摘要
讨论了Elman神经网络的结构与学习算法,研究了基于Elman网络的动态系统辨识模型、预测模型及预测算法,并与模糊控制相结合,研究神经网络多步预测模糊控制方法。仿真结果表明该方法可以提高系统的鲁棒性及稳定性,多步预测最佳模糊控制的控制精度及ITAE指标均较无预测时要优。
The structure and learning algorithm of the Elman network is discussed. The Elman network identification, predictive model and the algorithm are researched. By combined with fuzzy control, multistep predictive fuzzy control algorithm of the neural network is studied. The simulation result indicates that the method can improve the robustness and the stability of the system. The control precision and the ITAE target based on multistep predictive fuzzy control are better than that of the index without prediction.
出处
《南京航空航天大学学报》
EI
CAS
CSCD
北大核心
2006年第B07期66-69,共4页
Journal of Nanjing University of Aeronautics & Astronautics
