基于改进VME算法和mRVM的滚动轴承小样本复合故障诊断

doi:10.13229/j.cnki.jdxbgxb.20240528

摘要/Abstract

摘要：

针对传统信号分离算法难以高效、准确分析具体故障的问题，提出了一种结合变分模态分解（VMD）、拉普拉斯能量指标（LE）和变分模态提取（VME）的信号提取方法，并采用多分类相关向量机（mRVM）及DS证据理论进行智能故障诊断，该方法专注于小样本数据情境。首先，采用VMD-LE-VME方法从故障信号中提取有效故障信息，并获得多域特征。其次，将多域特征输入mRVM进行故障识别。最后，通过DS证据理论融合分类结果，得到最终的诊断结果。实验结果验证了本文方法在处理小样本数据时的有效性和优越性。

关键词: 故障诊断, 变分模态分解, 拉普拉斯能量指标, 变分模态提取, 多分类相关向量机, DS证据理论

Abstract:

To address the problem that traditional signal separation algorithms cannot efficiently and accurately analyze specific faults, a signal extraction method combining Variational Mode Decomposition (VMD), Laplacian Energy (LE) and Variational Mode Extraction (VME) was proposed, and multi-class Relevance Vector Machine (mRVM) together with Dempster-Shafer (DS) evidence theory was adopted for intelligent fault diagnosis. This method is dedicated to the small-sample data scenario. First, the VMD-LE-VME method is used to extract effective fault information from fault signals and obtain multi-domain features. Second, the multi-domain features are input into the mRVM for fault identification. Finally, the classification results are fused by means of DS evidence theory to derive the final diagnosis results. Experimental results verify the effectiveness and superiority of the proposed method in handling small-sample data.

Key words: fault diagnosis, variational mode decomposition, Laplacian energy, variational mode extraction, multiclass relevance vector machine, Dempster-Shafer evidence theory

中图分类号:

TH17

冯志刚,张志远,董冰,于明月. 基于改进VME算法和mRVM的滚动轴承小样本复合故障诊断[J]. 吉林大学学报(工学版), 2025, 55(12): 3831-3839.

Zhi-gang FENG,Zhi-yuan ZHANG,Bing DONG,Ming-yue YU. Small sample rolling bearing compound fault diagnosis based on improved VME and mRVM[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(12): 3831-3839.

图/表 16

图1

图2

表1

图3

图4

图5

图6

表2

图7

图8

表3

表4

图9

表5

表6

表7

参考文献 20

[1]	Wang X L, Shi J C, Zhang J. A power information guided-variational mode decomposition (PIVMD) and its application to fault diagnosis of rolling bearing[J]. Digital Signal Processing, 2023, 132: No.103814.
[2]	Li W H, Chen Z Y, He G L. A novel weighted adversarial transfer network for partial domain fault diagnosis of machinery[J]. IEEE Transactions on Industrial Informatics, 2020, 17(3): 1753-1762.
[3]	Oh B S, Guo X, Wan F Y, et al. Micro-Doppler mini-UAV classification using empirical-mode decomposition features[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 15(2): 227-231.
[4]	Liu Z, Jin Y, Zuo M J, et al. Time-frequency representation based on robust local mean decomposition for multicomponent AM-FM signal analysis[J]. Mechanical Systems and Signal Processing, 2017, 95: 468-487.
[5]	Mao M J, Zeng K X, Tan Z F, et al. Adaptive VMD-K-SVD-based rolling bearing fault signal enhancement Study[J]. Sensors, 2023, 23(20): No.8629.
[6]	崔玲丽, 吴春光, 邬娜. 基于EMD与ICA的滚动轴承复合故障诊断 [J]. 北京工业大学学报, 2014, 40(10): 1459-1464.
	Cui Ling-li, Wu Chun-guang, Wu Na. Composite fault diagnosis of rolling bearings based on EMD and ICA algorithm[J]. Journal of Beijing University of Technology. 2014, 40(10): 1459-1464.
[7]	杨斌, 张家玮, 樊改荣, 等. 最优参数MCKD与ELMD在轴承复合故障诊断中的应用研究[J]. 振动与冲击, 2019, 38(11): 59-67.
	Yang Bin, Zhang Jia-wei, Fan Gai-rong,et al. Application of OPMCKD and ELMD in bearing compound fault diagnosis[J]. Journal of Vibration and Shock, 2019, 38(11): 59-67.
[8]	Jiang X X, Wang J, Shen C Q, et al. An adaptive and efficient variational mode decomposition and its application for bearing fault diagnosis[J]. Structural Health Monitoring, 2021, 20(5): 2708-2725.
[9]	Estranda E. Characterization of the folding degree of proteins[J]. Bioinformatics, 2002, 18(5): 697-704.
[10]	Nazari M, Sakhaei S M. Variational mode extraction: a new efficient method to derive respiratory signals from ECG[J]. IEEE Journal of Biomedical and Health Informatics, 2017, 22(4): 1059-1067.
[11]	Kumar H S, Upadhyaya G. Fault diagnosis of rolling element bearing using continuous wavelet transform and K-nearest neighbour[J]. Materials Today: Proceedings, 2023, 92: 56-60.
[12]	Gu Y K, Zhou X Q, Yu D P, et al. Fault diagnosis method of rolling bearing using principal component analysis and support vector machine[J]. Journal of Mechanical Science and Technology, 2018, 32: 5079-5088.
[13]	Cao H R, Shao H D, Zhong X, et al. Unsupervised domain-share CNN for machine fault transfer diagnosis from steady speeds to time-varying speeds[J]. Journal of Manufacturing Systems, 2022, 62: 186-198.
[14]	Psorakis I, Damoulas T, Girolami M A. Multiclass relevance vector machines: sparsity and accuracy[J]. IEEE Transactions on Neural Networks, 2010, 21(10): 1588-1598.
[15]	Gao S Z, Yu Y F, Zhang Y M. Reliability assessment and prediction of rolling bearings based on hybrid noise reduction and BOA-MKRVM[J]. Engineering Applications of Artificial Intelligence, 2022, 116: No.105391.
[16]	Dong L, Chen Z Y, Hua R N, et al. Research on diagnosis method of centrifugal pump rotor faults based on IPSO-VMD and RVM[J]. Nuclear Engineering and Technology, 2023, 55(3): 827-838.
[17]	Zhao K Y, Li L, Chen Z Q, et al. A survey: optimization and applications of evidence fusion algorithm based on Dempster-Shafer theory[J]. Applied Soft Computing, 2022, 124: No.109075.
[18]	Li C X, Liu Y Q, Liao Y Y, et al. A VME method based on the convergent tendency of VMD and its application in multi-fault diagnosis of rolling bearings [J]. Measurement, 2022, 198: No.111360.
[19]	Tipping M E. The relevance vector machine[J]. Advances in Neural Information Processing Systems, 1999, 12: 652-658.
[20]	Pang B, Nazari M, Tang G J. Recursive variational mode extraction and its application in rolling bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2022, 165: No.108321.

