时变工况下基于精细复合多尺度散度熵的旋转机械故障诊断方法

PDF(1989 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (21) : 211-218.

论文

卢太武1，马洪波1，王先芝2，陈改革1

作者信息 +

Fault diagnosis method for rotating machinery based on fine composite multi-scale divergence entropy under time-varying working conditions

LU Taiwu1, MA Hongbo1, WANG Xianzhi2, CHEN Gaige1

Author information +

文章历史 +

摘要

时变工况下旋转机械的振动信号具有明显的时变调制的特点，熵值方法在提取该类信号特征时具有独特的优势。为了克服传统的熵值方法计算速度慢、熵值不稳定等问题，提出了一种基于精细复合多尺度散度熵的时变工况下旋转机械故障诊断方法，能够更有效地提取故障特征信息并提高故障诊断准确率。首先，采用重采样的方法将时域信号转为角域信号，并利用变分模态分解和独立分量分析相结合的方法对角域信号进行去噪。其次，采用精细复合多尺度散度熵对去噪后的角域信号进行特征提取，然后将提取到的特征输入 LR（Logistic Regression）分类器中识别故障类型。最后，通过时变工况下的齿轮实验对所提方法进行验证，结果表明，所提出的方法有效提高了时变工况下故障诊断准确率。

Abstract

The vibration signal of rotating machinery under time-varying working conditions presents time-varying characteristics. Entropy measure has unique advantages in extracting features from this type of signal. To make up the defects of low calculation efficiency and unstable complexity estimation of traditional entropy method, proposed a fault diagnosis method of rotating machinery under time-varying working conditions based on refined composite multiscale diversity entropy. The proposed method can extract more comprehensive fault feature information and improve the diagnostic accuracy. Firstly, the time domain signal is resampled into angular domain signal, and variational modal decomposition and independent component analysis is used to denoise the angular domain signal. Secondly, the refined composite multiscale diversity entropy is used to extract the features of the denoised signal. Then the extracted features are input into the LR (Logistic Regression) classifier to identify fault type. Finally, the proposed method is verified by gear experiments under time-varying conditions. The results show that the proposed method can effectively improve the diagnostic accuracy under time-varying conditions.

导出引用

卢太武1，马洪波1，王先芝2，陈改革1. 时变工况下基于精细复合多尺度散度熵的旋转机械故障诊断方法[J]. 振动与冲击, 2023, 42(21): 211-218

LU Taiwu1, MA Hongbo1, WANG Xianzhi2, CHEN Gaige1. Fault diagnosis method for rotating machinery based on fine composite multi-scale divergence entropy under time-varying working conditions[J]. Journal of Vibration and Shock, 2023, 42(21): 211-218

