Identification of power quality complex disturbances based on S-transform and SVM

This paper presents a new approach based on S-transform and support vector machine (SVM) for identification of power quality complex disturbances. Firstly, original power quality signals are processed by S-transform and features were extracted from the result of S-transform at different frequency areas. Then, 2 types of most distinguished feature are selected by statistic feature selection. The selected features are used as the input vector of SVM and to train a SVM based classifier for power quality disturbances recognition. Furthermore, the SVM classifier is used to classify the short-time power quality disturbances. The proposed method reduces the computing costs of feature calculation, meanwhile saves the time of training and classification. 8 types of power quality disturbances including 2 types of complex disturbances are accurate identified. The simulation results show the validity of this method.