Harmonic Current Identification by Adaline Neural Network and Real-Imaginary Instantaneous Powers Algorithm

This work is focused on harmonic current extraction and reactive power compensation using shunt
active power filter (SAPF). In order to fulfil this objective an algorithm based on (ADALINE) Neural
Network and Real and Imaginary Instantaneous Powers (ANN-RIIP) is developed to extract and
identify harmonic components. Moreover, this algorithm estimates total harmonic current and also
harmonic components individually. The developed algorithm is validated by computer simulation in
MATLAB/Simulink environment and implemented experimental in a dSPACE 1104 controller. The
method is easy to implement in real time compared to other methods such as pq. The results obtained
by simulation are in concordance with the experimental results confirming the effectiveness of the
proposed ANN-RIIP algorithm. The results have also demonstrated that the speed and accuracy of
the proposed algorithm can improve the performances of active power filters.