中文版 | English
题名

基于自适应模态分解的滚动轴承故障诊断算法研究

其他题名
RESEARCH ON ROLLING BEARING FAULT DIAGNOSIS ALGORITHM BASED ON ADAPTIVE MODE DECOMPOSITION
姓名
姓名拼音
YU Xinqi
学号
12032473
学位类型
硕士
学位专业
0809 电子科学与技术
学科门类/专业学位类别
08 工学
导师
张进
导师单位
计算机科学与工程系
论文答辩日期
2023-05-13
论文提交日期
2023-06-27
学位授予单位
南方科技大学
学位授予地点
深圳
摘要

滚动轴承广泛应用于旋转机械中,是机械系统中不可或缺的关键部件。一旦出现故障,将会严重降低整个机械系统的工作效率,甚至可能导致巨大的财产损失和人身伤害。因此,对于滚动轴承故障诊断方法的研究具有重要的理论和实际意义。

目前,轴承故障诊断的研究主要分为两类:一类是基于信号获取、信号处理、特征提取的诊断流程。其中,振动信号的模态分解方法被广泛研究,因为它可以直接分解出含有故障信息的成分。然而,当前的信号模态分解方法多需要先验的初始化设置,实际效果受到限制。另一类则是利用深度学习技术构造端到端的轴承故障诊断模型,但需要大量数据进行训练以确保高准确率,实际应用中存在困难。

为了解决上述问题,本文以滚动轴承为研究对象,基于振动特征,提出了一种新的自适应模态分解算法,并将其应用于轴承故障诊断。该算法采用自适应频谱分割的方法来确定模态数量和初始瞬时频率,提升了分解效果。同时,为了有效精确地提取各分解模态的特征,本文还提出了模态融合的特征提取算法,在保留所有模态的基础上,将峭度、均方根值以及峰值因数与熵的概念融合。最后,利用支持向量机进行故障分类,并开发了故障诊断平台,包括信号采集系统和故障诊断模块,并采集了故障数据集。

本论文在公开数据集和自研数据集上进行实验,验证了本算法的有效性。结果表明,所提出的自适应模态分解算法能够达到既不“欠分解”也不“过分解”的效果,在两个故障数据集上表现优异,对各类故障的诊断准确率均超过98%。这表明该算法可应用于轴承故障的快速诊断,为维护机械设备的正常运行提供了重要支持。

