水下目标UPF联合拓展PCRLB的近似最优定位精度建模  

Modeling of approximate optimal positioning accuracy for underwater target UPF joint extension PCRLB

作　　者：罗成名 刘子卓[1] 窦子程 费永帅 梅宇航 王彪 LUO Cheng-ming;LIU Zi-zhuo;DOU Zi-cheng;FEI Yong-shuai;MEI Yu-hang;WANG Biao(Ocean College,Jiangsu University of Science and Technology,Zhenjiang 212003,China;Jiangsu Key Laboratory of Power Transmission&Distribution Equipment Technology,Hohai University,Changzhou 213000,China)

机构地区：[1]江苏科技大学海洋学院,江苏镇江212003 [2]河海大学江苏省输配电装备技术重点实验室,江苏常州213000

出　　处：《控制与决策》2025年第1期103-110,共8页Control and Decision

基　　金：国家自然科学基金项目(62001195,52071164);江苏高校“青蓝工程”项目;江苏省输配电重点实验室开放基金项目(2023JSSPD10).

摘　　要：考虑到水下目标定位过程存在通信和采样中的不确定性,叠加含噪定位网络解算引入的额外误差,如何求解长航时水下目标定位误差方差下界用于评估定位性能至关重要.针对水下目标机动运行定位精度不稳定的问题,采用无迹粒子滤波和拓展后验克拉美罗估计,开展水下目标长航时近似最优精度建模和评估.首先,考虑水下多参量非线性模型易引起滤波退化,采用无迹粒子滤波对水下目标状态进行估计;然后,利用泰勒级数展开求解水下目标预测状态的近似逼近;接着,将滤波估计得到的状态值与近似估计得到的期望和方差,集成到水下目标三维拓展后验克拉美罗估计中;最后,开展无迹卡尔曼滤波0阶~2阶、粒子滤波、最大最小粒子滤波、无迹粒子滤波0阶~2阶与理论最优估计值的比较,所提出模型长航时目标位置和速度近似后验克拉美罗估计值能够逼近理论值,可用于水下目标长航时定位性能分析.Considering the uncertainty in communication and sampling in underwater target positioning process,it is crucial to calculate the variance lower bound of underwater target positioning errors for evaluating performance,as the additional errors introduced by the solution of noisy networks are superimposed.In response to the problem of unstable positioning accuracy in underwater target maneuvering operation,unscented particle filtering(UPF)and extended posterior Cramer-Rao lower bound(PCRLB)are adopted to carry out modeling and evaluation of approximate optimal accuracy for underwater target long endurance.Firstly,considering that multi parameter and nonlinear models are prone to filter degradation,the UPF is used to estimate the underwater target state.Secondly,Taylor series expansion is used to solve approximate approximation of predicted states of underwater targets.Then,the state values by filtering estimation and the expected and variance by approximate estimation are integrated into the three-dimensional extended PCRLB.Finally,the performance comparison is conducted among the unscented Kalman filtering(UKF)from order 0 to order 2,particle filter(PF),minimax particle filter(MPF),the UPF from order 0 to order 2,and the theoretical optimal estimation.The results indicate that the approximate PCRLB estimated values of the target position and velocity for the long-term of the proposed model can approach the theoretical value,and thus can be used for the analysis of the long-term positioning performance of underwater targets.

关 键 词：水下目标 无迹粒子滤波 定位建模 后验克拉美罗下界 定位精度 近似最优 

分 类 号：TP713[自动化与计算机技术—检测技术与自动化装置]