Fault diagnosis method of vehicle transmission system based on manifold fusion of parameter-varying wavelet
-
摘要: 应用流形学习方法非线性融合信号在不同小波参数下中央尺度对应的小波包络，研究了强背景噪声下车辆传动系统振动信号故障瞬态脉冲包络的有效提取问题，并与传统信号时频分解方法进行了对比研究；采用不同小波参数对振动信号进行连续小波变换，提取了每组参数下中央尺度上的小波包络；采用基尼指数选择若干包含故障瞬态脉冲信息的小波包络，构造了高维小波包络矩阵；采用局部切空间排列算法对高维小波包络进行流形融合，获得了反映故障瞬态脉冲包络本质结构的小波包络流形；为了验证所提方法的有效性和优越性，采用不同方法对轨道车辆轮对轴承和汽车变速齿轮箱的故障振动信号进行了对比分析。研究结果表明：在分析轴承外圈故障信号时，所提方法基尼指数比传统信号时频分解方法提高27.32%以上；在分析齿轮磨损故障信号时，所提方法基尼指数比传统信号时频分解方法提高26.74%以上。可见，所提方法通过综合具有不同形态的变参小波包络，可以在无需优化小波参数情况下，对车辆传动系统中的不同关键部件故障振动信号具有较好的自适应性，提取的故障脉冲包络中的带内噪声少，故障脉冲特性明显，容易识别其频谱中的故障特征频率，是检测车辆传动系统故障的一种有效方法。Abstract: The manifold learning method was utilized to nonlinearly fuse the wavelet envelopes corresponding to the central scale under different wavelet parameters. The problem of effective extraction of the fault transient impulse envelopes from the vibration signals in vehicle transmission systems under heavy background noise was studied, and a comparative study with the traditional time-frequency methods for signal decomposition was carried out. Different wavelet parameters were adopted for the vibration signals to perform continuous wavelet transform (CWT), and the wavelet envelope corresponding to the central scale under each group of wavelet parameters was extracted. Some wavelet envelopes containing the information of the fault transient impulses were selected by Gini index, and the high-dimensional matrix of wavelet envelopes was constructed. The high-dimensional wavelet envelopes were fused based on manifold by using the local tangent space alignment (LTSA) algorithm, and the wavelet envelope manifold reflecting the intrinsic structure of fault transient impulse envelopes was obtained. In order to verify the effectiveness and superiority of the proposed method, the fault vibration signals of a railway-vehicle-wheelset bearing and an automobile change-speed gearbox were analyzed comparatively by different methods. Research results indicate that, compared to the traditional time-frequency methods for signal decomposition, the proposed method can improve the Gini index by over 27.32% in the case of bearing signal with an outer-race fault, and by over 26.74% in the case of gearbox signal with a wearing fault. It can be seen that, by synthesizing the parameter-varying wavelet envelopes with different patterns, the proposed method is well adaptive to the vibration signals for the faults of different key parts in the vehicle transmission systems with no need for wavelet parameter optimization. The extracted envelopes of the fault transient impulses have less in-band noise and distinct fault impulsive features. These advantages are beneficial to the identification of the fault characteristic frequencies in the spectra of the extracted envelopes. Therefore, the proposed method is an effective method for the fault detection of vehicle transmission systems.
