针对传统空空导弹攻击区解算方法存在的问题,建立BP神经网络模型对空空导弹攻击区进行解算,通过对网络的离线训练,在满足要求精度的情况下较好的得到了空空导弹的攻击区。解算和仿真结果表明,该方法极大地提高了拟合的精度和速度,能够适应快速高精度的火控解算。

In order to solve the problems about traditional methods of air-to-air missile launch envelopes, the article has established the BP neural network model for solving the launch envelopes. Under the situation of sufficing the demand precision, it gains well the launch envelopes through training the network off-line. The results show that the method greatly increases the accuracy and speed of on-line launch envelopes computation. It can adapt the fire control computation of speediness and high precision, so it has some application values in combat.