摘要
提出一种基于Elman动态回归神经网络模型的鲁棒型广义预测控制(GPC).该算法首先用Elman网络对非线性系统进行辨识,建立预测模型,然后在控制中将模型输出值与测量输出值进行综合,代替量测输出用于控制中,从而降低辨识器与控制器对未建模动态的敏感性,加强控制器的适应能力和鲁棒性.仿真结果证明:将本算法应用于非线性系统预测控制,对未建模动态具有很强的鲁棒性和很好的控制能力.
A robust generalized predictive control (GPC) based on Elman neural network model is presented in this paper. First we identify the nonlinear system by Elman neural network. Since the output sequence used in the controller design is replaced by the combination of the measure output and the model output, so we can reduce the sensitivity of the identifier and controller for the unmodeling dynamic part, and increase the adaptive ability and robustness of the controller. The simulations show that the present method suits for the nonlinear system and has strong robustness and great control ability for the unmodeling dynamic system.
出处
《系统工程学报》
CSCD
2004年第5期503-506,共4页
Journal of Systems Engineering
