Rolling Bearings Fault Diagnosis Method Using EMD Decomposition and Probabilistic Neural Network

Aiming at the problem that the vibration signal of the early fault is weak. A fault diagnosis method of rolling bearing combined with empirical mode decomposition (EMD), principal component analysis (PCA) and probabilistic neural network (PNN) is proposed, in which the energy, kurtosis and skewness of first few IMFs are extracted as fault feature, the dimension of feature set is reduced by PCA, the new set is put into the PNN to identify fault recognition. The simulation shows that this method has higher fault diagnosis accuracy.