EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Residual Self-Attention-Based Temporal Deep Model for Predicting Aircraft Engine Failure within a Specific Cycle

Tong Zhou, Guojun Zhang, Yiqun Cai

Optimizations in Applied Machine Learning · 2023

DOI: 10.71070/oaml.v3i1.75 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optimizations in Applied Machine Learning, 2023. Verfasst von Tong Zhou und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aircraft engines are complex, high-performance machines operating under extreme conditions, where reliability is critical for aviation safety. Early detection of engine faults is essential not only to ensure passenger safety but also to reduce operational costs and maintain efficient flight schedules. Traditional fault detection methods rely on rule-based diagnostics, setting predetermined thresholds for engine parameters such as temperature and pressure. However, these methods are limited in accuracy and often fail to capture the intricate degradation patterns of engine components, leading to late fault detection and frequent false alarms. Recent advancements in machine learning, particularly in deep learning, offer promising alternatives. Machine learning models can analyze large-scale time-series data and recognize complex patterns that human expertise might overlook. Among these, Long Short-Term Memory (LSTM) networks, combined with self-attention mechanisms, have shown potential in capturing temporal dependencies crucial for predictive maintenance. This study proposes a Residual Self-Attention-based LSTM model for predicting aircraft engine failures. By integrating residual connections with self-attention, the model enhances pattern recognition and interpretability, offering improved fault prediction accuracy over traditional models. The model was trained on aircraft engine sensor data, achieving high performance across various metrics, suggesting that this architecture holds significant promise for proactive aircraft maintenance applications.

Zitieren

APA

Zhou, T., Zhang, G., & Cai, Y. (2023). Residual Self-Attention-Based Temporal Deep Model for Predicting Aircraft Engine Failure within a Specific Cycle. Optimizations in Applied Machine Learning. https://doi.org/10.71070/oaml.v3i1.75

Vancouver

Zhou T, Zhang G, Cai Y. Residual Self-Attention-Based Temporal Deep Model for Predicting Aircraft Engine Failure within a Specific Cycle. Optimizations in Applied Machine Learning. 2023. doi:10.71070/oaml.v3i1.75

BibTeX
@article{Zhou2023,
  author = {Zhou, Tong and Zhang, Guojun and Cai, Yiqun},
  title = {Residual Self-Attention-Based Temporal Deep Model for Predicting Aircraft Engine Failure within a Specific Cycle},
  journal = {Optimizations in Applied Machine Learning},
  year = {2023},
  doi = {10.71070/oaml.v3i1.75}
}
Kostenlos starten →