关键词
语种
中文
培养类别
独立培养
入学年份
2020
学位授予年份
2023-06
参考文献列表

[1] GRANEY B P, STARRY K. Rolling Element Bearing Analysis[J]. Materials Evaluation, 2012, 70(1): 78-85.
[2] CIPOLLINI F, ONETO L, CORADDU A, et al. Unsupervised Deep Learning for Induction Motor Bearings Monitoring[J]. Data-Enabled Discovery and Applications, 2019, 3(1): 1-13.
[3] TOMA R, PROSVIRIN A, KIM J. Bearing Fault Diagnosis of Induction Motors Using a Genetic Algorithm and Machine Learning Classifiers[J]. Sensors, 2020, 20(7): 1814.
[4] BEARD R V. Failure Accommodation in Linear System through Self Reorganization[D]. Massachusetts Institute of Technology, 1971.
[5] 曹宏瑞, 何正嘉, 訾艳阳. 高速滚动轴承力学特性建模与损伤机理分析[J]. 振动与冲击, 2012, 19: 134-140.
[6] 董振振. 滚动轴承复合故障机理及振动模型研究[D]. 哈尔滨工业大学, 2015.
[7] NTI-AUDIO. Fast Fourier Transformation FFT - Basics[EB/OL]. https://www.nti-audio.com/en/support/know-how/fast-fourier-transform-fft.
[8] VAN LOAN C. Computational Frameworks for the Fast Fourier Transform SIAM[M]. Society for Industrial and Applied Mathematics, 1992.
[9] ALLEN J. Short Term Spectral Analysis, Synthesis, and Modification by Discrete Fourier Transform[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1977, 2(3): 235-238.
[10] BURRUS C S. Wavelets and wavelet transforms[M]. Rice University, 2015.
[11] GILLES J. Empirical Wavelet Transform[J]. IEEE Transactions on Signal Processing, 2013, 61(16): 3999-4010.
[12] HUANG N E. Hilbert-Huang transform and its applications: Vol. 16[M]. World Scientific, 2014.
[13] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 1998, 454(1971): 903-995.
[14] DRAGOMIRETSKIY K, ZOSSO D. Variational Mode Decomposition[J]. IEEE Transactions on Signal Processing, 2013, 62(3): 531-544.
[15] HOECKER A, KARTVELISHVILI V. SVD Approach to Data Unfolding[J]. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1996, 372(3): 469-481.
[16] WANG J, MA Y, ZHANG L, et al. Deep Learning for Smart Manufacturing: Methods and Applications[J]. Journal of Manufacturing Systems, 2018, 48: 144-156.
[17] DONG S, LUO T, ZHONG L, et al. Fault Diagnosis of Bearing Based on the Kernel Principal Component Analysis and Optimized K-nearest Neighbour Model[J]. Journal of Low Frequency Noise, Vibration and Active Control, 2017, 36(4): 354-365.
[18] SHANNON C E, WEAVER W. A Mathematical Theory of Communication[J]. The Bell System Technical, 1948, 27(4): 379-423.
[19] CHEN W, WANG Z, XIE H, et al. Characterization of Surface EMG Signal based on Fuzzy Entropy[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15 (2): 266-272.
[20] RICHMAN J S. Sample Entropy Statistics and Testing for Order in Complex Physiological Signals[J]. Communications in Statistics—Theory and Methods, 2007, 36(5): 1005-1019.
[21] ALI J B, FNAIECH N, SAIDI L, et al. Application of Empirical Mode Decomposition and Artificial Neural Network for Automatic Bearing Fault Diagnosis based on Vibration Signals [J]. Applied Acoustics, 2015, 89: 16-27.
[22] RICHMAN J S, MOORMAN J R. Physiological Time-Series Analysis Using Approximate Entropy and Sample Entropy[J]. American Journal of Physiology-heart and Circulatory Physiology, 2000, 278: H2039-49.
[23] BANDT C, POMPE B. Permutation Entropy: A Natural Complexity Measure for Time Series [J]. Physical Review Letters, 2002, 88(17): 174102.
[24] LIANG J, ZHONG J H, YANG Z X. Correlated EEMD and Effective Feature Extraction for Both Periodic and Irregular Faults Diagnosis in Rotating Machinery[J]. Energies, 2017, 10(10): 1652.
[25] 杜福嘉, 黄康, 郭跃楠. 小波包和模糊熵特征融合的轴承故障诊断[J]. 机械设计与制造, 2023.
[26] AN X, PAN L. Bearing Fault Diagnosis of A Wind Turbine Based on Variational Mode Decomposition and Permutation Entropy[J]. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2017, 231(2): 200-206.
[27] KUAI M, CHENG G, PANG Y, et al. Research of Planetary Gear Fault Diagnosis Based on Permutation Entropy of CEEMDAN and ANFIS[J]. Sensors, 2018, 18(3): 782.
