On a validation split of NASA's CMAPSS FD001 data, a two-layer bidirectional LSTM with dropout predicts remaining useful life with RMSE 26.68, with no official test set evaluation.
Degradation modeling and remaining useful life prediction of aircraft engines using ensemble learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Turbofan Engine Remaining Useful Life (RUL) Prediction Based on Bi-Directional Long Short-Term Memory (BLSTM)
On a validation split of NASA's CMAPSS FD001 data, a two-layer bidirectional LSTM with dropout predicts remaining useful life with RMSE 26.68, with no official test set evaluation.