A real-time fatigue discrimination algorithm that takes into account the work characteristics of controllers is proposed in order to address the shortcomings of the current fatigue detection through facial information of controllers, such as the algorithm’s low robustness and infrequent integration of the actual scene of control. Firstly, the Attention Mesh algorithm is used to obtain the 3D coordinate information of 468 points on the face, and the thresholds of eye and mouth aspect ratios are calibrated sample by sample using the feature matching method. Secondly, three indicators are introduced, namely, the controller’s on-duty time, the real-time land and air call load, and the number of fatigue events, and these three indicators are dynamically mapped to the fatigue detection window through the exponential decay function and the fatigue frequency ratio of blinks within the dynamic decay time window is calculated through the calculation of the fatigue frequency ratio of blinks within the dynamic decay time window. The fatigue trend indicator is derived by calculating the percentage of blinking frequency within the dynamic decay time window. Finally, the EEG and facial video data of the post-shift control test of 30 mature release order controllers in the control room of a control unit are processed, and the fatigue indicator F_δ, obtained from the facial data, is correlated with the EEG fatigue indicator F_ε in the time dimension. The findings demonstrated that the validity and reliability of the suggested algorithms were confirmed, and the overall Pearson correlation coefficients in the bivariate cross-correlation analysis results of the 30 subject samples ranged from 0.462 to 0.785. The Sig. two-tailed significance tests were found at the 0.01 level, indicating a significant correlation.

In order to improve the stability of air traffic flow, this study investigated an aircraft multi-velocity difference car-following model considering offsets based on the characteristics of flight networking operations. Firstly, to quantitatively describe the influence of offsets between aircraft on the car-following behavior, the concept of offset hindrance was introduced, and the relationship between offset and the velocity of the leading aircraft was established, extending the car-following model to a three-dimensional mode. Secondly, by considering the multi-aircraft information interaction mode in the flight networking environment, a multi-velocity difference aircraft car-following model was constructed, and stability analysis methods were applied to derive the stability discrimination conditions and calculate the steady-state traffic capacity of the proposed model. Finally, based on the parameter calibration of the model, numerical simulation experiments were designed by using the multi-velocity difference car-following model considering three leading aircraft. The results show that the hindrance effect decreases as the offset increases, and for the same offset value, heavy aircraft have the highest hindrance effect while light aircraft have the lowest hindrance effect. The proposed model has a better stable region compared to traditional models, and the stability of the proposed model improves with an increase in the number of leading aircraft and the weight coefficient. Under the same parameter values, the fuel consumption coefficient of the proposed model is lower than that of the traditional car-following model, and when the sensitivity coefficient is set to 1 s⁻¹, the fuel consumption coefficient decreases by 27.12%. Numerical simulations demonstrate that the aircraft multi-velocity difference model contributes to improving the stability of air traffic flow and reducing fuel consumption.