本文提出以機率神經網路(Probabilistic Neural Network, PNN)應用於渦輪發電機組故障診斷(Turbine Generator Fault Diagnosis)之研究。利用機率神經網路之特性,用已知的故障數據對類神經網路進行訓練後,即可對渦輪發電機組的故障型態進行診斷。為驗證本文所提之PNN對渦輪發電機故障診斷之準確性,使用MATLAB撰寫PNN程式,並經過訓練後診斷新的樣本資料,分辨出故障型態,證明所提方法之準確性可達到100%。 This paper presents a Probabilistic Neural Network (PNN) for turbine generator fault diagnosis. Using the known data to train the neural network. Then, input the new samples to diagnose the fault type. In order to prove the accuracy of the PNN for turbine generator fault diagnosis, using MATLAB to develop PNN program. The simulation can prove the proposed method is effective and accurate.