作者：张玉学1, 潘宏侠1,2, 安邦1
作者单位：1. 中北大学机械与动力工程学院, 山西 太原 030051;
2. 中北大学系统辨识与诊断技术研究所, 山西 太原 030051
关键词：自动机;聚合经验模态;模糊C均值聚类算法;能量比;故障诊断
摘要：
针对自动机使用中常见的故障检测与识别问题，考虑到自动机振动响应信号非线性、短时、瞬态和冲击特性，提出基于聚合经验模态分解（EEMD）和模糊C均值（FCM）聚类结合的自动机故障诊断方法。首先，使用EEMD分解方法对自动机的振动信号进行分解，结合相关系数提取前5个固有模态函数（IMF）分量的能量百分比作为特征值，再用模糊C均值聚类对特征值进行聚类分析。通过对自动机不同工况分别用EEMD和EMD方法进行故障分类识别对比，结果表明：所有样本的诊断结果与实际情况基本符合，证明EEMD法有更好的分类效果，分类正确率达93.75%。从而验证该方法能有效应用在自动机故障诊断中。
Automaton fault diagnosis based on EEMD and FCM clustering
ZHANG Yuxue1, PAN Hongxia1,2, AN Bang1
1. School of Mechanical and Power Engineering, North University of China, Taiyuan 030051, China;
2. System Identification and Diagnosis Technology Research Institute, North University of China, Taiyuan 030051, China
Abstract: A method automaton fault diagnosis based on ensemble empirical mode decomposition(EEMD) and fuzzy C means clustering(FCM) is proposed for the detection and identification problems of common faults when using automaton in view of the nonlinear, short-time, transient and impact properties of the automaton vibration response signal. Firstly, EEMD decomposition method is used to decompose automaton vibration signal, and energy percentage of components of the first five intrinsic mode function(IMF) is extracted as the fault feature value based on relevant coefficients, then cluster analysis is carried out for those feature values based on FCM clustering. The EEMD and EMD methods are used to carry out fault classification, identification and comparison according to different working conditions of automaton. The results show that the diagnosed results of all samples are basically conform to the actual conditions, with classification accuracy reaching 93.75%, which verifies that the method can be effectively used for automaton fault diagnosis.
Keywords: automaton;EEMD;FCM;energy ratio;fault diagnosis
2017, 43(3): 106-110 收稿日期: 2016-07-22;收到修改稿日期: 2016-08-19
基金项目: 国家自然科学基金项目（51175480）
作者简介: 张玉学(1993-),男,河南鹤壁市人,硕士研究生,专业方向为信号识别与处理、装备系统检测与诊断。
参考文献
[1] 康郦,冯德朝. 某中口径舰炮自动机设计思想与特点分析[J]. 火炮发射与控制学报,2010(2):61-65.
[2] 曾晋春,杨国来,王晓锋. 某火炮自动机虚拟样机建模与仿真[J]. 火炮发射与控制学报,2008(3):42-45.
[3] 褚福磊. 机械故障诊断中的现代信号处理方法[M]. 北京:科学出版社,2009:51-54.
[4] WU Z H, HUANG N E. Ensemble empirical mode dec omposition:a noise assisted data analysis method[J]. Advances in Adaptive Data Analysis,2009,1(1):1-41.
[5] 王军辉,贾嵘,谭泊. 基于EEMD和模糊C均值聚类的风电机组齿轮箱故障诊断[J]. 太阳能学报,2015,36(2):319-324.
[6] 苗晟,王威廉,姚绍文. Hilbert-Huang变换发展历程及其应用[J]. 电子测量与仪器学报,2014,28(8):812-818.
[7] HUANG N E, SHEN Z, LONG S R, et al. The empir ical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time seriesanalysis[J]. Proceedings of the Royal Society of London A,1998,454(1971):903-995.
[8] 冯金福,鲁卿,张佳强. 一种基于鲁棒FCM算法的故障诊断方法[J]. 仪器仪表学报,2008,29(10):2175-2180.
[9] LEI Y G, HE Z J, ZI Y Y. Application of the EEMD method to rotor fault diagnosis of rotating machinery[J]. Mechanical Systems and Signal Processing,2009(23):1327-1338.
[10] 蔡静颖. 模糊聚类算法及应用[M]. 北京:冶金工业出版社,2015:71-77.
[11] PAL N R, BEZDEK J C. On cluster validity for the fuzzy c-means model[J]. IEEE Trans Fuzzy Systems,1995,3(3):370-379.
[12] 于淼. 复杂应力状态下高温低周疲劳短裂纹萌生及扩展规律研究[D]. 大连:大连理工大学,2006.
[13] 赵勇,杨慎华,郑祺峰. 激光预制裂纹槽的断裂分析[J]. 吉林大学学报(工学版),2011,41(4):984-987.
[14] 田园,潘宏侠,陈玉青,等. 应用S.L.Peng窄带分解与广义分形的自动机故障诊断[J]. 中国测试,2016,42(2):100-104.
