针对过载控制的神经网络制导律研究  

Research on RBF neural network guidance law for overload control

作　　者：王欣[1] 赵云凯 王育欣 WANG Xin;ZHAO Yunkai;WANG Yuxin(School of Equipment Engineering,Shenyang University of Science and Technology,Shenyang 110170,China;Information Engineering College,Tianjin Agricultural University,Tianjin 300392,China)

机构地区：[1]沈阳理工大学装备工程学院,沈阳110170 [2]天津农学院计算机与信息工程学院,天津300392

出　　处：《兵器装备工程学报》2023年第10期139-146,共8页Journal of Ordnance Equipment Engineering

基　　金：国家自然基金项目(12202285);天津农学院研究生教育教学研究与改革重点项目(2021-YA-6)。

摘　　要：针对高机动高突防能力目标的拦截问题,通过对比例导引律导引过程中过载与比例系数、视线角速率关系的分析,建立基于视线坐标系的三维弹-目相对运动模型,研究在该坐标系下的比例导引律加速度表现形式,据此设计实现K值自适应调整的RBF神经网络模型。通过与纯比例导引律的法向过载以及攻击时间对比,验证了RBF神经网络导引律在降低制导性能的前提下抑制视线角速率抖振、过载控制方面的有效性。Aiming at the interception problem of targets with high maneuverability and high penetration ability,through the analysis of the relationship between overload and proportional coefficient and line-of-sight angular rate in the guidance process of the guidance law,a three-dimensional missile-target relative motion model based on the line-of-sight coordinate system is established,and the acceleration representation of proportional guidance law in this coordinate system is studied,and the RBF neural network model to realize K-value adaptive adjustment is designed accordingly.Compared with the normal overload and attack time of pure proportional guidance law,the effectiveness of RBF neural network guidance law in suppressing line-of-sight angular rate chattering and overload control is verified on the premise of reducing guidance performance.

关 键 词：神经网络 末制导 比例导引律 过载控制 

分 类 号：TJ765.3[兵器科学与技术—武器系统与运用工程]