基于复合导引头态势的抗干扰评估方法

Anti-jamming Evaluation Method Based on Composite Seeker Situation

针对雷达抗干扰效果评估中,抗干扰方获取评估信息困难、主观性强等问题,以主/被动复合导引头的态势变化为主线,基于主动导引头感知的位置态势和导引头本身的态势、主/被动导引头侦察到敌方有源干扰信号的态势信息,建立抗干扰评估指标体系。基于态势的麻雀搜索算法优化卷积神经网络(Sparrow Search Algorithm-Convolutional Neural Network, SSA-CNN)方法开展导引头抗干扰效果评估。在态势信息存在缺失时,采用卷积自编码器(Convolutional Auto-Encoder, CAE)完成非完备信息下的导引头抗干扰效果评估。仿真结果表明,在复杂干扰环境下的2种人工智能算法对导引头抗干扰评估均具有优秀的有效性和准确性。

To solve the problems of difficulty in obtaining evaluation information and strong subjectivity of anti-jamming party in the evaluation of radar anti-jamming effects,the anti-jamming evaluation index system is established based on the situation change of the active and passive composite seeker as the main line,the position situation perceived by the active seeker and the situation of the seeker itself,as well as the situation information detected by the active/passive seeker from the enemy s active jamming signals.The anti-jamming performance of the seeker is evaluated by using the Sparrow Search Algorithm-Convolutional Neural Network(SSA-CNN)method.When the situation information is missing,the Convolutional Auto-Encoder(CAE)is used to evaluate the anti-jamming effect of the seeker with incomplete information.The simulation results show that two AI algorithms have excellent effectiveness and accuracy in evaluating the anti-jamming performance of the seeker in the complex jamming environment.