基于最优分解的时不变小波变换的油液磨粒特征提取方法  

Extracting Wear Debris Feature Using Time-invariant Wavelet Transform with Optimal Decomposition Depth

作　　者：彭娟[1] 李川[1] 

机构地区：[1]重庆工商大学废油资源化技术与装备教育部工程研究中心,重庆400067

出　　处：《润滑与密封》2013年第9期54-59,共6页Lubrication Engineering

基　　金：教育部科学技术研究重点项目(212143);重庆市自然科学基金项目(2010BB4261);重庆市教委科学技术研究项目(KJ120720;KJ120727)

摘　　要：分解层次的确定对磨粒特征的提取效果具有重要的影响。基于时不变小波变换,提出一种以残差信号的分段峭度均方差为准则的最优分解层次确定方法。该方法使用时不变小波变换方法提取磨粒信号,以提取出磨粒信号后的残差信号的分段峭度均方差作为准则,根据残差信号的信息自适应地确定最佳分解层。分别使用仿真信号和真实信号对该方法进行验证,结果表明,该方法较传统方法可提高油液中磨粒检测精度。The decomposition depth has very important influence to the extraction effect of the oil debris feature. Based on time-invariant wavelet transform, a mean square derivation of segmented kurtosis for residue criterion was put forward to determine the optimal decomposition depth. This method used time-invariant wavelet transform to extract the oil debris sig- nal, and determine the optimal decomposition depth adaptively.with the help of the mean square derivation of segmented kurtosis for residue criterion after extracting the oil debris signal. Both simulated and real signals were employed to evaluate the proposed approach. The results show that the proposed method is helpful to improve the accuracy of the wear debris detection.

关 键 词：磨粒 时不变小波变换 最优分解层 残差信号 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]