基于独立分量分析的航空发动机振动信号盲源分离

A blind source separation of aero-engine vibration signals on independent component analysis

阐述了基于峭度的盲源分离开关算法,对仿真信号进行分离,验证了该算法的可行性。并将该算法与FFT分离法结合,对某型双转子航空发动机高、低压转子实测振动信号进行了盲源分离实践,取得了很好的分离效果,从而为双转子发动机振动监测与故障诊断提供了一种可行的信号处理方法。

A blind source separation algorithm based on kurtosis was expounded in this paper. The method was adopted to separate imitating signals, in order to validate the correctness and feasibility of arithmetic. In combination with FFT separation, the blind source separation of the measured vibration signals which come from a high - pressure rotor and a low - pressure rotor of a twin - spool engine. It presents blind source separation techniques, which are proved that the separation is a feasible and effective signal processing methods for twin - spool engines＇ fault diagnosis and vibration monitoring.