An Approach with High Accuracy for Intelligent Analysis of Power System Harmonics
Wang Yao-nan · Proceedings of the CSEE · 2006
The FFT has a higher error in the harmonic analysis of the electric power system, especially for the phases. An algorithm of neural network based on Fourier series is presented. Because the algorithm model presented matches with the harmonic model of the electric power system, this algorithm obviously improves the convergence speed and accuracy of the neural network algorithm, so it can be applied to the precision analysis for electrical harmonic. In order to ensure the convergence of algorithm, the convergence theorem of the algorithm is proposed and proved. The theory gist to select learning rate is provided by the convergence theorem. To validate the validity of the algorithm, the simulating examples of harmonic analysis are given. The simulating results show that the high accurate amplitudes and phases of fundamental and various orders of harmonics could be obtained using the algorithm. Furthermore, the algorithm is not involved in operation of the complex number, thus the harmonic analysis method presented has significant value in the field of the power system harmonic measurement.