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.
Highlights
Bearingless motors have a wide application prospect because of its low energy consumption, high speed and no lubrication
Considering the advantages of kernel extreme learning machine (KELM), this paper proposes a BPMSM rotor position and displacement prediction model based on KELM
A high-precision prediction method based on KELM is proposed for the prediction of rotor position and displacement of BPMSM
Summary
Bearingless motors have a wide application prospect because of its low energy consumption, high speed and no lubrication. In literatures [5,6,7], sensorless control technology establishes a series of state observers to detect rotor position and velocity by detecting relevant electrical signals in the motor windings. This type of method relies on the back EMF of PMSM for position and speed estimation. In literature [10], the author adopts a novel windowed least algorithm to estimate the parameters with fixed value or the parameter with time varying characteristic In this regard, a rotor position and displacement prediction model for bearingless permanent magnet synchronous motor based on kernel extreme learning machine is proposed in the paper. The traditional parameter training problem is converted into a linear equation group to solve the problem, so the training and prediction time are greatly shortened
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