-
图 2 不同小波参数获得的TSD和其中央尺度对应的小波包络
Figure 2. TSDs and wavelet envelopes corresponding to central scales obtained by using different wavelet parameters
图 5 轨道车辆轮对轴承故障模拟试验台
Figure 5. Fault simulation test bench of wheelset bearings of railway vehicles
图 6 具有外圈故障的轮对轴承振动信号
Figure 6. Vibration signals of wheelset bearing with an outer-race fault
图 7 所提方法分析轮对轴承信号时中央尺度和最优近邻点个数的确定
Figure 7. Determinations of central scale and best neighborhood size when analyzing wheelset bearing signal by proposed method
图 8 所提方法分析轮对轴承信号得到的包络及其功率谱
Figure 8. Envelopes and corresponding power spectra of wheelset bearing signal obtained by proposed method
图 9 VMD方法分析轮对轴承信号得到的包络及其功率谱
Figure 9. Envelopes and corresponding power spectra of wheelset bearing signal obtained by VMD method
图 10 EEMD方法分析轮对轴承信号得到的包络及其功率谱
Figure 10. Envelopes and corresponding power spectra of wheelset bearing signal obtained by EEMD method
图 11 FK方法分析轮对轴承信号得到的包络及其功率谱
Figure 11. Envelopes and corresponding power spectra of wheelset bearing signal obtained by FK method
图 12 不同方法分析轮对轴承信号所得结果的基尼指数
Figure 12. Gini indexes obtained by different methods for wheelset bearing signal
图 15 所提方法分析齿轮箱信号时中央尺度和最优近邻点个数的确定
Figure 15. Determinations of central scale and best neighborhood size when analyzing gearbox signal by proposed method
图 16 所提方法分析齿轮箱信号得到的包络及其功率谱
Figure 16. Envelopes and corresponding power spectra of gearbox signal obtained by proposed method
图 17 VMD方法分析齿轮箱信号得到的包络及其功率谱
Figure 17. Envelopes and corresponding power spectra of gearbox signal obtained by VMD method
图 18 EEMD方法分析齿轮箱信号得到的包络及其功率谱
Figure 18. Envelopes and corresponding power spectra of gearbox signal obtained by EEMD method
图 19 FK方法分析齿轮箱信号得到的包络及其功率谱
Figure 19. Envelopes and corresponding power spectra of gearbox signal obtained by FK method
图 20 不同方法分析齿轮箱信号所得结果的基尼指数值
Figure 20. Values of Gini index of results obtained by different methods for gearbox signal
表 1 所提方法分析轮对轴承信号时选取的小波参数
Table 1. Wavelet parameters selected when analyzing wheelset bearing signal by proposed method
序号 fb/Hz fc/Hz 序号 fb/Hz fc/Hz 1 3.0 1.6 6 10.5 0.8 2 2.0 1.9 7 11.5 0.8 3 2.5 1.6 8 19.5 0.6 4 11.0 0.8 9 19.0 0.6 5 20.0 0.6 10 12.0 0.8 
下载: 导出CSV
表 2 所提方法分析齿轮箱信号时选取的小波参数
Table 2. Wavelet parameters selected when analyzing gearbox signal by proposed method
序号 fb/Hz fc/Hz 序号 fb/Hz fc/Hz 1 1.5 1.7 6 3.5 1.1 2 5.0 0.9 7 1.0 2.0 3 6.0 0.8 8 4.5 0.9 4 6.5 0.8 9 8.0 0.7 5 3.5 1.1 10 3.0 1.1
下载: 导出CSV
-
[1] 韩清振, 何仁. 基于非线性Drive-shaft模型的车辆传动系统冲击响应[J]. 交通运输工程学报, 2019, 19(1): 119-126. doi: 10.3969/j.issn.1671-1637.2019.01.012HAN Qing-zhen, HE Ren. Shock response of vehicle powertrain based on nonlinear drive-shaft model[J]. Journal of Traffic and Transportation Engineering, 2019, 19(1): 119-126. (in Chinese) doi: 10.3969/j.issn.1671-1637.2019.01.012 [2] KARPAT F, DIRIK A E, DOǦAN O, et al. A novel AI-based method for spur gear early fault diagnosis in railway gearboxes[C]//IEEE. 2020 Innovations in Intelligent Systems and Applications Conference (ASYU). New York: IEEE, 2020: 1-6. [3] GIANNOULI E, PAPAELIAS M, AMINI A, et al. Detection and evaluation of rolling stock wheelset defects using acoustic emission[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2021, 63(7): 403-408. doi: 10.1784/insi.2021.63.7.403 [4] KOO J S, OH H S. A new derailment coefficient considering dynamic and geometrical effects of a single wheelset[J]. Journal of Mechanical Science and Technology, 2014, 28(9): 3483-3498. doi: 10.1007/s12206-014-0809-8 [5] 沈长青, 王旭, 王冬, 等. 