基于ITD-SVD和MOMEDA的故障特征提取方法

doi:10.3969/j.issn.1007-7375.2021.06.007

工业工程 ›› 2021, Vol. 24 ›› Issue (6): 48-56.doi: 10.3969/j.issn.1007-7375.2021.06.007

基于ITD-SVD和MOMEDA的故障特征提取方法

杨静宗, 杨天晴, 吴丽玫

保山学院大数据学院，云南保山 678000

收稿日期:2020-05-13 发布日期:2022-01-24
通讯作者: 杨天晴(1991-),男,云南省人,讲师,硕士,主要研究方向为数据挖掘。E-mail:822134845@qq.com E-mail:822134845@qq.com
作者简介:杨静宗(1991—)，男，云南省人，副教授，博士，主要研究方向为复杂工业过程控制、检测与优化
基金资助:
云南省科技厅地方本科高校基础研究联合专项资助项目(2019FH001-121)；云南省大学生创新创业训练计划资助项目(S202010686007)；第十批保山市中青年学术和技术带头人培养项目资助(202109)

A Fault Feature Extraction Method Based on ITD-SVD and MOMEDA

YANG Jingzong, YANG Tianqing, WU Limei

School of Big Data, Baoshan University, Baoshan 678000, China

Received:2020-05-13 Published:2022-01-24

摘要/Abstract

摘要： 为提高滚动轴承故障诊断的准确性，提出一种基于固有时间尺度分解(ITD)、奇异值分解(SVD)和多点最优最小熵反褶积(MOMEDA)相结合的故障特征提取方法。首先，采用ITD分解故障振动信号，并构建基于峭度和相关系数的组合权重指标筛选准则，从而完成分量信号的筛选与重构。其次，对其进行SVD滤波降噪。最后，利用MOMEDA提取降噪后信号中的周期性冲击成分，并通过Hilbert包络谱分析得到诊断结果。经过实验数据分析，结果表明所提出的方法不仅能滤除噪声干扰，增强故障特征信息，而且能准确提取出故障特征。

关键词: 固有时间尺度分解, 奇异值分解(SVD), 多点最优最小熵反褶积(MOMEDA), 故障特征提取

Abstract: In order to improve the accuracy of rolling bearing fault diagnosis, a fault feature extraction method based on the combination of intrinsic time scale decomposition (ITD), singular value decomposition (SVD) and multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) is proposed. Firstly, ITD is used to decompose the fault vibration signal, and the component signal is filtered and reconstructed according to the combination of kurtosis and correlation coefficient weight index screening criteria. Then the SVD filter is used to reduce the noise. Finally, the periodic impact components in the noise reduced signal are extracted by MOMEDA, and the diagnosis results are obtained by Hilbert envelope analysis. Through the analysis of experimental data, the results show that the proposed method can not only filter out noise interference, enhancing fault feature information, but also extract fault features accurately.

Key words: intrinsic time scale decomposition, singular value decomposition (SVD), multipoint optimal minimum entropy deconvolution adjusted (MOMEDA), fault feature extraction

中图分类号:

TP18

杨静宗, 杨天晴, 吴丽玫. 基于ITD-SVD和MOMEDA的故障特征提取方法[J]. 工业工程, 2021, 24(6): 48-56.

YANG Jingzong, YANG Tianqing, WU Limei. A Fault Feature Extraction Method Based on ITD-SVD and MOMEDA[J]. Industrial Engineering Journal, 2021, 24(6): 48-56.

