Decoupling Control of Outer Rotor Coreless Bearingless Permanent Magnet Synchronous Motor Based on Least Squares Support Vector Machine Generalized Inverse Optimized by Improved Genetic Algorithm

Abstract

In the decoupling control process of the outer rotor coreless bearingless permanent magnet synchronous motor using a least squares support vector machine, the kernel width <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">σ</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and the penalty factor <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">γ</i> of the least squares support vector machine are difficult to tune, resulting in high kernel space complexity and low fitting accuracy. A new improved genetic algorithm is used to optimize the above parameters. First, the generalized inverse system model of the original nonlinear multiple-input multiple-output system is fitted online with the optimized least squares support vector machine, and the generalized inverse system model is connected in series with the original system to form a pseudolinear system. Then, a linear closed-loop controller is used for control. Simulations and experiments show that the robustness and wide applicability of the original system are guaranteed. The dynamic and static performances of the system are improved, verifying the effectiveness of the scheme.