针对风机齿轮箱轴承振动信号非线性非平稳性对故障诊断的干扰问题，提出一种基于降噪编码器深度特征学习和希尔伯特振动分解(Hilbert Vibration Decomposition，HVD)的智能故障诊断方法。引入峭度评估指标，对HVD分量进行模态选择，并以小波包提取分量能量熵构造特征向量，实现数据预处理。构建层叠降噪编码器(Stacked Denoising Autoencoder，SDAE)模型完成信号的特征学习和故障分类。采用两个轴承数据集进行算法验证，实验结果表明，提出的基于HVD小波包降噪编码方法(HWSDAE)能高效地识别故障信号，具有突出的故障诊断性能，单次最高诊断准确率高达100%，平均诊断准确率可达99.49%，相比未经预处理的轴承数据输入SDAE模型提高了13.52%的故障诊断精度。
Abstract
An intelligent detection method based on the deep feature learning and Hilbert vibration decomposition (Hilbert Vibration Decomposition, HVD) of the denoising encoder is proposed to address the problem of the disturbance caused by the nonlinear and non-stationarity effect of the vibration signals of the fan gearbox bearing. The kurtosis evaluation index is introduced to evaluate the HVD component modal, and the wavelet packet is used to extract the energy entropy of the component to construct the feature vector to realize data preprocessing. A stacked denoising encoder (Stacked Denoising Autoencoder, SDAE) model was constructed to complete signal feature learning and fault classification. Two bearing datasets were used for algorithm verification, the experimental results show that the proposed HVD wavelet packet denoising encoding method (HWSDAE) can effectively identify fault signals, has outstanding diagnostic performance, and the single diagnostic accuracy is up to 100%, the average diagnostic accuracy is 99.49%, improving the diagnostic accuracy by 13.52% compared to the unprepared bearing data input into the SDAE model.
关键词
故障诊断 /
希尔伯特振动分解 /
小波包分解 /
降噪编码器
{{custom_keyword}} /
Key words
Fault diagnosis; /
hilbert vibration decomposition; /
wavelet packet; denoising autoencoder
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Jardine A K S, Lin D, Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems & Signal Processing, 2006, 20(7): 1483-1510.
[2] M. Gan, C. Wang, and C. Zhu, “Construction of hierarchical diagnosis network based on deep learning and its application inthe fault patternrecognition of rolling element bearings,” Mechanical Systems and Signal Processing, 2016, 72: 92–104.
[3] 时培明, 赵娜, 苏冠华, 等. 变载荷齿轮箱故障信号智能检测方法[J]. 计量学报, 2018, 39(06): 847-851.
SHI Peiming, ZHAO Na, SU Guanhua, et al. Intelligent detection method of variable load gearbox fault signal [J]. Acta Metrologica Sinica, 2018, 39 (06): 847-851.
[4] Kumar A, Gandhi C P, Zhou Y , et al. Latest developments in gear defect diagnosis and prognosis: A review[J]. Measurement, 2020, 158: 107735.
[5] Qi Y, Shen C, Wang D, et al. Stacked Sparse Autoencoder-Based Deep Network for Fault Diagnosis of Rotating Machinery[J]. IEEE Access, 2017, 99: 1-1.
[6] Li X, Li X, Ma H. Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery[J]. Mechanical Systems and Signal Processing, 2020, 143: 106825.
[7] Zhang S, Wang M, Yang F, et al. Manifold Sparse Auto-Encoder for Machine Fault Diagnosis[J]. IEEE Sensors Journal, 2019, 99:1-1.
[8] Jiang G, He H, Xie P, et al. Stacked Multilevel-Denoising Autoencoders: A New Representation Learning Approach for Wind Turbine Gearbox Fault Diagnosis[J]. IEEE Transactions on Instrumentation & Measurement, 2017, 66(9): 2391-2402.
[9] 朱可恒, 宋希庚, 薛冬新. 希尔伯特振动分解在滚动轴承故障诊断中应用[J]. 振动与冲击, 2014, 33(14): 160-164.
ZHU KeHeng, SONG XiGeng, XUE DongXin. Roller bearing fault diagnosis using Hilbert vibration decomposition [J]. Journal of Vibration and Shock, 2014, 33(14): 160-164.
[10] Shi P, Guo X, Han D, et al. A sparse auto-encoder method based on compressed sensing and wavelet packet energy entropy for rolling bearing intelligent fault diagnosis. Journal of Mechanical Science and Technology, 2020, 34 (4): 1445-1458.
[11] 张斌, 沈国阳, 金英连, 等. 小波包能熵谱和证据融合推理的电梯急停诊断[J]. 计量学报, 2016 (37): 519.
ZHANG Bin, SHEN GuoYang, JIN YingLian, et al. Eievator fauit stop diagnosis based on waveiet packet energy spectrum and evidences fusion reasoning [J]. Acta Metrologica Sinica, 2016 (37): 519.
[12] 李松柏, 康子剑, 陶洁. 基于信息融合及堆栈降噪自编码的齿轮故障诊断[J]. 振动与冲击,2019, 38(05):224-229.
LI SongBo, KANG ZiJian, TAO Jie. Gear fault diagnosis based on information fusion and stacked de-noising auto-encoder [J]. Journal of Vibration and Shock, 2019, 38(05): 224-229.
[13] 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, 2015, s 64-65: 100-131.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2009 KB)
