This study proposes a degradation-aware dynamic masking augmentation method combined with a multiscale CNN–Transformer network to address non-stationary monitoring data, limited informative degradation samples, and the difficulty of jointly modeling local degradation patterns and temporal dependencies.
Abstract
Accurate remaining useful life (RUL) prediction is essential for condition-based maintenance and safe aero-engine operation. To address non-stationary monitoring data, limited informative degradation samples, and the difficulty of jointly modeling local degradation patterns and temporal dependencies, this study proposes a degradation-aware dynamic masking augmentation method combined with a multiscale CNN–Transformer network. The 21 sensor variables in the NASA C-MAPSS dataset are first grouped by physical meaning and reconstructed into four-dimensional state features. A degradation-state score integrating local variance and trend slope is then used to adapt temporal masking probabilities across degradation stages, while feature masking probabilities are assigned according to feature importance. Masked positions are filled with adjacent unmasked observations, and invalid augmented samples are removed through trend consistency verification. A multiscale CNN with channel attention extracts local degradation features, and a Transformer encoder captures temporal dependencies. Bayesian optimization is used to determine key hyperparameters. On FD001, the proposed method achieves an MSE of 348.3970, an MAE of 8.3908, and an R2 of 0.9227, reducing MSE and MAE by 4.27% and 28.42%, respectively, compared with ML-RFR. It also achieves the highest R2 of 0.9369 on FD003. Cross-dataset and multi-seed experiments further confirm its applicability and stability.
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.
Rajneesh Kumar, Shivam Ojha, Amit Shelke et al.· Scientific Reports· 0 citations
Remaining useful life (RUL) prediction is critical for improving reliability and supporting predictive maintenance in aero-engine systems. However, existing methods have limitations in jointly modeling the spatial correlations between multi-sensor signals and the temporal evolution characteristics of the degradation process. Hence, this study develops a knowledge-enhanced spatiotemporal framework for system-level aero-engine RUL prediction. Firstly, a graph based on the Pearson correlation coefficient (PCC) is constructed from monitoring data to capture data-driven dependencies among sensors. Afterwards, a thermodynamic-cycle-mechanism prior is incorporated into the PCC-based graph through the Hadamard product, forming a knowledge-enhanced graph that emphasizes physically meaningful sensor relationships. Subsequently, an enhanced graph attention module is designed to extract discriminative spatial representations from the knowledge-enhanced graph. Furthermore, relational representations between adjacent time steps are constructed to capture implicit temporal correlations and local degradation dynamics. Finally, a dual-stream GRU with an attention mechanism is employed to model the fused feature stream and relational feature stream for RUL prediction. Experiments on the CMAPSS and N-CMAPSS datasets demonstrate that the proposed method achieves competitive and overall superior performance compared with nine state-of-the-art methods. KESTF achieves the best average RMSE/Score of 12.83/580 on CMAPSS and 5.94/3468 on N-CMAPSS, validating its effectiveness and robustness.
Shangyi Ren, Dayong Han, Zixiang Li et al.· Applied Sciences· 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
The accurate prediction of Remaining Useful Life (RUL) is fundamental to Prognostics and Health Management (PHM), enabling predictive maintenance and ensuring the operational safety of complex industrial systems. While deep learning models have demonstrated significant potential in RUL estimation, existing approaches often struggle with noisy sensor signals, inconsistent predictions across overlapping time windows, and a lack of explicit modeling for the underlying temporal structure of the degradation process. This paper proposes a novel multi-view temporal structure-aware learning framework to address these challenges. The framework introduces a multi-view temporal perturbation mechanism that generates multiple perspectives of the degradation state, coupled with a Transformer-based backbone to capture long-range dependencies. To enhance stability and physical rationality, we design a multi-view consistency regularization term and a temporal ordering constraint learning mechanism. These components ensure that the model produces stable predictions across temporal shifts and adheres to the inherent monotonic degradation patterns. Experimental evaluations conducted on the NASA C-MAPSS dataset demonstrate that the proposed method significantly improves prediction accuracy, stability, and structural consistency compared to state-of-the-art baselines.
Transfer learning plays a crucial role in remaining useful life (RUL) prediction for bearings under complex operating conditions and small-sample scenarios. However, existing methods still face challenges such as unstable initial degradation point (IDP) detection, negative transfer caused by feature distribution discrepancies between the source and target domains, and difficulty in selecting appropriate hyperparameters. To address these issues, this paper proposes a bearing RUL prediction method integrating online IDP detection with intelligent optimization transfer learning. First, an adaptive continuous exceedance method is developed to identify the IDP, reducing the interference from healthy-stage data. Second, based on the identified degradation information, a transfer prediction network combining multi-layer bidirectional long short-term memory and a convolutional residual network is constructed. It captures multi-scale temporal dependencies and enhances cross-domain feature transferability. In addition, a golden sine strategy and restart mechanism are incorporated into an intelligent optimization algorithm to optimize network hyperparameters, improving convergence efficiency and prediction performance. Experiments on the IEEE PHM2012 and XJTU-SY datasets validate the effectiveness of the proposed method. Under the small-sample cross-condition transfer setting, the proposed method achieves a minimum mean absolute error of 0.028 and root mean square error of 0.060 after hyperparameter optimization, demonstrating its effectiveness and generalization capability with limited target-domain run-to-failure data.
Tong-Shan Liu, Yiming Li, Zhi-Hao Hu et al.· Measurement science and tech...· 0 citations
Degradation process (DP) modeling is widely used for remaining useful life (RUL) prediction, particularly when run-to-failure data are limited. Neural networks can present complex degradation trajectories without prescribing a fixed degradation function; however, recursive health indicator (HI) forecasting is prone to error accumulation and may fail to preserve the irreversible degradation trend over long horizons. To address these limitations, this study proposes a local-global feature mixer (LGFM) and trend-guided rollout-consistent (TG-RC) loss. The LGFM combines the original HI sequence with statistical and degradation-related features to reduce sensitivity to high-frequency noise and capture both local changes and global degradation states. The TG-RC loss supplements the conventional one-step mean squared error with a recursive multi-step rollout loss and a soft dynamic time warping alignment term based on a global trend prior. Consequently, it reduces the discrepancy between training and recursive inference, while guiding the predicted trajectory toward a consistent degradation direction. Experiments on two public bearing datasets show that the proposed framework improves long-term HI extrapolation stability and RUL prediction performance across different inspection times. The LGFM also maintains low computational complexity, while the TG-RC loss can be incorporated into various DP models to improve their long-term forecasting performance.
Hanbyeol Park, Hyerim Bae· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
