基于IEWT和IFractalNet的滚动轴承故障诊断

PDF(2869 KB)

振动与冲击 ›› 2020, Vol. 39 ›› Issue (24) : 134-142.

论文

杜小磊1,2,陈志刚1,2,王衍学1,3,张楠1

作者信息 +

Fault diagnosis of rolling bearings based on improved empirical wavelet transform and IFractalNet

DU Xiaolei1,2,CHEN Zhigang1,2,WANG Yanxue1,3, ZHANG Nan1

Author information +

文章历史 +

摘要

针对传统滚动轴承故障诊断方法易受噪声干扰，过度依赖专家经验等问题，提出了一种基于改进经验小波变换（IEWT）和改进分形网络(IFractalNet)的诊断方法。首先改进经验小波变换Fourier谱的分割方式，将轴承原始振动信号自适应分解为若干本征模态分量，并利用基于峭度、相关系数、能量比的综合评价指标筛选出最能反映信号故障特征的本征模态分量（imfs）；然后针对样本集不平衡问题改进分形网络的损失函数和激活函数；最后将筛选到的imfs重构并输入IFractalNet进行自动特征提取与故障识别。实验结果表明：提出方法能够有效地对滚动轴承进行多种故障类型和多种故障程度的识别，避免了复杂的人工特征提取过程，相较于其他方法具有更高的泛化能力、特征提取能力和故障识别能力。

Abstract

Considering that the traditional methods for rolling bearing fault diagnosis largely depend on expert prior knowledge and easily to be disturbed by noise, a method based on improved empirical wavelet transform (IEWT) and improved FractalNet (IFractalNet) was proposed.Firstly, the segmentation method of Fourier spectrum of empirical wavelet transform was improved, and the raw vibration signals of bearings were adaptively decomposed into several intrinsic modal functions (imfs).The imfs which can best reflect the fault characteristics of the raw signals were selected using the comprehensive evaluation index based on kurtosis, correlation coefficient, and energy ratio.Secondly, the loss function and activation function of FractalNet were improved to solve the imbalance problem of sample set.Finally, the selected imfs were reconstructed and fed into IFractalNet for automatic feature extraction and fault recognition.The experimental results indicate that the proposed method can effectively identify the bearings with multiple fault types and multiple fault severities, which is less affected by prior knowledge and subjective knowledge and avoids complex artificial feature extraction process.The generalization ability, feature extraction ability, and recognition ability of proposed method are superior to other methods.

导出引用

杜小磊1,2,陈志刚1,2,王衍学1,3,张楠1. 基于IEWT和IFractalNet的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(24): 134-142

DU Xiaolei1,2,CHEN Zhigang1,2,WANG Yanxue1,3, ZHANG Nan1. Fault diagnosis of rolling bearings based on improved empirical wavelet transform and IFractalNet[J]. Journal of Vibration and Shock, 2020, 39(24): 134-142

