基于联合LLE和SSR的滚动轴承故障诊断方法

张康智

doi:10.13224/j.cnki.jasp.20230263

基于联合LLE和SSR的滚动轴承故障诊断方法

doi: 10.13224/j.cnki.jasp.20230263

张康智

西安航空学院机械工程学院，西安 710077

基金项目: 陕西省科技厅项目（2019JM-535）；陕西省自然科学基础研究计划项目(2023-JC-QN-0614)

详细信息

作者简介:
张康智（1978-），男，副教授，硕士，主要从事机电液一体化技术的研究。E-mail：59851747@qq.com

中图分类号: V231.92
计量
- 文章访问数: 23
- HTML浏览量: 19
- PDF量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2023-04-21
- 网络出版日期: 2024-02-19

Fault diagnosis method of rolling bearing based on joint LLE and SSR

ZHANG Kangzhi

School of Mechanical Engineering，Xi’an Aeronautical Institute，Xi’an 710077，China

摘要

摘要:
针对滚动轴承振动信号具有较强的非线性，且包含较多冗余和无关特征，导致提取本质特征和故障识别困难，提出一种基于联合局部线性嵌入和稀疏自表示（joint locally linear embedding and sparse self-representation, JLLESSR）与参数优化支持向量机的滚动轴承故障诊断方法。该方法构造了一个统一的特征提取框架，依靠局部线性嵌入（locally linear embedding，LLE）挖掘高维数据的局部几何结构，同时通过稀疏自表示 (self-representation) 在低维空间挖掘高维数据的全局几何结构，得到表征滚动轴承运行状态的嵌入特征。然后，将得到的特征输入至交叉优化支持向量机（cross-validation support vector machine，CV-SVM）中进行故障识别。最后，在常见滚动轴承故障数据集上对所提出的方法进行测试，实验结果表明提出的方法能有效识别出滚动轴承不同类型的故障，并且故障诊断精度可达98.5%。
- 滚动轴承 /
- 振动信号 /
- 局部线性嵌入 /
- 联合局部线性嵌入和稀疏自表示 /
- 故障诊断
Abstract:
A rolling bearing fault diagnosis method based on joint locally linear embedding and sparse self-representation (JLLESSR) and parameter-optimized support vector machine is proposed for rolling bearing vibration signals with strong nonlinearity and containing more redundant and irrelevant features, which leads to difficulties in extracting essential features and fault identification. The method constructs a unified feature extraction framework, relying on local linear embedding (LLE) to mine the local geometric structure of high dimensional data, and self-representation to mine the global geometric structure of high dimensional data in low dimensional space, to obtain the embedding features characterizing the operating state of rolling bearings. Then, the obtained features are fed into a cross-validation support vector machine (CV-SVM) for fault identification. Finally, the proposed method is tested on a rolling bearing fault data set, and the experimental results show that the proposed method can effectively identify different types of rolling bearing faults, and the fault diagnosis accuracy can reach 98.5%.
- rolling bearing /
- vibration signal /
- locally linear embedding /
- joint locally linear embedding and sparse self-representation /
- fault diagnosis

HTML

图 1 局部线性嵌入算法的流程图

Figure 1. Flowchart of local linear embedding algorithm

下载: 全尺寸图片幻灯片

图 2 滚动轴承故障诊断流程图

Figure 2. Flow chart of rolling bearing fault diagnosis

下载: 全尺寸图片幻灯片

图 3 滚动轴承故障模拟实验台

Figure 3. Rolling bearing failure simulation test bench

下载: 全尺寸图片幻灯片

图 4 三轴加速度传感器

Figure 4. Three-axis acceleration sensor

下载: 全尺寸图片幻灯片

图 5 实验轴承

Figure 5. Bearings used in experiment

下载: 全尺寸图片幻灯片

图 6 滚动轴承振动信号时域表示

Figure 6. Time domain representation of rolling bearing vibration signals

下载: 全尺寸图片幻灯片

图 7 不同类型的信号频谱图

Figure 7. Spectrum diagram of different types of signals

下载: 全尺寸图片幻灯片

图 8 不同特征提取算法的三维可视化结果

Figure 8. 3-dimensional visualization results of different feature extraction algorithm

下载: 全尺寸图片幻灯片

图 9 不同参数下的轴承故障识别精度

Figure 9. Accuracy of bearing fault identification under different parameters

下载: 全尺寸图片幻灯片

表 1 轴承数据集的识别精度对比

Table 1. Comparison of identification accuracy of bearing dataset

模型	识别精度/%
模型	预测精度	召回率	F₁分数
LLE-CV-SVM	91.15	90.85	91.25
HLLE-CV-SVM	93.25	93.34	92.50
RLLE-CV-SVM	94.05	93.85	94.25
MS-LLECF-CV-SVM	95.15	94.35	95.00
MS-LLEFF-CV-SVM	95.50	95.75	95.65
JLLESSR-CV-SVM	98.75	98.60	98.50

