A Deep Learning-Based Stacking Ensemble Framework for Turbofan Engine Remaining Useful Life Prediction
Authors: Limon Bin Hossain, Md. Salehin Seyam, Md Rashedul Islam, Abdur Rahman, Md Sharifuzzaman
Organizations: Department of Industrial and Production Engineering Bangladesh University of Engineering and Technology Dhaka 1000, Bangladesh · Department of Industrial Engineering Clemson University Clemson, SC, USA · College of Engineering and Science Louisiana Tech University Ruston, LA 71270, USA · School of Engineering Technology Purdue Polytechnic Institute, Purdue University West Lafayette, IN, USA
This study proposes a two-level stacking ensemble framework for Remaining Useful Life (RUL) prediction of turbofan engines, evaluated on the NASA C-MAPSS benchmark using the FD001 and FD003 subsets. The framework integrates four heterogeneous deep learning base learners: Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), CNN-LSTM, and CNN-GRU, whose out-of-fold predictions are combined by an XGBoost meta-learner to capture complex degradation patterns while mitigating individual model biases. Comprehensive experiments demonstrate that the stacking ensemble achieves superior predictive performance, with Root Mean Square Error (RMSE) of 9.989 and 8.613, Mean Absolute Error (MAE) of 7.081 and 5.195, and R-squared values of 0.899 and 0.906 for FD001 and FD003, respectively. Compared to the best-reported baseline (TCAT: RMSE 11.12 and 11.02), the proposed method achieves RMSE reductions of 10.2 percent and 21.8 percent for FD001 and FD003, respectively. Feature correlation analysis, residual diagnostics, and training convergence curves validate the model's robustness. These findings underscore the efficacy of stacking ensemble methods for prognostics and health management in safety-critical aerospace applications.
Figures & tables
Property
FD001
FD002
FD003
FD004
Training Engines
100
260
100
249
Test Engines
100
259
100
248
Training Samples
17,731
48,558
21,120
56,815
Test Samples
100
259
100
248
Max Cycle (Train)
362
378
525
543
Min Cycle (Train)
128
128
145
128
TABLE I: Structural statistics of the NASA C-MAPSS benchmark subsets
Methodology
FD001
FD003
RMSE
MAE
R 2
RMSE
MAE
R 2
Simple Ageing Model [ 18 ]
16.79
–
–
17.48
–
–
PILmin-maxregret [ 19 ]
15.11
–
–
16.99
–
–
CNN-LSTM-Attention [ 10 ]
15.977
–
–
13.907
–
–
k-LSTM-GFT [ 16 ]
13.10
–
–
11.27
–
–
TCAT [ 12 ]
11.12
–
–
11.02
–
–
TABLE II: Comparison of RUL Prediction Performance on FD001 and FD003 Datasets
Model
RMSE
MAE
R 2
Dataset: FD001
LSTM
12.93
9.657
0.831
CNN
14.986
11.268
0.773
CNN-LSTM
13.968
11.162
0.802
CNN-GRU
13.071
10.121
0.827
Stacking Ensemble
9.989
7.081
0.899
TABLE III: Performance Metrics for Baseline and Proposed Models
Fig. 1: Correlation heatmap for the FD001 subset.
Fig. 2: Correlation heatmap for the FD003 subset.
Fig. 3: Actual vs. predicted RUL for FD001 and FD003.
Fig. 4: Residual analysis of the stacking ensemble predictions.
Fig. 5: Training convergence curves of the stacking ensemble.
Fig. 6: Performance comparison across all evaluated models.