Research of RBF Neural Networks Algorithm to Fault Diagnosis of Rotary Machinery

In order to overcome the problems of slow rate of convergence, falling easily into local minimum, instability learning performance caused by initial value in BP algorithm, a new diagnosis method based on RBF neural networks was proposed. And the diagnosis method is applied to rotary machinery fault diagnosis. The result shows that the RBF network has very high learning convergence speed and better classifying performance. RBF network has good practicality in the field of equipment fault diagnosis.