Research on power quality disturbance automatic recognition and location

A novel approach on power quality disturbance automatic recognition and location is presented in this paper. At first the DB4 wavelet is applied to decompose the signals containing disturbances, and to extract the feature vectors by wavelet coefficients at all scales according to Euclid distance measurement. Then disturbance types are recognized through the pattern recognition classifier based on neural network and genetic algorithm. Referred to the principle of differential protection in bus and line protections, the disturbance energy is defined as the characteristic, and disturbance location is solved by comparing the direction of disturbance energy and topology relation of related measurement points. The software system realizing above recognition and location of disturbances is developed for testing the approach. Numerical results show that the proposed approach is correct and effective.