基于正则神经网络模型的时滞混沌系统预测控制

研究模型未知、不稳定的不动点位置及其局部性态未知情形下的时滞混沌系统的控制问题。提出了一种神经网络预测控制方法,将模型未知时的时滞混沌运动控制到不稳定的不动点处。分析了控制系统(包括观测器、正则神经网络预测器和在线训练的线性神经网络预测控制器)的稳定性,与现有同类方法比较,本方法收敛速度快,算法简便。仿真实验表明了本方法的有效性。

Predictive control of time-delay chaotic systems based on regularized neural network model

The control of the time-delay chaotic system is studied when the system model,the location of the unstable fixed point and the local dynamics at the point are unknown.A neural predictive control method is proposed to control the chaotic motion in an unknown time-delay chaotic system onto the unstable fixed point.The proposed control system includes a watcher,a regularized neural predictor and an on-line trained linear neural predictive controller.We analyze the stability of the control system.The proposed algorithm is simple and its convergence speed is higher than that of existing similar algorithm.The simulations demonstrate the effectiveness of the control method.