一种鲁棒的递推总体最小二乘无源定位算法

来源期刊:中南大学学报(自然科学版)2015年第3期

论文作者:吴昊 陈树新 张衡阳 张艺航 倪娟

文章页码:886 - 894

关键词:无源定位;鲁棒估计;总体最小二乘估计;影响函数

Key words:passive location; robust estimation; total least squares estimation; influence function

摘    要:针对机载无源定位易受异常误差影响的问题,提出一种基于角度信息的鲁棒递推总体最小二乘定位(RRTLS)算法。建立机载无源定位模型,得出递推总体最小二乘(RTLS)解。推导RTLS算法的加权形式,构建鲁棒总体最小二乘极值准则。在此基础上建立等价权函数,使得当出现异常误差时,算法能够自动识别异常误差,并利用降权、剔除奇异点的方式减小异常误差的影响。研究结果表明:随着误差的增大,RRTLS算法的影响函数绝对值减小,抗异常误差能力较强。仿真结果表明:存在异常误差时,递推最小二乘(RLS)和RTLS定位结果受到扭曲,而RRTLS算法能够获得理想的估值,具有较强的鲁棒性。

Abstract: To solve the problem that airborne passive location is susceptible to outliers, a robust recursive total least squares (RRTLS) airborne passive location algorithm was proposed based on the angle information. The airborne passive location model was established and the recursive total least squares(RTLS) solution was obtained. The RTLS solution was transformed into the weighted pattern, and robust TLS extreme value criterion was formulated. Then, the equivalent weight function was founded, which made the algorithm distinguish the outliers automatically, and the effects from outliers were reduced by the weight-reduction and the singular points elimination. The results show that with the increase of error, the value of the influence function in the RRTLS algorithm decreases, and the algorithm has high anti-outliers ability. When there are outliers, the results on the RLS and RTLS location are not reliable. On the other hand, the RRTLS algorithm performs an ideal estimation with good robustness.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号