Study of Fault Diagnosis Based on Probabilistic Neural Network for Turbine Generator Unit

A fault diagnosis method of probabilistic neural network was presented for turbine generator unit. the probabilistic neural network is based on probability statistics theory and Bayes classification rule, so it can efficiently identify and diagnose the fault of turbine generator unit. Theoretical analysis, practical procedure of neural network setting and training are given out. The simulation results show that the proposed method can effectively diagnose the vibration fault of turbine generator, and has good application prospects.