关联维数分析方法在液压泵多故障诊断中的应用研究  

Feature Correlation Dimension Extraction Method for Hydraulic Pump Fault Diagnosis

作　　者：吴胜强[1] 陈海燕[1] 刘思远[2] 

机构地区：[1]邢台职业技术学院机电工程系,河北邢台054035 [2]燕山大学河北省重型机械流体动力传输与控制重点实验室,河北秦皇岛066004

出　　处：《液压与气动》2017年第3期32-37,共6页Chinese Hydraulics & Pneumatics

基　　金：国家自然科学基金(51505411)

摘　　要：针对液压泵故障信号非线性和非平稳性特征,提出了利用相空间重构技术和分形理论相结合的特征关联维数提取方法。该方法将液压泵不同故障模式下获取的一维振动信号重构到高维相空间,进行信息深层挖掘;通过对相空间特征信号关联维数变化规律的分析,找出对故障反映敏感的关联维数,由此进行故障识别。通过实验验证,该方法提取的关联维数能有效反映液压泵的故障特征,为液压泵多故障诊断方法的研究提供可靠的特征信息,具有良好的应用前景。Aimed at the nonlinear and non-stationary characteristics of the hydraulic pump fault vibration signals, the feature correlation dimension extraction method combined phase space reconstruction with fractal theory is pro- posed. The method reconstructs high-dimension phase space from one-dimension vibration signals of different fault states of the hydraulic pump so that deep data mining is achieved. Then through analysis of varying correlation dimension of phase space feature signals, feature correlation dimension （FCD） that corresponds to each fault state is extracted. The experiment shows that feature correlation dimension extracted by the method is effective to fault diagnosis of hydraulic pump. The method can provide reliable feature information for condition monitoring and fault diagnosis, and has a broad application prospect.

关 键 词：特征关联维数 故障诊断 相空间重构 特征提取 

分 类 号：TH137[机械工程—机械制造及自动化]