To improve the anti-interference test capability of missiles in complex electromagnetic environments， this paper proposed a Bayesian regularization design method for test samples of multi-sensitive factor anti-suppression interference. First， this method analyzed the typical multi-sensitive factors affecting the anti-suppression interference capability of the seeker and then designed a Bayesian regularization network to solve the test sample design problem of missile anti-interference. The constructed Bayesian regularization network for multi-sensitive factor anti-suppression interference tests could establish a nonlinear mapping relationship between different multi-sensitive anti-interference influencing factors and anti-interference capability， greatly reducing the sample size of traditional all-factor traversal tests. Then， the hyperparameter solving method for the constructed network was studied， thereby realizing the Bayesian regularization design method for test samples. Finally， simulation experiments on typical anti-suppression interference were conducted to verify the performance of the proposed test sample design method. The results indicate that the Bayesian regularization test sample design for multi-sensitive factor anti-suppression interference effectively shortens the time cycle， saves test resources， and provides theoretical support for the anti-interference test evaluation of precision-guided missiles.

The tiltrotor UAV has both hovering and vertical takeoff and landing capabilities in the air， as well as high speed cruise performance. Aiming at the problem that the rigid aerodynamic shape of a tiltrotor UAV cannot accurately simulate the real flight performance due to the structural deformation of the elastic material， a CFD/CSD coupling method combining rotor bi-directional loose coupling and wing unidirectional coupling is proposed to numerically simulate the aeroelastic problem of tiltrotor UAV in hover state. Using aeroelastic tailoring to optimize the composite layer of the blade， the maximum deformation displacement of the blade is reduced from 22.34 mm to 17.1 mm， and the hovering efficiency is improved from 69.95% to 72.69%. Computational simulations are conducted on the entire aircraft flow field， and the results show that after considering structural elastic deformation， the increase in thrust generated by the entire aircraft rotor system compared to the individual rotor system decreases from 2.09% to 1.18%. The high-pressure zone generated by the rotor downwash on the deformed wing surface shifts approximately 0.1m towards the wing tip direction compared to the undeformed wing.

Quickly and accurately mining and analyzing the target association relationship contained in radar historical data can provide assistance for the study of air target activity law， target identification and judgment， and give full play to the role of historical data. According to the space-time characteristics of the target， a new method of mining and analyzing the association relationship of air targets is designed. A time matching method is designed to generate time correlation data sets. A spatial association metric is designed to generate spatial association data sets. Dynamic time warping （DTW） and spanning tree algorithm are used to match and search the air targets with associated relations， and generate the set of associated relations. After digital simulation verification， this method can effectively mine the historical information of radar data and find the correlation rules between targets.

Compared with traditional configuration tiltrotor aircraft， tilting wing and rotor UAV can significantly reduce the aerodynamic interference of rotor wake on wings in hover， and increase flight efficiency. Regarding the continuous tilting transition process of the UAV with complex unsteady aerodynamic characteristics， the delayed detached eddy simulation （DDES） method， improved from the classical detached eddy simulation （DES） method， is used to simulate aerodynamic interference. During the tilting transition process， the aircraft's forward flight speed， rotor pitch angle， fuselage and fixed wing angle of attack， and nacelle inclination angle all dynamically change over time. By comparing with the traditional configuration， the aerodynamic performance changes and flow field mechanisms during the tilting transition process are analyzed. The simulation calculation results show that the UAV in the initial state of tilting is less affected by the rotor downwash. During the tilting process before the 30° nacelle inclination angle， due to the increased resistance of the tilting wing segment， the required thrust of the rotor are increased. The separation vortices generate during the tilting process of the tilting wing section collide with the downwash wake of the rotor， resulting in a larger wake interference area at the wing tip position and a downwash effect on the inner fixed wing tip， reducing the overall lift of the aircraft.

Threats often have the characteristics of dynamic evolution with the development of bilateral confrontation. Traditional threat assessment methods are more based on static threats and lack of prediction of dynamic threats. To solve this problem， this paper proposes a threat assessment method for aerial targets under confrontational conditions. Setting the red side as the attacking side and the blueside as the defending side. The reinforcement learning model is established with the enemy target as the agent， and its state space， action space， transition function and reward function are designed. The threat assessment model is established， the threat element index is established， and the threat assessment method is designed. The model is trained， and the trained model can predict the enemy aerial target threat according to the confrontation situation. Through test and analysis， the method is more reasonable for threat assessment of enemy aerial targets under confrontation conditions.