特征原子稀疏解析的多状态机械故障诊断方法

doi:10.3901/JME.2025.06.033

摘要/Abstract

摘要： 轴承作为机械设备关键部件，因多状态故障特征微弱或耦合的特性，导致故障特征难发掘，给机械设备的健康监测带来极大挑战。因此，提出基于特征原子稀疏解析的故障诊断方法，实现轴承多状态故障稀疏特征解析与诊断。首先，提出特征原子滤波器构造方法，基于可调Q因子小波变换的重构子带最大峭度准则提取小波基原子，并赋予基原子周期性先验特征匹配信号中的多状态故障成分。其次，构建多通道卷积稀疏多状态故障特征解析模型，基于多特征原子与交替方向乘子法优化的卷积稀疏编码解析稀疏系数分量，并重构各故障特征分量，实现多状态故障分量稀疏解析。同时，提出基于稀疏信号峭度与能量结合的稀疏度参数化方法。最后，通过重构分量的包络谱分析结果，确定信号中的特征成分，实现多状态故障诊断。通过仿真、试验和工业水泵等信号的试验验证，并与卷积字典学习方法相比，所提方法具有更好稀疏解析优势。

关键词: 多状态故障, 卷积稀疏解析, 特征解耦, 特征原子, 故障诊断

Abstract: As a critical component, bearings are difficult to excavate fault features due to the weak or coupled characteristics of multi-state fault features, which brings great challenges to the health monitoring of mechanical equipment. Therefore, a fault diagnosis method based on the sparse resolution of feature atoms is proposed to realize sparse feature resolution and diagnosis of multi-state faults. First, a feature atom filter construction method is proposed. The wavelet basis atoms are extracted based on the maximum kurtosis criterion of the reconstructed sub-band of the tunable Q-factor wavelet transform. The basis atoms are given periodic a priori features to match the multi-state fault components in the signal. Secondly, a multi-channel convolutional sparse multi-state fault feature resolution model is constructed. The sparse coefficient components are resolved based on convolutional sparse coding with multiple feature atoms and alternating direction multiplier method optimization. Reconstruct each fault feature component to realize the sparse resolution of multi-state fault components. Meanwhile, a sparsity parameterization method based on the combination of sparse signal kurtosis and energy is proposed. Finally, the results of the envelope spectrum analysis of the reconstructed components are used to determine the feature components in the signal for multi-state fault diagnosis.. The proposed method is experimentally verified through simulations, experiments and industrial pump signals, and has the advantage of better sparse resolution compared to the convolutional dictionary learning method.

Key words: multi-state faults, convolutional sparse parse, feature decoupling, feature atoms, fault diagnosis

中图分类号:

TG156

韩长坤, 卢威, 宋浏阳, 王华庆. 特征原子稀疏解析的多状态机械故障诊断方法[J]. 机械工程学报, 2025, 61(6): 33-42.

HAN Changkun, LU Wei, SONG Liuyang, WANG Huaqing. Multi-state Mechanical Fault Diagnosis Method Based on Feature Atom Sparse Parse[J]. Journal of Mechanical Engineering, 2025, 61(6): 33-42.

