局域均值分解中PF获取方法的改进  

Improvement of PF Definition of Local Mean Decomposition

作　　者：梁世杰[1] 韩维[2] 康小伟[2] 苏永前 

机构地区：[1]海军航空工程学院研究生管理大队,山东烟台264001 [2]海军航空工程学院飞行器工程系,山东烟台264001 [3]海军驻宜宾地区航空军事代表室,四川宜宾644000

出　　处：《航空计算技术》2012年第4期24-27,共4页Aeronautical Computing Technique

基　　金：国家自然科学基金项目资助(51005242)

摘　　要：航空发动机故障振动信号为典型的多分量信号,局域均值分解方法可以对其分离。在研究了经典的局域均值分解方法后,发现相邻的两个乘积函数(Production Function,PF)中存在模态混淆现象,表现为较高频PF中包含较低频PF的频率成分。针对这一问题,对PF的定义进行了改进,滤除了混淆在其中的低频信号,使信号分离更加充分。仿真信号的分析表明,改进后的算法分离效果优于原算法。试验信号的分析表明,方法可以用于航空发动机故障特征提取。Fault vibration signal of aero- engine is multi- component signals and local mean decomposition can analyse it. After studying the original method, this paper discovers that mode confusion exists between adjacent Production Function（PF）. The higher- frequency PF contains signal of lower- frequency PF. To solve this problem, an improved PF is defined and this way can filter the mode confusion signal. The ana- lyse of artificial signal showed that the improved LMD is better than the original LMD in signal separa- tion. The application results of test- data showed that the improved LMD can extract characteristics of aero - engine fault vibration signal effectively.

关 键 词：信号分离 LMD 调幅调频信号 包络线 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]