论文部分内容阅读
预测控制是以计算机为手段基于模型预测进行控制的方法，但是已有的预测控制算法通常是针对线性渐进稳定对象的，或者即使针对非线性使用了非线性模型，但由于算法过于复杂不能适用于快速系统．本文对复杂非线性系统提出了一种基于Ｂ－Ｐ神经网络的预测控制方法，仿真和实际结果表明该方法的有效性和快速性，能够实现对非线性系统的实时智能优化控制．
Predictive control is a computer-based method of controlling based on model predictions. However, the existing predictive control algorithms are usually aimed at linear asymptotically stable objects or even though nonlinear models are used for nonlinearity. However, because the algorithm is too complicated to apply to Fast system. In this paper, a predictive control method based on B-P neural network is proposed for complex nonlinear systems. The simulation and the practical results show that the proposed method is effective and fast, which can realize real-time intelligent optimal control of nonlinear systems.