| Abstrakt: |
The characteristics of nonlinear and strong coupling of a bearingless permanent magnet synchronous motor (BPMSM) greatly affect the improvement of its control performance. In the traditional decoupling control of least squares support vector machine (LSSVM) inverse system, the kernel function parameter σ and regularization parameter c are determined according to the empirical value, but not the nonoptimal value, so large error exists in the decoupling control. Therefore, this paper proposes a decoupling control method of LSSVM inverse system based on improved grey wolf optimization algorithm (IGWO). Firstly, the working principle of the BPMSM is described, and the mathematical model is derived. Secondly, the reversibility of the BPMSM is analyzed, and the σ and c of LSSVM are optimized by IGWO, before establishing a generalized inverse system for decoupling control. Thirdly, the simulation tests of the speed regulation and anti-interference are carried out, which show that the decoupling performance of the proposed method is better than the traditional LSSVM inverse system method. Finally, the dynamic experiments, static experiments, and anti-interference experiments are carried out. The feasibility and superiority of the proposed method are verified according to the built experimental platform. [ABSTRACT FROM AUTHOR] |
