摘要
提出一种基于径向基函数（ＲＢＦ）神经网络的一步超前预测控制算法。该方法只用一个网络，控制量的获取只求几步迭代，算法简单并有较好的实时性。通过对离散非线性系统的仿真证明了算法的有效性．
In this paper, a one-step ahead predictive control algorithm based on Radial Base Function (RBF)neural networks is proposed, which needs only one neural network. The algorithm is simple, and the control value can be acquired by only a few iterations. Thus it has good real-time property. Through the simulation for a discrete nonlinear system, it is obvious that the algorithm posseses good control performance such as robustness.
出处
《控制与决策》
EI
CSCD
北大核心
1996年第4期485-489,509,共6页
Control and Decision
基金
国家自然科学基金