基于多尺度卷积类内迁移学习的列车轴承故障诊断[J]. 交通运输工程学报, 2020, 20(5): 151-164. doi: 10.19818/j.cnki.1671-1637.2020.05.012SHEN Chang-qing, WANG Xu, WANG Dong, et al. Multi-scale convolution intra-class transfer learning for train bearing fault diagnosis[J]. Journal of Traffic and Transportation Engineering, 2020, 20(5): 151-164. (in Chinese) doi: 10.19818/j.cnki.1671-1637.2020.05.012 [6] MONTEIRO R P, CERRADA M, CABRERA D R, et al. Using a support vector machine based decision stage to improve the fault diagnosis on gearboxes[J]. Computational Intelligence and Neuroscience, 2019, 2019: 1383752. [7] ŁUKASIEWICZ M, KAŁACZYŃSKI T, MUSIAŁ J, et al. Diagnostics of buggy vehicle transmission gearbox technical state based on modal vibrations[J]. Journal of Vibroengineering, 2014, 16(6): 3137-3145. [8] 孙丽萍, 陈果, 谭真臻. 基于核主成分分析的小波尺度谱图像特征提取[J]. 交通运输工程学报, 2009, 9(5): 62-66. doi: 10.3321/j.issn:1671-1637.2009.05.011SUN Li-ping, CHEN Guo, TAN Zhen-zhen. Image feature extraction from wavelet scalogram based on kernel principle component analysis[J]. Journal of Traffic and Transportation Engineering, 2009, 9(5): 62-66. (in Chinese) doi: 10.3321/j.issn:1671-1637.2009.05.011 [9] HUNAG Wei-guo, SONG Ze-shu, ZHANG Cheng, et al. Multi-source fidelity sparse representation via convex optimization for gearbox compound fault diagnosis[J]. Journal of Sound and Vibration, 2021, 496: 115879. doi: 10.1016/j.jsv.2020.115879 [10] YANG Shao-pu, GU Xiao-hui, LIU Yong-qiang, et al. A general multi-objective optimized wavelet filter and its applications in fault diagnosis of wheelset bearings[J]. Mechanical Systems and Signal Processing, 2020, 145: 106914. doi: 10.1016/j.ymssp.2020.106914 [11] 吴守军, 冯辅周, 吴春志, 等. 快速峭度谱用于复合行星齿轮故障特征提取[J]. 机械传动, 2019, 43(10): 151-157. https://www.cnki.com.cn/Article/CJFDTOTAL-JXCD201910028.htmWU Shou-jun, FENG Fu-zhou, WU Chun-zhi, et al. Application of fast kurtosis spectrum in fault feature extraction of compound planetary gear[J]. Journal of Mechanical Transmission, 2019, 43(10): 151-157. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXCD201910028.htm [12] JIANG Xing-xing, WANG Jun, SHEN Chang-qing, 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. doi: 10.1177/1475921720970856 [13] 李奕璠, 刘建新, 林建辉, 等. 基于自适应多尺度形态学分析的车轮扁疤故障诊断方法[J]. 交通运输工程学报, 2015, 15(1): 58-65. doi: 10.3969/j.issn.1671-1637.2015.01.008LI Yi-fan, LIU Jian-xin, LIN Jian-hui, et al. Fault diagnosis method of railway vehicle with wheel flat based on self-adaptive multi-scale morphology analysis[J]. Journal of Traffic and Transportation Engineering, 2015, 15(1): 58-65. (in Chinese) doi: 10.3969/j.issn.1671-1637.2015.01.008 [14] 秦娜, 王开云, 金炜东, 等. 高速列车转向架故障的经验模态熵特征分析[J]. 交通运输工程学报, 2014, 14(1): 57-64, 74. doi: 10.3969/j.issn.1671-1637.2014.01.010QIN Na, WANG Kai-yun, JIN Wei-dong, et al. Fault feature analysis of high-speed train bogie based on empirical mode decomposition entropy[J]. Journal of Traffic and Transportation Engineering, 2014, 14(1): 57-64, 74. (in Chinese) doi: 10.3969/j.issn.1671-1637.2014.01.010 [15] SU Zu-qiang, XU Hai-tao, LUO Jiu-fei, et al. Fault diagnosis method based on a new manifold learning framework[J]. Journal of Intelligent and Fuzzy Systems, 2018, 34(6): 3413-3427. doi: 10.3233/JIFS-169522 [16] WANG Yi, TSE P W, TANG Bao-ping, et al. Kurtogram manifold learning and its application to rolling bearing weak signal detection[J]. Measurement, 2018, 127: 533-545. doi: 