Neural Networks Based Shunt Hybrid Active Power Filter for Harmonic Elimination

The growing use of nonlinear devices is introducing harmonics in power system networks that result distortion current and voltage signals causing damage to distribution systems. Therefore, systems, the elimination great significance. This paper presents an efficient techno-economical approach suppress improve factor using Shunt Hybrid Active Power Filters (SHAPF) based on neural network algorithms like Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Recurrent (RNN). objective proposed for SHAPF enhance performance by reducing Total Harmonic Distortion (THD). In our filter design approach, we tested compared conventional pq0 theory detect present system. Moreover, regulation DC supply inverter SHAPF, PI controller networks-based controllers are used compared. applicability three different load cases. simulation results show control techniques satisfy all international standards with minimum THD, neutral wire elimination, small fluctuations current. Furthermore, architectures accuracy computational complexity, RNN outperforming rest.