Feature extraction and fault diagnosis of gearbox based on ICEEMDAN, MPE, RF and SVM

DING Xiaofeng; ZHANG Yuhua

doi:10.13890/j.issn.1000-128X.2023.01.006

您当前的位置：

首页 >

文章列表页 >

Feature extraction and fault diagnosis of gearbox based on ICEEMDAN, MPE, RF and SVM

Railway Rolling Stock | 更新时间：2024-08-02

- Feature extraction and fault diagnosis of gearbox based on ICEEMDAN, MPE, RF and SVM
- Electric Drive for Locomotives Issue 1, Pages: 42-50(2023)
- 作者机构：
  
  上海电力大学电气工程学院，上海　　200090
- 作者简介：
- 基金信息：
- DOI：10.13890/j.issn.1000-128X.2023.01.006
  CLC： TH17;TH132
- Published：10 January 2023，
  
  Received：31 July 2022，
  
  Revised：26 November 2022，
- 稿件说明：
扫描看全文
丁晓锋, 张宇华. 基于ICEEMDAN-MPE-RF和SVM的齿轮箱特征提取与故障诊断[J]. 机车电传动, 2023(1): 42-50.

DING Xiaofeng, ZHANG Yuhua. Feature extraction and fault diagnosis of gearbox based on ICEEMDAN, MPE, RF and SVM[J]. Electric Drive for Locomotives, 2023(1): 42-50.
丁晓锋, 张宇华. 基于ICEEMDAN-MPE-RF和SVM的齿轮箱特征提取与故障诊断[J]. 机车电传动, 2023(1): 42-50. DOI： 10.13890/j.issn.1000-128X.2023.01.006.

DING Xiaofeng, ZHANG Yuhua. Feature extraction and fault diagnosis of gearbox based on ICEEMDAN, MPE, RF and SVM[J]. Electric Drive for Locomotives, 2023(1): 42-50. DOI： 10.13890/j.issn.1000-128X.2023.01.006.

摘要

针对齿轮箱非平稳振动信号特征提取难、特征向量冗余度高和故障识别率低的问题，提出基于改进的自适应噪声完备集成经验模态分解（Improved complete ensemble empirical mode decomposition with adaptive noise，ICEEMDAN）、多尺度排列熵（Multi-scale permutation entropy，MPE）、随机森林（Random forest，RF）特征重要性排序和支持向量机（Support vector machine，SVM）的齿轮箱特征提取与故障诊断方法。首先，通过ICEEMDAN将各种故障状态的齿轮振动信号分解为一系列不同频率分布的本征模态分量（Intrinsic mode functions，IMF）；然后，计算各阶IMF的MPE值获得非平稳信号时频分布下的非线性动力学特征；最后，通过RF算法评估特征重要性，选择高重要性敏感特征组成最优特征子集输入SVM进行故障模式识别。试验结果表明，该方法特征提取和表征能力强，在不同工况下的平均识别率可达99.79%，在多工况和小样本数据集上比其他方法更具稳健性。

Abstract

To solve the challenges related to non-stationary vibration signals in gearboxes

i.e. difficult feature extraction

high redundancy of feature vectors and low fault identification rate

this paper proposed a method of feature extraction and fault diagnosis of gearboxes based on the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN)

multi-scale permutation entropy (MPE)

random forest (RF) feature importance ranking and support vector machine (SVM). Firstly

the vibration signals of gears in various fault states were decomposed into a series of intrinsic mode functions (IMF) with different frequency distributions by ICEEMDAN. Then

the MPE values of the IMFs were calculated to obtain the nonlinear dynamic features of non-stationary signals in time-frequency distribution. Finally

the importance of such features was evaluated by the RF algorithm

and the sensitive features with high importance were selected to form the optimal feature subset as the input to SVM for fault pattern recognition. The experimental results show that this method with strong feature extraction and representation ability and as high as 99.79% recognition rate on average under different operating conditions is more robust in multi-operating conditions and small sample data sets

compared with other methods.

关键词

齿轮箱改进的自适应噪声完备集成经验模态分解多尺度排列熵随机森林支持向量机特征提取故障诊断

Keywords

gearboximproved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN)multi-scale permutation entropy (MPE)random forest (RF)support vector machine (SVM)feature extractionfault diagnosis

references

李长青, 林建辉, 胡永旭. 优化参数VMD和MED在列车齿轮箱滚动轴承故障诊断中的应用[J]. 机车电传动, 2020(3): 142-147.

LI Changqing, LIN Jianhui, HU Yongxu. Application of optimization parameters VMD and MED in fault diagnosis of train gearbox rolling bearings[J]. Electric Drive for Locomotives, 2020(3): 142-147.

PEI Xinglong, ZHENG Xiaoyang, WU Jinliang. Rotating machinery fault diagnosis through a transformer convolution network subjected to transfer learning[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-11.

WANG Chaoge, LI Hongkun, ZHANG Kongliang, et al. Intelligent fault diagnosis of planetary gearbox based on adaptive normalized CNN under complex variable working conditions and data imbalance[J]. Measurement, 2021, 180: 109565.

陈鹏, 赵小强, 朱奇先. 基于多尺度排列熵和改进多分类相关向量机的滚动轴承故障诊断方法[J]. 电子测量与仪器学报, 2020, 34(2): 20-28.

CHEN Peng, ZHAO Xiaoqiang, ZHU Qixian. Rolling bearing fault diagnosis method based on multi-scale permutation entropy and improved multi-class relevance vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(2): 20-28.

