面向无标签数据的旋转机械故障诊断方法

doi:10.13229/j.cnki.jdxbgxb20210355

摘要/Abstract

摘要：

针对旋转机械故障诊断算法大多面向有标签的数据，且参数多需要人为设置的问题，提出了一种面向无标签数据、参数自适应化的二次异常识别加聚类的无监督诊断算法。该方法通过改进经验小波变换和拉普拉斯分值算法对信号进行特征提取和选择，并采用二次异常识别结合改进模糊C均值聚类的无监督方法进行故障识别。通过电主轴转子系统故障数据验证，所提方法诊断精度可达93%，与传统无监督诊断方法对比，具有良好的准确性和鲁棒性。

关键词: 故障诊断, 旋转机械, 无标签数据, 参数自适应, 无监督学习

Abstract:

Most fault diagnosis algorithms for rotating machinery are labeled and need to be set manually， an unsupervised fault diagnosis algorithm with adaptive parameters for unlabeled fault data by introducing twice anomaly recognitions and clustering algorithms was proposed.The method extracts and selects signal features by improving empirical wavelet transform and Laplace score algorithm, and adopts the unsupervised method of quadratic anomaly identification combined with improved fuzzy C-means clustering for fault identification. Through the verification of the fault data of the rotor system of the electric spindle, the diagnostic accuracy of the proposed method can reach 93%. Compared with the traditional unsupervised diagnostic method, it has good accuracy and robustness.

Key words: fault diagnosis, rotating machinery, unlabeled data, adaptive parameters, unsupervised learning

中图分类号:

TH133.33

陈菲,杨峥,张志成,罗巍. 面向无标签数据的旋转机械故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(11): 2514-2522.

Fei CHEN,Zheng YANG,Zhi-cheng ZHANG,Wei LUO. Fault diagnosis method of rotating machinery for unlabeled data[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(11): 2514-2522.

