Aiming at the temperature control problem of the hypersonic vehicle transpiration cooling system， this paper proposes an active disturbance rejection controller （ADRC） to adjust the temperature of the porous medium on the vehicle wall based on the one-dimensional fixed boundary sweating cooling model， whose effectiveness and advantages are verified by a numerical simulation. The controller does not rely on the precise mathematical model of the temperature field of the porous medium. The heat flow disturbance is suppressed by extracting and compensating disturbance information from the input and output data of the system. The simulation results show that the ADRC designed for the transpiration cooling system can quickly track the reference temperature. Compared with the traditional PID control， the temperature response under ADRC has no overshoot. In addition， when external heat flow interference occurs， the ADRC has strong robustness and adaptability， which can provide a certain reference for the engineering application of transpiration cooling control systems.

Compared with single sensors， the multi-faceted and multi-type information collected by multi-source sensors is more valuable for air target classification. In view of the current problems of air target recognition methods having single features， inability to cross-validate classification results and low recognition accuracy， an attention-based centralized air target recognition method with dynamic fusion of multi-source sensor features is proposed. This method uses deep learning models to extract the photoelectric image， motion trajectory， RCS and electromagnetic features of the target vehicle. Considering that the importance of each sensor feature will change dynamically in the real environment， the attention mechanism and the distance parameter are used to dynamically allocate the feature weights. The experimental results on the simulation dataset show that compared with the single-sensor model， the centralized method improves the recognition accuracy by 12.89% on average， which is a significant improvement in recognition effect； compared with the distributed model based on hierarchical analysis voting， the centralized method is more robust and better adapted to complex environments while fusing multi-source features more effectively.