参考文献

[1] 肖扬, 王庆锋, 杨哲, 等. 旋转机械突发不平衡故障早期预警及诊断方法研究[J]. 机械工程学报, 2023, 59(11)：308-318. XIAO Yang, WANG Qingfeng, YANG Zhe, et al. Research on incipient warning and diagnosis method of sudden unbalance fault for rotating machinery[J]. Journal of Mechanical Engineering, 2023, 59(11)：308-318.
[2] DU G, JIANG T, WANG J, et al. Improved multi- bandwidth mode manifold for enhanced bearing fault diagnosis[J]. Chinese Journal of Mechanical Engineering[J]. 2022, 35：14.
[3] 苗永浩, 石惠芳, 李晨辉, 等. 谐波特征模式分解方法在轴承故障诊断中的应用[J]. 机械工程学报, 2023, 59(21)：234-244. MIAO Yonghao, SHI Huifang, LI Chenhui, et al. Harmonic feature mode decomposition and its application for bearing fault diagnosis[J]. Journal of Mechanical Engineering, 2023, 59(21)：234-244.
[4] 江星星, 宋秋昱, 杜贵府, 等. 变分模式分解方法研究与应用综述[J]. 仪器仪表学报, 2023, 44(1)：55-73. JIANG Xingxing, SONG Qiuyi, DU Guifu, et al. Review on research and application of variational mode decomposition[J]. Chinese Journal of Scientific Instrument, 2023, 44(1)：55-73.
[5] ZHAO N, ZHANG J, MAO Z, et al. Time-frequency feature extraction method of the multi-source shock signal based on improved VMD and bilateral adaptive laplace wavelet[J]. Chinese Journal of Mechanical Engineering, 2023, 36：36.
[6] 彭志科, 何永勇, 卢青, 等. 小波多重分形及其在振动信号分析中应用的研究[J]. 机械工程学报, 2002, 38(8)：59-63. PENG Zhike, HE Yongyong, LU Qing, et al. Wavelet multifractal spectrum：Application to analysis vibration signals[J]. Journal of Mechanical Engineering, 2002, 38(8)：59-63.
[7] COIFMAN R, WICKERHAUSER M. Entropy-based algorithms for best basis selection[J]. IEEE Transactions on Information Theory, 1992, 38(2)：713-718.
[8] XING Y, ZHANG H, LIU H. A novel fault diagnosis approach for rolling bearing based on CWT and adaptive sparse representation[J]. Shock and Vibration, 2022, 12：9079790.
[9] YAO R, JIANG H, YANG C, et al. Multiband weights- induced periodic sparse representation for bearing incipient fault diagnosis[J]. ISA Transactions, 2022, 136：483-502.
[10] 栗茂林, 梁霖, 王孙安. 基于稀疏表示的故障敏感特征提取方法[J]. 机械工程学报, 2013, 49(1)：73-80. LI Maolin, LIANG Lin, WANG Sunan. Sensitive feature extraction of machine faults based on sparse representation[J]. Journal of Mechanical Engineering, 2013, 49(1)：73-80.
[11] HAN C, LU W, WANG H, et al. Multistate fault diagnosis strategy for bearings based on an improved convolutional sparse coding with priori periodic filter group[J]. Mechanical Systems and Signal Processing, 2023, 188：109995.
[12] MALLAT S, ZHANG Z. Matching pursuits with time- frequency dictionaries[J]. IEEE Transactions on Signal Processing, 1993, 41(12)：3397-3415.
[13] 孙利雷, 秦进. 稀疏字典学习方法综述[J]. 贵州大学学报, 2018, 35(5)：81-86. SUN Lilei, QIN Jing. Review on sparse dictionary learning method[J]. Journal of Guizhou University, 2018, 35(5)：81-86.
[14] 郭俊锋, 石斌, 魏兴春, 等. 基于K-SVD字典学习算法的稀疏表示振动信号压缩测量重构方法[J]. 机械工程学报, 2018, 54(7)：97-106. GUO Junfeng, SHI Bin, WEI Xingchun, et al. A method of reconstruction of compressed measuring for mechanical vibration signals based on K-SVD dictionary-training algorithm sparse representation[J]. Journal of Mechanical Engineering, 2018, 54(7)：97-106.
