机动发射条件下电子干扰策略快速计算方法

A fast calculation method for electronic interference strategy under mobile launch conditions

针对机动发射条件下对突防诸元的快速计算要求,本文提出一种基于改进粒子群与反向传播(back propagation,BP)神经网络相结合的算法,通过改进粒子群算法分别优化发射区内多个发射点位下电子干扰突防策略,之后通过训练神经网络进行拟合,使突防策略能够达到快速计算的目的。考虑到粒子群算法存在的随机性,通过初始化过程中引入准优解粒子,并增加相关约束,使发射区内发射点能够快速求得最优解,并在相邻点之间保持较好的连贯稳定性,为神经网络训练提供较好的训练集。最终实现发射区内任意点位快速突防规划的目的,相关研究方法对作战方案拟制和运用具有一定参考意义。

In response to the fast calculation requirements for penetration datas under mobile launch conditions,an algorithm is proposed based on the combination of improved particle swarm optimization and back propagation(BP)neural network.The improved particle swarm algorithm optimizes the electronic interference penetration strategy at multiple fixed launch points in the combat area,and then trains the neural network for fitting,enabling the penetration strategy to achieve the goal of fast calculation.Considering the randomness of particle swarm optimization algorithm,by introducing quasi optimal solution particles during the initialization process and adding relevant constraints,the launch points in the launch area can quickly obtain the optimal solution and maintain good coherence and stability between adjacent points,providing a good training set for neural network training,and ultimately achieving the goal of rapid penetration planning at any point in the launch area.The relevant research methods have certain reference significance for the formulation and application of combat plans.