10.1016/j.measurement.2018.06.026 [17] ZHUANG Zhe, DING Jian-ming, TAN A C, et al. Fault detection of high-speed train wheelset bearing based on impulse-envelope manifold[J]. Shock and Vibration, 2017, DOI: 10.1155/2017/2104720. [18] DAI Lei, LI Quan-chang, CHEN Yi-jie, et al. Complex scale feature extraction for gearbox via adaptive multi-mode manifold learning[J]. Measurement, 2021, 174: 108688. doi: 10.1016/j.measurement.2020.108688 [19] WANG Jun, DU Gui-fu, ZHU Zhong-kui, et al. Fault diagnosis of rotating machines based on the EMD manifold[J]. Mechanical Systems and Signal Processing, 2020, 135: 106443. doi: 10.1016/j.ymssp.2019.106443 [20] WANG Jun, HE Qing-bo. Wavelet packet envelope manifold for fault diagnosis of rolling element bearings[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(11): 2515-2526. doi: 10.1109/TIM.2016.2566838 [21] WANG Jun, HE Qing-bo, KONG Fan-rang. Multiscale envelope manifold for enhanced fault diagnosis of rotating machines[J]. Mechanical Systems and Signal Processing, 2015, 52/53: 376-392. doi: 10.1016/j.ymssp.2014.07.021 [22] CHEN Jing-long, LI Zi-ping, PAN Jun, et al. Wavelet transform based on inner product in fault diagnosis of rotating machinery: a review[J]. Mechanical Systems and Signal Processing, 2016, 70/71: 1-35. doi: 10.1016/j.ymssp.2015.08.023 [23] WANG Yi, XU Guang-hua, LIANG Lin, et al. Detection of weak transient signals based on wavelet packet transform and manifold learning for rolling element bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2015, 54/55: 259-276. doi: 10.1016/j.ymssp.2014.09.002 [24] WANG Jun, HE Qing-bo. Exchanged ridge demodulation of time-scale manifold for enhanced fault diagnosis of rotating machinery[J]. Journal of Sound and Vibration, 2014, 333(11): 2450-2464. doi: 10.1016/j.jsv.2014.01.006 [25] DING Chuang-cang, ZHAO Ming, LIN Jing, et al. Multi-objective iterative optimization algorithm based optimal wavelet filter selection for multi-fault diagnosis of rolling element bearings[J]. ISA Transactions, 2019, 88: 199-215. [26] ZHANG Zhen-yue, ZHA Hong-yuan. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment[J]. Journal of Shanghai University (English Edition), 2004, 8(4): 406-424. [27] 江星星, 彭德民, 沈长青, 等. 快速固有成分滤波特征融合的轴承故障诊断方法[J]. 机械工程学报, 2022, 58(22): 1-11.JIANG Xing-xing, PENG De-min, SHEN Chang-qing, et al. The feature fusion of fast intrinsic component filtering for bearing fault diagnosis[J]. Journal of Mechanical Engineering, 2022, 58(22): 1-11. (in Chinese) [28] WANG Dong. Some further thoughts about spectral kurtosis, spectral L2/L1 norm, spectral smoothness index and spectral Gini index for characterizing repetitive transients[J]. Mechanical Systems and Signal Processing, 2018, 108: 360-368. [29] AOUABDI S, TAIBI M, BOURAS S, et al. Using multi-scale entropy and principal component analysis to monitor gears degradation via the motor current signature analysis[J]. Mechanical Systems and Signal Processing, 2017, 90: 298-316. [30] 许迪, 葛江华, 王亚萍, 等. 流形学习和M-KH-SVR的滚动轴承衰退预测[J]. 振动工程学报, 2018, 31(5): 892-901. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDGC201805020.htmXU Di, GE Jiang-hua, WANG Ya-ping, et al. Prediction for rolling bearing performance degradation based on manifold learning and M-KH-SVR[J]. Journal of Vibration Engineering, 2018, 31(5): 892-901. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDGC201805020.htm -
点击查看大图
计量
- 文章访问数: 381
- HTML全文浏览量: 156
- PDF下载量: 62
- 被引次数: 0
