Abstract: In view of the short-circuit fault situation of high-voltage AC transmission line,the three-phase AC voltage and current signals are transformed into wavelet packets to extract the fault features,and then the extracted features are input into the XGBoost model for fault diagnosis.The experimental results show that the fault identification accuracy of the fault diagnosis method based on wavelet packet transform and XGBoost is 99.6% for the fault of high-voltage AC transmission line under different operating conditions.Compared with other machine learning models,this method has high accuracy.

Key words: transmission lines, fault classification, wavelet packet transform, XGBoost