Objective evaluation of pilot fatigue is crucial for enhancing aviation safety. Although electroencephalography (EEG) is regarded as an effective tool for recognizing pilot fatigue, the direct application of deep learning models to raw EEG signals faces significant challenges due to issues such as massive data volume, excessively long training time, and model overfitting. Moreover, existing feature-based methods often suffer from data redundancy due to the lack of effective feature and channel selections, which compromises the model’s recognition efficiency and accuracy. To address these issues, this paper proposes a framework, named ASFT-Transformer, for fast and accurate detection of pilot fatigue. This framework first extracts time-domain and frequency-domain features from the four EEG frequency bands. Subsequently, it introduces a feature and channel selection strategy based on one-way analysis of variance and support vector machine (ANOVA-SVM) to identify the most fatigue-relevant features and pivotal EEG channels. Finally, the FT-Transformer (Feature Tokenizer + Transformer) model is employed for classification based on the selected features, transforming the fatigue recognition problem into a tabular data classification task. EEG data is collected from 32 pilots before and after actual simulator training to validate the proposed method. The results show that ASFT-Transformer achieved average accuracies of 97.24% and 87.72% based on cross-clip data partitioning and cross-subject data partitioning, which were significantly superior to several mainstream machine learning and deep learning models. Under the two types of cross-validation, the proposed feature and channel selection strategy not only improved the average accuracy by 2.45% and 8.07%, respectively, but also drastically reduced the average training time from above 1 h to under 10 min. This study offers civil aviation authorities and airline operators a tool to manage pilot fatigue objectively and effectively, thereby contributing to flight safety.

Discovering and mitigating potential risks in advance is essential for preventing aviation accidents on routine flights. Although anomaly detection-based explanation techniques have successfully uncovered potential risks for proactive flight safety management, explaining group-scale precursors using these methods is challenging due to the assumption that risky flights are significantly fewer in number than normal flights, as well as the reliance on non-domain knowledge for hyperparameter adjustment. To characterize the group-scale precursors more accurately, we propose a novel technique called Catalyst Mass-Based Clustering Analysis (CMCA), which employs a composite entropy-energy dissipation index during approach to evaluate the energy management performance. On this basis, an optimization objective is constructed to identify clusters exhibiting significant energy management differences during the approach phase. We successfully identify group-scale precursors with energy management issues by applying CMCA to a combination of minority-labeled and majority-unlabeled flights. Comparative experiments show that these precursors have energy levels that deviate from normal flights by 5.83% and 10.93%, respectively, 1000 ft above touchdown, demonstrating the effectiveness of our method. The analysis suggests that poor energy management awareness on the part of pilots could be responsible for these group-scale precursors. Notably, the results obtained using CMCA are comprehensible for Subject Matter Experts, making the method a valuable tool for proactive flight safety management.