应用VMD和多参数融合的齿轮箱故障诊断  

Research on Gearbox Fault Diagnosis Based on VMD and Multi-parameter Fusion

作　　者：安邦[1] 潘宏侠[1] 张媛[2] 张玉学[1] 赵雄鹏[1] 

机构地区：[1]中北大学机械与动力工程学院 [2]中国电子科技集团公司第二研究所

出　　处：《组合机床与自动化加工技术》2017年第4期92-95,共4页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金:基于粒子群优化和滤波技术的复杂传动装置早期故障诊断研究(50875247)

摘　　要：由于齿轮箱故障信号的非线性,以及各种噪声的影响导致故障特征难以确定,为了准确、高效地分析齿轮箱故障信号,提出了一种应用变分模态分解(VMD)和多参数融合的齿轮箱故障诊断方法。首先对齿轮箱故障信号进行变分模态分解,并与传统的经验模态分解(EMD)进行对比;同时提取各模态分量的能量百分比和信息熵作为特征值,并采用RBF神经网络进行故障诊断。实验结果表明变分模态分解能够有效避免模态混叠现象的发生,以VMD为基础的多参数融合方法能够准确、快速地实现齿轮箱的故障诊断。Because of the non-linearity of the gearbox fault signal,and the influence of various noises,it is difficult to extract the fault features of the gearbox.In order to analyze the fault signal accurately and efficiently,a method based on Variational Mode Decomposition（VMD） and multi-parameter fusion is proposed.Firstly,the VMD decomposition of fault signal is performed and compared with EMD decomposition results; Meanwhile,the energy percentage of each component is extracted and the information entropy of each sample is taken as the eigenvalue.Then the extracted feature parameters are input to the RBF neural network for fault diagnosis.The results showed that the variational mode decomposition can effectively avoid the phenomenon of modal mixture.The multi-parameter fusion method based on VMD can realize the fault diagnosis of gearbox accurately and quickly.

关 键 词：多参数融合 齿轮箱 故障诊断 

分 类 号：TH17[机械工程—机械制造及自动化] TG65[金属学及工艺—金属切削加工及机床]