Sensorless control for a switched reluctance wind generator, based on current slopes and neural networks. http://dx.doi.org/10.1109/TIE.2008.2005940

Abstract

In this paper, the analysis, design and implementation of a novel rotor position estimator for the control of variable speed Switched Reluctance Generators (SRGs) is presented. The rotor position is obtained from the information contained in the unsaturated instantaneous inductance. This unsaturated inductance is estimated calculating the slopes of phase currents and using a reduced size neural network (NN) whose inputs are the average current and the saturated inductance. The proposed estimator requires less processing time than traditional methods and can be fully implemented using a low cost DSP with very few additional analog/digital components. The rotor position estimator presented in this work can be applied to a Wind Energy Conversion System (WECS) where the SRG is used as a variable speed generator. This application is currently being studied because the SRG has well known advantages as robustness, low manufacturing cost and good size to power ratio. Simulation and experimental results are presented using a 2.5kW, 8/6 SRG prototype.