New application of artificial neural network-based direct power control for permanent magnet synchronous generator

Purpose. This article proposes a new strategy for Direct Power Control (DPC) based on the use of Artificial Neural Networks (ANN-DPC). The proposed ANN-DPC scheme is replacement PI and hysteresis regulators by neural regulators. Simulation results 1 kW system are provided to demonstrate efficiency robustness control during variations in active reactive power DC bus voltage. Methodology. Our direct instant powers. voltage regulator replaced more efficient robust artificial neuron networks. technique validated using MATLAB / Simulink software analysis working performances. Results. obtained clearly show that neuronal have good dynamic performances compared conventional (minimum response time, without overshoots). Originality. Regulation continuous sinusoidal currents network side Practical value. work concerns comparative study application DPC ANN techniques achieve performance permanent magnet synchronous generator. presents between control. first controller instantaneous powers In second technique, controllers parameters variation. simulation software.