Recognition of power quality disturbances using S-transform based ruled decision tree and fuzzy C-means clustering classifiers

TLDR: A method based on Stockwell's transform and Fuzzy C-means clustering initialized by decision tree has been proposed for detection and classification of power quality (PQ) disturbances and is established effectively by results of high accuracy.

Abstract: Display Omitted The S-transform based decision tree initialized Fuzzy C-means clustering technique is proposed for recognition of PQ disturbances.Sum absolute values curve is introduced to increase efficiency of algorithm.Results of FCM technique are more efficient compared with rule based decision tree.Validation of results is carried out with 100 data sets of each PQ disturbance with and without noise and comparing with real time results.Classification accuracy more than 99% is achieved even in the noisy environment. A method based on Stockwell's transform and Fuzzy C-means (FCM) clustering initialized by decision tree has been proposed in this paper for detection and classification of power quality (PQ) disturbances. Performance of this method is compared with S-transform based ruled decision tree. PQ disturbances are simulated in conformity with standard IEEE-1159 using MATLAB software. Different statistical features of PQ disturbance signals are obtained using Stockwell's transform based multi-resolution analysis of signals. These features are given as input to the proposed techniques such as rule-based decision tree and FCM clustering initialized by ruled decision tree for classification of various PQ disturbances. The PQ disturbances investigated in this study include voltage swell, voltage sag, interruption, notch, harmonics, spike, flicker, impulsive transient and oscillatory transient. It has been observed that the efficiency of classification based on ruled decision tree deteriorates in the presence of noise. However, the classification based on Fuzzy C-means clustering initialized by decision tree gives results with high accuracy even in the noisy environment. Validity of simulation results has been verified through comparisons with results in real time obtained using the Real Time Digital Simulator (RTDS) in hardware synchronization mode. The proposed algorithm is established effectively by results of high accuracy to detect and classify various electrical power quality disturbances.