图/表 13

图1

图2

图3

图4

表1

表2

图5

表3

表4

图6

表5

图7

表6

参考文献 28

1	Liu R, Yang B, Zio E, et al. Artificial intelligence for fault diagnosis of rotating machinery: a review[J]. Mechanical Systems & Signal Processing, 2018, 108: 33-47.
2	黄海松, 魏建安, 任竹鹏, 等. 基于失衡样本特性过采样算法与SVM的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(10): 65-74, 132.
	Huang Hai-song, Wei Jian-an, Ren Zhu-peng, et al. Rolling bearing fault diagnosis based on imbalanced sample characteristics oversampling algorithm and SVM[J]. Journal of Vibration and Shock, 2020, 39(10): 65-74, 132.
3	何雷, 刘溯奇, 蒋婷, 等. 基于改进LMD与BP神经网络的变速箱故障诊断[J]. 机械传动, 2020, 44(1): 171-176.
	He Lei, Liu Su-qi, Jiang Ting, et al. Gearbox fault diagnosis based on improved LMD and BP neural network[J]. Journal of Mechanical Transmission, 2020, 44(1): 171-176.
4	Gilles J. Empirical wavelet transform[J]. IEEE Transactions on Signal Processing, 2013, 61(16): 3999-4010.
5	Yu J, Hua Z, Li Z. A new compound faults detection method for rolling bearings based on empirical wavelet transform and chaotic oscillator[J]. Chaos, Solitons & Fractals, 2016, 89: 8-19.
6	何洋洋, 王馨怡, 董晶. 基于经验小波变换与谱峭度的船舶轴系故障特征提取方法[J]. 中国舰船研究, 2020, 15(): 98-106.
	He Yang-yang, Wang Xin-yi, Dong Jing. Fault feature extraction method for marine shafting based on empirical wavelet transform-spectral kurtosis[J]. Chinese Journal of Ship Research, 2020, 15(Sup.1): 98-106.
7	叶益丰. 基于MEWT-KPCA的电主轴故障诊断技术研究[D]. 长春: 吉林大学机械与航空航天工程学院, 2018.
	Ye Yi-feng. Fault diagnosis technology of motorized spindle based on MEWT-KPCA[D]. Changchun: School of Mechanical and Aerospace Engineering, Jilin University, 2018.
8	叶柯华, 李春, 胡璇. 基于经验小波变换和关联维数的风力机齿轮箱故障诊断[J]. 动力工程学报, 2021, 41(2): 113-120.
	Ye Ke-hua, Li Chun, Hu Xuan. Fault diagnosis of a wind turbine gearbox based on empirical wavelet transform and correlation dimension[J]. Journal of Chinese Society of Power Engineering, 2021, 41(2): 113-120.
9	赵若妤, 马宏忠, 魏旭, 等. 基于EWT及多尺度形态谱的高压并联电抗器故障诊断研究[J]. 电力系统保护与控制, 2020, 48(17): 68-75.
	Zhao Ruo-yu, Ma Hong-zhong, Wei Xu, et al. Research on fault diagnosis of a high voltage shunt reactor based on EWT and multiscale spectral spectrum[J]. Power System Protection and Control, 2020, 48(17): 68-75.
10	乔志城, 刘永强, 廖英英. 改进经验小波变换与最小熵解卷积在铁路轴承故障诊断中的应用[J]. 振动与冲击, 2021, 40(2): 81-90, 118.
	Qiao Zhi-cheng, Liu Yong-qiang, Liao Ying-ying. Application of improved wavelet transform and minimum entropy deconvolution in railway bearing fault diagnosis[J]. Journal of Vibration and Shock, 2021, 40(2): 81-90, 118.
11	常勇, 包广清, 程思凯, 等. 基于VMD和KFCM的轴承故障诊断方法优化与研究[J]. 西南大学学报: 自然科学版, 2020, 42(10): 146-155.
	Chang Yong, Bao Guang-qing, Cheng Si-kai, et al. Optimization and research of a bearing fault diagnosis method based on VMD and KFCM[J]. Journal of Southwest University(Natural Science Edition),2020, 42(10): 146-155.
12	林越, 刘廷章, 唐侃. 基于自适应模糊聚类与核主元分析混合模型的变压器异常检测[J]. 科技通报, 2020, 36(9): 56-60.
	Lin Yue, Liu Ting-zhang, Tang Kan. Anomaly detection of power transformer based on KFCM-KPCA hybrid model[J]. Bulletin of Science and Technology, 2020, 36(9): 56-60.
13	贺湘宇, 何清华. 基于有源自回归模型与模糊C-均值聚类的挖掘机液压系统故障诊断[J]. 吉林大学学报: 工学版, 2008, 38(1): 183-187.
	He Xiang-yu, He Qing-hua. Fault diagnosis for excavator hydraulic system based on auto-regressive with extra inputs model and fuzzy C-means clustering[J]. Journal of Jilin University(Engineering and Technology Edition), 2008, 38(1): 183-187.
14	王庆锋, 刘家赫, 卫炳坤, 等. 数据驱动的聚类分析故障识别方法研究[J]. 机械工程学报, 2020, 56(18): 7-14.
	Wang Qing-feng, Liu Jia-he, Wei Bing-kun, et al. Research on data-driven clustering analysis fault identification method[J]. Journal of Mechanical Engineering, 2020, 56(18): 7-14.
15	院老虎, 连冬杉, 张亮, 等. 基于密集连接卷积网络和支持向量机的飞行器机械部件故障诊断[J]. 吉林大学学报: 工学版, 2021, 51(5): 1635-1641.
	Yuan Lao-hu, Lian Dong-shan, Zhang Liang, et al. Fault diagnosis of key mechanical components of aircraft based on densenet and support vector machine [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1635-1641.
16	徐忠兰. 基于SOM神经网络的煤矿用防爆柴油机故障诊断[J]. 煤矿机械, 2021, 42(4): 175-177.
	Xu Zhong-lan. Fault diagnosis of mine explosion-proof diesel engine based on SOM neural network[J]. Coal Mine Machinery, 2021, 42(4): 175-177.
17	Lindeberg T. Scale-Space Theory in Computer Vision[M]. Berlin: Springer, 1994.
18	Gilles J, Heal K. A parameterless scale-space approach to find meaningful modes in Histograms-application to image and spectrum segmentation[J]. International Journal of Wavelets Multiresolution & Information Processing, 2014, 12(6): 1450044.
19	蔡艳平, 李艾华, 王涛, 等. 基于EMD-Wigner-Ville的内燃机振动时频分析[J]. 振动工程学报, 2010, 23(4): 430-437.
	Cai Yan-ping, Li Ai-hua, Wang Tao, et al. I.C. engine vibration time-frequency analysis based on EMD-Wigner-Ville[J]. Journal of Vibration Engineering, 2010, 23(4): 430-437.
20	He X, Cai D, Niyogi P. Laplacian score for feature selection[C]∥Advances in Neural Information Processing Systems 18, Vancouver, British Columbia, Canada, 2005: 507-514.
21	欧璐, 于德介. 基于拉普拉斯分值和模糊C均值聚类的滚动轴承故障诊断[J]. 中国机械工程, 2014, 25(10): 1352-1357.
	Lu Ou, Yu De-jie. Rolling bearing fault diagnosis based on laplacian score and fuzzy C-means clustering[J]. China Mechanical Engineering, 2014, 25(10): 1352-1357.
22	Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2005, 27(8): 1226-1238.
23	Breunig M M, Kriegel H P, Ng R T, et al. LOF: identifying density-based local outliers[C]∥ACM Sigmod International Conference on Management of Data, Dallas, United States, 2000: 93-104.
24	朱庆生,唐汇,冯骥.一种基于自然最近邻的离群检测算法[J]. 计算机科学, 2014, 41(3): 282-284, 311.
	Zhu Qing-sheng, Tang Hui, Feng Ji. Outlier detection algorithm based on natural nearest neighbor[J]. Computer Science, 2014, 41(3): 282-284, 311.
25	Ester M, Kriegel H P, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]∥International Conference on Knowledge Discovery and Data Mining, Orlando, USA, 1996: 226-231.
26	王光, 林国宇. 改进的自适应参数DBSCAN聚类算法[J]. 计算机工程与应用, 2020, 56(14): 45-51.
	Wang Guang, Lin Guo-yu. Improved adaptive parameter DBSCAN clustering algorithm[J]. Computer Engineering and Applications, 2020, 56(14): 45-51.
27	Bezdek J C, Ehrlich R, Full W. FCM: the fuzzy C-means clustering algorithm[J]. Computers & Geosciences, 1984, 10(2): 191-203.
28	Wang W, Zhang Y. On fuzzy cluster validity indices[J]. Fuzzy Sets & Systems, 2007, 158(19): 2095-2117.

