Fault diagnosis of power transformer based on PNN

As one of the main equipment of power plant and substation, the stability and safe operation of power transformer are of great signifcance to the power system. In order to improve the accuracy of power transformer fault diagnosis, a fault diagnosis method of power transformer based on probabilistic neural network（PNN） is studied based on the improved three-ratio method. Firstly, the fault diagnosis system is established in MATLAB. By analyzing the dissolved gas in transformer oil（DGA）, the three pairs of ratio of dissolved gas content in oil are used as the input vector of the network, and the output vector is the fault type of transformer. The simulation results show that the PNN diagnosis system has the advantages of fast diagnosis speed, high accuracy and strong sample addition ability.