Underdetermined blind source separation based on density peak clustering for gear fault identification
-
摘要: 为提高盲源分离算法在振动源数目估计问题中的噪声鲁棒性,提出了一种基于密度峰值聚类的欠定盲源分离算法。对预处理后的信号提取单源点,通过密度峰值聚类对单源点进行聚类得到混合矩阵的估计值。通过基于压缩感知模型对源信号进行重构,得到分离信号。为验证所提算法分离准确性和噪声鲁棒性,用所提算法对不同信噪比下的仿真信号进行分离,结果显示:在信噪比不低于4 dB时,所提算法均可以准确分离出源信号,算法的准确性和鲁棒性得到验证。设计旋转部件故障诊断试验台对所提算法在实际应用中的有效性进行验证,对实测复合故障振动信号进行分离,试验结果表明该算法成功分离出观测信号中的锥齿轮和行星齿轮单一故障特征,有助于工程中旋转部件故障诊断。Abstract: In order to improve the noise robustness of blind source separation algorithm in estimating the number of vibration sources,an underdetermined blind source separation method was proposed based on density peak clustering.Single source points were extracted from signals preprocessed,and then the mixed matrix was estimated by clustering single source points with density peak clustering.The separated signals were obtained by reconstructing the source signals based on the compressed sensing model.In order to verify the separation accuracy and noise robustness of the proposed algorithm,the simulation signals under different signal-to-noise ratios were separated by the proposed algorithm.The results showed that when the signal-to-noise ratios was not less than 4 dB,the proposed algorithm can accurately separate the source signals,and the accuracy and robustness of the algorithm were verified.A rotating component fault diagnosis test-bench was designed to verify the effectiveness of the proposed algorithm in practical application,and the measured composite fault vibration signal was processed.The test results showed that the algorithm successfully separated the single fault characteristics of bevel gear and planetary gear from the observed signal,contributing to the fault diagnosis of rotating components in engineering.
-
[1] 韩婷婷.基于改进盲源分离方法的齿轮箱故障诊断[D].辽宁 大连:大连理工大学,2019. [2] ANTONI J.Blind separation of vibration components: principles and demonstrations[J].Mechanical Systems and Signal Processing,2005,19(6):1166-1180. [3] LEE D,CHO D S,KIM K,et al.A simple iterative independent component analysis algorithm for vibration source signal identification of complex structures[J].International Journal of Naval Architecture and Ocean Engineering,2015,7(10):2092-6782. [4] HAILE M A,DYKAS B.Blind source separation for vibration-based diagnostics of rotorcraft bearings[J].Journal of Vibration and Control,2015,22(18):3807-3820. [5] 周晓峰.机械振动源的分离和识别方法研究[D].杭州:浙江大学,2012. [6] 杨广振,荆建平,明阳.利用航空发动机信号特征的振动源盲分离算法[J].西安交通大学学报,2017,51(6):20-27. [7] 孙灿飞,王友仁.直升机行星传动轮系故障诊断研究进展[J].航空学报,2017,38(7):111-124. [8] 李康宁,郭永刚,王肃静.一种并行主偏度分析算法及其在盲源分离上的应用[J].数据采集与处理,2020,35(5):910-919. [9] 季策,孙梦雪,张君.基于EMD改进算法的欠定混合盲分离[J].东北大学学报(自然科学版),2018,39(8):1108-1113. [10] 张赟,李本威,王永华.基于位势函数的欠定盲源分离识别诊断方法[J].航空动力学报,2010,25(1):218-223. [11] 李丽娜,曾庆勋,甘晓晔.基于势函数与压缩感知的欠定盲源分离[J].计算机应用,2014,34(3):658-662,667. [12] 付卫红,王璐,马丽芬.一种改进的势函数欠定盲源分离算法[J].西安电子科技大学学报,2014,41(6):1-5,88. [13] RODRIGUEZ A,LAIO A.Clustering by fast search and find of density peaks[J].Science,2014,344(6191):1492-1496. [14] 丁锋,秦峰伟.小波降噪及Hilbert变换在电机轴承故障诊断中的应用[J].电机与控制学报,2017,21(6):89-95. [15] HU Z,MA H.Blind modal estimation using smoothed pseudo Wigner-Ville distribution and density peaks clustering[J].Measurement Science and Technology,2020,31(10):105004.1-105004.18. [16] 陈叶旺,申莲莲,钟才明.密度峰值聚类算法综述[J].计算机研究与发展,2020,57(2):378-394. [17] 李宏坤,贺长波,于刚.利用稀疏盲源分离方法的叶片裂纹特征提取[J].振动工程学报,2017,30(3):510-518. [18] CHENG W,JIA Z,CHEN X,et al.Underdetermined convolutive blind source separation in the time-frequency domain based on single source points and experimental validation[J].Measurement Science and Technology,2020,31(9):095001.1-095001.22. [19] LU J,CHENG W,HE D.et al.A novel underdetermined blind source separation method with noise and unknown source number[J].Journal of Sound and Vibration,2019,457:67-91.
点击查看大图
计量
- 文章访问数: 73
- HTML浏览量: 7
- PDF量: 46
- 被引次数: 0