LI Yongbo, WANG Xianzhi, LIU Zhenbao, et al. The entropy algorithm and its variants in the fault diagnosis of rotating machinery: a review[J]. IEEE Access, 2018, 6: 66723-66741.

LIN Jinshan, DOU Chunhong, LIU Yingjie. Feature extraction based on generalized permutation entropy for condition monitoring of rotating machinery[J]. Nonlinear Dynamics, 2022, 107(1): 855-870.

王振亚, 姚立纲, 蔡永武, 等. 基于熵-流特征和樽海鞘群优化支持向量机的故障诊断方法[J]. 振动与冲击, 2021, 40(6): 107-114.

WANG Zhenya, YAO Ligang, CAI Yongwu, et al. Fault diagnosis method based on the entropy-manifold feature and SSO-SVM[J]. Journal of Vibration and Shock, 2021, 40(6): 107-114.

LI Yongbo, WANG Shun, LI Ni, et al. Multiscale symbolic diversity entropy: a novel measurement approach for time-series analysis and its application in fault diagnosis of planetary gearboxes[J]. IEEE Transactions on Industrial Informatics, 2022, 18(2): 1121-1131.

LI Hongmei, HUANG Jinying, YANG Xiwang, et al. Fault diagnosis for rotating machinery using multiscale permutation entropy and convolutional neural networks[J]. Entropy, 2020, 22(8): 851-874.

XU Xiaoli, LIU Xiuli. Fault diagnosis method for wind turbine gearbox based on image characteristics extraction and actual value negative selection algorithm[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2020, 34(14): 2054034.

ZHANG Xun, XU Guanghua, KUANG Jiachen, et al. A three-phase current tacholess envelope order analysis method for feature extraction of planetary gearbox under variable speed conditions[J]. Sensors, 2021, 21(17): 5714-5735.

SHI Haiyang, QIN Yi, WANG Yi, et al. An improved Viterbi algorithm for adaptive instantaneous angular speed estimation and its application into the machine fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-11.

党建, 罗燚, 田录林, 等. 基于优化的VMD融合信息熵和FA_PNN的风电机组齿轮箱故障诊断[J]. 太阳能学报, 2021, 42(1): 198-204.

DANG Jian, LUO Yi, TIAN Lulin, et al. Fault diagnosis of wind turbine gearbox based on optimized VMD fusion information entropy and FA_PNN[J]. Acta Energiae Solaris Sinica, 2021, 42(1): 198-204.

KUAI Moshen, CHENG Gang, PANG Yusong, et al. Research of planetary gear fault diagnosis based on permutation entropy of CEEMDAN and ANFIS[J]. Sensors, 2018, 18(3): 782-799.

王宏伟, 孙文磊, 张小栋, 等. 基于优化VMD复合多尺度散布熵及LSTM的风力发电机齿轮箱故障诊断方法研究[J]. 太阳能学报, 2022, 43(4): 288-295.

WANG Hongwei, SUN Wenlei, ZHANG Xiaodong, et al. Fault diagnosis method of wind turbine's gearbox based on composite multiscale dispersion entropy of optimised VMD and LSTM[J]. Acta Energiae Solaris Sinica, 2022, 43(4): 288-295.

BIE Fengfeng, GU Sheng, GUO Yue, et al. Research on gearbox impact feature extraction method based on improved ESMD[J]. Insight - Non-Destructive Testing and Condition Monitoring, 2022, 64(1): 20-27.

ZHANG Yi, LV Yong, GE Mao. Time-frequency analysis via complementary ensemble adaptive local iterative filtering and enhanced maximum correlation kurtosis deconvolution for wind turbine fault diagnosis[J]. Energy Reports, 2021, 7: 2418-2435.

COLOMINAS M A, SCHLOTTHAUER G, TORRES M E. Improved complete ensemble EMD: a suitable tool for biomedical signal processing[J]. Biomedical Signal Processing and Control, 2014, 14: 19-29.

BANDT C, POMPE B. Permutation entropy: a natural complexity measure for time series[J]. Physical Review Letters, 2002, 88(17): 174102.

AZIZ W, ARIF M. Multiscale permutation entropy of physiological time series[C]//IEEE. 2005 Pakistan Section Multitopic Conference. Karachi, Pakistan: IEEE, 2005: 1-6.

HAN Dongying, GUO Xiaoci, SHI Peiming. An intelligent fault diagnosis method of variable condition gearbox based on improved DBN combined with WPEE and MPE[J]. IEEE Access, 2020, 8: 131299-131309.

Views

下载量

CSCD

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault diagnosis technology for three-level inverter based on ICEEMDAN-FE and SVM

Stator Insulation Partial Discharge Test and Reliability Evaluation of Traction Motor

Extracting of Fault Features for Rotating Machinery of High-speed Train Based on EEMD Energy Entropy-LPP

Fault Diagnosis of Gearbox Bearings of High-speed Train Based on the SVD-MOMEDA

Application of an Impact Feature Extracting Method Based on WATV in Fault Diagnosis of High-speed Train Bearing

Related Author

CAO Ruijun

GUO Qiyi

Yuenan LIU

Min GENG

Junfeng GUI

Ruizhen CUI

Xilian WANG

Chen ZHANG

Related Institution

College of Electronic and Information Engineering, Tongji University

School of Electrical Engineering, Beijing Jiaotong University

Motor Vehicle Maintenance Department, CRRC Tangshan Co., Ltd.

Armored Vehicle Technology Department, Campus of Urumqi, Engineering University of PAP

CRRC Tangshan Co., Ltd.

⁰