基于欠定盲源分离的柴油机曲轴轴承故障诊断方法研究  

Fault Diagnosis for Crankshaft Bearing of Diesel Engine Based on Underdetermined Blind Source Separation

作　　者：朱江涛[1] 

机构地区：[1]山西交通职业技术学院,山西太原030031

出　　处：《车用发动机》2017年第4期36-42,共7页Vehicle Engine

摘　　要：针对柴油机曲轴轴承振动信号盲源分离的欠定问题,提出了基于相空间重构和动态聚类奇异值分解的适定化方法。首先通过引入广义时间窗的概念确定最佳时间延迟和嵌入维数,重构信号相空间矩阵;然后对其进行奇异值分解,并对奇异值进行动态聚类以确定最佳重构阶数,进而重构得到虚拟观测信号,从而将欠定问题转变为适定或超定;最后利用自适应Parafac方法对原观测信号与虚拟观测信号构成虚拟传播路径进行盲源分离得到有效源信号。仿真结果表明,该方法可有效分离出混合信号中的源信号,并将其应用到柴油机曲轴轴承故障诊断中,诊断准确率提高了18.4%。In order to solve the problems of underdetermined blind source separation for diesel engine crankshaft bearing vibration signal,a determined method based on singular value decomposition by using dynamic clustering and phase space reconstruction was proposed.A quasi-optimal embedding dimension and time delay values were first acquired through introducing the concept of generalized embedded window length in order to reconstruct phase space matrix.Then the singular value decomposition was applied to the matrix,the obtained singular values were conducted by using dynamic clustering to determine the optimal reconstruction order,the virtual observation signals were obtained,and hence the underdetermined problems became determined or overdetermined.Finally,the virtual observed signal and the original signal were composed into propagation paths so that the signal containing bearing fault characteristics was extracted by the blind source separation based on the algorithm of adaptive Parafac.The simulation results show that the method can extract the source signal from mixed signals effectively.The diagnosis accuracy increases by 18.4% by applying the method to diesel engine crankshaft bearing fault diagnosis.

关 键 词：振动信号 欠定盲源分离 相空间重构 奇异值分解 动态聚类 故障诊断 

分 类 号：TK418[动力工程及工程热物理—动力机械及工程]