下载: 导出CSV

参考文献(21)

[1]	李昕燃,靳伍银. 基于改进麻雀算法优化支持向量机的滚动轴承故障诊断研究[J]. 振动与冲击,2023,42(6): 106-114. LI Xinran,JIN Wuyin. Fault diagnosis of rolling bearings based on ISSA-SVM[J]. Journal of Vibration and Shock,2023,42(6): 106-114. (in Chinese LI Xinran, JIN Wuyin. Fault diagnosis of rolling bearings based on ISSA-SVM[J]. Journal of Vibration and Shock, 2023, 42(6): 106-114. (in Chinese)
[2]	李俊卿,胡晓东,耿继亚,等. 基于ACGAN和模型融合的电机轴承故障诊断方法[J]. 电机与控制应用,2023,50(2): 91-96. LI Junqing,HU Xiaodong,GENG Jiya,et al. Fault diagnosis method of motor bearing based on ACGAN and model fusion[J]. Electric Machines & Control Application,2023,50(2): 91-96. (in Chinese doi: 10.12177/emca.2022.157 LI Junqing, HU Xiaodong, GENG Jiya, et al. Fault diagnosis method of motor bearing based on ACGAN and model fusion[J]. Electric Machines & Control Application, 2023, 50(2): 91-96. (in Chinese) doi: 10.12177/emca.2022.157
[3]	殷海双,胡泽彪,刘远红,等. 基于鲁棒局部线性嵌入投票的轴承故障诊断[J]. 组合机床与自动化加工技术,2021(8): 81-84,89. YIN Haishuang,HU Zebiao,LIU Yuanhong,et al. Bearing fault diagnosis based on robust locally linear embedded vote[J]. Modular Machine Tool & Automatic Manufacturing Technique,2021(8): 81-84,89. (in Chinese YIN Haishuang, HU Zebiao, LIU Yuanhong, et al. Bearing fault diagnosis based on robust locally linear embedded vote[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2021(8): 81-84, 89. (in Chinese)
[4]	ROWEIS S T,SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science,2000,290(5500): 2323-2326. doi: 10.1126/science.290.5500.2323
[5]	WANG Xiang,ZHENG Yuan,ZHAO Zhenzhou,et al. Bearing fault diagnosis based on statistical locally linear embedding[J]. Sensors,2015,15(7): 16225-16247. doi: 10.3390/s150716225
[6]	ZHANG Yansheng,YE Dong,LIU Yuanhong,et al. Machinery fault diagnosis via an improved multi-linear subspace and locally linear embedding[J]. Transactions of the Institute of Measurement and Control,2018,40(14): 4014-4026. doi: 10.1177/0142331217739688
[7]	ZHANG Xingwu,YU Xiaolei,LIU Yilong,et al. Adaptive neighborhood selection based on locally linear embedding for the degradation index construction of traction motor bearing[J]. Measurement Science and Technology,2021,32(11): 115123. doi: 10.1088/1361-6501/ac18a5
[8]	LIU Guohong,LI Xiaomeng,WANG Cong,et al. Hessian locally linear embedding of PMU data for efficient fault detection in power systems[J]. IEEE Transactions on Instrumentation and Measurement,2022,71: 3502704.
[9]	ZHANG Yansheng,YE Dong,LIU Yuanhong. Robust locally linear embedding algorithm for machinery fault diagnosis[J]. Neurocomputing,2018,273: 323-332. doi: 10.1016/j.neucom.2017.07.048
[10]	LIU Yuanhong,HU Zebiao,ZHANG Yansheng. Bearing feature extraction using multi-structure locally linear embedding[J]. Neurocomputing,2021,428: 280-290. doi: 10.1016/j.neucom.2020.11.048
[11]	LIU Yuanhong,HU Zebiao,ZHANG Yansheng. Symmetric positive definite manifold learning and its application in fault diagnosis[J]. Neural Networks,2022,147: 163-174. doi: 10.1016/j.neunet.2021.12.013
[12]	王贡献,张淼,胡志辉,等. 基于多尺度均值排列熵和参数优化支持向量机的轴承故障诊断[J]. 振动与冲击,2022,41(1): 221-228. WANG Gongxian,ZHANG Miao,HU Zhihui,et al. Bearing fault diagnosis based on multi-scale mean permutation entropy and parametric optimization SVM[J]. Journal of Vibration and Shock,2022,41(1): 221-228. (in Chinese WANG Gongxian, ZHANG Miao, HU Zhihui, et al. Bearing fault diagnosis based on multi-scale mean permutation entropy and parametric optimization SVM[J]. Journal of Vibration and Shock, 2022, 41(1): 221-228. (in Chinese)
