A New Classification Scheme Based on Extended Kalman Filter and Support Vector Machine

In the field of power quality monitoring, due to the extensive quantity of measurements data, it is preferred that the detection, identification and classification of Power Quality Disturbances (PQD) can be performed automatically. This paper proposes a new efficient classification scheme based on two powerful techniques, the Extended Kalman Filter (EKF) and the Support Vector Machine (SVM). The feature extraction step plays the most important role, where, the EKF has a good advantage in reducing time computation by dispensing with the segmentation step. Moreover, only three suitable features are extracted from the parameters estimated based the EKF, thus conserve memory space and time do without need for feature selection step. After the normalization of the extracted features, in the second step, the SVM classifier is applied to classify these disturbances into their specific categories. Simulation results are examined under different Gaussian white noises to prove the efficiency of the proposed classification diagram. Moreover, performance comparisons with other methods proposed in the literature are conducted, to show the effectiveness of the proposed scheme in term of, consumption of memory space, computation time, implementation complexity, and classification accuracy.