Soft computing techniques for static series voltage regulator of self excited induction generator

Abstract

This paper deal with soft computing techniques such as artificial neural network (ANN), fuzzy logic controller (FLC) and proportional-integral (PI)-based static series voltage regulator (SSVR) for constant speed prime mover driven self excited induction generator (SEIG) feeding three phases linear and nonlinear loads. The constant speed prime mover such as biogas, biomass and gas-turbine driven standalone generating system has problem of poor voltage regulation. The SSVR is injects series voltage in to system to maintain constant source and load voltage with power quality improvement of source and load current. The SSVR is modeled using insulated gate bipolar junction transistor (IGBT)-based voltage controlled-voltage source converter (VC-VSC) with self supported DC bus. The A 7.5 kW, 415 V, 50 Hz asynchronous machine with voltage regulator and loads are designed, modeled and simulated in MATLAB environment. Simulated results are presented capability of an SEIG system with ANN, fuzzy and PI-based SSVR and their comparison.