Diagnosis of Partial Discharge Faults in Substation Main Transformer Considering Operating Loss
The increase of transformer operating loss will destroy the recognizable stability of discharge signal and lead to the reduction of transformer operation performance.The research of partial discharge fault diagnosis method of substation main transformer is carried out under the consideration of operating loss.The maximum kurtosis deconvolution (MKD) improved dual-tree complex wavelet transform (DTCWT) is introduced to denoise the partial discharge signals of substation main transformer.The combination method of multi-scale entropy and variational modal decomposition is used to extract the partial discharge fault features of the substation main transformer,and all the features are inputted into the back propagation (BP) neural network classifier to realize fault diagnosis.The experimental results show that using the proposed method for partial discharge fault diagnosis of substation main transformer can obtain highly accurate partial discharge fault diagnosis results.The proposed method has high reliability for practical application and helps to improve the stability of main transformer operation.
NETL
NSTL
万方数据