参考文献

[1] 李益兵, 王磊, 江丽. 基于PSO改进深度置信网络的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(5): 89-96
LI Yibing, WANG Lei, JIANG Li. Rolling bearing fault diagnosis based on DBN algorithm improved with PSO[J]. Journal of Vibration and Shock, 2020, 39(5): 89-96
[2] 杨磊, 杨帆, 何艳. 采用样本熵-完备经验模态分解的脑电信号眼电伪迹去除算法[J]. 西安交通大学学报, 2020, 54(8): 1-9
YANG Lei, YANG Fan, HE Yan. EOG artifacts removal algorithm for EEG signals based on sample entropy-complete ensemble empirical mode decomposition with adaptivenoise[J]. Journal of Xi'an Jiaotong University, 2020, 54(8): 1-9
[3] HUANG N E, SHEN Z, LONG S R. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non -stationary time series analysis[C/OL]. (1998-03-08). https://royalsocietypublishing.org/doi/10.1098/rspa.1998.0193.
[4] 赵书涛, 马莉, 朱继鹏, 等. 基于CEEMDAN样本熵与FWA-SVM的高压断路器机械故障诊断[J]. 电力自动化设备, 2020, 40(3): 181-186
ZHAO Shutao, MA Li, ZHU Jipeng, et al. Mechanical fault diagnosis of high voltage circuit breaker based on CEEMDAN sample entropy and FWA-SVM[J]. Electric Power Automation Equipment, 2020, 40(3): 181-186
[5] 张文斌, 江洁, 俞利宾, 等. 互补集合经验模式分解与奇异值能量谱在风电齿轮故障识别中的应用[J]. 太阳能学报, 2020, 41(2): 137-143
ZHANG Wenbin, JIANG Jie, YU Libin, et al. Application of complementary ensemble empirical mode decomposition and singular value energy spectrum in wind power gear fault identification[J]. Acta Energiae Solaris Sinica, 2020, 41(2): 137-143
[6] 邓勇, 胡徐松. 基于EMD和SPS的容差模拟电路故障诊断[J]. 电子测量与仪器学报, 2020, 34(2): 67-72
DENG Yong, HU Xusong. Fault diagnosis of tolerance analog circuit based on EMD and SPS method[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(2): 67-72
[7] 胡茑庆, 陈徽鹏, 程哲, 等. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7): 9-18
HU Niaoqing, CHEN Huipeng, CHEN Zhe, et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering, 2019, 55(7): 9-18
[8] YAN Jihong, LU Lei. Improved Hilbert-Huang transform based weak signal detection methodology and its application on incipient fault diagnosis and ECG signal analysis[J]. Signal Processing, 2014, 98: 74-87
[9] CHENG Junsheng, YU Dejie, TANG Jiashi. Application of frequency family separation method based upon EMD and local Hilbert energy spectrum method to gear fault diagnosis[J]. Mechanism and Machine Theory, 2008, 43(6): 712-723
[10] WU Zhaohua, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J/OL]. (2009-01-01). https://www-worldscientific-com-s.vpn.seu.edu.cn:8118/doi/abs/10.1142/S1793536909000047.
[11] FREI M G, OSORIO I. Intrinsic time-scale decomposition: time-frequency energy analysis and real-time filtering of non-stationary signals[J]. Royal Society of London Proceedings, 2007, 463: 321-342
[12] 张朝林, 范玉刚, 冯早. ITD-多尺度熵和ELM的风电轴承健康状态识别[J]. 机械科学与技术, 2018, 37(11): 1731-1736
ZHANG Zhaolin, FAN Yugang, FENG Zao. Health status recognition of wind turbine bearings based on ITD-MSE and ELM[J]. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(11): 1731-1736
[13] 任东方, 张涛, 韩洁. 结合ITD与非线性分析的通信辐射源个体识别方法[J]. 信号处理, 2018, 34(3): 331-339
REN Dongfang, ZHANG Tao, HAN Jie. Approach of specific communication emitter identification combining ITD and nonlinear analysis[J]. Journal of Signal Processing, 2018, 34(3): 331-339
[14] 赵雄鹏, 潘宏侠, 刘广璞, 等. 应用ITD分形模糊熵的自动机早期故障诊断[J]. 机械设计与制造, 2019(1): 134-137
ZHAO Xiongpeng, PAN Hongxia, LIU Guangpu, et al. Application of ITD fractal fuzzy entropyin automaton early fault diagnosis[J]. Machinery Design & Manufacture, 2019(1): 134-137
[15] PENG S, LIAO Y H, LIN J. The shock pulse index and its application in the fault diagnosis of rolling element bearings[J]. Sensors, 2017, 17(3): 535-560
[16] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study[J]. Mechanical Systems and Signal Processing Method, 2015, 64–65: 100-131

基于ITD-SVD和MOMEDA的故障特征提取方法

A Fault Feature Extraction Method Based on ITD-SVD and MOMEDA

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	禹春霞, 刘玉茹, 高旭. 面向用户个性化需求的云服务商推荐[J]. 工业工程, 2019, 22(2): 1-9.
[2]	包珊珊, 张敏, 尹健康, 蔡振宇. 考虑半托盘出库的堆垛机复合作业拣选路径优化研究[J]. 工业工程, 2019, 22(1): 90-99.
[3]	郝志刚. 考虑医患满意度和手术成本的日手术排程方法[J]. 工业工程, 2017, 20(4): 49-56,71.
[4]	蔡子维, 杨春燕. 可拓创新方法与六西格玛管理方法的集成研究[J]. 工业工程, 2017, 20(3): 60-67.
[5]	王维军, 罗伟. 基于改进智能水滴算法的冷链物流配送路径优化问题研究[J]. 工业工程, 2017, 20(2): 38-43.
[6]	禹春霞, 李南南. 面向燃气具的用户个性化推荐模型[J]. 工业工程, 2019, 22(6): 57-66.
[7]	芦娟, 夏扬坤, 邹安全, 符卓, 王松, 魏占国, 符瑛. 带装载能力的需求依背包拆分车辆路径问题[J]. 工业工程, 2019, 22(6): 67-73.
[8]	刘洪伟, 胡琪, 徐冉, 王明洁. 基于直线往复单智能RGV系统单工序调度研究[J]. 工业工程, 2020, 23(2): 34-40.
[9]	唐红涛, 方博, 高晓灵, 李香怡, 殷伟铭. 基于GSA-GA神经网络的铸造企业订单准入评价研究[J]. 工业工程, 2020, 23(4): 121-130.
[10]	唐红涛, 杨志鹏, 刘家毅. 考虑工序并行的差异工件批调度研究[J]. 工业工程, 2021, 24(3): 68-76,114.