Time-Frequency Analysis Based on PNN for Nonstationary Random Vibration of Spacecraft

In view of the disadvantages of the traditional time-varying algorithm about nonstationary random vibration signal of a spacecraft with close spaced modal frequency. A process neural network (PNN) based on the empirical mode decomposition (EMD) method is put forward. First, the EMD method is utilized to decompose the signal into several intrinsic mode functions (IMFs). Then for each IMF, The PNN is established and time-varying auto-spectral density is obtained. Finally, the time-varying auto-spectral density of the signal can be reconstituted by linear superposing. The example results show the effectiveness of this new method in time-frequency analysis.