Add rbfelm.py, implementing two new surrogate models for fluid field interpolation across non-matching meshes:
-
RBFELM: A single Radial Basis Function augmented Extreme Learning Machine that maps spatial coordinates to field quantities (e.g. pressure coefficient). Supports configurable RBF center sampling and local/global gamma estimation.
-
MultiRBFELM: An ensemble of local RBFELM models for large-scale problems where a single model is computationally unfeasible. Partitions the input domain via MiniBatchKMeans and trains one model per cluster, with overlap zones at cluster boundaries and inverse-distance blending at inference to ensure continuity across interfaces.
Add
rbfelm.py, implementing two new surrogate models for fluid field interpolation across non-matching meshes:RBFELM: A single Radial Basis Function augmented Extreme Learning Machine that maps spatial coordinates to field quantities (e.g. pressure coefficient). Supports configurable RBF center sampling and local/global gamma estimation.MultiRBFELM: An ensemble of localRBFELMmodels for large-scale problems where a single model is computationally unfeasible. Partitions the input domain via MiniBatchKMeans and trains one model per cluster, with overlap zones at cluster boundaries and inverse-distance blending at inference to ensure continuity across interfaces.