancing the exploration-exploitation trade-off in active learning for surrogate model-based reliability analysis via multi-objective optimization
Formulates active learning sample acquisition for surrogate model-based reliability analysis as multi-objective optimization yielding a Pareto set, with adaptive selection rules that show robust performance across tested limit-state functions.
-
Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis
A neural surrogate trained on a clinically-derived virtual cohort enables real-time hemodynamic prediction and cardiac output estimation while rejecting non-physiological parameter sets.
-
Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention
Hybrid mesh GNNs with geometry-aware attention achieve 3.20 mm temporal RMSE on a 25-sample full-vehicle lateral pole-impact test set while preserving interpretable displacement fields.