TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines
Sensors · 13.01.2025 · 25 (2) · 432
DOI: 10.3390/s25020432 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.01.2025. Verfasst von Zhaofei Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, China. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program of China, Artificial Intelligence Key Laboratory of Sichuan Province, Nature Science Foundation of Sichuan University of Science & Engineering.
Abstract (Originalsprache)
Accurately predicting the remaining useful life (RUL) is crucial for ensuring the safety and reliability of aircraft engine operation. However, aircraft engines operate in harsh conditions, with the characteristics of high speed, high temperature, and high load, resulting in high-dimensional and noisy data. This makes feature extraction inadequate, leading to low accuracy in the prediction of the RUL of aircraft engines. To address this issue, Transformer-TCN-Self-attention network (TTSNet) with feature fusion, as a parallel three-branch network, is proposed for predicting the RUL of aircraft engines. The model first applies exponential smoothing to smooth the data and suppress noise to the original signal, followed by normalization. Then, it uses a parallel transformer encoder, temporal convolutional network (TCN), and multi-head attention three-branch network to capture both global and local features of the time series. The model further completes feature dimension weight allocation and fusion through a multi-head self-attention mechanism, emphasizing the contribution of different features to the model. Subsequently, it fuses the three parts of features through a linear layer and concatenation. Finally, a fully connected layer is used to establish the mapping relationship between the feature matrix and the RUL label, obtaining the RUL prediction value. The model was validated on the C-MAPSS aircraft engine dataset. Experimental results show that compared to other related RUL models, the RMSE and Score reached 11.02 and 194.6 on dataset FD001, respectively; on dataset FD002, the RMSE and Score reached 13.25 and 874.1, respectively. On dataset FD003, the RMSE and Score reached 11.06 and 200.1 and on dataset FD004, the RMSE and Score reached 18.26 and 1968.5, respectively, demonstrating better performance of RUL prediction.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, China.
- Key Laboratory of Artificial Intelligence of Sichuan Province, Yibin 644000, China.
- School of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.
ORCID-Profile: Zhaofei Li
Förderung
- Sichuan Science and Technology Program of China
- Artificial Intelligence Key Laboratory of Sichuan Province
- Nature Science Foundation of Sichuan University of Science & Engineering
- Innovation Foundation Project of postgraduate of Sichuan University of Science & Engineering
- Nature Science Foundation of Sichuan University of Science & Engineering
- Fund for Innovation Foundation Project of Postgraduate of Sichuan University of Science & Engineering
Zitieren
APA
Li, Z., Luo, S., Liu, H., Tang, C., & Miao, J. (2025). TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines. Sensors, 25(2), 432. https://doi.org/10.3390/s25020432
Vancouver
Li Z, Luo S, Liu H, Tang C, Miao J. TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines. Sensors. 2025;25(2):432. doi:10.3390/s25020432
BibTeX
@article{Li2025,
author = {Li, Zhaofei and Luo, Shilin and Liu, Haiqing and Tang, Chaobin and Miao, Jianguo},
title = {TTSNet: Transformer–Temporal Convolutional Network–Self-Attention with Feature Fusion for Prediction of Remaining Useful Life of Aircraft Engines},
journal = {Sensors},
year = {2025},
volume = {25},
number = {2},
pages = {432},
doi = {10.3390/s25020432}
}
EUVIMED