奇异值小波降噪法在柱塞泵振动信号处理中的应用  

APPLICATION OF SINGULAR VALUE AND WAVELET DE-NOISING METHOD IN ANALYZING VIBRATION SIGNAL OF PISTON PUMP

作　　者：何庆飞[1] 陈桂明[1] 陈小虎[1] 姚春江[1] 张宪宇[1] 

机构地区：[1]第二炮兵工程学院装备管理工程系,西安710025

出　　处：《机械强度》2012年第4期475-480,共6页Journal of Mechanical Strength

基　　金：国防预研基金(9140A27020309JB4701);第二炮兵工程学院科技创新基金(XY2010JJB38)资助~~

摘　　要：针对小波阈值和奇异值分解降噪法的不足,研究一种新的小波阈值函数。提出一种基于改进阈值的奇异值小波降噪方法,该方法利用奇异值分解技术,将噪声非均匀分布的信号正交分解为噪声分布相对均匀的分量,并对每个分量进行小波阈值降噪,重构降噪后的分量,得到降噪信号。仿真实例证明,该方法与小波软、硬阈值及改进阈值法相比,不仅提高信噪比,而且能够更好地消除高斯噪声。利用该方法对柱塞泵不同状态振动信号进行降噪,结果表明,该方法能有效抑制噪声,为柱塞泵振动信号预处理提供一种更为有效的方法。In order to eliminate noise signal of piston pump vibration signal, a new wavelet threshold function was used for the shortcomings of wavelet threshold and singular decomposition de-noising method. An improved de-noising method was put forward by combining singular value decomposition and new wavelet threshold function de-noising method. In the new method, the noise signal is decomposed into noise uniformity vectors, and through wavelet threshold de-noising on every vector, finally, reconstruction signal. Emulation experiment results show that the method has better de-noising effect than wavelet soft, hard and new threshold de-noising methods. Different vibration signal of piston pump was de-noised by the method. The result proves it can reduce the noise of the vibration signal of piston Dump efficiently.

关 键 词：柱塞泵 振动信号 奇异值分解 小波阈值法 降噪 

分 类 号：TH322[机械工程—机械制造及自动化] TP274[自动化与计算机技术—检测技术与自动化装置]