作者：王建国, 杨云中, 秦波, 刘永亮

作者单位：内蒙古科技大学机械工程学院, 内蒙古 包头 014010

关键词：IMF分量;峭度和能量特征;最小二乘支持向量机;故障诊断

摘要：

针对齿轮振动信号非线性非平稳特性,为避免传统时频方法在表征设备状态时的不足,提出一种基于融合峭度与IMF能量特征和LS-SVM的齿轮故障诊断方法。首先,对齿轮振动信号在EMD分解;然后,提取包含主要故障信息的IMF分量的峭度特征和能量特征,组成融合特征向量;最后,将齿轮正常、齿根裂纹、断齿3种状态下的融合特征向量输入到LS-SVM,通过训练好的LS-SVM对齿轮状态进行分类识别。仿真实验结果表明:该方法能准确识别齿轮的工作状态,且与BP神经网络、SVM相比,有着更高的故障识别效率,可用于齿轮信号的故障诊断。

Gear fault diagnosis research based on kurtosis and IMF energy feature fusion and least squares support vector machine

WANG Jianguo, YANG Yunzhong, QIN Bo, LIU Yongliang

Mechanical Engineering School, Inner Mongolia University of Science & Technology, Baotou 014010, China

Abstract: Gear vibration signals have nonlinear and non-stationary characteristics. To avoid the disadvantages of existing time and frequency domain methods in the characterization of equipment state, this paper has been proposed a gearbox fault diagnosis method based on kurtosis and IMF energy feature fusion and least squares support vector machine. First, the gear vibration signals were decomposed by the EMD method. Second, the IMF components which contain major fault information were extracted and their energy and kurtosis feature calculated as fusion vectors. Third, the fusion feature vectors of three teeth conditions, viz., normal, root crack and broken, were input to the least squares support vector machine(LS-SVM) to classify and identify gearbox faults. The simulation results show that this method can accurately identify the gear working state and more efficient in fault identification compared with BP neural network and SVM. It can be used for diagnosing gear signal faults.

Keywords: IMF component;kurtosis and energy feature;LS-SVM;fault diagnosis

2016, 42(4): 93-97  收稿日期: 2015-06-01;收到修改稿日期: 2015-07-20

基金项目: 国家自然科学基金项目(21366017);内蒙古科技厅高新技术领域科技计划重大项目(20130302)

作者简介: 王建国(1958-),男,内蒙古呼和浩特市人,教授,硕士生导师,博士,研究方向为机电系统智能诊断与复杂工业过程建模的优化。

参考文献

[1] 张超,陈建军,郭迅. 基于EMD能量熵和支持向量机的齿轮故障诊断方法[J]. 振动与冲击,2010,29(10):216-220.
[2] 陈水宣,邹俊,易际明,等. 基于峭度和小波包能量特征的齿轮箱早期故障诊断及抗噪研究[J]. 机械传动,2012, 36(11):9-14.
[3] 吴伟,郑娟. 基于BP神经网络的齿轮故障诊断[J]. 机械研究与应用,2015,28(1):88-93.
[4] 于德介,程军圣,杨宇. Hilbert-Huang变换在齿轮故障诊断中的应用[J]. 机械工程学报,2005,41(6):102-106.
[5] 肖志勇,杨小玲,刘爱伦. 基于改进EMD和LSSVM的机械故障诊断[J]. 自动化仪表,2008,29(6):24-26.
[6] 唐贵基,庞尔军,王晓龙. 基于EMD的齿轮箱齿轮故障诊断的研究[J]. 机床与液压,2013,41(13):188-190.
[7] 韩清凯,于晓光. 基于振动分析的现代机械故障诊断原理及应用[M]. 北京:科学出版社,2010:49-51.
[8] 黄俊,潘宏侠,都衡. 基于EMD近似熵和LSSVM的齿轮箱故障诊断研究[J]. 组合机床与自动化加工技术,2014(3):111-113.
[9] 韩永杰,郝伟,董辛旻. 基于EMD和冲击脉冲的齿轮故障诊断[J]. 机械设计与制造,2009(10):222-224.
[10] ABBASIONA S, RAFSANJANIA A, FARSHIDIANFARB A,et al. Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine[J]. Mechanical Systems and Signal Processing,2007(21):2933-2945.
[11] LI Y B, XU M Q, WEI Y, et al. An improvement EMD method based on the optimized rational Hermite interpolation approach and its application to gear fault diagnosis[J]. Measurement,2015(63):330-345.
[12] YANG D L, LIU Y L, LI S B, et al. Gear fault diagnosis based on support vector machine optimized by artificial bee colony algorithm[J]. Mechanism and Machine Theory,2015,90(8):219-229.