电子学报 ›› 2016, Vol. 44 ›› Issue (7): 1734-1741.DOI: 10.3969/j.issn.0372-2112.2016.07.031

• 学术论文 • 上一篇    下一篇

保持粒子多样性的非退化粒子滤波方法研究

吴昊1,2, 孙晓燕1, 郭玉堂2, 刘路路2, 沈晶2   

  1. 1. 中国矿业大学信息与电气工程学院, 江苏徐州 221008;
    2. 合肥师范学院计算机学院, 安徽合肥 230601
  • 收稿日期:2015-01-28 修回日期:2015-08-10 出版日期:2016-07-25
    • 作者简介:
    • 吴昊 男,1983年5月出生,安徽舒城人.合肥师范学院讲师,2010硕士毕业于合肥工业大学,2015年进入中国矿业大学,博士生,从事图像处理、优化算法方面的有关研究.E-mail:dillon_wu@126.com;孙晓燕 女,1978年10月出生,江苏丰县人.教授、博士生导师、IEEE高级会员.从事进化优化算法及应用、多目标进化算法设计和机器学习等方面的工作.E-mail:xysun78@126.com
    • 基金资助:
    • 国家自然科学基金 (No.61301062,No.61503116,No.61375067); 中央高校基本科研业务经费 (No.2012QNA58); 安徽省高校自然基金 (No.KJ2013A217); 安徽省质量工程提升计划 (No.2013zy058); 安徽省教育厅高等学校省级优秀青年人才基金 (No.SQRL129ZD)

Non-Degeneracy Particle Filtering Method Research for Particle Diversity Preserving

WU Hao1,2, SUN Xiao-yan1, GUO Yu-tang2, LIU Lu-lu2, SHEN Jing2   

  1. 1. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221008, China;
    2. School of Computer Science and Technology, Hefei Normal University, Hefei, Anhui 230601, China
  • Received:2015-01-28 Revised:2015-08-10 Online:2016-07-25 Published:2016-07-25
    • Supported by:
    • National Natural Science Foundation of China (No.61301062, No.61503116, No.61375067); Fundamental Research Funds for the Central Universities (No.2012QNA58); Natural Science Foundation for Colleges and Universities in Anhui Province (No.KJ2013A217); Quality Engineering Improvement Project of Anhui Province (No.2013zy058); Foundation for Excellent Young Talent in univerities of Education Department of Anhui Province (No.SQRL129ZD)

摘要:

针对现有粒子滤波算法中的粒子退化问题以及重采样所引起的粒子多样性减弱问题,将自适应遗传算法与粒子滤波结合设计一种新的非退化粒子滤波算法.该算法通过对粒子使用遗传算子操作以保证粒子的多样性和有效性,根据粒子在前一时刻计算出来的先验信息自适应地实时调节当前时刻的遗传操作概率,有效增加了粒子对系统状态变化的适应性.实验结果表明,该算法可有效提高非线性系统状态的估计精度,尤其在系统状态发生突变的时候,可以得到较好的估计精度.

关键词: 粒子滤波, 遗传算法, 粒子退化, 自适应, 粒子多样性

Abstract:

To cope with the degeneracy in the existing particle filter algorithm and the diversity weakening caused by re-sampling,a new non-degeneracy algorithm is proposed in this paper by incorporating adaptive genetic algorithm into particle filter.By using genetic operators to generate new particles,the algorithm can adjust the current probability of genetic manipulation adaptively based on the previously calculated information so that the diversity and effectiveness of the particle can be ensured.It effectively improves the adaptability of particle to the changes of the system state.Experimental results show that this algorithm can effectively improve the estimation accuracy of the nonlinear system state.In particular,the algorithm can guarantee good estimation accuracy when the system state changes abruptly.

Key words: particle filter, genetic algorithm, particle degeneracy, adaptive, diversity of particle

中图分类号: