中文摘要：

针对高速永磁同步电机（high speed permanent magnet synchronous motor,HS-PMSM）的解耦控制系统,根据逆系统理论分析了其数学模型的可逆性,进一步提出一种基于在线最小二乘支持向量机（online least squares support vector machine,OLS-SVM）的逆系统方法,实现了HS-PMSM的高性能解耦控制。该方法设计了基于OLS-SVM的实时逆系统,并将其与原系统串联构成一种伪线性系统,实现了HS-PMSM系统的线性化和解耦。同时,在HS-PMSM逆控制系统中为获得高精度定子磁链观测,进一步引入一种基于带通滤波器和参数补偿（band-pass filter with parameter compensator,BPFC）的磁链观测器。通过仿真和实验研究,在宽速范围内转速和电流解耦控制、不同转速域转速跃跟踪和负载抗扰性能等几个方面验证了文中所提出的解耦控制方法的有效性。

英文摘要：

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.