Decoupling control of high speed permanent magnet synchronous motor based on online least squares support vector machine inverse system method

To enhance the decoupling control performance of the high speed permanent magnet synchronous motor (HS-PMSM), the mathematic model reversibility was testified based on the inverse system theory. And an online least squares support vector machine (OLS-SVM) based inverse system method was proposed for accurate identification of the HS-PMSM inverse model. By introducing the designed OLS-SVM real-time inverse system into the original HS-PMSM system, a pseudo-linear system was developed consequently. The HS-PMSM system was linearized and a decoupling system of speed and current was built. Meanwhile, to achieve the high accuracy stator flux estimation for the inverse control, a stator flux estimator based on the band-pass filter and parameter compensator (BPFC) was introduced and implemented. According to the simulation and experiment results, the utility of the proposed control strategy is demonstrated by the improved decoupling control performance of motor speed and current, the enhanced step speed tracking performance, the strong load anti-perturbation performance at the wide speed range.