Abstract
The problem of human-computer interaction mental workload in flight driving has great reference value for the prevention of safety hazards in aviation driving. This paper analyzes and studies the classification method of mental workload in flight driving by designing different simulated flight experiment tasks. This study uses a combination of EEG signals and subjective evaluation, through the use of convolutional neural networks and long short-term memory network method of combining EEG signals for research and analysis. The accuracy of EEG signal classification is as high as 94.9 %. NASA-TLX evaluation results show that there is a positive correlation between task load difficulty and evaluation score. The results show that the combination of convolutional neural network and long short-term memory network is suitable for pilots ’ mental workload classification. This study has important practical significance for flight accidents caused by pilots ’ mental workload.