A Harmonic Detecting Scheme Based On BP Neural Network

摘要

General harmonic detecting scheme is using the Fast Fourier Transform (FFT) for detection of all the harmonics (such as 1 to 50 times). While power units often do not care about the specific values of all the harmonics, but is only concerned with some key harmonics or several overall indicators. For the above reason, a new harmonic detecting scheme based on the algorithm of BP neural network is presented in this paper. It does not need to calculate all the harmonics, when the detection of individual indicators or overall indicators which are concerned by users can be achieved, and to achieve the above-mentioned detection target, by the analysis of computation of BP, DFT and FFT algorithm, the superiority of the scheme in terms of computation is proved. After the simulation of the scheme using a set of measured harmonic data, the results validate that the above scheme is simple and feasible, and its detecting accuracy is close to which of FFT.