相关文章 15

[1]	宋震,柳杰. 旋转机械振动频率时间序列预测算法[J]. 吉林大学学报(工学版), 2022, 52(8): 1764-1769.
[2]	曹洁,马佳林,黄黛麟,余萍. 一种基于多通道马尔可夫变迁场的故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(2): 491-496.
[3]	高文志,王彦军,王欣伟,张攀,李勇,董阳. 基于卷积神经网络的柴油机失火故障实时诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 417-424.
[4]	王进花,胡佳伟,曹洁,黄涛. 基于自适应变分模态分解和集成极限学习机的滚动轴承多故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 318-328.
[5]	董绍江,朱朋,裴雪武,李洋,胡小林. 基于子领域自适应的变工况下滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 288-295.
[6]	罗巍,卢博,陈菲,马腾. 基于PSO-SVM及时序环节的数控刀架故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(2): 392-399.
[7]	邓飞跃,吕浩洋,顾晓辉,郝如江. 基于轻量化神经网络Shuffle⁃SENet的高速动车组轴箱轴承故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(2): 474-482.
[8]	张龙,徐天鹏,王朝兵,易剑昱,甄灿壮. 基于卷积门控循环网络的齿轮箱故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 368-376.
[9]	陈晓雷,孙永峰,李策,林冬梅. 基于卷积神经网络和双向长短期记忆的稳定抗噪声滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 296-309.
[10]	欧阳丹彤,张必歌,田乃予,张立明. 结合格局检测与局部搜索的故障数据缩减方法[J]. 吉林大学学报(工学版), 2021, 51(6): 2144-2153.
[11]	院老虎,连冬杉,张亮,刘义. 基于密集连接卷积网络和支持向量机的飞行器机械部件故障诊断[J]. 吉林大学学报(工学版), 2021, 51(5): 1635-1641.
[12]	董延华,刘靓葳,赵靖华,李亮,解方喜. 基于BPNN在线学习预测模型的扭矩实时跟踪控制[J]. 吉林大学学报(工学版), 2021, 51(4): 1405-1413.
[13]	李伟,陈剑,陶善勇. 自适应耦合周期势系统随机共振信号增强方法[J]. 吉林大学学报(工学版), 2021, 51(3): 1091-1096.
[14]	欧阳丹彤,刘扬,刘杰. 故障响应指导下基于测试集的故障诊断方法[J]. 吉林大学学报(工学版), 2021, 51(3): 1017-1025.
[15]	潘凤文,弓栋梁,高莹,徐明伟,麻斌. 基于锂离子电池线性化模型的电流传感器故障诊断[J]. 吉林大学学报(工学版), 2021, 51(2): 435-441.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	数值
量程/g	±50
灵敏度/（mV·g^-1）	100
采样频率/Hz	0.5~9000
分辨率/g	0.0002

样本类型	样本数量
正常样本，编号：0~49	50
X方向连续冲击程度1，编号：56~62	7
X方向连续冲击程度2，编号：63~66	4
Y方向连续冲击程度1，编号：67~72	6
Y方向连续冲击程度2，编号：73~77	5
Z方向连续冲击程度1，编号：78~84	7
Z方向连续冲击程度2，编号：85~89	5
不对中，编号：50~55	6
转速突变，编号：90~92	3

算法	准确率α	误识别率δ	运行时间/s
LOF	0.95	0.16	6.6
DLLOF	0.94	0.02	2.1

编号	LOF	GLOF	编号	LOF	GLOF
5	1.21	7.46	70	2.11	6.79
42	0.97	无	71	2.54	7.94
50	2.78	10.92	72	1.97	8.38
51	3.17	12.9	73	2.92	5.58
52	2.91	11.58	74	2.3	11.41
53	2.74	10.73	75	2.63	14.5
54	4.11	14.64	76	3.25	15.02
55	2.72	10.61	77	2.6	13.39
56	3.05	7.12	78	0.98	无
57	2.04	8.12	79	1.9	5.14
58	1.65	11.05	80	0.97	无
59	1.63	7.75	81	1.92	6.02
60	2.77	13.96	82	1.86	5.46
61	1.82	8.07	83	2.18	6.32
62	3.49	14.29	84	4.08	11.53
63	4.46	15.1	85	2.82	10.63
64	4.31	18.05	86	4.05	15.2
65	4.45	17.89	87	3.68	16.24
66	4.6	18.04	88	3.68	15.03
67	2.21	12.23	89	2.41	13.62
68	1.74	8.66	90	1.48	3.98
69	2.02	7.64	91	1.78	5.87

簇数	PC值
5	0.08
6	0.12
7	0.09
8	0.18
9	0.13