中文摘要：

为实现五自由度无轴承异步电机高精度动态解耦控制,提出一种基于最小二乘支持向量机逆的解耦控制方法.首先,建立五自由度无轴承异步电机数学模型并进行可逆性分析,然后,利用最小二乘支持向量机在有限数据样本下对高维非线性函数的回归能力来辨识五自由度无轴承异步电机逆模型,并利用粒子群算法优化最小二乘支持向量机的参数,以提高对逆模型的拟合和预测精度,最后,将最小二乘支持向量机逆与原系统相串联得到伪线性系统,并设计PID闭环控制器对五自由度无轴承异步电机进行复合控制,实现了原系统径向位移、轴向位移、转速以及磁链间的非线性动态解耦.仿真研究验证了该控制策略的有效性.

英文摘要：

In order to realize high precision dynamic decoupling control of the 5-degree-of-freedom bearingless induction motor（BIM）,a decoupling control method based on least square support vector machine inverse（LSSVMI） is proposed. Firstly,the mathematical model of 5-degree-of-freedom BIM is established and the reversibility of the model is analyzed. Then,the inverse model was identified using LSSVM which has a good fitting capability to high dimensional nonlinear functions with limited samples,and the particle swarm optimization algorithm is used to optimize the parameters of LSSVM,so as to improve the fitting and prediction accuracy of the inverse model. The LSSVM is connected with the original system to get the pseudo linear system. The PID closed loop controller is designed to control the 5-degree-of-freedom BIM,and the nonlinear dynamic decoupling of radial displacement,axial displacement,rotational speed and flux linkage is realized. Simulation results verify the effectiveness of the proposed control strategy.