Analysis of non-stationary random vibration environment of industrial robot based on EMD and PNN

Abstract

Aiming at the characteristic of frequency density of non-stationary random vibration signals of industrial robots during machining, a multi-component process neural network (PNN) auto-regressive model was proposed based on empirical mode decomposition (EMD). First, the original time series were decomposed into intrinsic mode functions (IMF) of different scales by EMD. Then, the time-varying parameters of each IMF were analyzed by PNN and the time-varying power spectral density was determined. Finally, the time-varying independent power spectral density of all components is reconstructed by linear superposition as the time-varying independent power spectral density of the original signal. The calculation results show that the frequency resolution performance of this method is better than that of traditional analysis method.