[13]	王一鹏,陈学振,李连玉. 基于小波包混合特征和支持向量机的机床主轴轴承故障诊断研究[J]. 电子测量与仪器学报,2021,35(2): 59-64. WANG Yipeng,CHEN Xuezhen,LI Lianyu. Research on fault diagnosis of machine spindle bearing based on wavelet packet mixing feature and SVM[J]. Journal of Electronic Measurement and Instrumentation,2021,35(2): 59-64. (in Chinese WANG Yipeng, CHEN Xuezhen, LI Lianyu. Research on fault diagnosis of machine spindle bearing based on wavelet packet mixing feature and SVM[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(2): 59-64. (in Chinese)
[14]	史庆军,郭晓振,刘德胜. 基于特征量融合和支持向量机的轴承故障诊断[J]. 电子测量与仪器学报,2019,33(10): 104-111. SHI Qingjun,GUO Xiaozhen,LIU Desheng. Bearing fault diagnosis based on feature fusion and support vector machine[J]. Journal of Electronic Measurement and Instrumentation,2019,33(10): 104-111. (in Chinese SHI Qingjun, GUO Xiaozhen, LIU Desheng. Bearing fault diagnosis based on feature fusion and support vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2019, 33(10): 104-111. (in Chinese)
[15]	HU Zebiao,YIN Haishuang,LIU Yuanhong. Locally linear embedding vote: a novel filter method for feature selection[J]. Measurement,2022,190: 110535. doi: 10.1016/j.measurement.2021.110535
[16]	梁睿君,冉文丰,余传粮,等. 基于CWT-CNN的齿轮箱运行故障状态识别[J]. 航空动力学报,2021,36(12): 2465-2473. LIANG Ruijun,RAN Wenfeng,YU Chuanliang,et al. Recognition of gearbox operation fault state based on CWT-CNN[J]. Journal of Aerospace Power,2021,36(12): 2465-2473. (in Chinese LIANG Ruijun, RAN Wenfeng, YU Chuanliang, et al. Recognition of gearbox operation fault state based on CWT-CNN[J]. Journal of Aerospace Power, 2021, 36(12): 2465-2473. (in Chinese)
[17]	蒋忆睿,裴洋,陈磊,等. 多局部约束自表示的谱聚类算法[J]. 计算机工程与应用,2020,56(11): 172-178. JIANG Yirui,PEI Yang,CHEN Lei,et al. Multiple locality-constrained self-representation for spectral clustering[J]. Computer Engineering and Applications,2020,56(11): 172-178. (in Chinese doi: 10.3778/j.issn.1002-8331.1904-0087 JIANG Yirui, PEI Yang, CHEN Lei, et al. Multiple locality-constrained self-representation for spectral clustering[J]. Computer Engineering and Applications, 2020, 56(11): 172-178. (in Chinese) doi: 10.3778/j.issn.1002-8331.1904-0087
[18]	LIU Huawen,XU Xiaodan,LI Enhui,et al. Anomaly detection with representative neighbors[J]. IEEE Transactions on Neural Networks and Learning Systems,2023,34(6): 2831-2841. doi: 10.1109/TNNLS.2021.3109898
[19]	ABDI H,WILLIAMS L J. Principal component analysis[J]. Wiley Interdisciplinary Reviews: Computational Statistics,2010,2(4): 433-459. doi: 10.1002/wics.101
[20]	李红贤,韩延,吴敬涛,等. 基于ICA包络增强MEMD的滚动轴承故障诊断[J]. 航空动力学报,2021,36(2): 405-412. LI Hongxian,HAN Yan,WU Jingtao,et al. Rolling bearing fault diagnosis based on MEMD with ICA envelop enhancement[J]. Journal of Aerospace Power,2021,36(2): 405-412. (in Chinese LI Hongxian, HAN Yan, WU Jingtao, et al. Rolling bearing fault diagnosis based on MEMD with ICA envelop enhancement[J]. Journal of Aerospace Power, 2021, 36(2): 405-412. (in Chinese)
[21]	余志锋,熊邦书,李新民,等. 基于改进的SqueezeNet直升机滚动轴承故障诊断[J]. 航空动力学报,2022,37(6): 1162-1170. YU Zhifeng,XIONG Bangshu,LI Xinmin,et al. Fault diagnosis of helicopter rolling bearing based on improved SqueezeNet[J]. Journal of Aerospace Power,2022,37(6): 1162-1170. (in Chinese YU Zhifeng, XIONG Bangshu, LI Xinmin, et al. Fault diagnosis of helicopter rolling bearing based on improved SqueezeNet[J]. Journal of Aerospace Power, 2022, 37(6): 1162-1170. (in Chinese)