参考文献

[1] 陈保家,刘浩涛,徐超,等.深度置信网络在齿轮故障诊断中的应用[J].中国机械工程,2019,30(02):205-211.
CHEN Bao-jia, LIU Hao-tao, XU Chao, et al. Gear fault diagnosis based on DBNS[J]. China Mechanical Engineering, 2019,30(02):205-211.
[2] 周俊,马建林,徐华,等. EMD降噪在高速铁路路基沉降预测中的应用[J]. 振动与冲击, 2016,35(08): 66-72.
ZHOU Jun, MA Jian-lin, XU Hua, et al. Application of EMD noise reduction in prediction of subgrade settlement of high speed railway [J]. Journal of vibration and shock, 2016, 35(08): 66-72.
[3] 马增强,张俊甲,张安,等.基于VMD-SVD联合降噪和频率切片小波变换的滚动轴承故障特征提取[J].振动与冲击, 2018(17): 210-217.W
MA Zeng-qiang, ZHANG Jun-jia, ZHANG An, et al. Fault feature extraction of rolling bearings based on VMD-SVD joint de-noising and FSWT [J]. Journal of vibration and shock, 2018(17): 210-217.
[4] 李兵,刘明亮,杨平.EWT与GS-SVM在断路器机械故障诊断中的应用[J].哈尔滨工程大学学报,2018,39(08):1422-1430.
LI Bing, LIU Ming-liang, YANG Ping. Application of EWT and GS-SVM in mechanical fault diagnosis of circuit breakers [J]. Journal of Harbin Engineering University, 2018,39(08):1422-1430.
[5] Lecun Y, Bengio Y, Hinton G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.
[6] Jurgen S. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61(1): 85-117.
[7] 周奇才,刘星辰,赵炯,等.旋转机械一维深度卷积神经网络故障诊断研究[J].振动与冲击,2018,37(23):31-37.
ZHOU Qi-cai, LIU Xing-chen, ZHAO Jiong, et al. Fault diagnosis for rotating machinery based on 1D deep convolutional neural network [J]. Journal of Vibration and Shock, 2018,37(23):31-37.
[8] 曲建岭,余路,袁涛,等.基于一维卷积神经网络的滚动轴承自适应故障诊断算法[J].仪器仪表学报,2018,39(07):134-143.
QU Jian-ling, YU Lu, YUAN Tao, et al. Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network [J]. Chinese Journal of Scientific Instrument, 2018,39(07): 134-143.
[9] 汪久根,柯梁亮.基于残差网络的RV减速器故障诊断 [J].机械工程学报,2019,55(03):73-80.
WANG Jiu-gen, KE Liang-liang. Fault Diagnosis for RV Reducer Based on Residual Network [J]. Journal of Mechanical Engineering,2019,55(03):73-80.
[10] Gilles J. Empirical wavelet transform[J]. IEEE Transactions on Signal Processing, 2013, 61 (16) : 3999-4010.
[11] 何洋洋,吕跃刚,刘俊承.基于VMD与粒子滤波的滚动轴承故障诊断[J].可再生能源,2019,37(01):126-131.
HE Yang-yang, LV Yue-gang, LIU Jun-cheng. Fault diagnosis of rolling bearing based on VMD and particle filter[J]. Renewable Energy Resources, 2019,37(01):126-131.
[12] 朱艳萍,包文杰,涂晓彤, 等.改进的经验小波变换在滚动轴承故障诊断中的应用[J].噪声与振动控制,2018,38(01):199-203.
ZHU Yan-ping, BAO Wen-jie,TU Xiao-tong, et al. The application of improved wavelet transform in fault diagnosis of rolling bearing[J].Noise and Vibration Control,2018,38(01):199-203.
[13] 朱永利,贾亚飞,王刘旺,等.基于改进变分模态分解和 Hilbert变换的变压器局部放电信号特征提取及分类 [J].电工技术学报,2017, 32(09) :221-235.
ZHU Yong-li, JIA Ya-fei, WANG Liu-wang, et al. Feature extraction and classification on partial discharge signals of power transformers based on improved variational mode decomposition and hilbert transform[J]. Transactions of China Electrotechnical Society, 2017, 32(09): 221-235.
[14] Lauer F, Suen C Y, Bloch G. A trainable feature extractor for handwritten digit recognition [J]. Pattern Recognition, 2007, 40(6): 1816–1824.
[15] Larsson G , Maire M , Shakhnarovich G . FractalNet: Ultra-Deep Neural Networks without Residuals. arXiv preprintarXiv:1605.07648, 2016.
[16] 冯新扬,张巧荣,李庆勇.基于改进型深度网络数据融合的滚动轴承故障识别[J].重庆大学学报,2019,42(02):52-62.
FENG Xin-yang, ZHANG Qiao-rong, LI Qing-yong. Fault recognition of rolling bearing based on improved deep networks with data fusion in unbalanced data sets[J]. Journal of Chongqing University, 2019, 42(02):52-62.
[17] 刘宇晴,王天昊,徐旭.深度学习神经网络的新型自适应激活函数[J].吉林大学学报(理学版),2019,57(04):857-859.
LIU Yu-qing, WANG Tian-hao, XU Xu. New Adaptive Activation Function for Deep Learning Neural Networks[J]. Journal of Jilin University(Science Edition), 2019,57(04):857-859..
[18] Qu J X, Zhang Z S, Gong T. A novel intelligent method for mechanical fault diagnosis based on dual-tree complex wavelet packet transform and multiple classifier fusion [J]. Neurocomputing, 2016, 171: 837-853.