自然科学版 英文版
自然科学版 英文版
自然科学版 英文版
自然科学版 英文版
英文版编委
自然科学版 英文版
英文版首届青年编委

您目前所在的位置:首页 - 期刊简介 - 详细页面

中南大学学报(自然科学版)

Journal of Central South University

第50卷    第11期    总第303期    2019年11月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7207(2019)11-2763-10
基于EEMD多尺度样本熵的S700K转辙机故障诊断
魏文军1, 2,刘新发1

(1. 兰州交通大学 自动化与电气工程学院,甘肃 兰州,730070;
2. 兰州交通大学 光电技术与智能控制教育部重点实验室,甘肃 兰州,730070
)

摘 要: 针对S700K转辙机在运行过程中的故障诊断问题,提出一种基于集合经验模态分解(EEMD)的多尺度样本熵的信号分析及故障诊断方法。首先对S700K转辙机功率曲线进行EEMD分解,得到不同时间尺度的固有模态函数(IMF)分量,并提取每一个IMF分量的样本熵,由于样本熵能够有效区分不同信号的复杂度,故可获得转辙机不同状态下的特征参数。最后,利用这些不同运行状态下的特征参数构建特征模式矩阵,采用模糊聚类分析算法求解该矩阵的模糊等价矩阵。在模糊等价矩阵中,当λ(可变阈值)在[0, 1]范围内变动时,模糊等价矩阵转化为等价的布尔矩阵,由布尔矩阵可以得到动态聚类图并得到分类结果,从而实现故障诊断。研究结果表明:本文算法能准确提取故障特征且支持多种故障同时检测,有效提高了S700K转辙机故障诊断的精度与效率。

 

关键词: EEMD;多尺度样本熵;固有模态函数(IMF);模糊聚类;等价矩阵

Fault diagnosis of S700K switch machine based on EEMD multiscale sample entropy
WEI Wenjun1, 2, LIU Xinfa1

1. School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070;
2. Key Laboratory of Opto-technology and Intelligent Control of Ministry of Education,
Lanzhou Jiaotong University, Lanzhou 730070, China

Abstract:Aiming at the fault diagnosis of S700K switch machine in operation, a signal analysis and fault diagnosis method based on ensemble empirical mode decomposition (EEMD) and multiscale sample entropy was proposed. Firstly, the power curve of S700K switch machine was decomposed by EEMD, and the intrinsic mode function (IMF) of different time scales were obtained. The sample entropy of each IMF component was extracted. Because the sample entropy can effectively distinguish the complexity of different signals, the characteristic parameters of different states of the switch machine were obtained. Finally, the characteristic pattern matrix was constructed by using the characteristic parameters of the switch machine in different operation states, and the fuzzy equivalent matrix of the matrix was obtained by using the fuzzy clustering analysis algorithm. In the fuzzy equivalent matrix, when λ (variable threshold) changes within [0,1], the fuzzy equivalent matrix was transformed into the equivalent Boolean matrix. The dynamic clustering graph was obtained from the Boolean matrix and the classification result was obtained to realize fault diagnosis . The results show that the algorithm can accurately extract fault features and support multiple fault detection simultaneously. The accuracy and efficiency of fault diagnosis of S700K switch machine is effectively improved.

 

Key words: EEMD; multiscale sample entropy; intrinsic mode function (IMF); fuzzy clustering; equivalent matrix

中南大学学报(自然科学版)
  ISSN 1672-7207
CN 43-1426/N
ZDXZAC
中南大学学报(英文版)
  ISSN 2095-2899
CN 43-1516/TB
JCSTFT
版权所有:《中南大学学报(自然科学版、英文版)》编辑部
地 址:湖南省长沙市中南大学 邮编: 410083
电 话: 0731-88879765(中) 88836963(英) 传真: 0731-88877727
电子邮箱:zngdxb@csu.edu.cn 湘ICP备09001153号