中文 | English

J. Hefei Univ. Tech. (Nat. Sci.)

合肥工业大学学报(自然科学版)

JOURNAL OF HEFEI UNIVERSITY OF TECHNOLOGY (NATURAL SCIENCE)

Competent Authorities: Ministry of Education of the People's Republic of China

Sponsor by: Hefei University of Technology

ISSN 1000-1646, CN 34-1001/N

Radar signal sorting algorithm based on improved fuzzy C-means clustering

Download Full Text

基于改进模糊 C 均值聚类的雷达信号分选算法

Journal Information

J. Hefei Univ. Tech. (Nat. Sci.), May.2026, Vol.49 No.5: 621-628

DOI: 10.3969/j.issn.1003-5060.2026.05.007

Authors

ZHANG Zhenyu, CHEN Die

(School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China)

Abstract and Keywords

Abstract: In radar signal sorting, in response to the challenges faced by the fuzzy C-means(FCM) clustering algorithm, including the requirement to specify the number of clusters, sensitivity to the initial value, and unsatisfactory sorting performance in cases of uneven data distributions, this paper proposes an improved FCM clustering algorithm based on data field and cluster center constraints. The algorithm firstly determines the potential center by using the theory of the data field, and then the potential center is taken as a constraint point of the algorithm for clustering and sorting. The improved algorithm does not need to specify the number of clusters, is insensitive to the initial value, and achieves good sorting results when the data is unevenly distributed. Simulation experiments show that the sorting accuracy of the improved algorithm can reach more than 95%. Compared with the conventional clustering algorithms, the improved algorithm exhibits higher sorting accuracy and enhanced stability.

Keywords: radar signal sorting; fuzzy C-means(FCM) clustering algorithm; data field; pulse description word

作者信息

张振宇，陈碟

(电子科技大学数学科学学院，四川成都 611731)

摘要和关键词

摘要: 在雷达信号分选中, 针对模糊 C 均值(fuzzy C-means, FCM)聚类算法需预先指定聚类数目、对初值敏感以及数据数量分布不均时分选效果不佳等问题, 文章提出一种基于数据场和类中心约束的改进 FCM 算法。该算法首先利用数据场理论确定势心, 再将这些势心作为约束点进行聚类分选; 改进后的算法无需指定聚类数目, 对初值不敏感, 且在数据数量分布不均时仍能取得很好的分选效果。仿真实验结果表明, 改进算法的分选准确率高达 95% 以上, 与传统的聚类算法相比, 改进算法的分选准确率更高, 结果更稳定。

关键词: 雷达信号分选；模糊 C 均值（FCM）聚类算法；数据场；脉冲描述字

Funding

国家自然科学基金资助项目（71871046）

Previous Next

Back to Contents