基于支持向量回归机的自适应差分滤波算法研究

上海交通大学学报（自然版） ›› 2014, Vol. 48 ›› Issue (07): 929-935.

• 自动化技术、计算机技术 • 上一篇下一篇

基于支持向量回归机的自适应差分滤波算法研究

王宏健，徐金龙，刘向波，李娟，张爱华

（哈尔滨工程大学自动化学院，黑龙江哈尔滨 150001）

收稿日期:2013-10-22 出版日期:2014-07-28 发布日期:2014-07-28
基金资助:
国家自然科学基金(E091002/50979017)，教育部高等学校博士学科点专项科研基金(20092304110008)，中央高校基本科研业务费专项资金(HEUCFZ 1026)，哈尔滨市科技创新人才（优秀学科带头人）研究专项资金项目(2012RFXXG083)

Adaptive Divided Difference Filter Algorithm Based on Support Vector Regression

WANG Hongjian,XU Jinlong,LIU Xiangbo,LI Juan,ZHANG Aihua

（College of Automation, Harbin Engineering University, Harbin 150001, China）

Received:2013-10-22 Online:2014-07-28 Published:2014-07-28

摘要/Abstract

摘要：

针对差分滤波(DDF)算法存在因噪声统计特性与实际不符而导致的滤波精度降低甚至发散的问题，提出了一种基于支持向量回归机的自适应差分滤波(SVRADDF)算法.将测量值的新息协方差与理论协方差之间的差值作为支持向量回归机的输入、输出调节噪声统计特征的自适应因子，实时修正DDF噪声协方差，根据实际噪声变化调整噪声协方差矩阵，从而提高滤波精度. 针对水下目标纯方位角跟踪系统的蒙特卡洛仿真实验表明，在相同初始噪声特性条件下，所提出的SVRADDF算法具有较好的估计效果和鲁棒性，估计精度、稳定性及收敛时间等性能明显优于单纯DDF算法.

关键词: 差分滤波器, 自适应因子, 支持向量回归机, 蒙特卡洛仿真, 水下目标纯方位角跟踪

Abstract:

To solve the low filtering accuracy problem of the divided difference filter (DDF) algorithm, this paper proposed an support vector regression based adaptive divided difference filter (SVRADDF) algorithm. The difference between the measurement innovation covariance and theory covariance matrix were used as the adaptive factor of the input and output of the support vector regression machine for realtime correction of the DDF noise covariance and the adjustment of the noise covariance matrix according to the actual noise changes, so as to improve the filter precision. Monte Carlo simulation for underwater target bearingonly tracking systems indicates that, with the same initial noise conditions, the proposed SVRADDF algorithm has a better estimation performance and robustness. The accuracy, stability and covergence time are significantly better than the DDF algorithms.

Key words：

Key words: divided difference filter(DDF), adaptive factor, support vector regression(SVR), Monte Carlo simulation, underwater target bearing-only tracking

中图分类号:

TP 242.6

王宏健，徐金龙，刘向波，李娟，张爱华. 基于支持向量回归机的自适应差分滤波算法研究[J]. 上海交通大学学报（自然版）, 2014, 48(07): 929-935.

WANG Hongjian,XU Jinlong,LIU Xiangbo,LI Juan,ZHANG Aihua. Adaptive Divided Difference Filter Algorithm Based on Support Vector Regression[J]. Journal of Shanghai Jiaotong University, 2014, 48(07): 929-935.

参考文献

［1］Daum F E. Nonlinear filters: beyond the Kalman filter［J］. IEEE AES Systems Magazine, 2005, 20(8): 5769.

［2］BarShalom Y, Kirubarajan T. Estimation with applications to tracking and navigation［M］. New York: John Wiley & Sons, 2001.

［3］Simon J, Uhlman, Hugh F. A new approach for filtering nonlinear system［C］∥Proceedings of the American Control Conference. Seattle, Washington, 1995: 16281632.

［4］王小旭，赵琳，夏全喜. 噪声相关条件下Unscented卡尔曼滤波器设计［J］. 控制理论与应用， 2010, 27(10): 13621369.

WANG Xiaoxu, ZHAO Lin, XIA Quanxi. Design of unscented Kalman filter with correlative noise［J］. Control Theory & Applications， 2010, 27(10): 13621369.

［5］王小旭, 赵琳, 潘泉. 基于最小均方误差估计的噪声相关UKF设计［J］. 控制与决策， 2010, 25(9): 13931398.

WANG Xiaoxu, ZHAO Lin, PAN Quan. Design of UKF with correlatives nosies based on minimum mean square error estimation［J］. Control and Decision，2010, 25(9): 13931398.

［6］王小旭，梁彦，潘泉. 带有色量测噪声的非线性系统Unscented 卡尔曼滤波器［J］. 自动化学报， 2012, 38(6): 986998.

