低信息条件下的机载拦截武器目标分类轨迹预报方法研究

Research on Target Classification and Trajectory Prediction Method of Airborne Interceptor Weapons Under Low Information Condition

在三体博弈场景中,为了提升防御弹的拦截能力,需要对来袭目标的轨迹进行预报。受限于数据链的传输速率,目标信息的更新频率较低,基于卡尔曼滤波和轨迹拟合的弹道预报方法不再适用。为此,本文提出了一种在低信息支撑条件下的具备分类能力的目标轨迹预报方法。先根据载机对来袭目标的探测能力建立来袭目标的轨迹库,后使用轨迹库数据训练分类神经网络和轨迹预测神经网络;在线根据数据链传输的目标信息确定来袭目标类型,再通过最小二乘法解算来袭目标初始状态的最优估计,并实现轨迹预测。仿真试验表明本文提出的方法在低信息支撑条件下可以实现高精度的轨迹预报。

In the three-body game scenario,it is necessary to predict the trajectory of incoming targets to enhance the interception capabilities of defensive missiles.Limited by the transmission rate of data link,the update frequency of target information is low,and the trajectory prediction method based on the Kalman filter and trajectory fitting is not applicable.Therefore,this study presents a target trajectory prediction method capable of classification under low information support.Firstly,the trajectory database of incoming targets was established based on the detection ability of airborne radar,and then the classification neural network and trajectory prediction neural network were trained using the trajectory database.The type of the target was determined online according to the target information transmitted by the data link,and after that,the optimal estimation of the initial state of the incoming target was acquired by the least square method.Finally,the trajectory prediction was realized.Simulation results show that the proposed method can successfully achieve high-precision trajectory prediction under low information support condition.