Sensorless Control for a Switched Reluctance Wind Generator, Based on Current Slopes and Neural Networks

In this paper, the analysis, design, and implementation of a novel rotor position estimator for the control of variable-speed switched reluctance generators (SRGs) are presented. The rotor position is obtained using the unsaturated instantaneous inductance. This unsaturated inductance is estimated calculating the slope of the phase current 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 paper can be applied to a wind energy conversion system where the SRG is used as a variable-speed generator. This application is currently being studied because the SRG has well-known advantages such as robustness, low manufacturing cost, and good size-to-power ratio. Simulation and experimental results are presented using a 2.5-kW 8/6-SRG prototype.