基于EMD-AR谱频带能量特征的故障特征提取方法研究  

Research on Fault Feature Extraction Method Based on EMD-AR Spectrum Frequency Band Energy Features

作　　者：秦志英[1] 杨航港 赵月静[1] QIN Zhiying;YANG Hanggang;ZHAO Yuejing(School of Mechanical Engineering,Hebei University of Science and Technology,Shijiazhuang Hebei 050018,China)

机构地区：[1]河北科技大学机械工程学院,河北石家庄050018

出　　处：《机床与液压》2023年第11期219-223,共5页Machine Tool & Hydraulics

基　　金：河北省省级科技计划资助项目(20310803D)。

摘　　要：通过将经验模态分解(EMD)和AR功率谱参数估计模型相结合,提出一种基于EMD-AR谱估计提取频带能量特征的方法。对振动信号进行经验模态分解,并将分解后能量占比较大的前几组固有模态函数分别进行AR谱估计得到EMD-AR谱曲线;按照频带对EMD-AR谱曲线分段并分别对每一段的能量进行求和,归一化后作为特征值。搭建齿轮箱故障试验平台,采集振动信号进行EMD-AR谱频带能量特征提取,并将所得特征值输入到SVM中进行训练和诊断。结果表明:该特征提取方法结合SVM所得到的故障诊断模型具有较高的识别准确率,能够有效、准确地进行诊断识别。A method to extract the energy features of frequency bands based on EMD-AR spectrum estimation was proposed by combining the empirical mode decomposition(EMD)and AR power spectrum parameter estimation model.The EMD-AR spectrum curve was obtained by empirical mode decomposition of the vibration signal and AR spectrum estimation of the top groups of intrinsic mode functions(IMFs)that accounted for the larger energy after decomposition;then,the EMD-AR spectrum curve was segmented according to the frequency band and the energy of each segment was summed up and normalized as the feature value.By building a gearbox fault test bench,vibration signals were collected for EMD-AR spectrum frequency band energy feature extraction,and the obtained feature values were input into SVM for training and diagnosis.The results show that the fault diagnosis model obtained by this feature extraction method combined with SVM has a high recognition accuracy and can effectively and accurately perform diagnosis and recognition.

关 键 词：经验模态分解 AR功率谱估计 频带能量 支持向量机 齿轮故障 

分 类 号：TH165.3[机械工程—机械制造及自动化]