Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a hybrid CNN-BiLSTM-Attention model for Remaining Useful Life (RUL) prediction of turbofan engines, designed to capture both spatial correlations and temporal dependencies in sensor data. To address the safety-critical nature of RUL prediction, the model is trained with an asymmetric exponential loss function that heavily penalizes over-estimation of remaining life. Evaluated on the NASA C-MAPSS FD001 dataset, the model achieves a RMSE of 17.52 cycles and generates interpretable attention weight heatmaps highlighting the progression of engine degradation.
Penalizing over-optimistic Remaining Useful Life (RUL) predictions with an asymmetric loss function yields safer and more reliable industrial prognostics.
Turbofan engine degradation under sustained operational stress necessitates robust prognostic systems capable of accurately estimating the Remaining Useful Life (RUL) of critical components. Existing deep learning approaches frequently fail to simultaneously capture multi-sensor spatial correlations and long-range temporal dependencies, while standard symmetric loss functions inadequately penalize the safety-critical error of over-estimating residual life. This study proposes a hybrid architecture integrating Twin-Stage One-Dimensional Convolutional Neural Networks (1D-CNN), a Bidirectional Long Short-Term Memory (BiLSTM) network, and a custom Bahdanau Additive Attention mechanism. The model was trained and evaluated on the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) FD001 sub-dataset employing a zero-leakage preprocessing pipeline, piecewise-linear RUL labeling capped at 130 cycles, and the NASA-specified asymmetric exponential loss function that disproportionately penalizes over-estimation to enforce industrial safety constraints. Experiments on 100 test engines achieved a Root Mean Squared Error (RMSE) of 17.52 cycles and a NASA S-Score of 922.06. Furthermore, extracted attention weight heatmaps provide interpretable, per-engine insights into the temporal progression of degradation, supporting informed maintenance decision-making. The proposed framework demonstrates competitive performance against established baselines and offers a principled approach to safe, interpretable prognostics in industrial settings.