论文部分内容阅读
该文对于未知非线性离散单输入单输出(SISO)系统提出了一种基于支持向量机的内模控制方法。整个控制律包括标称控制器与鲁棒控制器2部分,标称控制器是基于支持向量机-非线性自回归滑动平均(SVM-NARMA)模型用二次型最优性能指标推导出来的,而鲁棒控制器可以减少不确定性对系统性能的影响。利用Lyapunov方法证明了闭环系统的稳定性和鲁棒性。结果表明:该方法不仅适用于不具有严格相对阶的系统,也适用于具有不稳定零动态的系统。大量仿真结果验证了该方法的有效性。
In this paper, an internal model control method based on support vector machines is proposed for the unknown nonlinear discrete single-input single-output (SISO) system. The whole control law includes two parts: nominal controller and robust controller. The nominal controller is derived from quadratic optimal performance index based on SVM-NARMA model. Robust controllers can reduce the impact of uncertainty on system performance. The Lyapunov method is used to prove the stability and robustness of the closed-loop system. The results show that this method is not only applicable to systems without strict relative order but also to systems with unstable and zero dynamics. A large number of simulation results verify the effectiveness of the method.