基于反向传播神经网络改进的增益修改卡尔曼滤波算法

doi:10.11772/j.issn.1001-9081.2016.05.1196

计算机应用 ›› 2016, Vol. 36 ›› Issue (5): 1196-1200.DOI: 10.11772/j.issn.1001-9081.2016.05.1196

基于反向传播神经网络改进的增益修改卡尔曼滤波算法

李世宝, 陈瑞祥, 刘建航, 陈海华, 丁淑妍, 龚琛

中国石油大学(华东) 计算机与通信工程学院, 山东青岛 266580

收稿日期:2015-11-04 修回日期:2015-12-23 出版日期:2016-05-10 发布日期:2016-05-09
通讯作者: 李世宝
作者简介:李世宝(1978-),男,山东潍坊人,副教授,硕士,主要研究方向:移动计算、无线传感器网络;陈瑞祥(1990-),男,山东济宁人,硕士研究生,主要研究方向:移动计算;刘建航(1978-),男,辽宁锦州人,博士,主要研究方向:车联网;陈海华(1983-),男,湖北武汉人,博士,主要研究方向:无线测向;丁淑妍(1973-),女,黑龙江大庆人,硕士,主要研究方向:正交频分复用;龚琛(1990-),男,安徽淮北人,硕士研究生,主要研究方向:无线测向。
基金资助:
山东省自然科学基金资助项目(ZR2014FM017);中央高校基本科研业务费专项资金资助项目(15CX05025A);青岛市黄岛区科技计划项目(2014-1-45)。

Improved modified gain extended Kalman filter algorithm based on back propagation neural network

LI Shibao, CHEN Ruixiang, LIU Jianhang, CHEN Haihua, DING Shuyan, GONG Chen

College of Computer and Communication Engineering, China University of Petroleum, Qingdao Shandong 266580, China

Received:2015-11-04 Revised:2015-12-23 Online:2016-05-10 Published:2016-05-09
Supported by:
This work is partially supported by the Natural Science Foundation of Shandong Province (ZR2014FM017), the Fundamental Research Funds for the Central Universities (15CX05025A), the Science and Technology Planning Project of Huangdao District, Qingdao (2014-1-45).

摘要/Abstract

摘要： 增益修改的卡尔曼滤波(MGEKF)算法在实际应用时,一般使用带有误差的测量值代替真实值进行增益修正计算,导致修正结果也被误差污染。针对这一问题,提出一种基于反向传播神经网络(BPNN)改进的MGEKF算法,该算法使用训练后的神经网络代替MGEKF的增益修正函数。该算法在网络训练阶段,以实际测量值作为神经网络的输入,真实值修正后的结果作为训练目标;在实际应用中,使用网络的输出修正卡尔曼增益。针对移动单站只测向目标定位问题进行了实验,实验结果表明:该算法与扩展卡尔曼滤波(EKF)、MGEKF、平滑增益修改的卡尔曼滤波(sMGEKF)算法相比:定位精度至少提升10%,并且有更强的稳定性。

关键词: 增益修改卡尔曼滤波, 反向传播神经网络, 只测向目标定位

Abstract: In practical application, Modified Gain Extended Kalman Filter (MGEKF) algorithm generally uses erroneous measured values instead of the real values for calculation, so the modified results also contain errors. To solve this problem, an improved MGEKF algorithm based on Back Propagation Neural Network (BPNN), termed BPNN-MGEKF algorithm, was proposed in this paper. At BPNN training time, measured values were used as the input, and modified results by true values as the output. BPNN-MGEKF was applied to single moving station bearing-only position experiment. The experimental results shows that, BPNN-MGEKF improves the positioning accuracy of more than 10% compared to extended Kalman filter, MGEKF and smoothing modified gain extended Kalman filter algorithm, and it is more stable.

Key words: Modified Gain Extended Kalman Filter (MGEKF), Back Propagation Neural Network (BPNN), bearing-only target positioning

中图分类号:

TP393

李世宝, 陈瑞祥, 刘建航, 陈海华, 丁淑妍, 龚琛. 基于反向传播神经网络改进的增益修改卡尔曼滤波算法[J]. 计算机应用, 2016, 36(5): 1196-1200.

LI Shibao, CHEN Ruixiang, LIU Jianhang, CHEN Haihua, DING Shuyan, GONG Chen. Improved modified gain extended Kalman filter algorithm based on back propagation neural network[J]. Journal of Computer Applications, 2016, 36(5): 1196-1200.

