摘要
针对滚珠丝杠故障信号的非线性和非平稳性特征,引入经验模态分解(EMD)的信号处理方法。将复杂的原信号分解为有限个本征模函数(IMF),提取IMF分量的能量作为特征值,利用BP神经网络进行故障类型识别。经试验验证,采用该方法能达到滚珠丝杠故障识别的目的且具有较高的识别率。
Empirical mode decomposition （EMD）was introduced into the nonlinear and non-stationary vibration signal processing for ball screw. The complex original signal was decomposed into a finite number of intrinsic mode functions （IMF）,the energy of IMF components was extracted as an eigenvalue,and then BP neural network was used for fault type identification. By experiments verifica-tion,the method can be used to achieve the purpose of the ball screw fault identification and has high recognition rate.
出处
《机床与液压》
北大核心
2013年第21期164-167,共4页
Machine Tool & Hydraulics
基金
国家自然科学项目(51075220)
青岛市科技计划基础研究项目(12-1-4-4-(3)-JCH)
关键词
滚珠丝杠
经验模态分解
本征模函数
BP网络
故障诊断
Ball screw
Empirical mode decomposition
Intrinsic mode functions
BP network
Fault diagnosis