相关文章 15

[1]	龙志友,万昭龙,董是,杨超,刘肖扬. 基于变分模态分解和极端梯度提升的公路边坡位移预测[J]. 吉林大学学报(工学版), 2025, 55(7): 2320-2332.
[2]	冯志刚,王首起,于明月. 基于变分模态提取及轻量级网络的滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2025, 55(6): 1883-1891.
[3]	王娜,崔月磊,李杨,王子从. 基于小波包对数能量图的滚动轴承故障诊断方法[J]. 吉林大学学报(工学版), 2025, 55(2): 494-502.
[4]	余萍,赵康,曹洁. 基于优化A-BiLSTM的滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2024, 54(8): 2156-2166.
[5]	王长建,刘久明,张锦洲,李斌. 基于高速摄影技术的行星减速箱故障激光序列脉冲诊断方法[J]. 吉林大学学报(工学版), 2024, 54(7): 1869-1875.
[6]	邱继伟,罗海胜,张亚,肖定国,赵冠捷,马茂冬. 基于解释结构模型的复杂系统故障诊断[J]. 吉林大学学报(工学版), 2024, 54(11): 3168-3174.
[7]	张玺君,尚继洋,余光杰,郝俊. 基于注意力的多尺度卷积神经网络轴承故障诊断[J]. 吉林大学学报(工学版), 2024, 54(10): 3009-3017.
[8]	李博,李欣,芮红,梁媛. 基于变分模态分解和灰狼优化极限学习机的隧道口边坡位移预测[J]. 吉林大学学报(工学版), 2023, 53(6): 1853-1860.
[9]	欧阳丹彤,孙睿,田新亮,高博涵. 基于集合阻塞的不确定系统中传感器选择方法[J]. 吉林大学学报(工学版), 2023, 53(2): 547-554.
[10]	张朝刚,侍中楼,李敏. 基于多状态时间序列预测学习的超精密机床主轴故障诊断仿真[J]. 吉林大学学报(工学版), 2023, 53(11): 3056-3061.
[11]	陈永刚,许继业,王海涌,熊文祥. 基于自适应神经模糊网络的转辙机故障诊断方法[J]. 吉林大学学报(工学版), 2023, 53(11): 3274-3280.
[12]	周怡娜,董宏丽,张勇,路敬祎. 基于VMD去噪和散布熵的管道信号特征提取方法[J]. 吉林大学学报(工学版), 2022, 52(4): 959-969.
[13]	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.
[14]	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.
[15]	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.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

IMF分量	LE
IMF1	0.075 9
IMF2	0.082 1
IMF3	0.051 3
IMF4	7.813 2

特征类型	训练集与测试集比例
特征类型	6∶4	5∶5	4∶6	3∶7	2∶8
时域频域	94.67	91.67	88.33	86.67	86.25
熵值	99.33	97.50	92.22	91.43	90