Chaos Synchronization-Based Detector for Power-Quality Disturbances Classification in a Power System

• Published in: IEEE transactions on power delivery Vol. 26; no. 2; pp. 944 - 953
• Main Authors: Huang, Cong-Hui, Lin, Chia-Hung, Kuo, Chao-Lin
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.04.2011; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Artificial neural networks; Butterfly patterns; Chaos; chaos synchronization (CS); Chaos theory; Classification; Detectors; Disturbances; Disturbances. Regulation. Protection; Dynamical systems; Dynamics; Electrical engineering. Electrical power engineering; Electrical power engineering; Error detection; Exact sciences and technology; Feature extraction; Lorenz chaos system; Mathematical analysis; Miscellaneous; Operation. Load control. Reliability; Optimization; particle swarm optimization (PSO); Power electronics, power supplies; Power networks and lines; Power system dynamics; Power system harmonics; probabilistic neural network (PNN); Training; Chaos; Harmonic; Automatic classification; Parameter estimation; Power system stability; Processing time; Learning; probabilistic neural network (PNN); Voltage stability; Energy quality; Robustness; Voltage fluctuation; particle swarm optimization (PSO); Probabilistic approach; Measurement sensor; Power electronics; chaos synchronization (CS) Lorenz chaos system; Pattern recognition; Neural network; Synchronization; Algorithm; Particle swarm optimization; Electrical network; Butterfly patterns; Service quality; Signal distortion
• ISSN: 0885-8977; 1937-4208
• DOI: 10.1109/TPWRD.2010.2090176

This paper proposes a chaos synchronization (CS)-based detector for power-quality disturbances classification in a power system. The Lorenz chaos system realized a CS-based detector to track the dynamic errors from the fundamental signal and the distorted signal, including power harmonics and voltage fluctuation phenomena. A CS-based detector uses dynamic error equations to extract the features and construct various butterfly patterns. The probabilistic neural network is an adaptive classifier that performs pattern recognition. The particle swarm optimization algorithm is used to estimate the optimal parameter and can heighten the accuracy. For a sample power system, the test results showed accurate discrimination, rapid learning, good robustness, and faster processing time for detecting disturbances.