为实现三自由度混合磁轴承高精度非线性解耦控制,提出一种基于最小二乘支持向量机的逆模辨识和解耦控制策略。通过分析逆系统的存在性,利用支持向量机的拟合能力,离线建立初始逆模型,并根据系统输入与模型输出的偏差信息,对初始逆模型进行在线校正,以使其能适应对象的变化;在此基础上,将校正后的逆模型作为前馈控制环节与原系统串联构成伪线性系统,设计PID控制器作为反馈控制环节对磁轴承系统进行复合控制。仿真结果表明逆模型辨识精度高,复合控制效果好。
To realize 3 degree of freedom hybrid magnetic bearing (3-DOF HMB) nonlinear decoupling control with high precision, an identification and decoupling control strategy of inverse system based on least squares support vector machine (LS-SVM) was proposed. The reversibility of system was analyzed, and the inverse model was built offline with SVM which has a good fitting capability. Then the inverse model was adjusted online by the error information between system input and model output. In addition, the inverse model adjusted as a forward feed controller was in series with original system to constitute pseudo linear system, PID designed as a feedback controller to realize the compound linear control for magnetic bearing. The simulation results show that the inverse model identified has high precision and the compound control strategy has good performance.