【摘要】 针对任意复杂非线性系统,提出一种通用的RBF网络动态系统逆控制方案,并提出了一种通过对聚类半径进行"粗调"和"细调"的最近邻聚类学习算法,利用构造伪系统的方法构成一种对非最小相位同样有效的神经网络动态逆控制与PID控制相结合的在线自学习控制策略。仿真研究证明,该控制策略不仅能使多种非线性对象跟踪多种参考信号,而且抗干扰能力和鲁棒性也很好。更多还原

【Abstract】 A novel scheme of RBF neural network dynamic inverse control was proposed for arbitrary complex nonlinear.Using the dynamic nearest neighbors clustering algorithm to train the RBF neural network.The crude regulation and fine regulation method was introduced in to guarantee the rationality of clubman.Through constructing pseudo-plant,a method of on-line self-learning control strategy was introduced,which combines inverse control based on RBFN with PID control.The method was still effective to the nonlinear non-minimum phase system.The simulation results demonstrated that the inverse control strategy can not only make manifold nonlinear objects track multi-reference signals,but also possess resistance to disturbance and excellent robustness.更多还原