Search

This study presents a novel technique for automated power quality (PQ) disturbance detection and classification in power distribution system using cross-correlation-based approach in conjunction with fuzzy logic. The proposed method requires minimum number of features when compared with conventional approaches for identification of disturbances. Total 17 types of PQ disturbances including eight basic and nine combinations which are very close to real situations are considered for the classification. The scheme is immune to real life uncorrelated noises due to incorporation of cross spectrum analysis in the feature extraction stage. Experimentation under real operating conditions is carried out in the laboratory using data acquisition system in order to test the proposed technique. The proposed scheme is also applied in IEEE 33-bus distribution system and validated by a real-time simulator. The developed classifier achieved 100% accuracy and could comfortably outperform several contemporary methods for PQ disturbance classification. [ABSTRACT FROM AUTHOR]

This study presents a novel technique for automated power quality (PQ) disturbance detection and classification in power distribution system using cross‐correlation‐based approach in conjunction with fuzzy logic. The proposed method requires minimum number of features when compared with conventional approaches for identification of disturbances. Total 17 types of PQ disturbances including eight basic and nine combinations which are very close to real situations are considered for the classification. The scheme is immune to real life uncorrelated noises due to incorporation of cross spectrum analysis in the feature extraction stage. Experimentation under real operating conditions is carried out in the laboratory using data acquisition system in order to test the proposed technique. The proposed scheme is also applied in IEEE 33‐bus distribution system and validated by a real‐time simulator. The developed classifier achieved 100% accuracy and could comfortably outperform several contemporary methods for PQ disturbance classification. [ABSTRACT FROM AUTHOR]