[28] ZHAO C, FENG Z, WEI X, et al. Sparse Classification Based on Dictionary Learning for Planet Bearing Fault Identification[J]. Expert Systems with Applications, 2018, 108: 233-245.
[29] XUE H, WANG M, LI Z, et al. Fault Feature Extraction Based on Artificial Hydrocarbon Network for Sealed Deep Groove Ball Bearings of In-wheel Motor[C]//2017: 1-5.
[30] HARMOUCHE J, DELPHA C, DIALLO D. Linear Discriminant Analysis for the Discrimination of Faults in Bearing Balls by Using Spectral Features[J]. 2014 First International Conference on Green Energy ICGE 2014, 2014: 182-187.
[31] ZHOU Y, YAN S, REN Y, et al. Rolling Bearing Fault Diagnosis Using Transient-extracting Transform and Linear Discriminant Analysis[J]. Measurement, 2021, 178: 109298.
[32] HE D, LI R, ZHU J, et al. Data Mining Based Full Ceramic Bearing Fault Diagnostic System Using AE Sensors[J]. IEEE Transactions on Neural Networks, 2011, 22(12): 2022-2031.
[33] WANG H, YU Z, GUO L. Real-time Online Fault Diagnosis of Rolling Bearings Based on KNN Algorithm[J]. Journal of Physics: Conference Series, 2020, 1486(3): 032019.
[34] WANG G, HE Y, HE K. Multi-Layer Kernel Learning Method Faced on Roller Bearing Fault Diagnosis[J]. Journal of Software, 2012, 7(7): 1531-1538.
[35] LI X, ZHENG A, ZHANG X, et al. Rolling Element Bearing Fault Detection Using Support Vector Machine with Improved Ant Colony Optimization[J]. Measurement, 2013, 46: 2726-2734.
[36] LI X, YANG Y, PAN H, et al. A Novel Deep Stacking Least Squares Support Vector Machine for Rolling Bearing Fault Diagnosis[J]. Computers in Industry, 2019, 110: 36-47.
[37] RAZAVI-FAR R, SAIF M. Ensemble of Extreme Learning Machines for Diagnosing Bearing Defects in Non-stationary Environments under Class Imbalance Condition[C]//2016: 1-6.
[38] UDMALE S S, SINGH S K. Application of Spectral Kurtosis and Improved Extreme Learning Machine for Bearing Fault Classification[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68(11): 4222-4233.
[39] CHEN Z, DENG S, CHEN X, et al. Deep Neural Networks-based Rolling Bearing Fault Diagnosis[J]. Microelectronics Reliability, 2017, 75: 327-333.
[40] GAN M, WANG C, ZHU C. Construction of Hierarchical Diagnosis Network Based on Deep Learning and Its Application in the Fault Pattern Recognition of Rolling Element Bearings[J]. Mechanical Systems and Signal Processing, 2016, 72-73: 92-104.
[41] LEI Y, HE Z, ZI Y. EEMD Method and WNN for Fault Diagnosis of Locomotive Roller Bearings[J]. Expert Systems with Applications, 2011, 38(6): 7334-7341.
[42] JANSSENS O, SLAVKOVIKJ V, VERVISCH B, et al. Convolutional Neural Network Based Fault Detection for Rotating Machinery[J]. Journal of Sound and Vibration, 2016, 377: 331-345.
[43] QIAN W, LI S, WANG J, et al. An Intelligent Fault Diagnosis Framework for Raw Vibration Signals: Adaptive Overlapping Convolutional Neural Network[J]. Measurement Science and Technology, 2018, 29: 109143.
[44] 郑建波, 何琳, 廖健, 等. 基于 CSCoh 与 CNN 的滚动轴承故障诊断[J]. 轴承, 2023.
[45] HUANG X, WEN G, DONG S, et al. Memory Residual Regression Autoencoder for Bearing Fault Detection[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-12.
[46] CHEN Z, LI W. Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(7): 1693-1702.
[47] GAO S, XU L, ZHANG Y, et al. Rolling Bearing Fault Diagnosis Based on SSA Optimized Self-adaptive DBN[J]. ISA Transactions, 2022, 128: 485-502.
[48] RAFA W. A Robust Bearing Fault Detection and Diagnosis Technique for Brushless DC Motors under Non-stationary Operating Conditions[J]. Journal of Control, Automation and Electrical Systems, 2015, 26: 241-254.
[49] JIANG H, XINGQIU L, SHAO H, et al. Intelligent Fault Diagnosis of Rolling Bearing Using Improved Deep Recurrent Neural Network[J]. Measurement Science and Technology, 2018, 29: 065107.
