Automated classification of power-quality disturbances using SVM and RBF networks

摘要: The authors propose a new method of power-quality classification using support vector machine (SVM) neural networks. Classifiers based on radial basis function (RBF) networks was, in parallel, applied to enable proper performance comparison. Both RBF and SVM are introduced considered be an appropriate tool for problems. Space phasor is used feature extraction from three-phase signals build distinguished patterns classifiers. In order create training testing vectors, different disturbance classes were simulated (e.g., sags, voltage fluctuations, transients) Matlab. Finally, the investigation results novel approach shown interpreted.