Aiming at the problem of strong subjectivity and insufficient data utilisation in the traditional ship formation combat effectiveness analysis method, this study proposes a performance analysis fitting model based on deep belief network (DBN), which effectively reconstructs the combat model and improves the accuracy of the effectiveness analysis of the combat system. Firstly, the ship formation air defence effectiveness analysis index system is constructed, and then the structure and training method of the performance analysis fitting model are introduced. Finally, based on the formation of air defence combat, the performance analysis fitting model based on DBN and its comparative experiments are simulated and analysed. Simulation results verify the applicability and effectiveness of the model and method.

针对传统的舰艇编队作战效能分析方法中存在的对数据利用不充分、对数据完整性要求较高的问题,提出了基于深度学习的效能拟合方法.从最具有代表性的敏感性分析方法Sobol指数法入手,利用深度学习方法优越的特征学习能力,基于深度信念网络(DBN)构建了效能拟合网络,结合无监督预训练和有监督调优实现了网络训练和参数优化,构建出效能拟合模型.将产生的数据应用于效能分析模型并与完全数据条件下的效能分析结果进行对比,验证了所提出的效能拟合模型对于不完全数据下的作战系统敏感性分析的有效性.

On account of the influences on cooperative task assignment brought by the uncertainty in the intelligence acquirement and volatility in the battlefield environment, a cooperative task assignment method of manned/unmanned aerial vehicle in uncertain environment is provided. Firstly, the weight vector of uncertain multiple attribute decision making problems is calculated with the uncertain information handled by interval value theory in all decision indexes. And then the cooperative task assignment model of manned/ unmanned aerial vehicles is established combining all the indexes and constraints discussed. Finally, the Genetic Algorithm (GA) is improved with the introduction of Contract Network Protocol (CNP) and is applied to solve the optimization model. The obtained optimized task assignment result testifies the applicability of the model and the effectiveness of the improved algorithm.

At present,one of the development trends of air-to-air missiles is that the missile is used to attack both ground and air targets.On the basis of the three-dimensional proportional guidance law,the genetic algorithm is used to solve the optimal fuzzy control rules,and then the fuzzy control theory is used to control the proportional coefficient component of the three-axis in the proportional guidance law,thus establishing an integrated guidance law that enables the missiles to effectively attack the air and ground targets.The missile air-ground integrated attack guidance law is compared with the traditional three-dimensional proportional guidance law through the simulation experiment.The simulated results show that the proposed navigation law can be used for missile attacking the air-to-ground targets effectively and hasving a greater hit angle in the attack on ground target,so it is suitable for the air-to-ground integrated attack mode.