A High-Precision Rotor Position and Displacement Prediction Method Specially for Bearingless Permanent Magnet Synchronous Motor

Abstract

The high performance sensorless performance of the bearingless permanent magnet synchronous motor is the main direction to improve the reliability of the drive system and reduce the cost of the system, and the high-precision rotor position and displacement prediction method is the key technology to realize the high performance sensorless operation. In view of the above problems, a rotor displacement and position prediction method based on kernel extreme learning machine is studied in this paper. On the basis of the mathematical model of BPMSM, this method predicted the position and displacement of the rotor according to the current and flux linkage of suspension windings and torque windings by KELM. The construction method of rotor position and displacement prediction model was described; meanwhile the implementation steps of offline training and online prediction were given. Finally, the error between the method and the actual value was compared by simulation and experiment. The results showed that the proposed method had high accuracy and could achieve real-time rotor position and displacement and then provides the basis for realizing sensorless operation control of BPMSM.