滚动轴承作为旋转机械设备的重要部件之一，其工作状态直接影响旋转设备的运行安全，因此其故障特征的有效提取对于保障机械设备正常运行具有重要的意义。实际应用中滚动轴承通常以变化的速度运行，并且单一传感器采集的轴承的非平稳信号往往被严重的背景噪声覆盖，使得故障特征的提取非常困难。为了解决这一问题，本文提出一种变转速下 范数与张量核范数联合约束的TRPCA的滚动轴承故障特征提取方法。首先，使用时频表示（Time-Frequency Representation，TFR）作为正向切片构建张量，分别探讨滚动轴承时变故障特征在张量域中的管稀疏性和背景噪声在张量域中的低管秩性。进而使用 范数与张量核范数联合约束的张量主成分分析（Tensor Robust Principal Component Analysis, TRPCA）对故障特征张量进行提取，得到管稀疏的故障特征张量。最后将提取的故障特征张量在通道索引中进行融合，得到能够有效表征故障特征的时频表示。仿真和实验分析验证了该方法在轴承故障特征提取中的有效性。
Abstract
As one of the important components of rotating mechanical equipment, the effective extraction of fault features from rolling bearings is of great importance to ensure the regular operation of mechanical equipment. In practical applications, rolling bearings usually operate at variable speeds, and the non-stationary signal of the bearings collected by a single sensor are often covered by severe background noise, making the task of fault feature extraction very difficult. This paper proposes a robust fault feature extraction method based on time-frequency analysis under variable speed conditions. First, the time-frequency representation (TFR) is used as frontal slices to construct the tensor, and explore the tubewise sparsity of time-varying fault features and the low rank property of the background noise in the tensor domain. Then, the tensor robust principal component analysis (TRPCA) with joint constraints of norm and tensor nuclear norm is used to extract the fault feature tensor, obtaining a tubewise sparse fault feature tensor. Finally, the extracted fault feature tensor is fused the channel index to get a time-frequency representation that can effectively represent the fault features. Simulation and experimental analyses verify the effectiveness of this method in bearing fault feature extraction.
关键词
张量 /
故障特征提取 /
变转速工况 /
TRPCA /
管稀疏
{{custom_keyword}} /
Key words
tensor /
fault feature extraction /
variable speed conditions /
TRPCA /
tubewise sparsity
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈鑫, 郭瑜, 伍星, 等. 基于CPW和SCD的行星轴承内圈故障特征提取 [J]. 振动测试与诊断, 2021, 41(05): 868-73+1030.
CHEN Xin, GUO Yu , WU Xing, et al. Fault Feature Extraction of Planetary Bearing Inner Ring Based on CPW and SCD [J]. Journal of Vibration, Measurement & Diagnosis. 2021, 41(05): 868-73+1030.
[2] 王冉, 周雁翔, 胡雄, 等. 基于EMD多尺度威布尔分布与HMM的轴承性能退化评估方法 [J]. 振动与冲击, 2022, 41(03): 209-15.
WANG Ran, ZHOU Yanxiang, HU Xiong, et al. Evaluation method of bearing performance degradation based on EMD multi-scale Weibull distribution and HMM. [J]. Journal of Vibration and Shock.2022. 41(3): 209-215.
[3] BORGHESANI P, SMITH W A, RANDALL R B, et al. Bearing signal models and their effect on bearing diagnostics [J]. Mechanical Systems and Signal Processing, 2022, 174: 109077.
[4] 张旭辉, 张超, 樊红卫, 等. 快速谱峭度结合阶次分析滚动轴承故障诊断 [J]. 振动测试与诊断, 2021, 41(06): 1090-5+235.
ZHANG Xuhui, ZHANG Chao, FAN Hongwei, et al. Improved Fault Diagnosis of Rolling Bearing by Fast Kurtogram and Order Analysis [J]. Journal of Vibration, Measurement & Diagnosis. 2021, 41(06): 1090-5+235.
[5] 张龙, 吴荣真, 周建民, 等. 滚动轴承性能退化的时序多元状态估计方法 [J]. 振动测试与诊断, 2021, 41(06): 1096-104+235-236.
ZHANG Long,WU Rongzhen,ZHOU Jianmin, et al. Performance Degradation Assessment of Rolling Bearing Based on AR Model and Multivariate State Estimation Technique [J]. Journal of Vibration, Measurement & Diagnosis. 2021, 41(06): 1096-104+235-236.
[6] WANG R, ZHANG J, FANG H, et al. Sparsity enforced time–frequency decomposition in the Bayesian framework for bearing fault feature extraction under time-varying conditions [J]. Mechanical Systems and Signal Processing, 2023, 185: 109755.
[7] YU L, ANTONI J, LECLèRE Q. COMBINED REGULARIZATION OPTIMIZATION FOR SEPARATING TRANSIENT SIGNAL FROM STRONG NOISE IN ROLLING ELEMENT BEARING DIAGNOSTICS; proceedings of the Proceedings of Surveillance 7, F, 2013 [C].
[8] 刘伟, 刘洋, 单雪垠, 等. 基于低秩-稀疏分解的滚动轴承故障特征提取 [J]. 北京化工大学学报(自然科学版), 2022, 49(06): 83-91.
LIU Wei, LIU Yang, SHAN XueYin, et al .Feature extraction for fault signals from a rolling bearing using low rank and sparse decomposition [J]. Journal of Beijing University of Chemical Technology, 2022, 49(6): 83-91.
[9] KOLDA T. Tensor decompositions and applications [J]. Siam Review, 2009.
[10] WANG A, JIN Z, YANG J. A Factorization Strategy for Tensor Robust PCA; proceedings of the Pattern Recognition, Cham, F 2020//, 2020 [C]. Springer International Publishing.
[11] LU C, FENG J, CHEN Y, et al. Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(4): 925-38.
[12] ZHANG Z, ELY G, AERON S, et al. Novel methods for multilinear data completion and de-noising based on tensor-SVD; proceedings of the IEEE, F, 2014 [C].
[13] GE M, LV Y, MA Y. Research on Multichannel Signals Fault Diagnosis for Bearing via Generalized Non-Convex Tensor Robust Principal Component Analysis and Tensor Singular Value Kurtosis [J]. IEEE Access, 2020, 8: 178425-49.
[14] 胡超凡, 王衍学. 基于张量分解的滚动轴承复合故障多通道信号降噪方法研究 [J]. 机械工程学报, 2019, 55(12): 50-7.
HU Chaofan, WANG Yanxue. Research on Multi-channel Signal Denoising Method for Multiple Faults Diagnosis of Rolling Element Bearings Based on Tensor Factorization [J]. Journal of Mechanical Engineering, 2019, 55(12): 50-57.
[15] XU Y, WU Z, CHANUSSOT J, et al. Joint Reconstruction and Anomaly Detection From Compressive Hyperspectral Images Using Mahalanobis Distance-Regularized Tensor RPCA [J]. IEEE Transactions on Geoence and Remote Sensing, 2018: 2919-30.
[16] HOU F, SELESNICK I, CHEN J, et al. Fault diagnosis for rolling bearings under unknown time-varying speed conditions with sparse representation [J]. Journal of Sound and Vibration, 2021, 494: 115854.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(4256 KB)
