The study demonstrates that combining CNN–LSTM with an appropriate optimization strategy improves the reliability and accuracy of RUL prediction for turbofan engines and shows that Stochastic Gradient Descent provides the best convergence behaviour and prediction accuracy for the proposed architecture.
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.
Experimental results demonstrate that the hybrid architecture consistently outperforms the standalone TCN and Reservoir components, as well as other benchmark methods, achieving substantially improved PHM scores while retaining competitive RMSE performance.
Mahika Annie Verghese, C. Columbus, E. Elakiya· Scientific Reports· 0 citations
A two-level stacking ensemble framework for Remaining Useful Life prediction of turbofan engines, evaluated on the NASA C-MAPSS benchmark using the FD001 and FD003 subsets, demonstrates the efficacy of stacking ensemble methods for prognostics and health management in safety-critical aerospace applications.
Limon Bin Hossain, Md. Salehin Seyam, Md. Rashedul Islam et al.· 0 citations
To improve the operational readiness of combat aircraft engines and reduce unplanned maintenance costs, accurately estimating the remaining useful life (RUL) is critical. Traditional maintenance often proves insufficient under dynamic mission profiles. In this study, a deep learning-based predictive maintenance model capable of autonomously extracting features from multivariate sensor data was developed. Using the NASA C-MAPSS FD001 and FD004 datasets, data were converted into sequential blocks via 50- and 30-step sliding windows, respectively. The model's architectural superiority in autonomously extracting temporal degradation features was validated against RF, CNN-LSTM, and BiLSTM baselines. On FD001, it achieved an R-squared (R2) of 0.8901, a 13.28 RMSE, and a 320.34 NASA risk score, demonstrating generalizability on the multi-regime FD004 dataset with a 15.71 RMSE. The proposed maintenance protocol achieved a 0.9973 AUC at the critical 30-cycle threshold, ensuring high reliability. Additionally, a decision-support simulator has been developed to validate this protocol under aggressive combat flight profiles.
Remaining useful life (RUL) prediction of the gears is essential for the health management and predictive maintenance of planetary gear transmissions (PGTs), which are widely used in aero engines, helicopters, and wind turbines. However, due to run-to-failure data are usually limited, existing models still face challenges in accurately characterizing gear degradation trends under different fault modes. Deep learning (DL) algorithms have become effective tools for RUL prediction, but their performance is highly dependent on the selection of appropriate hyper-parameters. To address these issues, this paper proposes a hybrid convolutional neural network and bidirectional long short-term memory neural network (CNN-BiLSTM) model for predicting the RUL of the sun gear in a PGT. The pelican optimization algorithm (POA) is introduced to automatically optimize the key parameters of the CNN-BiLSTM model, thereby reducing the dependence on manual tuning. A run-to-failure experiment with four accelerometer channels was conducted to obtain vibration data from a planetary gearbox. The results show that the proposed POA-CNN-BiLSTM model achieves accurate RUL prediction, and its prediction performance is improved by optimizing the number of hidden units, initial learning rate, and regularization parameters through POA.
He Dai, Shuyu Wang, Shunan Luo et al.· IEEE Access· 0 citations
The proposed CNN-BiLSTM model consistently outperforms CNN, DCNN, RNN, and BiLSTM approaches in terms of RMSE and MAE, providing more accurate and robust prediction results for aeroengine systems operating under complex degradation conditions.
Q. Zhang, X. J. Yang, S. H. Zhu et al.· Advanced Electromagnetics· 0 citations
Remaining Useful Life (RUL) prediction for turbofan engines plays a vital role in predictive maintenance, ensuring operational safety and efficiency in aviation. Although data-driven approaches using machine learning and deep learning have shown potential, they face challenges such as limited data and distribution shifts caused by varying operating conditions. Domain Adaptation (DA) has emerged as a promising solution, enabling knowledge transfer from source domains with abundant data to target domains with scarce data while mitigating distributional shifts. Given the unique properties of turbofan engines-such as complex operating conditions, high-dimensional sensor data, and slower-changing signals-it is essential to conduct a focused review of DA techniques specifically tailored to turbofan engines. To address this need, this paper provides a comprehensive review of DA solutions for turbofan engine RUL prediction, analyzing key methodologies, challenges, and recent advancements. A novel taxonomy tailored to turbofan engines is introduced, organizing approaches into methodology-based (how DA is applied), alignment-based (where distributional shifts occur due to operational variations), and problem-based (why certain adaptations are needed to address specific challenges). This taxonomy offers a multidimensional view that goes beyond traditional classifications by accounting for the distinctive characteristics of turbofan engine data and the standard process of applying DA techniques to this area. Additionally, we evaluate selected DA techniques on turbofan engine datasets, providing practical insights for practitioners and identifying key challenges. Future research directions are identified to guide the development of more effective DA techniques, advancing the state of RUL prediction for turbofan engines.
Yucheng Wang, Mohamed Ragab, Yubo Hou et al.· IEEE/CAA Journal of Automati...· 4 citations