摘要
针对污泥回流泵振动信号易受噪声污染、故障特征提取困难的问题,提出基于经验模态分解(EMD)与独立成分分析(ICA)的故障诊断方法。首先,将振动信号进行EMD分解得到一系列本征模态函数(IMF)。然后,对各个本征模态函数进行主成分分析,选取满足贡献累加值的分量重构信号,并与原信号组成矩阵进行ICA解混处理。最后,将处理后的数据进行Hilbert变换与频谱分析,通过对比处理后的正常信号与故障信号的特征频率差异,实现污泥回流泵的故障诊断。实验结果表明,本文所提出的故障诊断方法能够有效降低噪声干扰,准确提取出故障特征并实现故障诊断的目的。
A fault diagnosis method based on empirical mode decomposition(EMD)and independent component analysis(ICA)is proposed to solve the problems that the vibration signal of sludge reflux pump is susceptible to noise pollution and the fault feature extraction is difficult.Firstly,the vibration signal is decomposed by EMD to obtain a series of intrinsic mode functions(IMF).Then,principal component analysis is carried out on each intrinsic mode function,and the components that satisfied the cumulative contribution value were selected to reconstruct the signals,and ICA demixing is performed with the original signal composition matrix.Finally,the processed data is analyzed by Hilbert transform and spectrum analysis,and the fault diagnosis of sludge reflux pump is realized by comparing the characteristic frequency difference between the normal signal and the fault signal.The experimental results show that the proposed fault diagnosis method can effectively reduce the noise interference,accurately extract the fault features and achieve the purpose of fault diagnosis.
作者
李如玉
项伟
田立勇
于宁
LI Ruyu;XIANG Wei;TIAN Liyong;YU Ning(Shenyang Ligong University,Shenyang 110159,China;School of Mechanical Engineering,Liaoning Technical University,Fuxin 123000,China)
出处
《沈阳理工大学学报》
CAS
2021年第3期79-84,共6页
Journal of Shenyang Ligong University
关键词
污泥回流泵
经验模态分解
独立成分分析
信号处理
故障诊断
sludge reflux pump
empirical mode decomposition
independent component analysis
signal processing
fault diagnosis