WANG Xiaoxu, LIANG Yan, PAN Quan. unscented Kalman filter for nonlinear systems with colored measurement noise［J］. ACTA AUTOMATICA SINCA， 2012, 38(6): 986998.

［7］Leven W F, Lanterman A D. Unscented Kalman filter for multiple target tracking with symmetric measurement equations［J］. IEEE Transactions on Automatic Control， 2009, 54(2): 370375.

［8］Kim C, Sakthivel R, Chung W K. Unscented FastSLAM: a robust and efficient solution to the SLAM problem［J］. IEEE Transactions On Robotics， 2008, 24(4): 808820.

［9］Ning X L, Fang J C. A new autonomous celestial navigation method for the lunar rover［J］. Robotics and Autonomous Systems， 2009, 57(1): 4854.

［10］Kim J S, Shin D R, Serpedin E. Adaptive multiuser receiver with joint channel and time delay estimation of CDMA signals based on the squareroot unscented filter［J］. Digital Signal Processing， 2009, 19(3): 504520.

［11］范炜，李勇. Sigma点卡尔曼滤波方法精度分析［C］∥2009 Chinese Control and Decision Conference. Cuilin: IEEE, 2009: 28832888.

［12］Lefebvre T, Bruyninckx H, De Schutter J. Kalman Filter for nonlinear systems: a comparison of performance［J］. International Journal of Control， 2004, 77(7): 639653

［13］Dunik J, Simandl M. Performance analysis of derivativefree filters［C］∥Proceedings of the 44th IEEE Conference on Decision and Control. Seville: IEEE, 2005:19411946.

［14］Norgaard M, Poulsen N K, Ravn O. New developments in state estimation for nonlinear systems［J］. Automatica， 2000, 36(2000): 16271638.

［15］DeokJin L. Nonlinear bayesian filtering with applications to estimation and navigation［D］. Texas A&M University, 2005:134139.

［16］Shi Y, Chongzhao H, Liang Y. Improved divided difference filter based on NewtonRaphson method for target tracking［C］∥12th International Conference on Information Fusion. Seattle, WA, USA, 2009: 20682074.

［17］Wang C, Zhang J, Mu J. Maximum likelihoodbased iterated divided difference filter for nonlinear systems from discrete noisy measurement［J］. Sensors， 2012, 2012(12): 89128929.

［18］Subrahmanya N, Shin Y C. Adaptive divided difference filtering for simultaneous state and parameter estimation［J］. Automatic， 2009, 45(2009): 16861693.

［19］Bhale P G, Dwivedi P N, Kumar P, et al. Estimation of ballistic coefficient of reentry vehicle with divided difference filtering using noisy RF seeker data［C］∥IEEE International Conference on Industrial Technology. Mumbai: IEEE, 2006: 10871092.

［20］穆静，王长元，张娟. 基于离差差分滤波算法的再入目标状态估计［J］. 西安工业大学学报， 2011, 31(4): 377381.

MU Jing, WANG Changyuan, ZHANG Juan. State estimation of reentry target based on divided difference filter［J］. Journal of Xi’an Technological University， 2011, 31(4): 377381.

［21］Tripathy P, Srivastava S C, Singh S N. A diveided by difference filter based algorithm for estimation of generator rotor angle utilizing synchrophasor measurements［J］. IEEE Transactions On Instrumentation And Measurement， 2010, 59(6): 15621570.

［22］Karlgaard C D, Shen H. Desensitized divided difference filtering for induction motor state estimation［C］∥44th IEEE Southeastern Symposium on System Theory. Jacksonvile: IEEE, 2012：145150.

［23］Fang J, Han X. InFlight alignment algorithm based on ADD2 for airborne POS［J］. The Journal of Navigation， 2013, 66: 209225.

［24］Vapnik V N. The nature of statistical learning［M］. Berlin: Springer, 1995.

[1]	张晓文，孙小明，蒋祖华，胡家文. 考虑生产线平衡的串-并联生产系统机会维护策略[J]. 上海交通大学学报（自然版）, 2015, 49(05): 702-707.
[2]	任会峰, 阳春华, 周璇, 桂卫华, 鄢锋. 基于最小二乘支持向量回归机的矿浆酸碱度鲁棒软测量[J]. 上海交通大学学报（自然版）, 2011, 45(08): 1136-1139.
[3]	胡友涛, 胡昌华. 一种基于遗传算法优化小波支持向量回归机的实时寿命预测方法[J]. 上海交通大学学报（自然版）, 2011, 45(08): 1216-1220.
[4]	张心光, 邹早建. 基于支持向量回归机的船舶操纵响应模型辨识[J]. 上海交通大学学报（自然版）, 2011, 45(04): 501-504.

基于支持向量回归机的自适应差分滤波算法研究

Adaptive Divided Difference Filter Algorithm Based on Support Vector Regression

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价