Classification of Wide Variety Range of Power Quality Disturbances Based on Two Dimensional Image Processing Techniques

Identification of voltage and current disturbances is an important task in power system monitoring and protection. In this paper, a new algorithm for online characterization of awide range of voltage disturbances based on two dimensional wavelet transformation is proposed. This algorithm is morecomplicated than algorithms based on one dimensional wavelet transformation, but it can be used to characterize a wide variety range of disturbances, including steady state disturbances, transients with slow variations and transients with rapid changes. In this approach, after each cycle, a matrix is formed based on that cycle and the thirty one cycles before it, in a way that the samples of voltage signal in one cycle form one row ofthe matrix. This matrix can be regarded as a two dimensional image. The resulted image is decomposed into approximation and detail images by two dimensional wavelet transformation. Various disturbances result into special patterns in detail images, and by processing the detail images, the disturbance type can be determined

کلیدواژه ها:

Power quality ، Event detection and classification ، Two dimensional wavelet transformation ، Pattern classification ، Feature ، Classifier system