Diagnosis of Inter-Turn Fault in the Transformer Winding using Wavelet Based AI Approaches
In this paper, Wavelet based ANFIS for finding the inter-turn fault of a transformer is proposed. The detector uniquely responds to the winding inter-turn fault with remarkably high sensitivity. Discrimination of different percentages of winding affected by inter-turn fault is provided via ANFIS having an eight dimensional input vector. This input vector is obtained from features extracted from DWT of inter-turn faulty current, leaving the transformer phase winding. Training data for ANFIS are generated via a simulation of transformer with inter-turn fault using MATLAB. The proposed algorithm using ANFIS gives more satisfactory performance than ANN and GABPN with selected statistical data of decomposed levels of faulty current.