基于EMD分解和支持向量机的齿轮箱故障诊断与研究  

Intelligent Diagnosis Research of Fault s in Gear Box Based on Support Vector Machines and EMD resolution method

作　　者：刘晓娟[1] 潘宏侠[1] 

机构地区：[1]中北大学机械工程与自动化学院,太原030051

出　　处：《柴油机设计与制造》2011年第3期21-26,39,共7页Design and Manufacture of Diesel Engine

摘　　要：齿轮箱存在故障时,其振动信号往往表现出非平稳特性,并且故障特征信息往往淹没在强大的背景噪声中,难以实现有效诊断。提出了采用基于EMD方法的特征能量值提取法及支持向量机的智能模式诊断方法,并将二者结合运用于齿轮箱的故障诊断,实现了齿轮箱故障的智能识别与诊断。实验结果证明了EMD方法与支持向量机相结合用于齿轮箱故障诊断的正确性与可行性。When the fault of gear box occurs, the vibration signals often show non-stationary characteristics and the fault information is often submerged in the strong background noise. This paper, based on EMD resolution method and support vector machines, is research on the techniques of the fault energy feature extraction and intelligent diagnosis of gearbox. The final result shows that the method is correct and feasible.

关 键 词：齿轮箱 故障诊断 EMD 支持向量机 

分 类 号：TH165.3[机械工程—机械制造及自动化]