基于IMF相关比例划分的液压复合故障特征提取方法研究

Research on Feature Extraction Method of Hydraulic Composite Fault Based on IMF Correlation Ratio Division

为解决液压系统中不同的单故障信号具有一定数量的共有特征频率导致复合故障特征难以分离和提取的问题,提出了基于EEMD分解的IMF相关比例划分的液压复合故障特征提取方法。通过EEMD分解将复合故障信号分解成若干IMF分量,同样将已预先实测获得的两个单故障信号也分解成IMF分量组,将复合故障信号的每组IMF分量分别与两个单故障信号相对应的IMF分量一一作互相关分析,然后按相关系数比例将复合故障信号划分成两组信号,实现复合故障特征的分离并进行提取,最后分别与实测的两个单故障信号比较确定复合故障的组成。实验结果表明,该方法能够有效地从液压复合故障中分离并提取出故障特征频率。

The separation and extraction of compound hydraulic fault feature is one of the difficulties of state monitoring and fault diagnosis. In order to solve the problem that compound hydraulic fault feature is difficult to be separated due to their common frequencies with its corresponded single-fault signals. A feature extraction method of signal based on IMFs＇ correlation values is proposed. Firstly decompose the compound signals of mixed two fault conditions and its corresponded single-fault signals to three series of IMFs. Then calculate the correlation values respectively between the IMFs of the compound signal with the IMFs of the single-fault signals. And divide the first series IMFs into two groups of time series proportionally according to the correlation values. Then the extracted signals are achieved by adding the time series respectively. Finally,the composite fault types are identified by comparing with the measured single fault signals. It is shown through the experimental results that the proposed method effectively extracts the single-fault frequency from the compound signal.