Temporal-sequential modeling for remaining useful life estimation of turbofan engine

Abstract

Abstract Accurate prediction of Remaining Useful Life (RUL) is essential for predictive maintenance of turbofan engines, as it helps reduce unexpected failures and maintenance costs while improving system reliability. The objective of this study is to develop an accurate and robust deep learning framework for RUL prediction using multivariate time-series sensor data and to investigate the influence of different optimization algorithms on prediction performance. A hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model is proposed, where convolutional layers extract local degradation features and LSTM layers learn the long-term temporal relationships present in engine degradation data. A sliding-window strategy together with early RUL capping is employed to improve training stability and model generalization. The proposed model is evaluated on all four subsets (FD001–FD004) of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset and achieves RMSE values of 12.79, 21.94, 15.09, and 33.71, respectively. Among the evaluated subsets, the model delivers the best performance on FD001 and outperforms several existing deep learning approaches reported in the literature. In addition, five optimization algorithms are systematically compared under the same experimental settings. The results show that Stochastic Gradient Descent (SGD) provides the best convergence behaviour and prediction accuracy for the proposed architecture. Overall, the study demonstrates that combining CNN–LSTM with an appropriate optimization strategy improves the reliability and accuracy of RUL prediction for turbofan engines.