Independent component analysis for the fault features of liquid propellant rocket engine
Ren Hai-feng · Journal of Propulsion Technology · 2004
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.