应用独立分量分析提取液体火箭发动机的故障特征

Independent component analysis for the fault features of liquid propellant rocket engine

关键词:  液体推进剂火箭发动机  故障诊断  独立分量分析+  特征选择  小波消噪+

Key words:  Liquid propellant rocket engine  Fault diagnosis  Independent component analysis~+  Feature selection  Wavelet de-noising~+

摘要:

以某型液体火箭发动机为研究对象,针对故障诊断中故障特征提取难的问题,提出了应用小波消噪技术和独立分量分析获取高品质源信号,并利用源信号进行故障诊断的思路,对发动机热试车压强信号进行了实例分析。研究结果表明,该方法提高了诊断信号的质量,有效地提取了故障特征。

Abstract:

Complete and high quality diagnostic information is necessary for identifying the faults correctly. However, in the fault diagnosis of liquid propellant rocket engine, the information of measured signal is not enough for fault diagnosis. The source signals contain more diagnostic information than the mixed signals through measurements.By way of applying Independent Component Analysis (ICA) and Wavelet De-noising to separate source signals from mixed signals, the features of signals were extracted for further studies. The example reveals that this method is effective.