Fault Diagnosis of Rolling Bearing Based on PNN

Aiming at the mapping complexity between fault symptoms and fault patterns of rolling bearing,and the problems of falling easily into part minimums and low velocity of convergence in BP neural network,PNN is put forward to diagnose rolling bearing.11 static features of time signals are adopted as the sample symptoms,PNN is trained to diagnose rolling bearings.The results show that PNN can achieve different fault diagnosis of ball bearing in proving accuracy,repressing the network to sink local minimum,and shortening the study time.