二阶多重同步挤压变换及其在涡轮泵信号处理中的应用

Second-order multisynchrosqueezing transform and its application in turbopump signal processing

液体火箭发动机涡轮泵振动信号在变工况情况下表现出非平稳和强噪声特性,为特征频率分量提取带来困难。针对该问题,首先,提出二阶多重同步挤压变换(second-order multisynchrosqueezing transform,SMSST)时频分析方法,完成了数学推导并证明了其收敛性。在此基础上,提出基于自适应带通滤波与脊线提取的转频分量提取方法。用仿真信号对SMSST方法进行验证并与传统方法比较。最后,将基于SMSST的转频特征提取方法应用于发动机转速辨识和故障诊断,并用实际数据进行验证。结果表明,与传统时频分析方法相比,SMSST具有更高的时频分析精度。提出的方法可以提供有效、可靠、冗余的转速测量手段,并且该方法可以支撑故障早期预警。

Vibration signals of a liquid rocket engine represent nonstationarity and strong noise,which brings difficulties in characteristic frequency component extraction.In order to solve the problem,a time-frequency analysis method called second-order multisynchrosqueezing transform(SMSST)was proposed.Mathematical derivation of this method and the proof of its convergency was completed.Then a rotation frequency component extraction method based on adaptive band filtering and ridge extraction was presented.The SMSST was compared to traditional time-frequency analysis methods using generated signal.Finally the SMSST-based rotation frequency component extraction method was applied with actual data in rotation speed identification and fault diagnosis.Result shows that the SMSST has better accuracy in time-frequency analysis compared with traditional methods.The proposed method provides an effective,reliable,redundant way to measure rotation speed.And the method is able to support fault early warning.