参考文献

[1] STANSFIELD R G. Statistical theory of DF fixing[J]. Journal of the Institution of Electrical Engineers-Part ⅢA:Radio Communication, 1947, 94(15):762-770.
[2] 华铁洲, 李冬海, 胡德秀. 改进的单站无源定位方法[J]. 计算机应用, 2010, 30(Z1):27-28.(HUA T Z, LI D H, HU D X. Improved method of single observer passive localization[J]. Journal of Computer Applications, 2010, 30(Z1):27-28.)
[3] SONG T L, SPEYER J L. A stochastic analysis of a modified gain extended Kalman filter with applications to estimation with bearings only measurements[J].IEEE Transactions on Automatic Control, 1985, 30(10):940-949.
[4] BLACKRNAN S, HOUSE A. Design and Analysis of Modern Tracking Systems[M]. Boston, MA:Artech House, 1999:1-24.
[5] BLACKMAN S, WHITE T, BLYTH B, et al. Integration of passive ranging with Multiple Hypothesis Tracking (MHT) for application with angle-only measurements[C]//Proceedings of Signal and Data Processing of Small Targets 2010. Bellingham, WA:SPIE, 2010:769815.
[6] SPINGARN K. Passive position location estimation using the extended Kalman filter[J]. IEEE Transactions on Aerospace and Electronic Systems, 1987, AES-23(4):558-567.
[7] GALKOWSKI P J, ISLAM M. An alternative derivation of the modified gain function of song and speyer[J]. IEEE Transactions on Automatic Control, 1991, 36(11):1323-1326.
[8] RISTIC B, ARULAMPALAM S, GORDON N. Beyond the Kalman filter[J]. IEEE Aerospace and Electronic Systems Magazine, 2004, 19(7):37-38.
[9] WAN E, van der MERWE R. The unscented Kalman filter for nonlinear estimation[C]//Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium. Piscataway, NJ:IEEE, 2000:153-158.
[10] QIAN Z, SONG T L. Improvement of bearings only target tracking using smoothing[C]//Proceedings of the 2014 IEEE International Conference on Control Science and Systems Engineering. Piscataway, NJ:IEEE, 2014:1-5.
[11] HUANG Y, SONG T L. Iterated modified gain extended Kalman filter with applications to bearings only tracking[J]. Journal of Automation and Control Engineering, 2015, 3(6):1439-1442.
[12] 林盾, 陈俐. BP神经网络在模拟非线性系统输出中的应用[J]. 武汉理工大学学报:交通科学与工程版, 2003, 27(5):731-734.(LIN D, CHEN L. Application of BP neural network to modeling output of nonlinear system[J]. Journal of Wuhan University of Technology (Transportation Science and Engineering), 2003, 27(5):731-734.)
[13] NERGUIZIAN C, DESPINS C, AFFÉS S. Geolocation in mines with an impulse response fingerprinting technique and neural networks[J]. IEEE Transactions on Wireless Communications, 2006, 5(3):603-611.
[14] HAYKIN S. Neural Networks:a Comprehensive Foundation[M]. 2nd Ed. Upper Saddle River:Prentice Hall, 2001:178-269.
[15] 闵惜琳, 刘国华. 用Matlab神经网络工具箱开发BP网络应用[J]. 计算机应用, 2001, 21(Z1):163-164.(MIN X L, LIU G H. Development of BP network application using Matlab neural network toolbox[J]. Journal of Computer Applications, 2001, 21(Z1):163-164.)

基于反向传播神经网络改进的增益修改卡尔曼滤波算法

Improved modified gain extended Kalman filter algorithm based on back propagation neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

[1]	褚苏荣, 牛之贤, 宋春花, 牛保宁. 面向移动端的渐进网格简化算法[J]. 计算机应用, 2020, 40(3): 806-811.
[2]	韩颖, 赵萌, 陈胜勇, 王照锡. 基于最大截面特征的病变宫颈细胞核的自动筛查[J]. 计算机应用, 2019, 39(4): 1189-1195.
[3]	陈浩广, 王银河. 基于扩展BP神经网络的一类非线性系统自适应控制设计[J]. 计算机应用, 2017, 37(6): 1670-1673.
[4]	刘巧玲, 李劲, 肖人彬. 基于参数反演的网络舆情传播趋势预测——以新浪微博为例[J]. 计算机应用, 2017, 37(5): 1419-1423.
[5]	征察, 吉立新, 李邵梅, 高超. 基于多模态信息融合的新闻图像人脸标注[J]. 计算机应用, 2017, 37(10): 3006-3011.
[6]	邵良杉, 郭雅婵. 基于Codebook的视频火焰识别算法[J]. 计算机应用, 2015, 35(5): 1483-1487.
[7]	罗丹, 罗海勇. 基于随机森林的跌倒检测算法[J]. 计算机应用, 2015, 35(11): 3157-3160.
[8]	张玲王玲吴桐. 基于改进的粒子群算法优化反向传播神经网络的热舒适度预测模型[J]. 计算机应用, 2014, 34(3): 775-779.
[9]	徐红艳党晓婉冯勇李军平. 基于BP神经网络的Deep Web实体识别方法[J]. 计算机应用, 2013, 33(03): 776-779.
[10]	马东昱孙龙清. 基于图像特征的籽棉品级分级模型的研究[J]. 计算机应用, 2010, 30(8): 2235-2238.
[11]	张宏斌贾志新. 基于逆向思维的系统可靠性精确分配模型[J]. 计算机应用, 2009, 29(09): 2468-2470.