基于相空间重构和K-L变换的压缩机故障诊断

Study on Compressor Fault Diagnosis Based on Space Reconstruction and K-L Transform

为有效利用往复式天然气压缩机故障工作状态下振动系统的非线性特征,采用了一种集相空间重构技术K-L变换为一体的特征提取和特征压缩方案,并成功应用于对某型压缩机的故障诊断。用相空间重构提取了高维的征取量,为了降低特征维数,引入K-L变换进行特征压缩。通过对3类典型故障类别一定样本数量的振动数据进行仿真,仿真结果表明该方法提取的特征量,具有很好的聚类性,能很好地把3类故障区分,达到对故障诊断的目的。

To effectively make use of the nonlinear property of vibration system of reciprocating natural gas compressor under the fault working condition,a comprehensive feature extraction and compression method is proposed based on phase space reconstruction and K-L transform and it is applied to diagnose compressor fault successfully.High dimension feature is extracted based on phase space reconstruction,and K-L transform is cited to reduce the feature dimension.Simulation is done based on some samples＇ vibration data of 3 types of typical faults.The results show that the feature parameter which is extracted by this method has nice classification performance,and has good performance in the application of fault diagnosis.