Power transmission line fault classification system and method based on improved oversampling

The invention discloses a power transmission line fault classification system and method based on improved oversampling. Firstly, historical fault information of a state grid serves as a database, the database is divided into a plurality of sub-data sets according to fault types, and each sub-data set is composed of transient current traveling waves at the fault moment of a power transmission line; secondly, a K-means method is adopted to perform clustering operation on minority classes in the fault data set, and BSMOTE is adopted to perform oversampling so as to realize balance of all classes, and a balanced data set is formed; then, time domain and frequency domain features of transient current traveling waves in the balance data set are calculated to form a feature data set; and finally, establishing a classification model based on CNN and SVM deep learning algorithms, and training the classification model by using the feature data set to obtain a trained fault classification model. And classifying and ide