New method for online interturn faults detection in power transformer with using probabilistic neural network

In recent years with notice increase reliability in power system and Intelligent Systems and also notice that transformers are one of the main part of the transmission and distribution systems، online monitoring of these equipment in power system are require. In this paper، a new method for online interturn fault detection base on leakage flux in power transformer are propose. When an interturn fault occur the symmetry of flux destruction and leakage flux increase or decrease and for various location and severity of fault leakage flux is different and it can be used for fault detection. In this paper for measure these flux we using search coils that mounted on HV winding. To fault detection and classify we using probabilistic neural network. and for decrease the information volume PCA is used. The simulation results are compare and verified with experimental result and show that this propose method is very good.