Fault Diagnosis of Gear By Using VMD-Modulo Square Threshold and PNN
-
摘要: 针对故障齿轮振动信号的非平稳和调制特性,提出了在变分模态分解(VMD)-模平方阈值降噪的基础上利用概率神经网络(PNN)进行齿轮故障诊断的方法。首先,利用VMD将原始振动信号分解为若干个本征模态函数分量,采用模平方阈值方法对各分量处理后并重构;然后,提取重构信号的峭度和均方根作为特征值组成特征向量;最后,将特征向量输入PNN实现故障类型识别。通过齿轮故障试验分析,将其与基于EMD-模平方阈值、LMD-模平方阈值和EEMD-模平方阈值的BP神经网络故障诊断方法相比较。结果表明,该方法能有效的提取特征信息,故障诊断准确率高达96.875%,证明了所提方法的可行性和有效性。Abstract: Aiming at non-stationary and modulation characteristics of fault vibration signals of gear, a fault diagnosis method is proposed by using the probabilistic neural network(PNN) on the basis of the variational mode decomposition(VMD)-modulo square threshold diagnosing. Firstly, the signals was decomposed into the several intrinsic mode functions(IMF) and each one was processed with the modulo squared threshold method. Then, the kurtosis and root mean square of the signals which were reconstructed with IMFs after the modulo squared threshold method were extracted as fault feature vectors for pattern recognition. Finally, the feature vector was input PNN model to realize the fault type identification. Through gear fault tests, based on EMD-modulo square threshold, LMD-modulo square threshold and EEMD-modulo square threshold, the accuracy was up to 96.875% comparing with BPNN, in which the feasibility and effectiveness of the present method was verified.
-
表 1 齿轮点蚀信号峭度值
信号处理 原始信号 VMD降噪 VMD-模平方阈值降噪 峭度 17.746 9 32.985 0 53.690 8 表 2 齿轮故障诊断准确率
分类器 EMD-模平方阈值 LMD-模平方阈值 EEMD-模平方阈值 VMD-模平方阈值 BPNN 78.125 62.5 84.375 93.75 PNN 84.375 68.75 87.5 96.875 -
[1] 何正嘉, 陈进, 王太勇, 等.机械故障诊断理论及应用[M].北京:高等教育出版社, 2010He Z J, Chen J, Wang T Y, et al. Theories and applications of machinery fault diagnostics[M]. Beijing:Higher Education Press, 2010(in Chinese) [2] 胥永刚, 赵国亮, 马朝永, 等.双树复小波域MCA降噪在齿轮故障诊断中的应用[J].航空动力学报, 2016, 31(1):219-226 http://d.old.wanfangdata.com.cn/Periodical/hkdlxb201601028Xu Y G, Zhao G L, Ma C Y, et al. Denoising method based on dual-tree complex wavelet transform and MCA and its application in gear fault diagnosis[J]. Journal of Aerospace Power, 2016, 31(1):219-226(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/hkdlxb201601028 [3] 程军圣, 马兴伟, 杨宇.基于VPMCD和EMD的齿轮故障诊断方法[J].振动与冲击, 2013, 32(20):9-13 doi: 10.3969/j.issn.1000-3835.2013.20.003Cheng J S, Ma X W, Yang Y. Gear fault diagnosis method based on VPMCD and EMD[J]. Journal of Vibration and Shock, 2013, 32(20):9-13(in Chinese) doi: 10.3969/j.issn.1000-3835.2013.20.003 [4] 程军圣, 杨怡, 杨宇.基于LMD的谱峭度方法在齿轮故障诊断中的应用[J].振动与冲击, 2012, 31(18):20-23 http://d.old.wanfangdata.com.cn/Periodical/zdycj201218007Cheng J S, Yang Y, Yang Y. Application of spectral kurtosis approach based on local mean decomposition (LMD) in gear fault diagnosis[J]. Journal of Vibration and Shock, 2012, 31(18):20-23(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdycj201218007 [5] 宁少慧, 韩振南, 武学峰, 等.EEMD和TFPF联合降噪法在齿轮故障诊断中的应用[J].振动、测试与诊断, 2017, 37(5):1011-1017 http://d.old.wanfangdata.com.cn/Periodical/zdcsyzd201705024Ning S H, Han Z N, Wu X F, et al. Application of combined TFPF and EEMD denoising method in gear fault diagnosis[J]. Journal of Vibration, Measurement & Diagnosis, 2017, 37(5):1011-1017(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdcsyzd201705024 [6] Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3):531-544 doi: 10.1109/TSP.2013.2288675 [7] 郑近德, 潘海洋, 杨树宝, 等.广义变分模态分解方法及其在变工况齿轮故障诊断中的应用[J].振动工程学报, 2017, 30(3):502-509 http://d.old.wanfangdata.com.cn/Periodical/zdgcxb201703019Zheng J D, Pan H Y, Yang S B, et al. Generalized variational mode decomposition and its applications to gearbox fault diagnosis under variable conditions[J]. Journal of Vibration Engineering, 2017, 30(3):502-509(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdgcxb201703019 [8] 唐贵基, 王晓龙.变分模态分解方法及其在滚动轴承早期故障诊断中的应用[J].振动工程学报, 2016, 29(4):638-648 http://d.old.wanfangdata.com.cn/Periodical/zdgcxb201604011Tang G J, Wang X L, Variational mode decomposition method and its application on incipient fault diagnosis of rolling bearing[J]. Journal of Vibration Engineering, 2016, 29(4):638-648(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdgcxb201604011 [9] Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3):531-544 doi: 10.1109/TSP.2013.2288675 [10] Abdoos A A. A new intelligent method based on combination of VMD and ELM for short term wind power forecasting[J]. Neurocomputing, 2016, 203:111-120 doi: 10.1016/j.neucom.2016.03.054 [11] 刘长良, 武英杰, 甄成刚.基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J].中国电机工程学报, 2015, 35(13):3358-3365 http://d.old.wanfangdata.com.cn/Periodical/zgdjgcxb201513020Liu C L, Wu Y J, Zhen C G. Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy C means clustering[J]. Proceedings of the CSEE, 2015, 35(13):3358-3365(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zgdjgcxb201513020 [12] Donoho D L. De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory, 1995;41(3):613-627 doi: 10.1109/18.382009 [13] 李杰, 曲芸, 刘俊, 等.模平方小波阈值在MEMS陀螺信号降噪中的应用[J].中国惯性技术学报, 2008, 16(2):236-239 http://d.old.wanfangdata.com.cn/Periodical/zggxjsxb200802027Li J, Qu Y, Liu J, et al. Application of modular square wavelet threshold for denoising MEMS-based gyros signal[J]. Journal of Chinese Inertial Technology, 2008, 16(2):236-239(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zggxjsxb200802027 [14] 吴小涛, 杨锰, 袁晓辉, 等.基于峭度准则EEMD及改进形态滤波方法的轴承故障诊断[J].振动与冲击, 2015, 34(2):38-44 http://d.old.wanfangdata.com.cn/Periodical/zdycj201502008Wu X T, Yang M, Yuan X H, et al. Bearing fault diagnosis using EEMD and improved morphological filtering method based on kurtosis criterion[J]. Journal of Vibration and Shock, 2015, 34(2):38-44(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdycj201502008 [15] Porwik P, Doroz R, Orczyk T. Signatures verification based on PNN classifier optimised by PSO algorithm[J]. Pattern Recognition, 2016, 60:998-1014 doi: 10.1016/j.patcog.2016.06.032