Dynamic harmonic identification in converter waveforms using radial basis function neural networks (RBFNN) and p-q power theory

Radial basis function neural networks (RBFNN) are used to dynamically identify harmonics content in converter waveforms based on p-q (real power-imaginary power) theory. The converter waveforms are analyzed and the harmonic contents are identified over a wide operating range. The proposed RBFNN filtering training algorithm are based on systematic and computationally efficient training method called hybrid learning method. The small size and the robustness of the resulted network reflect the effectiveness of the proposed algorithm. The analysis is verified using MATLAB simulation.