Speed sensorless control of PMSM via linear Kalman filtering

This paper presents a novel PMSM sensorless control scheme based on a linear Kalman filter (LKF) observer. The LKF algorithm estimates the rotor flux components in the stator reference frame by measuring stator currents and voltages, and using a mathematical model based on rotor equations of the motor, and an observation model based on the imaginary power equation. In this way, the LKF algorithm is completely independent on stator resistance, and therefore rotor position estimates are not affected by even strong resistance variations. The proposed observer is linear but time-varying because the rotor speed is treated as a model parameter to be on-line updated. Estimation of rotor speed is performed in two steps: firstly a rough speed estimation is obtained by processing the estimates of rotor position; then a simple speed observer is used to improve the accuracy of speed estimates. The observer output, i.e. the final speed estimate, is fed back to both the speed control loop and LKF algorithm.