Application of LVQ neural networks combined with genetic algorithm in power quality signals classification

Abstract

In this paper, a learning vector quantization (LVQ) artificial neural network (ANN) combined with a genetic algorithm (GA) is used as a new approach for the classification of power quality (PQ) disturbances. A new GA operator is proposed also. The GA can overcome the disadvantages of the learning vector quantization (LVQ) artificial neural network (ANN), such as slow convergence and possibility of being trapped at a locally minimum value. Compared with LVQ ANN, the convergence and generalization ability of GA-LVQ ANN is improved remarkably. The GA operator proposed can help to accelerate this process. The efficient and validity of this method is verified by the results.