MKDPINN combines Reptile-style meta-learning with a learned PDE regularizer and reports strong RUL predictions on C-MAPSS and industrial pumps, but the physics term is fitted rather than independently grounded.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction
MKDPINN combines Reptile-style meta-learning with a learned PDE regularizer and reports strong RUL predictions on C-MAPSS and industrial pumps, but the physics term is fitted rather than independently grounded.