Pilot workload is a critical factor influencing flight safety. This study collects both subjective and objective data on pilot workload using the NASA-TLX questionnaire and electroencephalogram acquisition systems during simulated flight tasks. The raw EEG signals are denoised through preprocessing techniques, and relevant EEG features are extracted using time-domain and frequency-domain analysis methods. One-way ANOVA is employed to examine the statistical differences in EEG indicators under varying workload levels. A fusion model based on CNN-Bi-LSTM is developed to train and classify the extracted EEG features, enabling accurate identification of pilot workload states. The results demonstrate that the proposed hybrid model achieves a recognition accuracy of 98.2% on the test set, confirming its robustness. Additionally, under increased workload conditions, frequency-domain features outperform time-domain features in discriminative power. The model proposed in this study effectively recognizes pilot workload levels and offers valuable insights for civil aviation safety management and pilot training programs.
This paper aims to uncover the generation patterns of pilot intentions during complex flight missions and to identify pilot intention states, thereby enabling airborne warning systems to understand and predict pilot intentions for early warning strategies. To achieve this, we designed a simulated flight experiment incorporating various risk scenarios to induce pilot intentions, collected eye-tracking data reflecting pilot intention states, and proposed a method for identifying the persistence of pilot intentions based on eye-tracking data. We then constructed a pilot intention dataset and analyzed the time–frequency characteristics of eye-tracking data in the intention persistence state, revealing key behavioral features following the generation of pilot intentions. Furthermore, we examined eye-tracking features that enhance the performance of pilot intention recognition models. Finally, we developed a deep learning model integrating recurrent neural networks (RNN) and bidirectional long short-term memory (BiLSTM) networks to recognize pilot intentions. The results demonstrate that the model achieved a recognition accuracy of 97.8% on the test set, and its performance in identifying pilot intention states was validated through comparison with a baseline model. This study confirms that eye-tracking data can effectively identify pilot intention states and offers new insights into aircraft safety early warning and intelligent control systems.
26 August 2026 in Reliability Engineering & System Safety