参考文献

[1] 林京，赵明. 变转速下机械设备动态信号分析方法的回顾与展望[J]. 中国科学:技术科学，2015, 45(07): 669–686.
LIN Jing, ZHAO Ming. Review and prospect of dynamic signal analysis methods of mechanical equipment under variable speed[J]. Science China Technological Science, 2015, 45(07): 669-686.
[2] 桂勇，韩勤锴，李峥. 变速行星齿轮系统故障诊断方法[J]. 振动.测试与诊断，2016, 36(02): 220–226.
GUI Yong, HAN Qinkai, LI Zheng. Fault diagnosis of planetary gear system under time-varying speed conditions[J]. Journal of Vibration, Measurement&Diagnosis, 2016, 36(02): 220-226.
[3] Feng Z, Chen X, Wang T. Time-varying demodulation analysis for rolling bearing fault diagnosis under variable speed conditions[J]. Journal of Sound and Vibration, 2017, 400: 71–85.
[4] Xue L, Li N, Lei Y, et al. Incipient fault detection for rolling element bearings under varying speed conditions[J]. Materials, 2017, 10(6): 675.
[5] Li S, An Z, Lu J. A novel data-driven fault feature separation method and its application on intelligent fault diagnosis under variable working conditions[J]. IEEE Access, 2020, 8: 113702-113712.
[6] Zhao M, Lin J, Xu X, et al. Tacholess envelope order analysis and its application to fault detection of rolling element bearings with varying speeds[J]. Sensors, 2013, 13(8): 10856–10875.
[7] 谭帅，马遥，侍洪波，等. 基于时序关联分析的旋转机械故障诊断[J]. 振动与冲击，2022, 41(8): 171-178.
TAN Shuai, MA Yao, SHI Hongbo, et al. Fault diagnosis of rotating machinery based on time-series correlation analysis[J]. Journal of Vibration and Shock, 2022, 41(8): 171-178.
[8] 陈龙，史文库，张曙光，等. 基于改进型峰值搜索算法的变速箱振动阶比分析[J]. 振动.测试与诊断，2020, 40(06): 1071-1076.
CHEN Long, SHI Wenku, ZHANG Shuguang, et al. Order tracking automobile gearbox in acceleration condition based on improved peak search algorithm[J]. Journal of Vibration, Measurement&Diagnosis, 2020, 40(06): 1071-1076.
[9] Shao Y, Ding Y, Mechefske C K. Engine fault detection using angle domain signal envelope algorithm[J]. Proceedings of the Institution of Mechanical Engineers Part I-Journal of Systems and Control Engineering, 2013, 227(6): 541–551.
[10] 晏云海，郭瑜，伍星. 基于循环谱分析的鲁棒性滚动轴承故障特征提取方法[J]. 振动与冲击，2022, 41(6): 1-7.
YAN Yunhai, GUO Yu, WU Xing. Robust rolling bearing fault feature extraction method based on cyclic spectrum analysis[J]. Journal of Vibration and Shock, 2022, 41(6): 1-7.
[11] 周小龙，徐鑫莉，王尧，等. 基于变分模态分解和最大重叠小波包变换的齿轮信号去噪方法[J]. 振动与冲击，2021, 40(12): 265-274.
ZHOU Xiaolong, XU Xinli, WANG Yao, et al. A gear signal de-noising method based on variational mode decomposition and maximal overlap discrete wavelet packet transform[J]. Journal of Vibration and Shock, 2021, 40(12): 1-7.
[12] Liu H, Liu C, Huang Y. Adaptive feature extraction using sparse coding for machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2011, 25(2): 558–574.
[13] Li Y, Wang X, Liu Z, et al. The entropy algorithm and its variants in the fault diagnosis of rotating machinery: a review[J]. IEEE Access, 2018, 6: 66723–66741.
[14] Li Y, Liu F, Wang S, et al. multi-scale symbolic lempel-ziv: an effective feature extraction approach for fault diagnosis of railway vehicle systems[J]. IEEE Transactions on Industrial Informatics, 2021, 17: 199-208.
[15] Richman J S, Moorman J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. American journal of physiology. Heart and circulatory physiology, 2000, 278(6): H2039-49.
[16] Chen W, Wang Z, Xie H, et al. Characterization of surface EMG signal based on fuzzy entropy[J]. IEEE Transactions on neural systems and rehabilitation engineering, 2007, 15(2): 266-272.
[17] Costa M, Goldberger A L, Peng C-K. Multiscale entropy to distinguish physiologic and synthetic RR time series[J]. Computers in cardiology, 2002, 29: 137–40.
[18] Li Y, Feng K, Liang X, et al. A fault diagnosis method for planetary gearboxes under non-stationary working conditions using improved Vold-Kalman filter and multi-scale sample entropy[J]. Journal of Sound and Vibration, 2019, 439: 271–286.
[19] 姜万录，赵亚鹏，张淑清，等. 精细复合多尺度波动散布熵在液压泵故障诊断中的应用[J]. 振动与冲击，2022, 41(8): 7-16.
JIANG Wanlu, ZHAO Yapeng, ZHANG Shuqing, et al. Application of refined composite multiscale fluctuation dispersion entropy in hydraulic pumps fault diagnosis[J]. Journal of Vibration and Shock, 2022, 41(8): 7-16.
[20] Wang X, Si S, Li Y. Multiscale diversity entropy: a novel dynamical measure for fault diagnosis of rotating machinery[J]. IEEE Transactions on Industrial Informatics, 2021, 17(8): 5419–5429.
[21] 刘强，赵荣珍，杨泽本. K-VMD融合包络熵与SVM滚动轴承识别方法研究[J]. 噪声与振动控制，2022, 42(03), 92-97.
LIU Qiang, ZHAO Rongzhen, YANG . Research of fault recognition method of rolling bearings based on K-VMD envelope entropy and SVM[J]. Noise and Vibration Control, 2022, 42(03): 92-97.
[22] 田宝平，应昊蓉，杨文境，等. 结合ICA和复数神经网络的双麦阵列盲源分离方法[J]. 信号处理，2021, 37(11): 2185-2192.
TIAN Baoping, YING Haorong, YANG Wenjing et al. Blind source separation of binary array based on ICA and complex neural network[J]. Journal of Signal Processing, 2021, 37(11): 2185-2192.
[23] Li Y, Wang X, Si S, et al . Entropy based fault classification using the case western reserve university data: a benchmark study[J]. IEEE Transactions on Reliability, 2020, 69(2): 754–767.