A fault diagnosis approach of reciprocating compressor gas valve based on local mean decomposition and autoregressive-generalized autoregressive conditional heteroscedasticity model

作者：Lei, Na^*; Tang, Youfu; Lei, Yong

来源：Journal of Vibroengineering, 2016, 18(2): 838-848.

• fault diagnosis
• LMD
• AR-GARCH
• gas valve
• reciprocating compressor

Vibration signal of reciprocating compressor gas valve represents nonlinear, non-stationary and multiple impulse characteristics. To extract the features of the signal, an integration approach based on local mean decomposition (LMD) method and autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) model is proposed. First, the property of LMD is investigated in the paper, which indicates that LMD method not only can effectively alleviate non-stationary feature and restrain the end effect of non-stationary signal, but also can accurately improve the resolution of time-frequency analysis. Then, the first five PF components of gas valve signal are modeled by AR(1)-GARCH(1, 1) model as the feature vectors without any prior knowledge about the fault mechanism. Finally, the BP neural networks are applied to diagnose the faults of reciprocating compressor gas valve based on the feature vectors above. The results indicate that high diagnosis accuracy can be obtained by integrating LMD method and AR-GARCH model. So the approach proposed in the paper provides an effective measure to extract the fault feature of reciprocating compressor gas valve.

• 出版日期2016-3
• 单位东北石油大学