Sensorless Control of Bearingless Permanent Magnet Synchronous Motor Based on LS-SVM Inverse System

Abstract

In order to solve the problems of low integration, low reliability, and high cost caused by mechanical sensors used in bearingless permanent magnet synchronous motor (BPMSM) control systems, a novel speed and displacement sensorless control method using a least-squares support vector machine (LS-SVM) left inverse system is proposed in this paper. Firstly, the suspension force generation principle of the BPMSM is introduced, and the mathematical model of the BPMSM is derived. Secondly, the observation principle of the left inverse system is explained, and the left reversibility of the established speed and displacement subsystem is proved. Thirdly, the left inverse systems of the speed and displacement subsystems are constructed by using the LS-SVM, and the complete speed and displacement sensorless control system is constructed. Finally, the simulations and experiments of the proposed method are performed. The research results demonstrate that the proposed observation method can identify the speed and displacement quickly and accurately, and the sensorless control method can realize the stable operation of the BPMSM without speed and displacement sensors.

Control of Permanent Magnet Synchronous Motors for Track Applications

“…The electromechanical sensors utilized inside the bearingless permanent magnet synchronous motor (BPMSM) in [42] have some drawbacks, such as growing the size, expense, and difficulty of the motors, and the detecting outcomes are easily influenced by environmental conditions. A motion and elevation sensorless control solution based on least square support vector machine (LS-SVM) left inversion system is suggested in [42] to address these issues. The reliability and efficacy of the LS-SVM left inversion system experimental method suggested in this study are demonstrated by the realization of the detection of rotational speeds and rotor radial displacement.…”

Saliency Model Extension for Sensorless Initial Position and Polarity Detection of Permanent Magnet Synchronous Motors

“…For an ideal machine that has identical phase windings, the three-phase voltage equation ( 11) contains 9 unknown inductances and 18 unknown elements in the abc Hessian, Γ abc , defined in (9), that are all functions of the rotor position.…”

“…The next step for building the machine model was the Park transformation of the idealized Hessian matrix and the measured data. We developed and used (69) to compute the Park or dq0 transform of the flattened 9×3 Hessian matrix defined by (9). T (ϑ) stands for the Park transformation matrix (47).…”

Permanent Magnet Synchronous Motor Model Extension for High-Frequency Signal Injection-Based Sensorless Magnet Polarity Detection

“…The operation of a traditional PMSM drive requires a shaft-mounted optical encoder or a resolver to determine the rotor position. However, in many industrial installations, the application of the shaft sensor increases the cost and size of the motor, reduces the reliability and the overall ruggedness of the drive, and limits the application in harsh environments [5,7,8]. Furthermore, many shaft sensors provide the initial rotor position with an inadequate resolution and incremental encoders do not provide it at all.…”