不确定混沌系统的径向基函数神经网络反馈补偿控制

对不确定混沌系统控制问题, 研究了一种基于径向基函数神经网络(radial basis function neural network, RBFNN)的反馈补偿控制方法. 该方法首先用RBFNN对混沌系统的动力学特性进行学习, 然后用训练好的RBFNN模型对混沌系统进行反馈补偿控制. 该方法的特点是不需要被控混沌系统的数学模型,可以快速跟踪任意给定的参考信号. 数值仿真试验表明了该控制方法不仅具有响应速度快、控制精度高, 而且具有较强的抑制混沌系统参数摄动能力和抗干扰能力.

Feedback compensation control on chaotic system with uncertainty based on radial basis function neural network

For the problem of controlling uncertain chaotic systems, a method of feedback compensation control based on the radial basis function neural network (RBFNN) is studied. In the proposed method, dynamic properties of chaotic system is first trained by RBFNN, and then feedback compensation control for chaotic system is implemented using trained good RBFNN model. The characteristics of this method is that this method can quickly track any given reference signal with on requirement for any mathematic model of controlled chaos system. The numerical simulation results show that the proposed control method not only has the fast response speed, high control accuracy, but also has a stronger ability to suppress parameter perturbation and to resist interference to chaos system.