[15] 余发军, 周凤星, 严保康. 基于字典学习的轴承早期故障稀疏特征提取[J]. 振动与冲击, 2016, 35(6)：181-186. YU Fajun, ZHOU Fengxing, YAN Baokang. Bearing initial fault feature extraction via sparse representation based on dictionary learning[J]. Journal of Vibration and Shock, 2016, 35(6)：181-186.
[16] 王华庆, 任帮月, 宋浏阳, 等. 基于终止准则改进K-SVD字典学习的稀疏表示特征增强方法[J]. 机械工程学报, 2019, 55(7)：35-43. WANG Huaqing, REN Bangyue, SONG Liuyang, et al. Sparse representation method based on termination criteria improved K-SVD dictionary learning for feature enhancement[J]. Journal of Mechanical Engineering, 2019, 55(7)：35-43.
[17] KONG Y, QIN Z, WANG T. et al. Data-driven dictionary design–based sparse classification method for intelligent fault diagnosis of planet bearings[J]. Structural Health Monitoring, 2022, 21(4)：1313-1328.
[18] DING J, ZHAO W, MIAO B, et al. Adaptive sparse representation based on circular-structure dictionary learning and its application in wheelset-bearing fault detection[J] Mechanical Systems and Signal Processing, 2018, 111：399-422.
[19] 牛柱强, 张玮, 许书庆, 等. 基于ACMD与K-SVD的滚动轴承微弱故障特征诊断技术[J]. 轴承, 2025(3)：97-103. NIU Zhuqiang, ZHANG Wei, XU Shuqing, et al. Weak fault diagnosis technology of rolling bearing based on ACMD and K-SVD[J]. Bearing, 2025(3)：97-103.
[20] YANG B, LIU R, CHEN X. Fault diagnosis for a wind turbine generator bearing via sparse representation and shift-invariant K-SVD[J]. IEEE Transactions on Industrial Informatics, 2017, 13(3)：1321-1331.
[21] CRISTINA G, BRENDT W. Convolutional dictionary learning：a comparative review and new algorithms[J]. IEEE Transactions on Computational Imaging, 2018, 4(3)：366-381.
[22] MARVASTI F, AMINI A, HADDADI F, et al. A unified approach to sparse signal processing[J]. EURASIP Journal on Advances in Signal Processing, 2012, 2012：44.
[23] ZHANG Z, HUANG W, LIAO Y, et al. Bearing fault diagnosis via generalized logarithm sparse regularization[J]. Mechanical Systems and Signal Processing, 2022, 167：108576.
[24] QIN L, LIN Z, SHE Y, et al. A comparison of typical l_p minimization algorithms[J]. Neurocomputing, 2013, 119(16)：413-424.
[25] HAN C, LU W, WANG P, et al. A recursive sparse representation strategy for bearing fault diagnosis[J]. Measurement, 2022, 187：110360.
[26] YIN N, SUN D, MEGG Z, et al. Gearbox fault diagnosis based on generalized multivariate logarithmic regularization[J]. 2023, 34(6)：065103.
[27] ZHANG Z, WANG J, LI S, et al. Fast nonlinear convolutional sparse filtering：A novel early-stage fault diagnosis method of rolling bearing[J]. Measurement, 2023, 207：112347.
[28] MA S, HAN Q, CHU F. Sparse representation learning for fault feature extraction and diagnosis of rotating machinery[J]. Expert Systems With Applications, 2023, 232：120858.
[29] 宋泽树, 黄伟国, 石娟娟, 等. 广义平滑对数正则化稀疏分解方法研究及其在齿轮箱复合故障诊断中的应用[J]. 机械工程学报, 2022, 58(23)：123-137. SONG Zeshu, HUANG Weiguo, SHI Juanjuan, et al. Research on generalized smooth logarithm regularization sparse decomposition method and its application in compound fault diagnosis of gearbox[J]. Journal of Mechanical Engineering, 2022, 58(23)：123-137.
[30] SELESNICK I. Wavelet transform with tunable Q-factor[J]. IEEE Transactions on Signal Processing, 2011, 59(8)：3560-3575.
[31] BRENDT W. Efficient algorithms for convolutional sparse representations[J]. IEEE Transactions on Image Processing, 2016, 25(1)：301-315.