[50] HAN T, PANG J, TAN A C. Remaining Useful Life Prediction of Bearing Based on Stacked Autoencoder and Recurrent Neural Network[J]. Journal of Manufacturing Systems, 2021, 61: 576-591.
[51] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative Adversarial Nets[C]//GHAHRAMANI Z, WELLING M, CORTES C, et al. Advances in Neural Information Processing Systems: Vol. 27. Curran Associates, Inc., 2014.
[52] LIU J, ZHANG C, JIANG X. Imbalanced Fault Diagnosis of Rolling Bearing Using Improved MsR-GAN and Feature Enhancement-driven CapsNet[J]. Mechanical Systems and Signal Processing, 2022, 168: 108664.
[53] CERRADA M, SÁNCHEZ R V, LI C, et al. A review on Data-driven Fault Severity Assessment in Rolling Bearings[J]. Mechanical Systems and Signal Processing, 2018, 99: 169-196.
[54] LU N, ZHUANG G, MA Z, et al. A Zero-Shot Intelligent Fault Diagnosis System Based on EEMD[J]. IEEE Access, 2022, 10: 54197-54207.
[55] YIN C, WANG Y, MA G, et al. Weak Fault Feature Extraction of Rolling Bearings Based on Improved Ensemble Noise-reconstructed EMD and Adaptive Threshold Denoising[J]. Mechanical Systems and Signal Processing, 2022, 171: 108834.
[56] SMITH J S. The local Mean Decomposition and Its Application to EEG Perception Data[J]. Journal of the Royal Society Interface, 2005, 2(5): 443-454.
[57] CHEN S, DONG X, PENG Z, et al. Nonlinear Chirp Mode Decomposition: A Variational Method[J]. IEEE Transactions on Signal Processing, 2017, 65(22): 6024-6037.
[58] HESTENES M R. Multiplier and Gradient Methods[J]. Journal of Optimization Theory and Applications, 1969, 4(5): 303-320.
[59] ROCKAFELLAR R T. A Dual Approach to Solving Nonlinear Programming Problems by Unconstrained Optimization[J]. Mathematical programming, 1973, 5(1): 354-373.
[60] BERTSEKAS D P. Constrained Optimization and Lagrange Multiplier Methods[M]. Academic press, 2014.
[61] WANG J, ZHANG Y, ZHANG F, et al. Accuracy-improved Bearing Fault Diagnosis Method Based on AVMD Theory and AWPSO-ELM Model[J]. Measurement, 2021, 181: 109666.
[62] DAUBECHIES I, LU J, WU H T. Synchrosqueezed Wavelet Transforms: An Empirical Mode Decomposition-like Tool[J]. Applied and Computational Harmonic Analysis, 2011, 30(2): 243-261.
[63] DUBEY R, SHARMA R R, UPADHYAY A, et al. Automated Variational Non-linear Chirp Mode Decomposition for Bearing Fault Diagnosis[J]. IEEE Transactions on Industrial Informatics, 2023: 1-9.
[64] DENG L, ZHAO R. Fault Feature Extraction of A Rotor System Based on Local Mean Decomposition and Teager Energy Kurtosis[J]. Journal of Mechanical Science and Technology, 2014, 28: 1161-1169.
[65] DELON J, DESOLNEUX A, LISANI J L, et al. A Nonparametric Approach for Histogram Segmentation[J]. IEEE Transactions on Image Processing, 2006, 16(1): 253-261.
[66] OZERTEM U, ERDOGMUS D. A Nonparametric Approach for Active Contours[C]//2007 International Joint Conference on Neural Networks. 2007: 1407-1410.
[67] 北京瑞森新谱科技股份有限公司. RS1284 八进四出数据采集卡[EB/OL]. http://www.rstech.com.cn/goods!changeLanguage.action?flag=cn&nd=128#001.
[68] FEDERATION M M. Triaxial-Beschleunigungsaufnehmer[EB/OL]. https://www.mmf.de/triaxialaufnehmer.htm#ks903.
[69] WANG Y, ZENG L, WANG L, et al. An Efficient Incremental Learning of Bearing FaultImbalanced Data Set via Filter StyleGAN[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-10.

所在学位评定分委会
电子科学与技术
国内图书分类号
TH133.33
来源库
人工提交
成果类型学位论文
条目标识符http://sustech.caswiz.com/handle/2SGJ60CL/544152
专题工学院_计算机科学与工程系
推荐引用方式
GB/T 7714
俞欣琪. 基于自适应模态分解的滚动轴承故障诊断算法研究[D]. 深圳. 南方科技大学,2023.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可 操作
12032473-俞欣琪-计算机科学与工(6530KB)----限制开放--请求全文
个性服务
原文链接
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
导出为Excel格式
导出为Csv格式
Altmetrics Score
谷歌学术
谷歌学术中相似的文章
[俞欣琪]的文章
百度学术
百度学术中相似的文章
[俞欣琪]的文章
必应学术
必应学术中相似的文章
[俞欣琪]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
[发表评论/异议/意见]
暂无评论

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。