基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法  

Adaptive Control Bat Algorithm Intelligent Optimization Particle Filter for Maneuvering Target Tracking

作　　者：陈志敏[1] 吴盘龙[2] 薄煜明[2] 田梦楚[2] 岳聪[2] 顾福飞[1] CHEN Zhi-min;WU Pan-long;BO Yu-ming;TIAN Meng-chu;YUE Cong;GU Fu-fei(China Satellite Maritime Tracking and Controlling Department,Jiangyin,Jiangsu 214431,China;School of Automation,Nanjing University of Science and Technology,Nanjing,Jiangsu 210094,China)

机构地区：[1]中国卫星海上测控部,江苏江阴214431 [2]南京理工大学自动化学院,江苏南京210094

出　　处：《电子学报》2018年第4期886-894,共9页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61501521;No.U1330133;No.61473153);中国博士后科学基金(No.2015M582861)

摘　　要：标准粒子滤波重采样过程中对粒子的直接删除会导致粒子贫化,并且综合性价比不高,难以满足高频段精密跟踪雷达的需求.针对上述问题,本文提出了基于自控蝙蝠算法优化粒子滤波的机动目标跟踪方法.该方法首先在粒子滤波中引入蝙蝠算法,用粒子表征蝙蝠个体,模拟蝙蝠群体搜索猎物的过程,使粒子向高似然区域移动.同时,改进算法将粒子接受新状态的比例作为反馈量,设计了自适应闭环控制策略对算法的全局搜索能力和局部搜索能力进行全程动态控制,使得粒子分布更加合理,从而进一步提高了粒子滤波的精度.最后在分别在基础非线性滤波模型和强机动强干扰目标跟踪模型中对改进算法的性能进行了测试.实验结果表明,改进算法提高了目标跟踪的精度.Resampling of particle filters will cause particle depletion and the comprehensive performance is low,which can hardly meet the requirement of high frequency accurate radar.To address to the problem,a novel adaptive control bat algorithm optimized particle filter for maneuvering target tracking was proposed in this paper.It introduced bat algorithm into particle filter and took particle as bat individual to simulate the process of hunting and made particles move to high likelihood area.Meanwhile,by taking proportion of accepting as feedback,the improved algorithm designed closed-loop control strategy and controlled the balance between ability of global optimization and local optimization and improved rationality of particles distribution and accuracy of filter.Finally,the improved algorithm was tested in basic nonlinear filter model and strong maneuvering-jamming target tracking model.The experimental results prove that the new algorithm conduces to enhancement of the precision for target tracking.

关 键 词：粒子滤波 蝙蝠算法 粒子多样性 闭环控制 目标跟踪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]