基于特征提取的液压缸内泄漏智能故障诊断方法研究

Research on Intelligent Fault Diagnosis Method of Hydraulic Cylinder Internal Leakage Based on Feature Extraction

为提高液压缸内泄漏故障的诊断精度,实现智能故障诊断,以EHA液压系统为研究对象,基于距离区分技术对故障特征进行提取,以时域、频域、小波能量以及AR模型等参数为主要敏感特征,并通过机器学习算法以及BP神经网络算法对故障特征进行分类。结果表明,相较于BP神经算法,机器学习算法分类精度更高,能对液压缸内泄故障进行有效诊断。

In order to improve the diagnostic accuracy of hydraulic cylinder internal leakage faults and achieve intelligent fault diagnosis,this study takes the EHA hydraulic system as the research object,extracts the fault features based on the distance differentiation technique,and takes the parameters of the time domain,the frequency domain,the wavelet energy,and the AR model as the main sensitive features,and classifies the fault features by the machine learning algorithm and the BP neural network algorithm.The results show that compared with the BP neural algorithm,the machine learning algorithm has higher classification accuracy and can effectively diagnose the hydraulic cylinder internal leakage fault.