摘要
针对故障轴承的特征难以提取以及状态识别困难的问题,提出了基于经验模态分解(EMD)-多尺度排列熵(MPE)与隐马尔科夫模型(HMM)的滚动轴承故障识别方法。首先,运用EMD滤波降噪原理对滚动轴承振动信号进行降噪,而后将已降噪的信号进行多尺度排列熵分析并提取不同尺度下排列熵的较大值作为信号特征。最后,将特征信号向量输入已训练好的HMM模型进行故障类型判别。并与支持向量机(SVM)进行比较研究。实验结果表明,基于EMD-MPE与HMM的滚动轴承故障诊断方法对滚动轴承的故障状态能够进行有效地识别。
Aiming at the faulty signal of rolling bearing being featured and the fault states being classified difficultly, the method of fault diagnosis for rolling bearing based on EMD-MPE and HMM is applied to this paper. Firstly, the vibration signal is decomposed into various values of permutation entropy （PE） based on multi scaling factor by MPE after EMD denoising. It＇ s necessary to extract the larger values corresponding to the scaling factor as the feature vectors. Finally, the feature vectors are input into the trained HMM for recognition. The experimental results show that the method of EMD-MPE and HMM is superior to the meth- od of EMD-MPE and SVM, and it can identify the fault states of rolling bearing accurately and effectively.
出处
《组合机床与自动化加工技术》
北大核心
2016年第12期76-79,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然科学基金项目(51275052)
国家科技重大专项"高档数控机床与基础制造装备"(2013ZX04011-012)
