Detection and Classification of Complex Power Quality Disturbances Using Hilbert Transform and Rule Based Decision Tree

This research work presents an algorithm based on the Hilbert Transform and rule based decision tree for detection and classification of the complex power quality disturbances. The power quality disturbances are generated using various combinations of the mathematical relations of single stage PQ disturbances such as voltage sag, voltage swell, momentary interruption (MI), oscillatory transient (OT), impulsive transient (IT), spike and notch. These complex PQ disturbance signals are decomposed using Hilbert Transform. Features are extracted from output of the Hilbert Transform which is given as input to the rule based decision tree for classification purpose. Effectiveness of the proposed approach is shown by calculating efficiency of the proposed algorithm on testing 50 data sets of each complex PQ disturbance obtained by varying the parameters of the disturbances.