基于时间序列分析的压气机喘振检测

喘振检测对于保障压气机安全运转具有重要意义。以压气机出口总压作为喘振检测特征信号,采用时间序列分析方法建立了AR模型。多步预测的误差和滞后现象显示AR模型难以预测突发性的喘振现象。在喘振发生时,残差方差急剧增大,模型参数变化显著,设定合适的门限可及时可靠地检测出喘振信号。

Compressor Surge Detecting Based on Time Series Analysis

Surge detecting is essential important to ensure compressors operation safety.The compressor exit total pressure is adopted as a characteristic signal to detect surges.An AR(autoregressive) model is constructed with the time series analysis method.It shows that an AR model is difficult to predict a sudden surge,because errors and delay are too large to be ignored in multi-step predication.The residual variance increases rapidly and model parameters are changed significantly while compressors surging.In this...